Skip to content

B
Better you
Commit 2fbef0f4 authored by Jayamini Samaratunga's avatar Jayamini Samaratunga
Browse files
Options

smart assistant api endpoint added

parent e86bdbd9
Show whitespace changes
Inline Side-by-side
Showing with 3070 additions and 8003 deletions
backend/activityRecommender.ipynb deleted 100644 → 0
View file @ e86bdbd9
{"cells":[{"cell_type":"markdown","id":"1bc3e577","metadata":{"id":"1bc3e577"},"source":["# Weighted Average By Emotions"]},{"cell_type":"code","execution_count":2,"id":"b58f8656","metadata":{"id":"b58f8656","executionInfo":{"status":"ok","timestamp":1650702524009,"user_tz":-330,"elapsed":2861,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}}},"outputs":[],"source":["import numpy as np\n","import pandas as pd\n","from sklearn.ensemble import VotingClassifier\n","from sklearn.model_selection import train_test_split\n","from sklearn import model_selection"]},{"cell_type":"code","execution_count":3,"id":"68014c5d","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":332},"id":"68014c5d","executionInfo":{"status":"ok","timestamp":1650702524010,"user_tz":-330,"elapsed":36,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}},"outputId":"78726289-38ad-4cc9-a8a5-deefc396ff8c"},"outputs":[{"output_type":"execute_result","data":{"text/plain":[" Score Weight Model Emotion\n","0 20 1 A Happy\n","1 40 2 A Sad\n","2 90 3 A Angry\n","3 80 1 B Happy\n","4 60 2 B Sad\n","5 10 3 B Angry\n","6 5 1 C Happy\n","7 60 2 C Sad\n","8 90 3 C Angry"],"text/html":["\n"," <div id=\"df-1adcdae1-2809-456f-8be1-cbad54e27237\">\n"," <div class=\"colab-df-container\">\n"," <div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n"," <th>Score</th>\n"," <th>Weight</th>\n"," <th>Model</th>\n"," <th>Emotion</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>20</td>\n"," <td>1</td>\n"," <td>A</td>\n"," <td>Happy</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>40</td>\n"," <td>2</td>\n"," <td>A</td>\n"," <td>Sad</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>90</td>\n"," <td>3</td>\n"," <td>A</td>\n"," <td>Angry</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>80</td>\n"," <td>1</td>\n"," <td>B</td>\n"," <td>Happy</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>60</td>\n"," <td>2</td>\n"," <td>B</td>\n"," <td>Sad</td>\n"," </tr>\n"," <tr>\n"," <th>5</th>\n"," <td>10</td>\n"," <td>3</td>\n"," <td>B</td>\n"," <td>Angry</td>\n"," </tr>\n"," <tr>\n"," <th>6</th>\n"," <td>5</td>\n"," <td>1</td>\n"," <td>C</td>\n"," <td>Happy</td>\n"," </tr>\n"," <tr>\n"," <th>7</th>\n"," <td>60</td>\n"," <td>2</td>\n"," <td>C</td>\n"," <td>Sad</td>\n"," </tr>\n"," <tr>\n"," <th>8</th>\n"," <td>90</td>\n"," <td>3</td>\n"," <td>C</td>\n"," <td>Angry</td>\n"," </tr>\n"," </tbody>\n","</table>\n","</div>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1adcdae1-2809-456f-8be1-cbad54e27237')\"\n"," title=\"Convert this dataframe to an interactive table.\"\n"," style=\"display:none;\">\n"," \n"," <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n"," width=\"24px\">\n"," <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n"," <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n"," </svg>\n"," </button>\n"," \n"," <style>\n"," .colab-df-container {\n"," display:flex;\n"," flex-wrap:wrap;\n"," gap: 12px;\n"," }\n","\n"," .colab-df-convert {\n"," background-color: #E8F0FE;\n"," border: none;\n"," border-radius: 50%;\n"," cursor: pointer;\n"," display: none;\n"," fill: #1967D2;\n"," height: 32px;\n"," padding: 0 0 0 0;\n"," width: 32px;\n"," }\n","\n"," .colab-df-convert:hover {\n"," background-color: #E2EBFA;\n"," box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n"," fill: #174EA6;\n"," }\n","\n"," [theme=dark] .colab-df-convert {\n"," background-color: #3B4455;\n"," fill: #D2E3FC;\n"," }\n","\n"," [theme=dark] .colab-df-convert:hover {\n"," background-color: #434B5C;\n"," box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n"," filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n"," fill: #FFFFFF;\n"," }\n"," </style>\n","\n"," <script>\n"," const buttonEl =\n"," document.querySelector('#df-1adcdae1-2809-456f-8be1-cbad54e27237 button.colab-df-convert');\n"," buttonEl.style.display =\n"," google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n"," async function convertToInteractive(key) {\n"," const element = document.querySelector('#df-1adcdae1-2809-456f-8be1-cbad54e27237');\n"," const dataTable =\n"," await google.colab.kernel.invokeFunction('convertToInteractive',\n"," [key], {});\n"," if (!dataTable) return;\n","\n"," const docLinkHtml = 'Like what you see? Visit the ' +\n"," '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n"," + ' to learn more about interactive tables.';\n"," element.innerHTML = '';\n"," dataTable['output_type'] = 'display_data';\n"," await google.colab.output.renderOutput(dataTable, element);\n"," const docLink = document.createElement('div');\n"," docLink.innerHTML = docLinkHtml;\n"," element.appendChild(docLink);\n"," }\n"," </script>\n"," </div>\n"," </div>\n"," "]},"metadata":{},"execution_count":3}],"source":["df = pd.DataFrame(\n"," {\n"," \"Score\": [20, 40, 90, 80, 60, 10, 5, 60, 90],\n"," \"Weight\": [1, 2, 3, 1, 2, 3, 1, 2, 3],\n"," \"Model\": [\"A\", \"A\", \"A\", \"B\", \"B\", \"B\", \"C\", \"C\", \"C\"],\n"," \"Emotion\": [\"Happy\", \"Sad\", \"Angry\", \"Happy\", \"Sad\", \"Angry\", \"Happy\", \"Sad\", \"Angry\"],\n"," }\n",")\n","df"]},{"cell_type":"code","execution_count":4,"id":"b58a8c3b","metadata":{"id":"b58a8c3b","executionInfo":{"status":"ok","timestamp":1650702524011,"user_tz":-330,"elapsed":31,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}}},"outputs":[],"source":["def grouped_weighted_avg(values, weights, by):\n"," return (values * weights).groupby(by).sum() / weights.groupby(by).sum() "]},{"cell_type":"code","execution_count":5,"id":"e47fb44a","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"e47fb44a","executionInfo":{"status":"ok","timestamp":1650702524012,"user_tz":-330,"elapsed":30,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}},"outputId":"e2c527f1-1ab4-41bf-a4ec-318e064efbf7"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["Emotion\n","Angry 63.333333\n","Happy 35.000000\n","Sad 53.333333\n","dtype: float64"]},"metadata":{},"execution_count":5}],"source":["grouped_weighted_avg(df[\"Score\"], df[\"Weight\"], df[\"Emotion\"])\n","#grouped_weighted_avg(df[\"Score\"], df[\"Weight\"], df[\"Emotion\"]).max()"]},{"cell_type":"markdown","id":"8dae3123","metadata":{"id":"8dae3123"},"source":["# creating the ensemble model"]},{"cell_type":"code","execution_count":6,"id":"cc27761f","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":143},"id":"cc27761f","executionInfo":{"status":"ok","timestamp":1650702524013,"user_tz":-330,"elapsed":23,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}},"outputId":"33daf663-b473-4a01-fdd3-e4383a20019f"},"outputs":[{"output_type":"execute_result","data":{"text/plain":[" Score Emotion\n","0 63.333333 Happy\n","1 35.000000 Sad\n","2 53.333333 Angry"],"text/html":["\n"," <div id=\"df-a78189e0-b628-4700-8527-0392cd1ac901\">\n"," <div class=\"colab-df-container\">\n"," <div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n"," <th>Score</th>\n"," <th>Emotion</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>63.333333</td>\n"," <td>Happy</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>35.000000</td>\n"," <td>Sad</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>53.333333</td>\n"," <td>Angry</td>\n"," </tr>\n"," </tbody>\n","</table>\n","</div>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a78189e0-b628-4700-8527-0392cd1ac901')\"\n"," title=\"Convert this dataframe to an interactive table.\"\n"," style=\"display:none;\">\n"," \n"," <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n"," width=\"24px\">\n"," <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n"," <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n"," </svg>\n"," </button>\n"," \n"," <style>\n"," .colab-df-container {\n"," display:flex;\n"," flex-wrap:wrap;\n"," gap: 12px;\n"," }\n","\n"," .colab-df-convert {\n"," background-color: #E8F0FE;\n"," border: none;\n"," border-radius: 50%;\n"," cursor: pointer;\n"," display: none;\n"," fill: #1967D2;\n"," height: 32px;\n"," padding: 0 0 0 0;\n"," width: 32px;\n"," }\n","\n"," .colab-df-convert:hover {\n"," background-color: #E2EBFA;\n"," box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n"," fill: #174EA6;\n"," }\n","\n"," [theme=dark] .colab-df-convert {\n"," background-color: #3B4455;\n"," fill: #D2E3FC;\n"," }\n","\n"," [theme=dark] .colab-df-convert:hover {\n"," background-color: #434B5C;\n"," box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n"," filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n"," fill: #FFFFFF;\n"," }\n"," </style>\n","\n"," <script>\n"," const buttonEl =\n"," document.querySelector('#df-a78189e0-b628-4700-8527-0392cd1ac901 button.colab-df-convert');\n"," buttonEl.style.display =\n"," google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n"," async function convertToInteractive(key) {\n"," const element = document.querySelector('#df-a78189e0-b628-4700-8527-0392cd1ac901');\n"," const dataTable =\n"," await google.colab.kernel.invokeFunction('convertToInteractive',\n"," [key], {});\n"," if (!dataTable) return;\n","\n"," const docLinkHtml = 'Like what you see? Visit the ' +\n"," '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n"," + ' to learn more about interactive tables.';\n"," element.innerHTML = '';\n"," dataTable['output_type'] = 'display_data';\n"," await google.colab.output.renderOutput(dataTable, element);\n"," const docLink = document.createElement('div');\n"," docLink.innerHTML = docLinkHtml;\n"," element.appendChild(docLink);\n"," }\n"," </script>\n"," </div>\n"," </div>\n"," "]},"metadata":{},"execution_count":6}],"source":["op = pd.DataFrame(\n"," {\n"," \"Score\": [63.333333, 35.000000, 53.333333],\n"," \"Emotion\": [\"Happy\", \"Sad\", \"Angry\"],\n"," }\n",")\n","op"]},{"cell_type":"code","execution_count":7,"id":"9baf4921","metadata":{"id":"9baf4921","executionInfo":{"status":"ok","timestamp":1650702524013,"user_tz":-330,"elapsed":19,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}}},"outputs":[],"source":["# X = op.Emotion\n","# y = op.Score\n","# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30)\n","# kfold = model_selection.KFold(n_splits=2) \n","# creating the ensemble model\n","# estimators = []\n","# ensemble = VotingClassifier(estimators)\n","# results = model_selection.cross_val_score(ensemble, X_train, y_train, cv=kfold)\n","# print(); print(results)"]},{"cell_type":"code","execution_count":7,"id":"7817cf3c","metadata":{"id":"7817cf3c","executionInfo":{"status":"ok","timestamp":1650702524014,"user_tz":-330,"elapsed":18,"user":{"displayName":"Jayamini Samaratunga","userId":"01953412388746517714"}}},"outputs":[],"source":["\n"]}],"metadata":{"kernelspec":{"display_name":"Python 3 (ipykernel)","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.9.7"},"colab":{"name":"weightedAverage.ipynb","provenance":[]}},"nbformat":4,"nbformat_minor":5}
\ No newline at end of file
backend/friendRecommenderRL.ipynb deleted 100644 → 0
View file @ e86bdbd9
This source diff could not be displayed because it is too large. You can view the blob instead.
backend/smart_assistant/.idea/.gitignore 0 → 100644
View file @ 2fbef0f4
# Default ignored files
/shelf/
/workspace.xml
backend/smart_assistant/.idea/RL.iml 0 → 100644
View file @ 2fbef0f4
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Python 3.8 (gym_rl)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>
\ No newline at end of file
backend/smart_assistant/.idea/inspectionProfiles/Project_Default.xml 0 → 100644
View file @ 2fbef0f4
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredPackages">
<value>
<list size="32">
<item index="0" class="java.lang.String" itemvalue="opencv-python" />
<item index="1" class="java.lang.String" itemvalue="cmake" />
<item index="2" class="java.lang.String" itemvalue="numpy" />
<item index="3" class="java.lang.String" itemvalue="dlib" />
<item index="4" class="java.lang.String" itemvalue="thop" />
<item index="5" class="java.lang.String" itemvalue="scikit-image" />
<item index="6" class="java.lang.String" itemvalue="opencv-contrib-python" />
<item index="7" class="java.lang.String" itemvalue="wincertstore" />
<item index="8" class="java.lang.String" itemvalue="networkx" />
<item index="9" class="java.lang.String" itemvalue="tifffile" />
<item index="10" class="java.lang.String" itemvalue="Flask-Cors" />
<item index="11" class="java.lang.String" itemvalue="PyYAML" />
<item index="12" class="java.lang.String" itemvalue="torch" />
<item index="13" class="java.lang.String" itemvalue="torchvision" />
<item index="14" class="java.lang.String" itemvalue="mysql-connector-python" />
<item index="15" class="java.lang.String" itemvalue="pandas" />
<item index="16" class="java.lang.String" itemvalue="tqdm" />
<item index="17" class="java.lang.String" itemvalue="regex" />
<item index="18" class="java.lang.String" itemvalue="mediapipe" />
<item index="19" class="java.lang.String" itemvalue="seaborn" />
<item index="20" class="java.lang.String" itemvalue="better-profanity" />
<item index="21" class="java.lang.String" itemvalue="colorama" />
<item index="22" class="java.lang.String" itemvalue="PyWavelets" />
<item index="23" class="java.lang.String" itemvalue="imutils" />
<item index="24" class="java.lang.String" itemvalue="pytz" />
<item index="25" class="java.lang.String" itemvalue="torchaudio" />
<item index="26" class="java.lang.String" itemvalue="Flask" />
<item index="27" class="java.lang.String" itemvalue="Pillow" />
<item index="28" class="java.lang.String" itemvalue="flashtext" />
<item index="29" class="java.lang.String" itemvalue="unidecode" />
<item index="30" class="java.lang.String" itemvalue="sklearn" />
<item index="31" class="java.lang.String" itemvalue="nltk" />
</list>
</value>
</option>
</inspection_tool>
</profile>
</component>
\ No newline at end of file
backend/smart_assistant/.idea/inspectionProfiles/profiles_settings.xml 0 → 100644
View file @ 2fbef0f4
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>
\ No newline at end of file
backend/smart_assistant/.idea/misc.xml 0 → 100644
View file @ 2fbef0f4
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (gym_rl)" project-jdk-type="Python SDK" />
<component name="PyCharmProfessionalAdvertiser">
<option name="shown" value="true" />
</component>
</project>
\ No newline at end of file
backend/smart_assistant/.idea/modules.xml 0 → 100644
View file @ 2fbef0f4
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/RL.iml" filepath="$PROJECT_DIR$/.idea/RL.iml" />
</modules>
</component>
</project>
\ No newline at end of file
backend/smart_assistant/.ipynb_checkpoints/notebook-checkpoint.ipynb 0 → 100644
View file @ 2fbef0f4
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "invisible-penguin",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pycaret.classification import *"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "removed-affect",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>input_1</th>\n",
" <th>input_2</th>\n",
" <th>input_3</th>\n",
" <th>pred</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>57.99879</td>\n",
" <td>46.27261</td>\n",
" <td>99.97455</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>51.99879</td>\n",
" <td>90.99575</td>\n",
" <td>46.27261</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>98.87455</td>\n",
" <td>90.99261</td>\n",
" <td>86.27225</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>91.24879</td>\n",
" <td>20.34575</td>\n",
" <td>42.27261</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>51.99879</td>\n",
" <td>93.99575</td>\n",
" <td>46.27261</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>922</th>\n",
" <td>96.53788</td>\n",
" <td>54.73844</td>\n",
" <td>17.69907</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>923</th>\n",
" <td>44.53781</td>\n",
" <td>88.37842</td>\n",
" <td>66.92945</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>924</th>\n",
" <td>69.38968</td>\n",
" <td>22.95433</td>\n",
" <td>59.82559</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>925</th>\n",
" <td>67.09695</td>\n",
" <td>54.56414</td>\n",
" <td>53.96752</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>926</th>\n",
" <td>32.12081</td>\n",
" <td>80.49886</td>\n",
" <td>30.47048</td>\n",
" <td>5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>927 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" input_1 input_2 input_3 pred\n",
"0 57.99879 46.27261 99.97455 0\n",
"1 51.99879 90.99575 46.27261 1\n",
"2 98.87455 90.99261 86.27225 2\n",
"3 91.24879 20.34575 42.27261 3\n",
"4 51.99879 93.99575 46.27261 4\n",
".. ... ... ... ...\n",
"922 96.53788 54.73844 17.69907 3\n",
"923 44.53781 88.37842 66.92945 1\n",
"924 69.38968 22.95433 59.82559 1\n",
"925 67.09695 54.56414 53.96752 2\n",
"926 32.12081 80.49886 30.47048 5\n",
"\n",
"[927 rows x 4 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('data/data.csv')\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "needed-eleven",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_081c1_row44_col1{\n",
" background-color: lightgreen;\n",
" }</style><table id=\"T_081c1_\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Description</th> <th class=\"col_heading level0 col1\" >Value</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_081c1_row0_col0\" class=\"data row0 col0\" >session_id</td>\n",
" <td id=\"T_081c1_row0_col1\" class=\"data row0 col1\" >1559</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_081c1_row1_col0\" class=\"data row1 col0\" >Target</td>\n",
" <td id=\"T_081c1_row1_col1\" class=\"data row1 col1\" >pred</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_081c1_row2_col0\" class=\"data row2 col0\" >Target Type</td>\n",
" <td id=\"T_081c1_row2_col1\" class=\"data row2 col1\" >Multiclass</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_081c1_row3_col0\" class=\"data row3 col0\" >Label Encoded</td>\n",
" <td id=\"T_081c1_row3_col1\" class=\"data row3 col1\" >0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_081c1_row4_col0\" class=\"data row4 col0\" >Original Data</td>\n",
" <td id=\"T_081c1_row4_col1\" class=\"data row4 col1\" >(927, 4)</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
" <td id=\"T_081c1_row5_col0\" class=\"data row5 col0\" >Missing Values</td>\n",
" <td id=\"T_081c1_row5_col1\" class=\"data row5 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
" <td id=\"T_081c1_row6_col0\" class=\"data row6 col0\" >Numeric Features</td>\n",
" <td id=\"T_081c1_row6_col1\" class=\"data row6 col1\" >0</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
" <td id=\"T_081c1_row7_col0\" class=\"data row7 col0\" >Categorical Features</td>\n",
" <td id=\"T_081c1_row7_col1\" class=\"data row7 col1\" >3</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
" <td id=\"T_081c1_row8_col0\" class=\"data row8 col0\" >Ordinal Features</td>\n",
" <td id=\"T_081c1_row8_col1\" class=\"data row8 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
" <td id=\"T_081c1_row9_col0\" class=\"data row9 col0\" >High Cardinality Features</td>\n",
" <td id=\"T_081c1_row9_col1\" class=\"data row9 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
" <td id=\"T_081c1_row10_col0\" class=\"data row10 col0\" >High Cardinality Method</td>\n",
" <td id=\"T_081c1_row10_col1\" class=\"data row10 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
" <td id=\"T_081c1_row11_col0\" class=\"data row11 col0\" >Transformed Train Set</td>\n",
" <td id=\"T_081c1_row11_col1\" class=\"data row11 col1\" >(648, 479)</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
" <td id=\"T_081c1_row12_col0\" class=\"data row12 col0\" >Transformed Test Set</td>\n",
" <td id=\"T_081c1_row12_col1\" class=\"data row12 col1\" >(279, 479)</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
" <td id=\"T_081c1_row13_col0\" class=\"data row13 col0\" >Shuffle Train-Test</td>\n",
" <td id=\"T_081c1_row13_col1\" class=\"data row13 col1\" >True</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
" <td id=\"T_081c1_row14_col0\" class=\"data row14 col0\" >Stratify Train-Test</td>\n",
" <td id=\"T_081c1_row14_col1\" class=\"data row14 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
" <td id=\"T_081c1_row15_col0\" class=\"data row15 col0\" >Fold Generator</td>\n",
" <td id=\"T_081c1_row15_col1\" class=\"data row15 col1\" >StratifiedKFold</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
" <td id=\"T_081c1_row16_col0\" class=\"data row16 col0\" >Fold Number</td>\n",
" <td id=\"T_081c1_row16_col1\" class=\"data row16 col1\" >10</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
" <td id=\"T_081c1_row17_col0\" class=\"data row17 col0\" >CPU Jobs</td>\n",
" <td id=\"T_081c1_row17_col1\" class=\"data row17 col1\" >-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
" <td id=\"T_081c1_row18_col0\" class=\"data row18 col0\" >Use GPU</td>\n",
" <td id=\"T_081c1_row18_col1\" class=\"data row18 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
" <td id=\"T_081c1_row19_col0\" class=\"data row19 col0\" >Log Experiment</td>\n",
" <td id=\"T_081c1_row19_col1\" class=\"data row19 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
" <td id=\"T_081c1_row20_col0\" class=\"data row20 col0\" >Experiment Name</td>\n",
" <td id=\"T_081c1_row20_col1\" class=\"data row20 col1\" >clf-default-name</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row21\" class=\"row_heading level0 row21\" >21</th>\n",
" <td id=\"T_081c1_row21_col0\" class=\"data row21 col0\" >USI</td>\n",
" <td id=\"T_081c1_row21_col1\" class=\"data row21 col1\" >e8b1</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row22\" class=\"row_heading level0 row22\" >22</th>\n",
" <td id=\"T_081c1_row22_col0\" class=\"data row22 col0\" >Imputation Type</td>\n",
" <td id=\"T_081c1_row22_col1\" class=\"data row22 col1\" >simple</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row23\" class=\"row_heading level0 row23\" >23</th>\n",
" <td id=\"T_081c1_row23_col0\" class=\"data row23 col0\" >Iterative Imputation Iteration</td>\n",
" <td id=\"T_081c1_row23_col1\" class=\"data row23 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row24\" class=\"row_heading level0 row24\" >24</th>\n",
" <td id=\"T_081c1_row24_col0\" class=\"data row24 col0\" >Numeric Imputer</td>\n",
" <td id=\"T_081c1_row24_col1\" class=\"data row24 col1\" >mean</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row25\" class=\"row_heading level0 row25\" >25</th>\n",
" <td id=\"T_081c1_row25_col0\" class=\"data row25 col0\" >Iterative Imputation Numeric Model</td>\n",
" <td id=\"T_081c1_row25_col1\" class=\"data row25 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row26\" class=\"row_heading level0 row26\" >26</th>\n",
" <td id=\"T_081c1_row26_col0\" class=\"data row26 col0\" >Categorical Imputer</td>\n",
" <td id=\"T_081c1_row26_col1\" class=\"data row26 col1\" >constant</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row27\" class=\"row_heading level0 row27\" >27</th>\n",
" <td id=\"T_081c1_row27_col0\" class=\"data row27 col0\" >Iterative Imputation Categorical Model</td>\n",
" <td id=\"T_081c1_row27_col1\" class=\"data row27 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row28\" class=\"row_heading level0 row28\" >28</th>\n",
" <td id=\"T_081c1_row28_col0\" class=\"data row28 col0\" >Unknown Categoricals Handling</td>\n",
" <td id=\"T_081c1_row28_col1\" class=\"data row28 col1\" >least_frequent</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row29\" class=\"row_heading level0 row29\" >29</th>\n",
" <td id=\"T_081c1_row29_col0\" class=\"data row29 col0\" >Normalize</td>\n",
" <td id=\"T_081c1_row29_col1\" class=\"data row29 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row30\" class=\"row_heading level0 row30\" >30</th>\n",
" <td id=\"T_081c1_row30_col0\" class=\"data row30 col0\" >Normalize Method</td>\n",
" <td id=\"T_081c1_row30_col1\" class=\"data row30 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row31\" class=\"row_heading level0 row31\" >31</th>\n",
" <td id=\"T_081c1_row31_col0\" class=\"data row31 col0\" >Transformation</td>\n",
" <td id=\"T_081c1_row31_col1\" class=\"data row31 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row32\" class=\"row_heading level0 row32\" >32</th>\n",
" <td id=\"T_081c1_row32_col0\" class=\"data row32 col0\" >Transformation Method</td>\n",
" <td id=\"T_081c1_row32_col1\" class=\"data row32 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row33\" class=\"row_heading level0 row33\" >33</th>\n",
" <td id=\"T_081c1_row33_col0\" class=\"data row33 col0\" >PCA</td>\n",
" <td id=\"T_081c1_row33_col1\" class=\"data row33 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row34\" class=\"row_heading level0 row34\" >34</th>\n",
" <td id=\"T_081c1_row34_col0\" class=\"data row34 col0\" >PCA Method</td>\n",
" <td id=\"T_081c1_row34_col1\" class=\"data row34 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row35\" class=\"row_heading level0 row35\" >35</th>\n",
" <td id=\"T_081c1_row35_col0\" class=\"data row35 col0\" >PCA Components</td>\n",
" <td id=\"T_081c1_row35_col1\" class=\"data row35 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row36\" class=\"row_heading level0 row36\" >36</th>\n",
" <td id=\"T_081c1_row36_col0\" class=\"data row36 col0\" >Ignore Low Variance</td>\n",
" <td id=\"T_081c1_row36_col1\" class=\"data row36 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row37\" class=\"row_heading level0 row37\" >37</th>\n",
" <td id=\"T_081c1_row37_col0\" class=\"data row37 col0\" >Combine Rare Levels</td>\n",
" <td id=\"T_081c1_row37_col1\" class=\"data row37 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row38\" class=\"row_heading level0 row38\" >38</th>\n",
" <td id=\"T_081c1_row38_col0\" class=\"data row38 col0\" >Rare Level Threshold</td>\n",
" <td id=\"T_081c1_row38_col1\" class=\"data row38 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row39\" class=\"row_heading level0 row39\" >39</th>\n",
" <td id=\"T_081c1_row39_col0\" class=\"data row39 col0\" >Numeric Binning</td>\n",
" <td id=\"T_081c1_row39_col1\" class=\"data row39 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row40\" class=\"row_heading level0 row40\" >40</th>\n",
" <td id=\"T_081c1_row40_col0\" class=\"data row40 col0\" >Remove Outliers</td>\n",
" <td id=\"T_081c1_row40_col1\" class=\"data row40 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row41\" class=\"row_heading level0 row41\" >41</th>\n",
" <td id=\"T_081c1_row41_col0\" class=\"data row41 col0\" >Outliers Threshold</td>\n",
" <td id=\"T_081c1_row41_col1\" class=\"data row41 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row42\" class=\"row_heading level0 row42\" >42</th>\n",
" <td id=\"T_081c1_row42_col0\" class=\"data row42 col0\" >Remove Multicollinearity</td>\n",
" <td id=\"T_081c1_row42_col1\" class=\"data row42 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row43\" class=\"row_heading level0 row43\" >43</th>\n",
" <td id=\"T_081c1_row43_col0\" class=\"data row43 col0\" >Multicollinearity Threshold</td>\n",
" <td id=\"T_081c1_row43_col1\" class=\"data row43 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row44\" class=\"row_heading level0 row44\" >44</th>\n",
" <td id=\"T_081c1_row44_col0\" class=\"data row44 col0\" >Remove Perfect Collinearity</td>\n",
" <td id=\"T_081c1_row44_col1\" class=\"data row44 col1\" >True</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row45\" class=\"row_heading level0 row45\" >45</th>\n",
" <td id=\"T_081c1_row45_col0\" class=\"data row45 col0\" >Clustering</td>\n",
" <td id=\"T_081c1_row45_col1\" class=\"data row45 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row46\" class=\"row_heading level0 row46\" >46</th>\n",
" <td id=\"T_081c1_row46_col0\" class=\"data row46 col0\" >Clustering Iteration</td>\n",
" <td id=\"T_081c1_row46_col1\" class=\"data row46 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row47\" class=\"row_heading level0 row47\" >47</th>\n",
" <td id=\"T_081c1_row47_col0\" class=\"data row47 col0\" >Polynomial Features</td>\n",
" <td id=\"T_081c1_row47_col1\" class=\"data row47 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row48\" class=\"row_heading level0 row48\" >48</th>\n",
" <td id=\"T_081c1_row48_col0\" class=\"data row48 col0\" >Polynomial Degree</td>\n",
" <td id=\"T_081c1_row48_col1\" class=\"data row48 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row49\" class=\"row_heading level0 row49\" >49</th>\n",
" <td id=\"T_081c1_row49_col0\" class=\"data row49 col0\" >Trignometry Features</td>\n",
" <td id=\"T_081c1_row49_col1\" class=\"data row49 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row50\" class=\"row_heading level0 row50\" >50</th>\n",
" <td id=\"T_081c1_row50_col0\" class=\"data row50 col0\" >Polynomial Threshold</td>\n",
" <td id=\"T_081c1_row50_col1\" class=\"data row50 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row51\" class=\"row_heading level0 row51\" >51</th>\n",
" <td id=\"T_081c1_row51_col0\" class=\"data row51 col0\" >Group Features</td>\n",
" <td id=\"T_081c1_row51_col1\" class=\"data row51 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row52\" class=\"row_heading level0 row52\" >52</th>\n",
" <td id=\"T_081c1_row52_col0\" class=\"data row52 col0\" >Feature Selection</td>\n",
" <td id=\"T_081c1_row52_col1\" class=\"data row52 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row53\" class=\"row_heading level0 row53\" >53</th>\n",
" <td id=\"T_081c1_row53_col0\" class=\"data row53 col0\" >Feature Selection Method</td>\n",
" <td id=\"T_081c1_row53_col1\" class=\"data row53 col1\" >classic</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row54\" class=\"row_heading level0 row54\" >54</th>\n",
" <td id=\"T_081c1_row54_col0\" class=\"data row54 col0\" >Features Selection Threshold</td>\n",
" <td id=\"T_081c1_row54_col1\" class=\"data row54 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row55\" class=\"row_heading level0 row55\" >55</th>\n",
" <td id=\"T_081c1_row55_col0\" class=\"data row55 col0\" >Feature Interaction</td>\n",
" <td id=\"T_081c1_row55_col1\" class=\"data row55 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row56\" class=\"row_heading level0 row56\" >56</th>\n",
" <td id=\"T_081c1_row56_col0\" class=\"data row56 col0\" >Feature Ratio</td>\n",
" <td id=\"T_081c1_row56_col1\" class=\"data row56 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row57\" class=\"row_heading level0 row57\" >57</th>\n",
" <td id=\"T_081c1_row57_col0\" class=\"data row57 col0\" >Interaction Threshold</td>\n",
" <td id=\"T_081c1_row57_col1\" class=\"data row57 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row58\" class=\"row_heading level0 row58\" >58</th>\n",
" <td id=\"T_081c1_row58_col0\" class=\"data row58 col0\" >Fix Imbalance</td>\n",
" <td id=\"T_081c1_row58_col1\" class=\"data row58 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row59\" class=\"row_heading level0 row59\" >59</th>\n",
" <td id=\"T_081c1_row59_col0\" class=\"data row59 col0\" >Fix Imbalance Method</td>\n",
" <td id=\"T_081c1_row59_col1\" class=\"data row59 col1\" >SMOTE</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fe592d54370>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cat_features = ['input_1', 'input_2', 'input_3']\n",
"experiment = setup(df, target='pred', categorical_features=cat_features)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "reverse-brunswick",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
" #T_0fe86_ th {\n",
" text-align: left;\n",
" }#T_0fe86_row0_col0,#T_0fe86_row1_col0,#T_0fe86_row2_col0,#T_0fe86_row2_col2,#T_0fe86_row3_col0,#T_0fe86_row4_col0,#T_0fe86_row5_col0,#T_0fe86_row6_col0,#T_0fe86_row7_col0,#T_0fe86_row8_col0,#T_0fe86_row8_col1,#T_0fe86_row8_col2,#T_0fe86_row8_col4,#T_0fe86_row8_col5,#T_0fe86_row9_col0,#T_0fe86_row9_col1,#T_0fe86_row9_col2,#T_0fe86_row9_col3,#T_0fe86_row9_col4,#T_0fe86_row9_col5,#T_0fe86_row10_col0,#T_0fe86_row10_col1,#T_0fe86_row10_col4,#T_0fe86_row10_col5,#T_0fe86_row11_col0,#T_0fe86_row11_col1,#T_0fe86_row11_col2,#T_0fe86_row11_col4,#T_0fe86_row11_col5,#T_0fe86_row12_col0,#T_0fe86_row12_col1,#T_0fe86_row12_col2,#T_0fe86_row12_col4,#T_0fe86_row12_col5{\n",
" text-align: left;\n",
" text-align: left;\n",
" }#T_0fe86_row0_col1,#T_0fe86_row0_col2,#T_0fe86_row0_col3,#T_0fe86_row0_col4,#T_0fe86_row0_col5,#T_0fe86_row0_col6,#T_0fe86_row0_col7,#T_0fe86_row1_col1,#T_0fe86_row1_col2,#T_0fe86_row1_col3,#T_0fe86_row1_col4,#T_0fe86_row1_col5,#T_0fe86_row1_col6,#T_0fe86_row1_col7,#T_0fe86_row2_col1,#T_0fe86_row2_col3,#T_0fe86_row2_col4,#T_0fe86_row2_col5,#T_0fe86_row2_col6,#T_0fe86_row2_col7,#T_0fe86_row3_col1,#T_0fe86_row3_col2,#T_0fe86_row3_col3,#T_0fe86_row3_col4,#T_0fe86_row3_col5,#T_0fe86_row3_col6,#T_0fe86_row3_col7,#T_0fe86_row4_col1,#T_0fe86_row4_col2,#T_0fe86_row4_col3,#T_0fe86_row4_col4,#T_0fe86_row4_col5,#T_0fe86_row4_col6,#T_0fe86_row4_col7,#T_0fe86_row5_col1,#T_0fe86_row5_col2,#T_0fe86_row5_col3,#T_0fe86_row5_col4,#T_0fe86_row5_col5,#T_0fe86_row5_col6,#T_0fe86_row5_col7,#T_0fe86_row6_col1,#T_0fe86_row6_col2,#T_0fe86_row6_col3,#T_0fe86_row6_col4,#T_0fe86_row6_col5,#T_0fe86_row6_col6,#T_0fe86_row6_col7,#T_0fe86_row7_col1,#T_0fe86_row7_col2,#T_0fe86_row7_col3,#T_0fe86_row7_col4,#T_0fe86_row7_col5,#T_0fe86_row7_col6,#T_0fe86_row7_col7,#T_0fe86_row8_col3,#T_0fe86_row8_col6,#T_0fe86_row8_col7,#T_0fe86_row9_col6,#T_0fe86_row9_col7,#T_0fe86_row10_col2,#T_0fe86_row10_col3,#T_0fe86_row10_col6,#T_0fe86_row10_col7,#T_0fe86_row11_col3,#T_0fe86_row11_col6,#T_0fe86_row11_col7,#T_0fe86_row12_col3,#T_0fe86_row12_col6,#T_0fe86_row12_col7{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: yellow;\n",
" }#T_0fe86_row0_col8,#T_0fe86_row1_col8,#T_0fe86_row3_col8,#T_0fe86_row4_col8,#T_0fe86_row5_col8,#T_0fe86_row6_col8,#T_0fe86_row7_col8,#T_0fe86_row8_col8,#T_0fe86_row9_col8,#T_0fe86_row10_col8,#T_0fe86_row11_col8,#T_0fe86_row12_col8{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: lightgrey;\n",
" }#T_0fe86_row2_col8{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: yellow;\n",
" background-color: lightgrey;\n",
" }</style><table id=\"T_0fe86_\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Model</th> <th class=\"col_heading level0 col1\" >Accuracy</th> <th class=\"col_heading level0 col2\" >AUC</th> <th class=\"col_heading level0 col3\" >Recall</th> <th class=\"col_heading level0 col4\" >Prec.</th> <th class=\"col_heading level0 col5\" >F1</th> <th class=\"col_heading level0 col6\" >Kappa</th> <th class=\"col_heading level0 col7\" >MCC</th> <th class=\"col_heading level0 col8\" >TT (Sec)</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row0\" class=\"row_heading level0 row0\" >lr</th>\n",
" <td id=\"T_0fe86_row0_col0\" class=\"data row0 col0\" >Logistic Regression</td>\n",
" <td id=\"T_0fe86_row0_col1\" class=\"data row0 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row0_col2\" class=\"data row0 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row0_col3\" class=\"data row0 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row0_col4\" class=\"data row0 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row0_col5\" class=\"data row0 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row0_col6\" class=\"data row0 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row0_col7\" class=\"data row0 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row0_col8\" class=\"data row0 col8\" >0.4370</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row1\" class=\"row_heading level0 row1\" >dt</th>\n",
" <td id=\"T_0fe86_row1_col0\" class=\"data row1 col0\" >Decision Tree Classifier</td>\n",
" <td id=\"T_0fe86_row1_col1\" class=\"data row1 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row1_col2\" class=\"data row1 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row1_col3\" class=\"data row1 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row1_col4\" class=\"data row1 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row1_col5\" class=\"data row1 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row1_col6\" class=\"data row1 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row1_col7\" class=\"data row1 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row1_col8\" class=\"data row1 col8\" >0.0450</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row2\" class=\"row_heading level0 row2\" >ridge</th>\n",
" <td id=\"T_0fe86_row2_col0\" class=\"data row2 col0\" >Ridge Classifier</td>\n",
" <td id=\"T_0fe86_row2_col1\" class=\"data row2 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row2_col2\" class=\"data row2 col2\" >0.0000</td>\n",
" <td id=\"T_0fe86_row2_col3\" class=\"data row2 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row2_col4\" class=\"data row2 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row2_col5\" class=\"data row2 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row2_col6\" class=\"data row2 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row2_col7\" class=\"data row2 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row2_col8\" class=\"data row2 col8\" >0.0200</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row3\" class=\"row_heading level0 row3\" >rf</th>\n",
" <td id=\"T_0fe86_row3_col0\" class=\"data row3 col0\" >Random Forest Classifier</td>\n",
" <td id=\"T_0fe86_row3_col1\" class=\"data row3 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row3_col2\" class=\"data row3 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row3_col3\" class=\"data row3 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row3_col4\" class=\"data row3 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row3_col5\" class=\"data row3 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row3_col6\" class=\"data row3 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row3_col7\" class=\"data row3 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row3_col8\" class=\"data row3 col8\" >0.1280</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row4\" class=\"row_heading level0 row4\" >ada</th>\n",
" <td id=\"T_0fe86_row4_col0\" class=\"data row4 col0\" >Ada Boost Classifier</td>\n",
" <td id=\"T_0fe86_row4_col1\" class=\"data row4 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row4_col2\" class=\"data row4 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row4_col3\" class=\"data row4 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row4_col4\" class=\"data row4 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row4_col5\" class=\"data row4 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row4_col6\" class=\"data row4 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row4_col7\" class=\"data row4 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row4_col8\" class=\"data row4 col8\" >0.0490</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row5\" class=\"row_heading level0 row5\" >gbc</th>\n",
" <td id=\"T_0fe86_row5_col0\" class=\"data row5 col0\" >Gradient Boosting Classifier</td>\n",
" <td id=\"T_0fe86_row5_col1\" class=\"data row5 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row5_col2\" class=\"data row5 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row5_col3\" class=\"data row5 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row5_col4\" class=\"data row5 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row5_col5\" class=\"data row5 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row5_col6\" class=\"data row5 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row5_col7\" class=\"data row5 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row5_col8\" class=\"data row5 col8\" >0.3950</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row6\" class=\"row_heading level0 row6\" >et</th>\n",
" <td id=\"T_0fe86_row6_col0\" class=\"data row6 col0\" >Extra Trees Classifier</td>\n",
" <td id=\"T_0fe86_row6_col1\" class=\"data row6 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row6_col2\" class=\"data row6 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row6_col3\" class=\"data row6 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row6_col4\" class=\"data row6 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row6_col5\" class=\"data row6 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row6_col6\" class=\"data row6 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row6_col7\" class=\"data row6 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row6_col8\" class=\"data row6 col8\" >0.1700</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row7\" class=\"row_heading level0 row7\" >lightgbm</th>\n",
" <td id=\"T_0fe86_row7_col0\" class=\"data row7 col0\" >Light Gradient Boosting Machine</td>\n",
" <td id=\"T_0fe86_row7_col1\" class=\"data row7 col1\" >0.1852</td>\n",
" <td id=\"T_0fe86_row7_col2\" class=\"data row7 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row7_col3\" class=\"data row7 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row7_col4\" class=\"data row7 col4\" >0.0343</td>\n",
" <td id=\"T_0fe86_row7_col5\" class=\"data row7 col5\" >0.0579</td>\n",
" <td id=\"T_0fe86_row7_col6\" class=\"data row7 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row7_col7\" class=\"data row7 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row7_col8\" class=\"data row7 col8\" >0.0320</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row8\" class=\"row_heading level0 row8\" >svm</th>\n",
" <td id=\"T_0fe86_row8_col0\" class=\"data row8 col0\" >SVM - Linear Kernel</td>\n",
" <td id=\"T_0fe86_row8_col1\" class=\"data row8 col1\" >0.1698</td>\n",
" <td id=\"T_0fe86_row8_col2\" class=\"data row8 col2\" >0.0000</td>\n",
" <td id=\"T_0fe86_row8_col3\" class=\"data row8 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row8_col4\" class=\"data row8 col4\" >0.0290</td>\n",
" <td id=\"T_0fe86_row8_col5\" class=\"data row8 col5\" >0.0495</td>\n",
" <td id=\"T_0fe86_row8_col6\" class=\"data row8 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row8_col7\" class=\"data row8 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row8_col8\" class=\"data row8 col8\" >0.0400</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row9\" class=\"row_heading level0 row9\" >lda</th>\n",
" <td id=\"T_0fe86_row9_col0\" class=\"data row9 col0\" >Linear Discriminant Analysis</td>\n",
" <td id=\"T_0fe86_row9_col1\" class=\"data row9 col1\" >0.1667</td>\n",
" <td id=\"T_0fe86_row9_col2\" class=\"data row9 col2\" >0.4464</td>\n",
" <td id=\"T_0fe86_row9_col3\" class=\"data row9 col3\" >0.1500</td>\n",
" <td id=\"T_0fe86_row9_col4\" class=\"data row9 col4\" >0.0309</td>\n",
" <td id=\"T_0fe86_row9_col5\" class=\"data row9 col5\" >0.0521</td>\n",
" <td id=\"T_0fe86_row9_col6\" class=\"data row9 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row9_col7\" class=\"data row9 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row9_col8\" class=\"data row9 col8\" >0.0570</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row10\" class=\"row_heading level0 row10\" >knn</th>\n",
" <td id=\"T_0fe86_row10_col0\" class=\"data row10 col0\" >K Neighbors Classifier</td>\n",
" <td id=\"T_0fe86_row10_col1\" class=\"data row10 col1\" >0.1543</td>\n",
" <td id=\"T_0fe86_row10_col2\" class=\"data row10 col2\" >0.5000</td>\n",
" <td id=\"T_0fe86_row10_col3\" class=\"data row10 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row10_col4\" class=\"data row10 col4\" >0.0238</td>\n",
" <td id=\"T_0fe86_row10_col5\" class=\"data row10 col5\" >0.0413</td>\n",
" <td id=\"T_0fe86_row10_col6\" class=\"data row10 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row10_col7\" class=\"data row10 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row10_col8\" class=\"data row10 col8\" >0.0380</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row11\" class=\"row_heading level0 row11\" >nb</th>\n",
" <td id=\"T_0fe86_row11_col0\" class=\"data row11 col0\" >Naive Bayes</td>\n",
" <td id=\"T_0fe86_row11_col1\" class=\"data row11 col1\" >0.1543</td>\n",
" <td id=\"T_0fe86_row11_col2\" class=\"data row11 col2\" >0.4939</td>\n",
" <td id=\"T_0fe86_row11_col3\" class=\"data row11 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row11_col4\" class=\"data row11 col4\" >0.0238</td>\n",
" <td id=\"T_0fe86_row11_col5\" class=\"data row11 col5\" >0.0413</td>\n",
" <td id=\"T_0fe86_row11_col6\" class=\"data row11 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row11_col7\" class=\"data row11 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row11_col8\" class=\"data row11 col8\" >0.0300</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0fe86_level0_row12\" class=\"row_heading level0 row12\" >qda</th>\n",
" <td id=\"T_0fe86_row12_col0\" class=\"data row12 col0\" >Quadratic Discriminant Analysis</td>\n",
" <td id=\"T_0fe86_row12_col1\" class=\"data row12 col1\" >0.1420</td>\n",
" <td id=\"T_0fe86_row12_col2\" class=\"data row12 col2\" >0.0000</td>\n",
" <td id=\"T_0fe86_row12_col3\" class=\"data row12 col3\" >0.1667</td>\n",
" <td id=\"T_0fe86_row12_col4\" class=\"data row12 col4\" >0.0203</td>\n",
" <td id=\"T_0fe86_row12_col5\" class=\"data row12 col5\" >0.0355</td>\n",
" <td id=\"T_0fe86_row12_col6\" class=\"data row12 col6\" >0.0000</td>\n",
" <td id=\"T_0fe86_row12_col7\" class=\"data row12 col7\" >0.0000</td>\n",
" <td id=\"T_0fe86_row12_col8\" class=\"data row12 col8\" >0.0300</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fe5be09cd00>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"best_model = compare_models()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "editorial-culture",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
" #T_cc34d_ th {\n",
" text-align: left;\n",
" }#T_cc34d_row0_col0,#T_cc34d_row0_col4,#T_cc34d_row1_col0,#T_cc34d_row1_col1,#T_cc34d_row1_col3,#T_cc34d_row1_col5,#T_cc34d_row1_col6,#T_cc34d_row1_col7,#T_cc34d_row2_col0,#T_cc34d_row2_col1,#T_cc34d_row2_col3,#T_cc34d_row2_col4,#T_cc34d_row2_col5,#T_cc34d_row2_col6,#T_cc34d_row2_col7,#T_cc34d_row3_col0,#T_cc34d_row3_col1,#T_cc34d_row3_col3,#T_cc34d_row3_col4,#T_cc34d_row3_col5,#T_cc34d_row3_col6,#T_cc34d_row3_col7,#T_cc34d_row4_col0,#T_cc34d_row4_col1,#T_cc34d_row4_col3,#T_cc34d_row4_col4,#T_cc34d_row4_col5,#T_cc34d_row4_col6,#T_cc34d_row4_col7,#T_cc34d_row5_col0,#T_cc34d_row5_col1,#T_cc34d_row5_col3,#T_cc34d_row5_col4,#T_cc34d_row5_col5,#T_cc34d_row5_col6,#T_cc34d_row5_col7,#T_cc34d_row6_col0,#T_cc34d_row6_col1,#T_cc34d_row6_col3,#T_cc34d_row6_col4,#T_cc34d_row6_col5,#T_cc34d_row6_col6,#T_cc34d_row6_col7,#T_cc34d_row7_col0,#T_cc34d_row7_col1,#T_cc34d_row7_col3,#T_cc34d_row7_col4,#T_cc34d_row7_col5,#T_cc34d_row7_col6,#T_cc34d_row7_col7,#T_cc34d_row8_col0,#T_cc34d_row8_col1,#T_cc34d_row8_col3,#T_cc34d_row8_col4,#T_cc34d_row8_col5,#T_cc34d_row8_col6,#T_cc34d_row8_col7,#T_cc34d_row9_col0,#T_cc34d_row9_col1,#T_cc34d_row9_col3,#T_cc34d_row9_col4,#T_cc34d_row9_col5,#T_cc34d_row9_col6,#T_cc34d_row9_col7,#T_cc34d_row10_col0,#T_cc34d_row10_col1,#T_cc34d_row10_col3,#T_cc34d_row10_col4,#T_cc34d_row10_col5,#T_cc34d_row10_col6,#T_cc34d_row10_col7,#T_cc34d_row11_col0,#T_cc34d_row11_col1,#T_cc34d_row11_col3,#T_cc34d_row11_col4,#T_cc34d_row11_col5,#T_cc34d_row11_col6,#T_cc34d_row11_col7,#T_cc34d_row12_col0,#T_cc34d_row12_col1,#T_cc34d_row12_col3,#T_cc34d_row12_col4,#T_cc34d_row12_col5,#T_cc34d_row12_col6,#T_cc34d_row12_col7{\n",
" text-align: left;\n",
" text-align: left;\n",
" }#T_cc34d_row0_col1,#T_cc34d_row0_col2,#T_cc34d_row0_col3,#T_cc34d_row0_col5,#T_cc34d_row0_col6,#T_cc34d_row0_col7,#T_cc34d_row1_col2,#T_cc34d_row1_col4,#T_cc34d_row2_col2,#T_cc34d_row3_col2,#T_cc34d_row4_col2,#T_cc34d_row5_col2,#T_cc34d_row6_col2,#T_cc34d_row7_col2,#T_cc34d_row8_col2,#T_cc34d_row9_col2,#T_cc34d_row10_col2,#T_cc34d_row11_col2,#T_cc34d_row12_col2{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: yellow;\n",
" }#T_cc34d_row0_col8,#T_cc34d_row1_col8,#T_cc34d_row2_col8,#T_cc34d_row3_col8,#T_cc34d_row4_col8,#T_cc34d_row5_col8,#T_cc34d_row6_col8,#T_cc34d_row7_col8,#T_cc34d_row8_col8,#T_cc34d_row9_col8,#T_cc34d_row10_col8,#T_cc34d_row11_col8{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: lightgrey;\n",
" }#T_cc34d_row12_col8{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: yellow;\n",
" background-color: lightgrey;\n",
" }</style><table id=\"T_cc34d_\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Model</th> <th class=\"col_heading level0 col1\" >Accuracy</th> <th class=\"col_heading level0 col2\" >AUC</th> <th class=\"col_heading level0 col3\" >Recall</th> <th class=\"col_heading level0 col4\" >Prec.</th> <th class=\"col_heading level0 col5\" >F1</th> <th class=\"col_heading level0 col6\" >Kappa</th> <th class=\"col_heading level0 col7\" >MCC</th> <th class=\"col_heading level0 col8\" >TT (Sec)</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row0\" class=\"row_heading level0 row0\" >nb</th>\n",
" <td id=\"T_cc34d_row0_col0\" class=\"data row0 col0\" >Naive Bayes</td>\n",
" <td id=\"T_cc34d_row0_col1\" class=\"data row0 col1\" >0.9540</td>\n",
" <td id=\"T_cc34d_row0_col2\" class=\"data row0 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row0_col3\" class=\"data row0 col3\" >0.9134</td>\n",
" <td id=\"T_cc34d_row0_col4\" class=\"data row0 col4\" >0.9426</td>\n",
" <td id=\"T_cc34d_row0_col5\" class=\"data row0 col5\" >0.9468</td>\n",
" <td id=\"T_cc34d_row0_col6\" class=\"data row0 col6\" >0.9508</td>\n",
" <td id=\"T_cc34d_row0_col7\" class=\"data row0 col7\" >0.9521</td>\n",
" <td id=\"T_cc34d_row0_col8\" class=\"data row0 col8\" >0.0070</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row1\" class=\"row_heading level0 row1\" >svm</th>\n",
" <td id=\"T_cc34d_row1_col0\" class=\"data row1 col0\" >SVM - Linear Kernel</td>\n",
" <td id=\"T_cc34d_row1_col1\" class=\"data row1 col1\" >0.9511</td>\n",
" <td id=\"T_cc34d_row1_col2\" class=\"data row1 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row1_col3\" class=\"data row1 col3\" >0.9012</td>\n",
" <td id=\"T_cc34d_row1_col4\" class=\"data row1 col4\" >0.9429</td>\n",
" <td id=\"T_cc34d_row1_col5\" class=\"data row1 col5\" >0.9459</td>\n",
" <td id=\"T_cc34d_row1_col6\" class=\"data row1 col6\" >0.9476</td>\n",
" <td id=\"T_cc34d_row1_col7\" class=\"data row1 col7\" >0.9489</td>\n",
" <td id=\"T_cc34d_row1_col8\" class=\"data row1 col8\" >0.0150</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row2\" class=\"row_heading level0 row2\" >rf</th>\n",
" <td id=\"T_cc34d_row2_col0\" class=\"data row2 col0\" >Random Forest Classifier</td>\n",
" <td id=\"T_cc34d_row2_col1\" class=\"data row2 col1\" >0.8966</td>\n",
" <td id=\"T_cc34d_row2_col2\" class=\"data row2 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row2_col3\" class=\"data row2 col3\" >0.8296</td>\n",
" <td id=\"T_cc34d_row2_col4\" class=\"data row2 col4\" >0.8688</td>\n",
" <td id=\"T_cc34d_row2_col5\" class=\"data row2 col5\" >0.8783</td>\n",
" <td id=\"T_cc34d_row2_col6\" class=\"data row2 col6\" >0.8893</td>\n",
" <td id=\"T_cc34d_row2_col7\" class=\"data row2 col7\" >0.8922</td>\n",
" <td id=\"T_cc34d_row2_col8\" class=\"data row2 col8\" >0.0930</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row3\" class=\"row_heading level0 row3\" >et</th>\n",
" <td id=\"T_cc34d_row3_col0\" class=\"data row3 col0\" >Extra Trees Classifier</td>\n",
" <td id=\"T_cc34d_row3_col1\" class=\"data row3 col1\" >0.8880</td>\n",
" <td id=\"T_cc34d_row3_col2\" class=\"data row3 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row3_col3\" class=\"data row3 col3\" >0.8140</td>\n",
" <td id=\"T_cc34d_row3_col4\" class=\"data row3 col4\" >0.8636</td>\n",
" <td id=\"T_cc34d_row3_col5\" class=\"data row3 col5\" >0.8721</td>\n",
" <td id=\"T_cc34d_row3_col6\" class=\"data row3 col6\" >0.8802</td>\n",
" <td id=\"T_cc34d_row3_col7\" class=\"data row3 col7\" >0.8829</td>\n",
" <td id=\"T_cc34d_row3_col8\" class=\"data row3 col8\" >0.0730</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row4\" class=\"row_heading level0 row4\" >dt</th>\n",
" <td id=\"T_cc34d_row4_col0\" class=\"data row4 col0\" >Decision Tree Classifier</td>\n",
" <td id=\"T_cc34d_row4_col1\" class=\"data row4 col1\" >0.8824</td>\n",
" <td id=\"T_cc34d_row4_col2\" class=\"data row4 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row4_col3\" class=\"data row4 col3\" >0.7896</td>\n",
" <td id=\"T_cc34d_row4_col4\" class=\"data row4 col4\" >0.8576</td>\n",
" <td id=\"T_cc34d_row4_col5\" class=\"data row4 col5\" >0.8661</td>\n",
" <td id=\"T_cc34d_row4_col6\" class=\"data row4 col6\" >0.8743</td>\n",
" <td id=\"T_cc34d_row4_col7\" class=\"data row4 col7\" >0.8776</td>\n",
" <td id=\"T_cc34d_row4_col8\" class=\"data row4 col8\" >0.0070</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row5\" class=\"row_heading level0 row5\" >lr</th>\n",
" <td id=\"T_cc34d_row5_col0\" class=\"data row5 col0\" >Logistic Regression</td>\n",
" <td id=\"T_cc34d_row5_col1\" class=\"data row5 col1\" >0.8737</td>\n",
" <td id=\"T_cc34d_row5_col2\" class=\"data row5 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row5_col3\" class=\"data row5 col3\" >0.8046</td>\n",
" <td id=\"T_cc34d_row5_col4\" class=\"data row5 col4\" >0.8308</td>\n",
" <td id=\"T_cc34d_row5_col5\" class=\"data row5 col5\" >0.8449</td>\n",
" <td id=\"T_cc34d_row5_col6\" class=\"data row5 col6\" >0.8646</td>\n",
" <td id=\"T_cc34d_row5_col7\" class=\"data row5 col7\" >0.8685</td>\n",
" <td id=\"T_cc34d_row5_col8\" class=\"data row5 col8\" >0.0200</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row6\" class=\"row_heading level0 row6\" >gbc</th>\n",
" <td id=\"T_cc34d_row6_col0\" class=\"data row6 col0\" >Gradient Boosting Classifier</td>\n",
" <td id=\"T_cc34d_row6_col1\" class=\"data row6 col1\" >0.8735</td>\n",
" <td id=\"T_cc34d_row6_col2\" class=\"data row6 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row6_col3\" class=\"data row6 col3\" >0.8024</td>\n",
" <td id=\"T_cc34d_row6_col4\" class=\"data row6 col4\" >0.8337</td>\n",
" <td id=\"T_cc34d_row6_col5\" class=\"data row6 col5\" >0.8468</td>\n",
" <td id=\"T_cc34d_row6_col6\" class=\"data row6 col6\" >0.8644</td>\n",
" <td id=\"T_cc34d_row6_col7\" class=\"data row6 col7\" >0.8681</td>\n",
" <td id=\"T_cc34d_row6_col8\" class=\"data row6 col8\" >1.0480</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row7\" class=\"row_heading level0 row7\" >lda</th>\n",
" <td id=\"T_cc34d_row7_col0\" class=\"data row7 col0\" >Linear Discriminant Analysis</td>\n",
" <td id=\"T_cc34d_row7_col1\" class=\"data row7 col1\" >0.8224</td>\n",
" <td id=\"T_cc34d_row7_col2\" class=\"data row7 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row7_col3\" class=\"data row7 col3\" >0.8178</td>\n",
" <td id=\"T_cc34d_row7_col4\" class=\"data row7 col4\" >0.9004</td>\n",
" <td id=\"T_cc34d_row7_col5\" class=\"data row7 col5\" >0.8324</td>\n",
" <td id=\"T_cc34d_row7_col6\" class=\"data row7 col6\" >0.8142</td>\n",
" <td id=\"T_cc34d_row7_col7\" class=\"data row7 col7\" >0.8238</td>\n",
" <td id=\"T_cc34d_row7_col8\" class=\"data row7 col8\" >0.0110</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row8\" class=\"row_heading level0 row8\" >ridge</th>\n",
" <td id=\"T_cc34d_row8_col0\" class=\"data row8 col0\" >Ridge Classifier</td>\n",
" <td id=\"T_cc34d_row8_col1\" class=\"data row8 col1\" >0.7648</td>\n",
" <td id=\"T_cc34d_row8_col2\" class=\"data row8 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row8_col3\" class=\"data row8 col3\" >0.6448</td>\n",
" <td id=\"T_cc34d_row8_col4\" class=\"data row8 col4\" >0.6944</td>\n",
" <td id=\"T_cc34d_row8_col5\" class=\"data row8 col5\" >0.7178</td>\n",
" <td id=\"T_cc34d_row8_col6\" class=\"data row8 col6\" >0.7483</td>\n",
" <td id=\"T_cc34d_row8_col7\" class=\"data row8 col7\" >0.7536</td>\n",
" <td id=\"T_cc34d_row8_col8\" class=\"data row8 col8\" >0.0070</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row9\" class=\"row_heading level0 row9\" >knn</th>\n",
" <td id=\"T_cc34d_row9_col0\" class=\"data row9 col0\" >K Neighbors Classifier</td>\n",
" <td id=\"T_cc34d_row9_col1\" class=\"data row9 col1\" >0.7245</td>\n",
" <td id=\"T_cc34d_row9_col2\" class=\"data row9 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row9_col3\" class=\"data row9 col3\" >0.6068</td>\n",
" <td id=\"T_cc34d_row9_col4\" class=\"data row9 col4\" >0.6581</td>\n",
" <td id=\"T_cc34d_row9_col5\" class=\"data row9 col5\" >0.6783</td>\n",
" <td id=\"T_cc34d_row9_col6\" class=\"data row9 col6\" >0.7049</td>\n",
" <td id=\"T_cc34d_row9_col7\" class=\"data row9 col7\" >0.7134</td>\n",
" <td id=\"T_cc34d_row9_col8\" class=\"data row9 col8\" >0.0100</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row10\" class=\"row_heading level0 row10\" >lightgbm</th>\n",
" <td id=\"T_cc34d_row10_col0\" class=\"data row10 col0\" >Light Gradient Boosting Machine</td>\n",
" <td id=\"T_cc34d_row10_col1\" class=\"data row10 col1\" >0.7020</td>\n",
" <td id=\"T_cc34d_row10_col2\" class=\"data row10 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row10_col3\" class=\"data row10 col3\" >0.5602</td>\n",
" <td id=\"T_cc34d_row10_col4\" class=\"data row10 col4\" >0.6662</td>\n",
" <td id=\"T_cc34d_row10_col5\" class=\"data row10 col5\" >0.6769</td>\n",
" <td id=\"T_cc34d_row10_col6\" class=\"data row10 col6\" >0.6820</td>\n",
" <td id=\"T_cc34d_row10_col7\" class=\"data row10 col7\" >0.6896</td>\n",
" <td id=\"T_cc34d_row10_col8\" class=\"data row10 col8\" >0.1150</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row11\" class=\"row_heading level0 row11\" >ada</th>\n",
" <td id=\"T_cc34d_row11_col0\" class=\"data row11 col0\" >Ada Boost Classifier</td>\n",
" <td id=\"T_cc34d_row11_col1\" class=\"data row11 col1\" >0.2665</td>\n",
" <td id=\"T_cc34d_row11_col2\" class=\"data row11 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row11_col3\" class=\"data row11 col3\" >0.1133</td>\n",
" <td id=\"T_cc34d_row11_col4\" class=\"data row11 col4\" >0.2253</td>\n",
" <td id=\"T_cc34d_row11_col5\" class=\"data row11 col5\" >0.2293</td>\n",
" <td id=\"T_cc34d_row11_col6\" class=\"data row11 col6\" >0.2141</td>\n",
" <td id=\"T_cc34d_row11_col7\" class=\"data row11 col7\" >0.3162</td>\n",
" <td id=\"T_cc34d_row11_col8\" class=\"data row11 col8\" >0.0370</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_cc34d_level0_row12\" class=\"row_heading level0 row12\" >qda</th>\n",
" <td id=\"T_cc34d_row12_col0\" class=\"data row12 col0\" >Quadratic Discriminant Analysis</td>\n",
" <td id=\"T_cc34d_row12_col1\" class=\"data row12 col1\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col2\" class=\"data row12 col2\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col3\" class=\"data row12 col3\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col4\" class=\"data row12 col4\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col5\" class=\"data row12 col5\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col6\" class=\"data row12 col6\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col7\" class=\"data row12 col7\" >0.0000</td>\n",
" <td id=\"T_cc34d_row12_col8\" class=\"data row12 col8\" >0.0040</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fa819dc5490>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"top3 = compare_models(n_select = 3)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "documentary-flooring",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Transformation Pipeline and Model Successfully Saved\n"
]
},
{
"data": {
"text/plain": [
"(Pipeline(memory=None,\n",
" steps=[('dtypes',\n",
" DataTypes_Auto_infer(categorical_features=['Category Number',\n",
" 'Rating No'],\n",
" display_types=True, features_todrop=[],\n",
" id_columns=[],\n",
" ml_usecase='classification',\n",
" numerical_features=[],\n",
" target='Meal Plan No',\n",
" time_features=[])),\n",
" ('imputer',\n",
" Simple_Imputer(categorical_strategy='not_available',\n",
" fill_value_categorical=None,\n",
" fill_val...\n",
" ('binn', 'passthrough'), ('rem_outliers', 'passthrough'),\n",
" ('cluster_all', 'passthrough'),\n",
" ('dummy', Dummify(target='Meal Plan No')),\n",
" ('fix_perfect', Remove_100(target='Meal Plan No')),\n",
" ('clean_names', Clean_Colum_Names()),\n",
" ('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),\n",
" ('dfs', 'passthrough'), ('pca', 'passthrough'),\n",
" ['trained_model',\n",
" GaussianNB(priors=None, var_smoothing=1e-09)]],\n",
" verbose=False),\n",
" 'meal_plan_naive_bayes.pkl')"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"save_model(top3[0], model_name='meal_plan_naive_bayes')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "egyptian-manor",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
backend/smart_assistant/EmotionEnv.py 0 → 100644
View file @ 2fbef0f4
from gym import Env
from gym.spaces import Discrete, Box
import numpy as np
import random
class EmotionEnv(Env):
def __init__(self):
# Actions we can take, down, stay, up
self.action_space = Discrete(3)
# Friends array
self.observation_space = Box(low=np.array([0]), high=np.array([10]))
# Set start emotion
self.state = 3 + random.randint(-3, 3)
# Set emotion length
self.emotion_length = 60
def step(self, action):
# should take actions by human
# print('This is suggested friend id', action)
# self.state += int(input("Enter your emotional level : "))
self.state = action
# Reduce emotion length by 1 second
self.emotion_length -= 1
reward = 0
# Calculate reward
if self.state == 0:
reward = -2
elif self.state == 1:
reward = -1
elif self.state == 2:
reward = 1
elif self.state == 3:
reward = 2
elif self.state == 4:
reward = 3
elif self.state == 5:
reward = 4
# Check if emotion is done
if self.emotion_length <= 0:
done = True
else:
done = False
# self.state += random.randint(-1,1)
# Set placeholder for info
info = {}
# Return step information
return self.state, reward, done, info
def render(self):
# Implement viz
pass
def reset(self):
# Reset emotion state
self.state = 38 + random.randint(-3, 3)
# Reset emotion time
self.shower_length = 60
return self.state
backend/smart_assistant/api.py 0 → 100644
View file @ 2fbef0f4
from flask import Flask, request, url_for, redirect, render_template
from flask_cors import CORS
import json
import os
import EmotionEnv
from pycaret.classification import *
import numpy as np
env = EmotionEnv.EmotionEnv()
env.observation_space.sample()
state = env.reset()
done = False
score = 0
model = load_model('Logistic_Regression')
app = Flask(__name__)
CORS(app)
@app.route('/', methods=['GET', 'POST'])
def welcome():
return_str = '{ "status" : "app works" }'
return json.loads(return_str)
@app.route('/friend_suggestion', methods=['GET', 'POST'])
def friend_suggestion():
input_1 = request.form['input_1']
input_2 = request.form['input_2']
input_3 = request.form['input_3']
global score
data = np.array([['input_1', 'input_2', 'input_3'], [input_1, input_2, input_3]])
result = predict_model(model, data=pd.DataFrame(data=data[0:, 0:], index=data[0:, 0], columns=data[0, 0:])).iat[1, 3]
print(result)
action = env.action_space.sample()
n_state, reward, done, info = env.step(action)
score += int(result)
return_str = '{ "suggested_friend_id" : ' + str(action) + '}'
print(return_str)
return json.loads(return_str)
if __name__ == '__main__':
app.run(host="0.0.0.0", port=5500, debug=True)
backend/smart_assistant/checkpoint 0 → 100644
View file @ 2fbef0f4
model_checkpoint_path: "dqn_weights.h5f"
all_model_checkpoint_paths: "dqn_weights.h5f"
backend/smart_assistant/logs.log 0 → 100644
View file @ 2fbef0f4
2022-05-06 16:30:15,144:INFO:PyCaret Supervised Module
2022-05-06 16:30:15,145:INFO:ML Usecase: classification
2022-05-06 16:30:15,145:INFO:version 2.3.3
2022-05-06 16:30:15,145:INFO:Initializing setup()
2022-05-06 16:30:15,145:INFO:setup(target=pred, ml_usecase=classification, available_plots={'parameter': 'Hyperparameters', 'auc': 'AUC', 'confusion_matrix': 'Confusion Matrix', 'threshold': 'Threshold', 'pr': 'Precision Recall', 'error': 'Prediction Error', 'class_report': 'Class Report', 'rfe': 'Feature Selection', 'learning': 'Learning Curve', 'manifold': 'Manifold Learning', 'calibration': 'Calibration Curve', 'vc': 'Validation Curve', 'dimension': 'Dimensions', 'feature': 'Feature Importance', 'feature_all': 'Feature Importance (All)', 'boundary': 'Decision Boundary', 'lift': 'Lift Chart', 'gain': 'Gain Chart', 'tree': 'Decision Tree', 'ks': 'KS Statistic Plot'}, train_size=0.7, test_data=None, preprocess=True, imputation_type=simple, iterative_imputation_iters=5, categorical_features=['input_1', 'input_2', 'input_3'], categorical_imputation=constant, categorical_iterative_imputer=lightgbm, ordinal_features=None, high_cardinality_features=None, high_cardinality_method=frequency, numeric_features=None, numeric_imputation=mean, numeric_iterative_imputer=lightgbm, date_features=None, ignore_features=None, normalize=False, normalize_method=zscore, transformation=False, transformation_method=yeo-johnson, handle_unknown_categorical=True, unknown_categorical_method=least_frequent, pca=False, pca_method=linear, pca_components=None, ignore_low_variance=False, combine_rare_levels=False, rare_level_threshold=0.1, bin_numeric_features=None, remove_outliers=False, outliers_threshold=0.05, remove_multicollinearity=False, multicollinearity_threshold=0.9, remove_perfect_collinearity=True, create_clusters=False, cluster_iter=20, polynomial_features=False, polynomial_degree=2, trigonometry_features=False, polynomial_threshold=0.1, group_features=None, group_names=None, feature_selection=False, feature_selection_threshold=0.8, feature_selection_method=classic, feature_interaction=False, feature_ratio=False, interaction_threshold=0.01, fix_imbalance=False, fix_imbalance_method=None, transform_target=False, transform_target_method=box-cox, data_split_shuffle=True, data_split_stratify=False, fold_strategy=stratifiedkfold, fold=10, fold_shuffle=False, fold_groups=None, n_jobs=-1, use_gpu=False, custom_pipeline=None, html=True, session_id=None, log_experiment=False, experiment_name=None, log_plots=False, log_profile=False, log_data=False, silent=False, verbose=True, profile=False, profile_kwargs=None, display=None)
2022-05-06 16:30:15,145:INFO:Checking environment
2022-05-06 16:30:15,146:INFO:python_version: 3.8.5
2022-05-06 16:30:15,146:INFO:python_build: ('default', 'Sep 4 2020 02:22:02')
2022-05-06 16:30:15,146:INFO:machine: x86_64
2022-05-06 16:30:15,160:INFO:platform: macOS-10.16-x86_64-i386-64bit
2022-05-06 16:30:15,162:WARNING:cannot find psutil installation. memory not traceable. Install psutil using pip to enable memory logging.
2022-05-06 16:30:15,162:INFO:Checking libraries
2022-05-06 16:30:15,162:INFO:pd==1.2.2
2022-05-06 16:30:15,162:INFO:numpy==1.19.5
2022-05-06 16:30:15,162:INFO:sklearn==0.23.2
2022-05-06 16:30:15,162:INFO:lightgbm==3.2.1
2022-05-06 16:30:15,163:WARNING:catboost not found
2022-05-06 16:30:15,163:WARNING:xgboost not found
2022-05-06 16:30:16,122:INFO:mlflow==1.20.2
2022-05-06 16:30:16,123:INFO:Checking Exceptions
2022-05-06 16:30:16,123:INFO:Declaring global variables
2022-05-06 16:30:16,123:INFO:USI: e8b1
2022-05-06 16:30:16,123:INFO:pycaret_globals: {'log_plots_param', 'iterative_imputation_iters_param', 'n_jobs_param', 'create_model_container', '_ml_usecase', '_all_metrics', 'transform_target_method_param', '_all_models', 'X_train', 'gpu_param', 'X_test', 'pycaret_globals', 'master_model_container', 'experiment__', 'fold_shuffle_param', 'y_train', 'html_param', 'fold_param', 'logging_param', '_all_models_internal', 'fix_imbalance_param', 'transform_target_param', 'USI', 'exp_name_log', 'imputation_classifier', 'display_container', 'fold_groups_param_full', '_internal_pipeline', 'prep_pipe', '_available_plots', 'imputation_regressor', 'fold_generator', 'fix_imbalance_method_param', 'y_test', '_gpu_n_jobs_param', 'target_param', 'data_before_preprocess', 'seed', 'stratify_param', 'fold_groups_param', 'y', 'X'}
2022-05-06 16:30:16,123:INFO:Preparing display monitor
2022-05-06 16:30:16,123:INFO:Preparing display monitor
2022-05-06 16:30:16,137:INFO:Importing libraries
2022-05-06 16:30:16,137:INFO:Copying data for preprocessing
2022-05-06 16:30:16,144:INFO:Declaring preprocessing parameters
2022-05-06 16:30:16,145:INFO:Creating preprocessing pipeline
2022-05-06 16:30:16,153:INFO:Preprocessing pipeline created successfully
2022-05-06 16:30:16,153:ERROR:(Process Exit): setup has been interupted with user command 'quit'. setup must rerun.
2022-05-06 16:30:16,153:INFO:Creating global containers
2022-05-06 16:30:16,156:INFO:Internal pipeline: Pipeline(memory=None, steps=[('empty_step', 'passthrough')], verbose=False)
2022-05-06 16:30:20,035:WARNING:Couldn't import xgboost.XGBClassifier
2022-05-06 16:30:20,036:WARNING:Couldn't import catboost.CatBoostClassifier
2022-05-06 16:30:20,114:WARNING:Couldn't import xgboost.XGBClassifier
2022-05-06 16:30:20,114:WARNING:Couldn't import catboost.CatBoostClassifier
2022-05-06 16:30:20,115:INFO:Creating grid variables
2022-05-06 16:30:20,136:INFO:create_model_container: 0
2022-05-06 16:30:20,136:INFO:master_model_container: 0
2022-05-06 16:30:20,137:INFO:display_container: 1
2022-05-06 16:30:20,143:INFO:Pipeline(memory=None,
steps=[('dtypes',
DataTypes_Auto_infer(categorical_features=['input_1',
'input_2',
'input_3'],
display_types=True, features_todrop=[],
id_columns=[],
ml_usecase='classification',
numerical_features=[], target='pred',
time_features=[])),
('imputer',
Simple_Imputer(categorical_strategy='not_available',
fill_value_categorical=None,
fill_value_n...
('scaling', 'passthrough'), ('P_transform', 'passthrough'),
('binn', 'passthrough'), ('rem_outliers', 'passthrough'),
('cluster_all', 'passthrough'),
('dummy', Dummify(target='pred')),
('fix_perfect', Remove_100(target='pred')),
('clean_names', Clean_Colum_Names()),
('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),
('dfs', 'passthrough'), ('pca', 'passthrough')],
verbose=False)
2022-05-06 16:30:20,143:INFO:setup() succesfully completed......................................
2022-05-06 16:30:25,217:INFO:Initializing compare_models()
2022-05-06 16:30:25,218:INFO:compare_models(include=None, fold=None, round=4, cross_validation=True, sort=Accuracy, n_select=1, budget_time=None, turbo=True, errors=ignore, fit_kwargs=None, groups=None, verbose=True, display=None, exclude=None)
2022-05-06 16:30:25,218:INFO:Checking exceptions
2022-05-06 16:30:25,219:INFO:Preparing display monitor
2022-05-06 16:30:25,219:INFO:Preparing display monitor
2022-05-06 16:30:25,265:INFO:Initializing Logistic Regression
2022-05-06 16:30:25,266:INFO:Total runtime is 1.2250741322835286e-05 minutes
2022-05-06 16:30:25,282:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:25,282:INFO:Initializing create_model()
2022-05-06 16:30:25,283:INFO:create_model(estimator=lr, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:25,283:INFO:Checking exceptions
2022-05-06 16:30:25,284:INFO:Importing libraries
2022-05-06 16:30:25,284:INFO:Copying training dataset
2022-05-06 16:30:25,286:INFO:Defining folds
2022-05-06 16:30:25,286:INFO:Declaring metric variables
2022-05-06 16:30:25,301:INFO:Importing untrained model
2022-05-06 16:30:25,317:INFO:Logistic Regression Imported succesfully
2022-05-06 16:30:25,345:INFO:Starting cross validation
2022-05-06 16:30:25,346:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:29,718:INFO:Calculating mean and std
2022-05-06 16:30:29,720:INFO:Creating metrics dataframe
2022-05-06 16:30:29,728:INFO:Uploading results into container
2022-05-06 16:30:29,729:INFO:Uploading model into container now
2022-05-06 16:30:29,729:INFO:create_model_container: 1
2022-05-06 16:30:29,729:INFO:master_model_container: 1
2022-05-06 16:30:29,729:INFO:display_container: 2
2022-05-06 16:30:29,730:INFO:LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)
2022-05-06 16:30:29,730:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:29,813:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:29,814:INFO:Creating metrics dataframe
2022-05-06 16:30:29,831:INFO:Initializing K Neighbors Classifier
2022-05-06 16:30:29,831:INFO:Total runtime is 0.07610479990641277 minutes
2022-05-06 16:30:29,843:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:29,843:INFO:Initializing create_model()
2022-05-06 16:30:29,844:INFO:create_model(estimator=knn, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:29,844:INFO:Checking exceptions
2022-05-06 16:30:29,844:INFO:Importing libraries
2022-05-06 16:30:29,844:INFO:Copying training dataset
2022-05-06 16:30:29,846:INFO:Defining folds
2022-05-06 16:30:29,846:INFO:Declaring metric variables
2022-05-06 16:30:29,859:INFO:Importing untrained model
2022-05-06 16:30:29,873:INFO:K Neighbors Classifier Imported succesfully
2022-05-06 16:30:29,899:INFO:Starting cross validation
2022-05-06 16:30:29,900:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:30,285:INFO:Calculating mean and std
2022-05-06 16:30:30,287:INFO:Creating metrics dataframe
2022-05-06 16:30:30,298:INFO:Uploading results into container
2022-05-06 16:30:30,298:INFO:Uploading model into container now
2022-05-06 16:30:30,298:INFO:create_model_container: 2
2022-05-06 16:30:30,299:INFO:master_model_container: 2
2022-05-06 16:30:30,299:INFO:display_container: 2
2022-05-06 16:30:30,300:INFO:KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
metric_params=None, n_jobs=-1, n_neighbors=5, p=2,
weights='uniform')
2022-05-06 16:30:30,300:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:30,364:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:30,365:INFO:Creating metrics dataframe
2022-05-06 16:30:30,382:INFO:Initializing Naive Bayes
2022-05-06 16:30:30,382:INFO:Total runtime is 0.08528782924016318 minutes
2022-05-06 16:30:30,391:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:30,392:INFO:Initializing create_model()
2022-05-06 16:30:30,392:INFO:create_model(estimator=nb, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:30,392:INFO:Checking exceptions
2022-05-06 16:30:30,392:INFO:Importing libraries
2022-05-06 16:30:30,392:INFO:Copying training dataset
2022-05-06 16:30:30,393:INFO:Defining folds
2022-05-06 16:30:30,393:INFO:Declaring metric variables
2022-05-06 16:30:30,403:INFO:Importing untrained model
2022-05-06 16:30:30,415:INFO:Naive Bayes Imported succesfully
2022-05-06 16:30:30,439:INFO:Starting cross validation
2022-05-06 16:30:30,440:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:30,740:INFO:Calculating mean and std
2022-05-06 16:30:30,743:INFO:Creating metrics dataframe
2022-05-06 16:30:30,752:INFO:Uploading results into container
2022-05-06 16:30:30,753:INFO:Uploading model into container now
2022-05-06 16:30:30,753:INFO:create_model_container: 3
2022-05-06 16:30:30,753:INFO:master_model_container: 3
2022-05-06 16:30:30,753:INFO:display_container: 2
2022-05-06 16:30:30,753:INFO:GaussianNB(priors=None, var_smoothing=1e-09)
2022-05-06 16:30:30,753:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:30,815:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:30,815:INFO:Creating metrics dataframe
2022-05-06 16:30:30,830:INFO:Initializing Decision Tree Classifier
2022-05-06 16:30:30,830:INFO:Total runtime is 0.09275476535161337 minutes
2022-05-06 16:30:30,841:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:30,841:INFO:Initializing create_model()
2022-05-06 16:30:30,841:INFO:create_model(estimator=dt, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:30,842:INFO:Checking exceptions
2022-05-06 16:30:30,842:INFO:Importing libraries
2022-05-06 16:30:30,842:INFO:Copying training dataset
2022-05-06 16:30:30,844:INFO:Defining folds
2022-05-06 16:30:30,844:INFO:Declaring metric variables
2022-05-06 16:30:30,855:INFO:Importing untrained model
2022-05-06 16:30:30,866:INFO:Decision Tree Classifier Imported succesfully
2022-05-06 16:30:30,886:INFO:Starting cross validation
2022-05-06 16:30:30,887:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:31,342:INFO:Calculating mean and std
2022-05-06 16:30:31,345:INFO:Creating metrics dataframe
2022-05-06 16:30:31,353:INFO:Uploading results into container
2022-05-06 16:30:31,353:INFO:Uploading model into container now
2022-05-06 16:30:31,354:INFO:create_model_container: 4
2022-05-06 16:30:31,354:INFO:master_model_container: 4
2022-05-06 16:30:31,354:INFO:display_container: 2
2022-05-06 16:30:31,355:INFO:DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',
max_depth=None, max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, presort='deprecated',
random_state=1559, splitter='best')
2022-05-06 16:30:31,355:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:31,416:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:31,417:INFO:Creating metrics dataframe
2022-05-06 16:30:31,432:INFO:Initializing SVM - Linear Kernel
2022-05-06 16:30:31,432:INFO:Total runtime is 0.10277804931004843 minutes
2022-05-06 16:30:31,440:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:31,441:INFO:Initializing create_model()
2022-05-06 16:30:31,441:INFO:create_model(estimator=svm, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:31,441:INFO:Checking exceptions
2022-05-06 16:30:31,441:INFO:Importing libraries
2022-05-06 16:30:31,441:INFO:Copying training dataset
2022-05-06 16:30:31,442:INFO:Defining folds
2022-05-06 16:30:31,443:INFO:Declaring metric variables
2022-05-06 16:30:31,456:INFO:Importing untrained model
2022-05-06 16:30:31,477:INFO:SVM - Linear Kernel Imported succesfully
2022-05-06 16:30:31,497:INFO:Starting cross validation
2022-05-06 16:30:31,497:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:31,900:INFO:Calculating mean and std
2022-05-06 16:30:31,903:INFO:Creating metrics dataframe
2022-05-06 16:30:31,912:INFO:Uploading results into container
2022-05-06 16:30:31,912:INFO:Uploading model into container now
2022-05-06 16:30:31,912:INFO:create_model_container: 5
2022-05-06 16:30:31,912:INFO:master_model_container: 5
2022-05-06 16:30:31,912:INFO:display_container: 2
2022-05-06 16:30:31,913:INFO:SGDClassifier(alpha=0.0001, average=False, class_weight=None,
early_stopping=False, epsilon=0.1, eta0=0.001, fit_intercept=True,
l1_ratio=0.15, learning_rate='optimal', loss='hinge',
max_iter=1000, n_iter_no_change=5, n_jobs=-1, penalty='l2',
power_t=0.5, random_state=1559, shuffle=True, tol=0.001,
validation_fraction=0.1, verbose=0, warm_start=False)
2022-05-06 16:30:31,913:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:31,976:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:31,976:INFO:Creating metrics dataframe
2022-05-06 16:30:31,996:INFO:Initializing Ridge Classifier
2022-05-06 16:30:31,996:INFO:Total runtime is 0.1121807336807251 minutes
2022-05-06 16:30:32,003:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:32,004:INFO:Initializing create_model()
2022-05-06 16:30:32,004:INFO:create_model(estimator=ridge, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:32,004:INFO:Checking exceptions
2022-05-06 16:30:32,004:INFO:Importing libraries
2022-05-06 16:30:32,004:INFO:Copying training dataset
2022-05-06 16:30:32,005:INFO:Defining folds
2022-05-06 16:30:32,005:INFO:Declaring metric variables
2022-05-06 16:30:32,012:INFO:Importing untrained model
2022-05-06 16:30:32,024:INFO:Ridge Classifier Imported succesfully
2022-05-06 16:30:32,045:INFO:Starting cross validation
2022-05-06 16:30:32,046:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:32,247:INFO:Calculating mean and std
2022-05-06 16:30:32,249:INFO:Creating metrics dataframe
2022-05-06 16:30:32,258:INFO:Uploading results into container
2022-05-06 16:30:32,258:INFO:Uploading model into container now
2022-05-06 16:30:32,258:INFO:create_model_container: 6
2022-05-06 16:30:32,259:INFO:master_model_container: 6
2022-05-06 16:30:32,259:INFO:display_container: 2
2022-05-06 16:30:32,259:INFO:RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
max_iter=None, normalize=False, random_state=1559,
solver='auto', tol=0.001)
2022-05-06 16:30:32,259:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:32,320:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:32,320:INFO:Creating metrics dataframe
2022-05-06 16:30:32,340:INFO:Initializing Random Forest Classifier
2022-05-06 16:30:32,341:INFO:Total runtime is 0.11792469819386801 minutes
2022-05-06 16:30:32,348:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:32,349:INFO:Initializing create_model()
2022-05-06 16:30:32,349:INFO:create_model(estimator=rf, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:32,349:INFO:Checking exceptions
2022-05-06 16:30:32,349:INFO:Importing libraries
2022-05-06 16:30:32,349:INFO:Copying training dataset
2022-05-06 16:30:32,350:INFO:Defining folds
2022-05-06 16:30:32,350:INFO:Declaring metric variables
2022-05-06 16:30:32,360:INFO:Importing untrained model
2022-05-06 16:30:32,375:INFO:Random Forest Classifier Imported succesfully
2022-05-06 16:30:32,395:INFO:Starting cross validation
2022-05-06 16:30:32,396:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:33,671:INFO:Calculating mean and std
2022-05-06 16:30:33,675:INFO:Creating metrics dataframe
2022-05-06 16:30:33,684:INFO:Uploading results into container
2022-05-06 16:30:33,684:INFO:Uploading model into container now
2022-05-06 16:30:33,684:INFO:create_model_container: 7
2022-05-06 16:30:33,684:INFO:master_model_container: 7
2022-05-06 16:30:33,684:INFO:display_container: 2
2022-05-06 16:30:33,685:INFO:RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,
criterion='gini', max_depth=None, max_features='auto',
max_leaf_nodes=None, max_samples=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100,
n_jobs=-1, oob_score=False, random_state=1559, verbose=0,
warm_start=False)
2022-05-06 16:30:33,685:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:33,750:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:33,750:INFO:Creating metrics dataframe
2022-05-06 16:30:33,767:INFO:Initializing Quadratic Discriminant Analysis
2022-05-06 16:30:33,768:INFO:Total runtime is 0.1417108496030172 minutes
2022-05-06 16:30:33,779:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:33,780:INFO:Initializing create_model()
2022-05-06 16:30:33,780:INFO:create_model(estimator=qda, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:33,780:INFO:Checking exceptions
2022-05-06 16:30:33,780:INFO:Importing libraries
2022-05-06 16:30:33,780:INFO:Copying training dataset
2022-05-06 16:30:33,782:INFO:Defining folds
2022-05-06 16:30:33,782:INFO:Declaring metric variables
2022-05-06 16:30:33,789:INFO:Importing untrained model
2022-05-06 16:30:33,800:INFO:Quadratic Discriminant Analysis Imported succesfully
2022-05-06 16:30:33,822:INFO:Starting cross validation
2022-05-06 16:30:33,822:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:34,126:INFO:Calculating mean and std
2022-05-06 16:30:34,129:INFO:Creating metrics dataframe
2022-05-06 16:30:34,137:INFO:Uploading results into container
2022-05-06 16:30:34,138:INFO:Uploading model into container now
2022-05-06 16:30:34,138:INFO:create_model_container: 8
2022-05-06 16:30:34,138:INFO:master_model_container: 8
2022-05-06 16:30:34,138:INFO:display_container: 2
2022-05-06 16:30:34,139:INFO:QuadraticDiscriminantAnalysis(priors=None, reg_param=0.0,
store_covariance=False, tol=0.0001)
2022-05-06 16:30:34,139:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:34,199:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:34,200:INFO:Creating metrics dataframe
2022-05-06 16:30:34,216:INFO:Initializing Ada Boost Classifier
2022-05-06 16:30:34,216:INFO:Total runtime is 0.1491849462191264 minutes
2022-05-06 16:30:34,224:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:34,224:INFO:Initializing create_model()
2022-05-06 16:30:34,224:INFO:create_model(estimator=ada, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:34,224:INFO:Checking exceptions
2022-05-06 16:30:34,224:INFO:Importing libraries
2022-05-06 16:30:34,225:INFO:Copying training dataset
2022-05-06 16:30:34,226:INFO:Defining folds
2022-05-06 16:30:34,226:INFO:Declaring metric variables
2022-05-06 16:30:34,233:INFO:Importing untrained model
2022-05-06 16:30:34,245:INFO:Ada Boost Classifier Imported succesfully
2022-05-06 16:30:34,266:INFO:Starting cross validation
2022-05-06 16:30:34,266:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:34,761:INFO:Calculating mean and std
2022-05-06 16:30:34,762:INFO:Creating metrics dataframe
2022-05-06 16:30:34,766:INFO:Uploading results into container
2022-05-06 16:30:34,766:INFO:Uploading model into container now
2022-05-06 16:30:34,766:INFO:create_model_container: 9
2022-05-06 16:30:34,766:INFO:master_model_container: 9
2022-05-06 16:30:34,766:INFO:display_container: 2
2022-05-06 16:30:34,767:INFO:AdaBoostClassifier(algorithm='SAMME.R', base_estimator=None, learning_rate=1.0,
n_estimators=50, random_state=1559)
2022-05-06 16:30:34,767:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:34,827:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:34,827:INFO:Creating metrics dataframe
2022-05-06 16:30:34,845:INFO:Initializing Gradient Boosting Classifier
2022-05-06 16:30:34,845:INFO:Total runtime is 0.15966373284657798 minutes
2022-05-06 16:30:34,855:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:34,855:INFO:Initializing create_model()
2022-05-06 16:30:34,855:INFO:create_model(estimator=gbc, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:34,855:INFO:Checking exceptions
2022-05-06 16:30:34,856:INFO:Importing libraries
2022-05-06 16:30:34,856:INFO:Copying training dataset
2022-05-06 16:30:34,857:INFO:Defining folds
2022-05-06 16:30:34,857:INFO:Declaring metric variables
2022-05-06 16:30:34,865:INFO:Importing untrained model
2022-05-06 16:30:34,876:INFO:Gradient Boosting Classifier Imported succesfully
2022-05-06 16:30:34,897:INFO:Starting cross validation
2022-05-06 16:30:34,898:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:38,844:INFO:Calculating mean and std
2022-05-06 16:30:38,847:INFO:Creating metrics dataframe
2022-05-06 16:30:38,855:INFO:Uploading results into container
2022-05-06 16:30:38,856:INFO:Uploading model into container now
2022-05-06 16:30:38,856:INFO:create_model_container: 10
2022-05-06 16:30:38,856:INFO:master_model_container: 10
2022-05-06 16:30:38,856:INFO:display_container: 2
2022-05-06 16:30:38,857:INFO:GradientBoostingClassifier(ccp_alpha=0.0, criterion='friedman_mse', init=None,
learning_rate=0.1, loss='deviance', max_depth=3,
max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100,
n_iter_no_change=None, presort='deprecated',
random_state=1559, subsample=1.0, tol=0.0001,
validation_fraction=0.1, verbose=0,
warm_start=False)
2022-05-06 16:30:38,857:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:38,918:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:38,918:INFO:Creating metrics dataframe
2022-05-06 16:30:38,936:INFO:Initializing Linear Discriminant Analysis
2022-05-06 16:30:38,936:INFO:Total runtime is 0.22784423430760703 minutes
2022-05-06 16:30:38,949:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:38,949:INFO:Initializing create_model()
2022-05-06 16:30:38,949:INFO:create_model(estimator=lda, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:38,949:INFO:Checking exceptions
2022-05-06 16:30:38,949:INFO:Importing libraries
2022-05-06 16:30:38,949:INFO:Copying training dataset
2022-05-06 16:30:38,951:INFO:Defining folds
2022-05-06 16:30:38,951:INFO:Declaring metric variables
2022-05-06 16:30:38,958:INFO:Importing untrained model
2022-05-06 16:30:38,972:INFO:Linear Discriminant Analysis Imported succesfully
2022-05-06 16:30:38,989:INFO:Starting cross validation
2022-05-06 16:30:38,990:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:39,561:INFO:Calculating mean and std
2022-05-06 16:30:39,564:INFO:Creating metrics dataframe
2022-05-06 16:30:39,572:INFO:Uploading results into container
2022-05-06 16:30:39,573:INFO:Uploading model into container now
2022-05-06 16:30:39,573:INFO:create_model_container: 11
2022-05-06 16:30:39,573:INFO:master_model_container: 11
2022-05-06 16:30:39,573:INFO:display_container: 2
2022-05-06 16:30:39,573:INFO:LinearDiscriminantAnalysis(n_components=None, priors=None, shrinkage=None,
solver='svd', store_covariance=False, tol=0.0001)
2022-05-06 16:30:39,573:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:39,634:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:39,635:INFO:Creating metrics dataframe
2022-05-06 16:30:39,658:INFO:Initializing Extra Trees Classifier
2022-05-06 16:30:39,658:INFO:Total runtime is 0.23988233009974164 minutes
2022-05-06 16:30:39,668:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:39,668:INFO:Initializing create_model()
2022-05-06 16:30:39,668:INFO:create_model(estimator=et, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:39,668:INFO:Checking exceptions
2022-05-06 16:30:39,669:INFO:Importing libraries
2022-05-06 16:30:39,669:INFO:Copying training dataset
2022-05-06 16:30:39,670:INFO:Defining folds
2022-05-06 16:30:39,670:INFO:Declaring metric variables
2022-05-06 16:30:39,678:INFO:Importing untrained model
2022-05-06 16:30:39,690:INFO:Extra Trees Classifier Imported succesfully
2022-05-06 16:30:39,713:INFO:Starting cross validation
2022-05-06 16:30:39,713:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:41,414:INFO:Calculating mean and std
2022-05-06 16:30:41,417:INFO:Creating metrics dataframe
2022-05-06 16:30:41,425:INFO:Uploading results into container
2022-05-06 16:30:41,425:INFO:Uploading model into container now
2022-05-06 16:30:41,425:INFO:create_model_container: 12
2022-05-06 16:30:41,426:INFO:master_model_container: 12
2022-05-06 16:30:41,426:INFO:display_container: 2
2022-05-06 16:30:41,426:INFO:ExtraTreesClassifier(bootstrap=False, ccp_alpha=0.0, class_weight=None,
criterion='gini', max_depth=None, max_features='auto',
max_leaf_nodes=None, max_samples=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=-1,
oob_score=False, random_state=1559, verbose=0,
warm_start=False)
2022-05-06 16:30:41,427:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:41,486:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:41,486:INFO:Creating metrics dataframe
2022-05-06 16:30:41,505:INFO:Initializing Light Gradient Boosting Machine
2022-05-06 16:30:41,505:INFO:Total runtime is 0.27066943248112996 minutes
2022-05-06 16:30:41,516:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:41,516:INFO:Initializing create_model()
2022-05-06 16:30:41,516:INFO:create_model(estimator=lightgbm, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe5bc69ab20>, kwargs={})
2022-05-06 16:30:41,516:INFO:Checking exceptions
2022-05-06 16:30:41,516:INFO:Importing libraries
2022-05-06 16:30:41,516:INFO:Copying training dataset
2022-05-06 16:30:41,517:INFO:Defining folds
2022-05-06 16:30:41,517:INFO:Declaring metric variables
2022-05-06 16:30:41,524:INFO:Importing untrained model
2022-05-06 16:30:41,544:INFO:Light Gradient Boosting Machine Imported succesfully
2022-05-06 16:30:41,570:INFO:Starting cross validation
2022-05-06 16:30:41,570:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:41,891:INFO:Calculating mean and std
2022-05-06 16:30:41,893:INFO:Creating metrics dataframe
2022-05-06 16:30:41,902:INFO:Uploading results into container
2022-05-06 16:30:41,902:INFO:Uploading model into container now
2022-05-06 16:30:41,902:INFO:create_model_container: 13
2022-05-06 16:30:41,902:INFO:master_model_container: 13
2022-05-06 16:30:41,903:INFO:display_container: 2
2022-05-06 16:30:41,904:INFO:LGBMClassifier(boosting_type='gbdt', class_weight=None, colsample_bytree=1.0,
importance_type='split', learning_rate=0.1, max_depth=-1,
min_child_samples=20, min_child_weight=0.001, min_split_gain=0.0,
n_estimators=100, n_jobs=-1, num_leaves=31, objective=None,
random_state=1559, reg_alpha=0.0, reg_lambda=0.0, silent=True,
subsample=1.0, subsample_for_bin=200000, subsample_freq=0)
2022-05-06 16:30:41,904:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:41,965:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:41,965:INFO:Creating metrics dataframe
2022-05-06 16:30:42,004:INFO:Initializing create_model()
2022-05-06 16:30:42,004:INFO:create_model(estimator=LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False), fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=False, predict=False, fit_kwargs={}, groups=None, refit=True, verbose=False, system=False, metrics=None, display=None, kwargs={})
2022-05-06 16:30:42,004:INFO:Checking exceptions
2022-05-06 16:30:42,005:INFO:Importing libraries
2022-05-06 16:30:42,005:INFO:Copying training dataset
2022-05-06 16:30:42,005:INFO:Defining folds
2022-05-06 16:30:42,006:INFO:Declaring metric variables
2022-05-06 16:30:42,006:INFO:Importing untrained model
2022-05-06 16:30:42,006:INFO:Declaring custom model
2022-05-06 16:30:42,007:INFO:Logistic Regression Imported succesfully
2022-05-06 16:30:42,008:INFO:Cross validation set to False
2022-05-06 16:30:42,008:INFO:Fitting Model
2022-05-06 16:30:42,073:INFO:LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)
2022-05-06 16:30:42,073:INFO:create_models() succesfully completed......................................
2022-05-06 16:30:42,167:INFO:create_model_container: 13
2022-05-06 16:30:42,167:INFO:master_model_container: 13
2022-05-06 16:30:42,167:INFO:display_container: 2
2022-05-06 16:30:42,168:INFO:LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)
2022-05-06 16:30:42,168:INFO:compare_models() succesfully completed......................................
2022-05-06 16:30:48,398:INFO:Initializing compare_models()
2022-05-06 16:30:48,399:INFO:compare_models(include=None, fold=None, round=4, cross_validation=True, sort=Accuracy, n_select=3, budget_time=None, turbo=True, errors=ignore, fit_kwargs=None, groups=None, verbose=True, display=None, exclude=None)
2022-05-06 16:30:48,399:INFO:Checking exceptions
2022-05-06 16:30:48,400:INFO:Preparing display monitor
2022-05-06 16:30:48,400:INFO:Preparing display monitor
2022-05-06 16:30:48,439:INFO:Initializing Logistic Regression
2022-05-06 16:30:48,439:INFO:Total runtime is 2.682209014892578e-06 minutes
2022-05-06 16:30:48,450:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:48,451:INFO:Initializing create_model()
2022-05-06 16:30:48,451:INFO:create_model(estimator=lr, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:48,451:INFO:Checking exceptions
2022-05-06 16:30:48,451:INFO:Importing libraries
2022-05-06 16:30:48,451:INFO:Copying training dataset
2022-05-06 16:30:48,453:INFO:Defining folds
2022-05-06 16:30:48,453:INFO:Declaring metric variables
2022-05-06 16:30:48,465:INFO:Importing untrained model
2022-05-06 16:30:48,475:INFO:Logistic Regression Imported succesfully
2022-05-06 16:30:48,499:INFO:Starting cross validation
2022-05-06 16:30:48,500:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:48,891:INFO:Calculating mean and std
2022-05-06 16:30:48,893:INFO:Creating metrics dataframe
2022-05-06 16:30:48,899:INFO:Uploading results into container
2022-05-06 16:30:48,899:INFO:Uploading model into container now
2022-05-06 16:30:48,899:INFO:create_model_container: 14
2022-05-06 16:30:48,899:INFO:master_model_container: 14
2022-05-06 16:30:48,900:INFO:display_container: 3
2022-05-06 16:30:48,900:INFO:LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)
2022-05-06 16:30:48,900:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:48,962:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:48,962:INFO:Creating metrics dataframe
2022-05-06 16:30:48,986:INFO:Initializing K Neighbors Classifier
2022-05-06 16:30:48,986:INFO:Total runtime is 0.009119101365407308 minutes
2022-05-06 16:30:48,994:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:48,994:INFO:Initializing create_model()
2022-05-06 16:30:48,994:INFO:create_model(estimator=knn, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:48,995:INFO:Checking exceptions
2022-05-06 16:30:48,995:INFO:Importing libraries
2022-05-06 16:30:48,995:INFO:Copying training dataset
2022-05-06 16:30:48,996:INFO:Defining folds
2022-05-06 16:30:48,996:INFO:Declaring metric variables
2022-05-06 16:30:49,012:INFO:Importing untrained model
2022-05-06 16:30:49,023:INFO:K Neighbors Classifier Imported succesfully
2022-05-06 16:30:49,042:INFO:Starting cross validation
2022-05-06 16:30:49,042:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:49,389:INFO:Calculating mean and std
2022-05-06 16:30:49,390:INFO:Creating metrics dataframe
2022-05-06 16:30:49,396:INFO:Uploading results into container
2022-05-06 16:30:49,397:INFO:Uploading model into container now
2022-05-06 16:30:49,397:INFO:create_model_container: 15
2022-05-06 16:30:49,397:INFO:master_model_container: 15
2022-05-06 16:30:49,397:INFO:display_container: 3
2022-05-06 16:30:49,397:INFO:KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
metric_params=None, n_jobs=-1, n_neighbors=5, p=2,
weights='uniform')
2022-05-06 16:30:49,398:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:49,470:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:49,470:INFO:Creating metrics dataframe
2022-05-06 16:30:49,491:INFO:Initializing Naive Bayes
2022-05-06 16:30:49,491:INFO:Total runtime is 0.01754063367843628 minutes
2022-05-06 16:30:49,500:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:49,501:INFO:Initializing create_model()
2022-05-06 16:30:49,501:INFO:create_model(estimator=nb, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:49,501:INFO:Checking exceptions
2022-05-06 16:30:49,502:INFO:Importing libraries
2022-05-06 16:30:49,502:INFO:Copying training dataset
2022-05-06 16:30:49,503:INFO:Defining folds
2022-05-06 16:30:49,503:INFO:Declaring metric variables
2022-05-06 16:30:49,518:INFO:Importing untrained model
2022-05-06 16:30:49,533:INFO:Naive Bayes Imported succesfully
2022-05-06 16:30:49,555:INFO:Starting cross validation
2022-05-06 16:30:49,555:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:49,789:INFO:Calculating mean and std
2022-05-06 16:30:49,790:INFO:Creating metrics dataframe
2022-05-06 16:30:49,796:INFO:Uploading results into container
2022-05-06 16:30:49,796:INFO:Uploading model into container now
2022-05-06 16:30:49,796:INFO:create_model_container: 16
2022-05-06 16:30:49,797:INFO:master_model_container: 16
2022-05-06 16:30:49,797:INFO:display_container: 3
2022-05-06 16:30:49,797:INFO:GaussianNB(priors=None, var_smoothing=1e-09)
2022-05-06 16:30:49,797:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:49,860:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:49,860:INFO:Creating metrics dataframe
2022-05-06 16:30:49,876:INFO:Initializing Decision Tree Classifier
2022-05-06 16:30:49,877:INFO:Total runtime is 0.023960848649342854 minutes
2022-05-06 16:30:49,886:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:49,886:INFO:Initializing create_model()
2022-05-06 16:30:49,886:INFO:create_model(estimator=dt, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:49,887:INFO:Checking exceptions
2022-05-06 16:30:49,887:INFO:Importing libraries
2022-05-06 16:30:49,887:INFO:Copying training dataset
2022-05-06 16:30:49,888:INFO:Defining folds
2022-05-06 16:30:49,889:INFO:Declaring metric variables
2022-05-06 16:30:49,904:INFO:Importing untrained model
2022-05-06 16:30:49,918:INFO:Decision Tree Classifier Imported succesfully
2022-05-06 16:30:49,943:INFO:Starting cross validation
2022-05-06 16:30:49,944:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:50,539:INFO:Calculating mean and std
2022-05-06 16:30:50,540:INFO:Creating metrics dataframe
2022-05-06 16:30:50,544:INFO:Uploading results into container
2022-05-06 16:30:50,544:INFO:Uploading model into container now
2022-05-06 16:30:50,544:INFO:create_model_container: 17
2022-05-06 16:30:50,544:INFO:master_model_container: 17
2022-05-06 16:30:50,544:INFO:display_container: 3
2022-05-06 16:30:50,544:INFO:DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',
max_depth=None, max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, presort='deprecated',
random_state=1559, splitter='best')
2022-05-06 16:30:50,544:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:50,602:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:50,603:INFO:Creating metrics dataframe
2022-05-06 16:30:50,618:INFO:Initializing SVM - Linear Kernel
2022-05-06 16:30:50,618:INFO:Total runtime is 0.036322466532389325 minutes
2022-05-06 16:30:50,629:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:50,629:INFO:Initializing create_model()
2022-05-06 16:30:50,629:INFO:create_model(estimator=svm, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:50,629:INFO:Checking exceptions
2022-05-06 16:30:50,629:INFO:Importing libraries
2022-05-06 16:30:50,630:INFO:Copying training dataset
2022-05-06 16:30:50,630:INFO:Defining folds
2022-05-06 16:30:50,631:INFO:Declaring metric variables
2022-05-06 16:30:50,642:INFO:Importing untrained model
2022-05-06 16:30:50,654:INFO:SVM - Linear Kernel Imported succesfully
2022-05-06 16:30:50,680:INFO:Starting cross validation
2022-05-06 16:30:50,681:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:51,037:INFO:Calculating mean and std
2022-05-06 16:30:51,039:INFO:Creating metrics dataframe
2022-05-06 16:30:51,046:INFO:Uploading results into container
2022-05-06 16:30:51,046:INFO:Uploading model into container now
2022-05-06 16:30:51,046:INFO:create_model_container: 18
2022-05-06 16:30:51,046:INFO:master_model_container: 18
2022-05-06 16:30:51,046:INFO:display_container: 3
2022-05-06 16:30:51,047:INFO:SGDClassifier(alpha=0.0001, average=False, class_weight=None,
early_stopping=False, epsilon=0.1, eta0=0.001, fit_intercept=True,
l1_ratio=0.15, learning_rate='optimal', loss='hinge',
max_iter=1000, n_iter_no_change=5, n_jobs=-1, penalty='l2',
power_t=0.5, random_state=1559, shuffle=True, tol=0.001,
validation_fraction=0.1, verbose=0, warm_start=False)
2022-05-06 16:30:51,047:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:51,110:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:51,111:INFO:Creating metrics dataframe
2022-05-06 16:30:51,133:INFO:Initializing Ridge Classifier
2022-05-06 16:30:51,133:INFO:Total runtime is 0.04490296840667725 minutes
2022-05-06 16:30:51,142:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:51,143:INFO:Initializing create_model()
2022-05-06 16:30:51,143:INFO:create_model(estimator=ridge, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:51,143:INFO:Checking exceptions
2022-05-06 16:30:51,143:INFO:Importing libraries
2022-05-06 16:30:51,143:INFO:Copying training dataset
2022-05-06 16:30:51,145:INFO:Defining folds
2022-05-06 16:30:51,145:INFO:Declaring metric variables
2022-05-06 16:30:51,158:INFO:Importing untrained model
2022-05-06 16:30:51,171:INFO:Ridge Classifier Imported succesfully
2022-05-06 16:30:51,197:INFO:Starting cross validation
2022-05-06 16:30:51,198:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:51,425:INFO:Calculating mean and std
2022-05-06 16:30:51,426:INFO:Creating metrics dataframe
2022-05-06 16:30:51,433:INFO:Uploading results into container
2022-05-06 16:30:51,434:INFO:Uploading model into container now
2022-05-06 16:30:51,434:INFO:create_model_container: 19
2022-05-06 16:30:51,434:INFO:master_model_container: 19
2022-05-06 16:30:51,434:INFO:display_container: 3
2022-05-06 16:30:51,434:INFO:RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
max_iter=None, normalize=False, random_state=1559,
solver='auto', tol=0.001)
2022-05-06 16:30:51,435:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:51,495:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:51,495:INFO:Creating metrics dataframe
2022-05-06 16:30:51,514:INFO:Initializing Random Forest Classifier
2022-05-06 16:30:51,514:INFO:Total runtime is 0.05125253200531006 minutes
2022-05-06 16:30:51,527:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:51,528:INFO:Initializing create_model()
2022-05-06 16:30:51,528:INFO:create_model(estimator=rf, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:51,529:INFO:Checking exceptions
2022-05-06 16:30:51,529:INFO:Importing libraries
2022-05-06 16:30:51,529:INFO:Copying training dataset
2022-05-06 16:30:51,532:INFO:Defining folds
2022-05-06 16:30:51,532:INFO:Declaring metric variables
2022-05-06 16:30:51,549:INFO:Importing untrained model
2022-05-06 16:30:51,559:INFO:Random Forest Classifier Imported succesfully
2022-05-06 16:30:51,587:INFO:Starting cross validation
2022-05-06 16:30:51,588:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:52,951:INFO:Calculating mean and std
2022-05-06 16:30:52,953:INFO:Creating metrics dataframe
2022-05-06 16:30:52,969:INFO:Uploading results into container
2022-05-06 16:30:52,969:INFO:Uploading model into container now
2022-05-06 16:30:52,969:INFO:create_model_container: 20
2022-05-06 16:30:52,970:INFO:master_model_container: 20
2022-05-06 16:30:52,970:INFO:display_container: 3
2022-05-06 16:30:52,971:INFO:RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,
criterion='gini', max_depth=None, max_features='auto',
max_leaf_nodes=None, max_samples=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100,
n_jobs=-1, oob_score=False, random_state=1559, verbose=0,
warm_start=False)
2022-05-06 16:30:52,971:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:53,034:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:53,034:INFO:Creating metrics dataframe
2022-05-06 16:30:53,056:INFO:Initializing Quadratic Discriminant Analysis
2022-05-06 16:30:53,056:INFO:Total runtime is 0.07694983084996541 minutes
2022-05-06 16:30:53,065:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:53,066:INFO:Initializing create_model()
2022-05-06 16:30:53,066:INFO:create_model(estimator=qda, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:53,066:INFO:Checking exceptions
2022-05-06 16:30:53,066:INFO:Importing libraries
2022-05-06 16:30:53,067:INFO:Copying training dataset
2022-05-06 16:30:53,068:INFO:Defining folds
2022-05-06 16:30:53,068:INFO:Declaring metric variables
2022-05-06 16:30:53,080:INFO:Importing untrained model
2022-05-06 16:30:53,096:INFO:Quadratic Discriminant Analysis Imported succesfully
2022-05-06 16:30:53,123:INFO:Starting cross validation
2022-05-06 16:30:53,124:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:53,435:INFO:Calculating mean and std
2022-05-06 16:30:53,438:INFO:Creating metrics dataframe
2022-05-06 16:30:53,446:INFO:Uploading results into container
2022-05-06 16:30:53,447:INFO:Uploading model into container now
2022-05-06 16:30:53,447:INFO:create_model_container: 21
2022-05-06 16:30:53,447:INFO:master_model_container: 21
2022-05-06 16:30:53,447:INFO:display_container: 3
2022-05-06 16:30:53,447:INFO:QuadraticDiscriminantAnalysis(priors=None, reg_param=0.0,
store_covariance=False, tol=0.0001)
2022-05-06 16:30:53,448:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:53,509:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:53,509:INFO:Creating metrics dataframe
2022-05-06 16:30:53,528:INFO:Initializing Ada Boost Classifier
2022-05-06 16:30:53,528:INFO:Total runtime is 0.08481958309809368 minutes
2022-05-06 16:30:53,537:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:53,537:INFO:Initializing create_model()
2022-05-06 16:30:53,537:INFO:create_model(estimator=ada, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:53,537:INFO:Checking exceptions
2022-05-06 16:30:53,537:INFO:Importing libraries
2022-05-06 16:30:53,537:INFO:Copying training dataset
2022-05-06 16:30:53,539:INFO:Defining folds
2022-05-06 16:30:53,539:INFO:Declaring metric variables
2022-05-06 16:30:53,551:INFO:Importing untrained model
2022-05-06 16:30:53,561:INFO:Ada Boost Classifier Imported succesfully
2022-05-06 16:30:53,583:INFO:Starting cross validation
2022-05-06 16:30:53,584:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:54,222:INFO:Calculating mean and std
2022-05-06 16:30:54,225:INFO:Creating metrics dataframe
2022-05-06 16:30:54,234:INFO:Uploading results into container
2022-05-06 16:30:54,234:INFO:Uploading model into container now
2022-05-06 16:30:54,235:INFO:create_model_container: 22
2022-05-06 16:30:54,235:INFO:master_model_container: 22
2022-05-06 16:30:54,235:INFO:display_container: 3
2022-05-06 16:30:54,235:INFO:AdaBoostClassifier(algorithm='SAMME.R', base_estimator=None, learning_rate=1.0,
n_estimators=50, random_state=1559)
2022-05-06 16:30:54,236:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:54,296:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:54,297:INFO:Creating metrics dataframe
2022-05-06 16:30:54,318:INFO:Initializing Gradient Boosting Classifier
2022-05-06 16:30:54,318:INFO:Total runtime is 0.09798289934794109 minutes
2022-05-06 16:30:54,326:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:54,327:INFO:Initializing create_model()
2022-05-06 16:30:54,327:INFO:create_model(estimator=gbc, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:54,327:INFO:Checking exceptions
2022-05-06 16:30:54,327:INFO:Importing libraries
2022-05-06 16:30:54,327:INFO:Copying training dataset
2022-05-06 16:30:54,328:INFO:Defining folds
2022-05-06 16:30:54,328:INFO:Declaring metric variables
2022-05-06 16:30:54,339:INFO:Importing untrained model
2022-05-06 16:30:54,351:INFO:Gradient Boosting Classifier Imported succesfully
2022-05-06 16:30:54,371:INFO:Starting cross validation
2022-05-06 16:30:54,371:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:58,323:INFO:Calculating mean and std
2022-05-06 16:30:58,326:INFO:Creating metrics dataframe
2022-05-06 16:30:58,334:INFO:Uploading results into container
2022-05-06 16:30:58,334:INFO:Uploading model into container now
2022-05-06 16:30:58,334:INFO:create_model_container: 23
2022-05-06 16:30:58,334:INFO:master_model_container: 23
2022-05-06 16:30:58,335:INFO:display_container: 3
2022-05-06 16:30:58,336:INFO:GradientBoostingClassifier(ccp_alpha=0.0, criterion='friedman_mse', init=None,
learning_rate=0.1, loss='deviance', max_depth=3,
max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100,
n_iter_no_change=None, presort='deprecated',
random_state=1559, subsample=1.0, tol=0.0001,
validation_fraction=0.1, verbose=0,
warm_start=False)
2022-05-06 16:30:58,336:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:58,397:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:58,398:INFO:Creating metrics dataframe
2022-05-06 16:30:58,415:INFO:Initializing Linear Discriminant Analysis
2022-05-06 16:30:58,415:INFO:Total runtime is 0.16626373132069905 minutes
2022-05-06 16:30:58,423:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:58,423:INFO:Initializing create_model()
2022-05-06 16:30:58,423:INFO:create_model(estimator=lda, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:58,423:INFO:Checking exceptions
2022-05-06 16:30:58,424:INFO:Importing libraries
2022-05-06 16:30:58,424:INFO:Copying training dataset
2022-05-06 16:30:58,425:INFO:Defining folds
2022-05-06 16:30:58,425:INFO:Declaring metric variables
2022-05-06 16:30:58,433:INFO:Importing untrained model
2022-05-06 16:30:58,444:INFO:Linear Discriminant Analysis Imported succesfully
2022-05-06 16:30:58,463:INFO:Starting cross validation
2022-05-06 16:30:58,465:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:30:59,073:INFO:Calculating mean and std
2022-05-06 16:30:59,077:INFO:Creating metrics dataframe
2022-05-06 16:30:59,086:INFO:Uploading results into container
2022-05-06 16:30:59,086:INFO:Uploading model into container now
2022-05-06 16:30:59,087:INFO:create_model_container: 24
2022-05-06 16:30:59,087:INFO:master_model_container: 24
2022-05-06 16:30:59,087:INFO:display_container: 3
2022-05-06 16:30:59,088:INFO:LinearDiscriminantAnalysis(n_components=None, priors=None, shrinkage=None,
solver='svd', store_covariance=False, tol=0.0001)
2022-05-06 16:30:59,088:INFO:create_model() succesfully completed......................................
2022-05-06 16:30:59,148:INFO:SubProcess create_model() end ==================================
2022-05-06 16:30:59,148:INFO:Creating metrics dataframe
2022-05-06 16:30:59,166:INFO:Initializing Extra Trees Classifier
2022-05-06 16:30:59,166:INFO:Total runtime is 0.17878599961598712 minutes
2022-05-06 16:30:59,175:INFO:SubProcess create_model() called ==================================
2022-05-06 16:30:59,176:INFO:Initializing create_model()
2022-05-06 16:30:59,176:INFO:create_model(estimator=et, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:30:59,176:INFO:Checking exceptions
2022-05-06 16:30:59,176:INFO:Importing libraries
2022-05-06 16:30:59,176:INFO:Copying training dataset
2022-05-06 16:30:59,177:INFO:Defining folds
2022-05-06 16:30:59,177:INFO:Declaring metric variables
2022-05-06 16:30:59,186:INFO:Importing untrained model
2022-05-06 16:30:59,197:INFO:Extra Trees Classifier Imported succesfully
2022-05-06 16:30:59,218:INFO:Starting cross validation
2022-05-06 16:30:59,219:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:31:00,932:INFO:Calculating mean and std
2022-05-06 16:31:00,933:INFO:Creating metrics dataframe
2022-05-06 16:31:00,941:INFO:Uploading results into container
2022-05-06 16:31:00,942:INFO:Uploading model into container now
2022-05-06 16:31:00,942:INFO:create_model_container: 25
2022-05-06 16:31:00,942:INFO:master_model_container: 25
2022-05-06 16:31:00,942:INFO:display_container: 3
2022-05-06 16:31:00,943:INFO:ExtraTreesClassifier(bootstrap=False, ccp_alpha=0.0, class_weight=None,
criterion='gini', max_depth=None, max_features='auto',
max_leaf_nodes=None, max_samples=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=-1,
oob_score=False, random_state=1559, verbose=0,
warm_start=False)
2022-05-06 16:31:00,943:INFO:create_model() succesfully completed......................................
2022-05-06 16:31:01,002:INFO:SubProcess create_model() end ==================================
2022-05-06 16:31:01,003:INFO:Creating metrics dataframe
2022-05-06 16:31:01,026:INFO:Initializing Light Gradient Boosting Machine
2022-05-06 16:31:01,027:INFO:Total runtime is 0.20979684988657632 minutes
2022-05-06 16:31:01,036:INFO:SubProcess create_model() called ==================================
2022-05-06 16:31:01,036:INFO:Initializing create_model()
2022-05-06 16:31:01,036:INFO:create_model(estimator=lightgbm, fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=True, predict=True, fit_kwargs={}, groups=None, refit=False, verbose=False, system=False, metrics=None, display=<pycaret.internal.Display.Display object at 0x7fe592e74b20>, kwargs={})
2022-05-06 16:31:01,036:INFO:Checking exceptions
2022-05-06 16:31:01,036:INFO:Importing libraries
2022-05-06 16:31:01,037:INFO:Copying training dataset
2022-05-06 16:31:01,038:INFO:Defining folds
2022-05-06 16:31:01,038:INFO:Declaring metric variables
2022-05-06 16:31:01,047:INFO:Importing untrained model
2022-05-06 16:31:01,061:INFO:Light Gradient Boosting Machine Imported succesfully
2022-05-06 16:31:01,080:INFO:Starting cross validation
2022-05-06 16:31:01,081:INFO:Cross validating with StratifiedKFold(n_splits=10, random_state=None, shuffle=False), n_jobs=-1
2022-05-06 16:31:01,326:INFO:Calculating mean and std
2022-05-06 16:31:01,329:INFO:Creating metrics dataframe
2022-05-06 16:31:01,337:INFO:Uploading results into container
2022-05-06 16:31:01,337:INFO:Uploading model into container now
2022-05-06 16:31:01,338:INFO:create_model_container: 26
2022-05-06 16:31:01,338:INFO:master_model_container: 26
2022-05-06 16:31:01,338:INFO:display_container: 3
2022-05-06 16:31:01,338:INFO:LGBMClassifier(boosting_type='gbdt', class_weight=None, colsample_bytree=1.0,
importance_type='split', learning_rate=0.1, max_depth=-1,
min_child_samples=20, min_child_weight=0.001, min_split_gain=0.0,
n_estimators=100, n_jobs=-1, num_leaves=31, objective=None,
random_state=1559, reg_alpha=0.0, reg_lambda=0.0, silent=True,
subsample=1.0, subsample_for_bin=200000, subsample_freq=0)
2022-05-06 16:31:01,339:INFO:create_model() succesfully completed......................................
2022-05-06 16:31:01,399:INFO:SubProcess create_model() end ==================================
2022-05-06 16:31:01,399:INFO:Creating metrics dataframe
2022-05-06 16:31:01,444:INFO:Initializing create_model()
2022-05-06 16:31:01,444:INFO:create_model(estimator=LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False), fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=False, predict=False, fit_kwargs={}, groups=None, refit=True, verbose=False, system=False, metrics=None, display=None, kwargs={})
2022-05-06 16:31:01,444:INFO:Checking exceptions
2022-05-06 16:31:01,444:INFO:Importing libraries
2022-05-06 16:31:01,445:INFO:Copying training dataset
2022-05-06 16:31:01,445:INFO:Defining folds
2022-05-06 16:31:01,445:INFO:Declaring metric variables
2022-05-06 16:31:01,445:INFO:Importing untrained model
2022-05-06 16:31:01,445:INFO:Declaring custom model
2022-05-06 16:31:01,446:INFO:Logistic Regression Imported succesfully
2022-05-06 16:31:01,446:INFO:Cross validation set to False
2022-05-06 16:31:01,446:INFO:Fitting Model
2022-05-06 16:31:01,492:INFO:LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)
2022-05-06 16:31:01,492:INFO:create_models() succesfully completed......................................
2022-05-06 16:31:01,553:INFO:Initializing create_model()
2022-05-06 16:31:01,553:INFO:create_model(estimator=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',
max_depth=None, max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, presort='deprecated',
random_state=1559, splitter='best'), fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=False, predict=False, fit_kwargs={}, groups=None, refit=True, verbose=False, system=False, metrics=None, display=None, kwargs={})
2022-05-06 16:31:01,554:INFO:Checking exceptions
2022-05-06 16:31:01,554:INFO:Importing libraries
2022-05-06 16:31:01,554:INFO:Copying training dataset
2022-05-06 16:31:01,555:INFO:Defining folds
2022-05-06 16:31:01,555:INFO:Declaring metric variables
2022-05-06 16:31:01,555:INFO:Importing untrained model
2022-05-06 16:31:01,555:INFO:Declaring custom model
2022-05-06 16:31:01,556:INFO:Decision Tree Classifier Imported succesfully
2022-05-06 16:31:01,556:INFO:Cross validation set to False
2022-05-06 16:31:01,556:INFO:Fitting Model
2022-05-06 16:31:01,693:INFO:DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',
max_depth=None, max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, presort='deprecated',
random_state=1559, splitter='best')
2022-05-06 16:31:01,693:INFO:create_models() succesfully completed......................................
2022-05-06 16:31:01,757:INFO:Initializing create_model()
2022-05-06 16:31:01,758:INFO:create_model(estimator=RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
max_iter=None, normalize=False, random_state=1559,
solver='auto', tol=0.001), fold=StratifiedKFold(n_splits=10, random_state=None, shuffle=False), round=4, cross_validation=False, predict=False, fit_kwargs={}, groups=None, refit=True, verbose=False, system=False, metrics=None, display=None, kwargs={})
2022-05-06 16:31:01,758:INFO:Checking exceptions
2022-05-06 16:31:01,758:INFO:Importing libraries
2022-05-06 16:31:01,758:INFO:Copying training dataset
2022-05-06 16:31:01,759:INFO:Defining folds
2022-05-06 16:31:01,759:INFO:Declaring metric variables
2022-05-06 16:31:01,759:INFO:Importing untrained model
2022-05-06 16:31:01,759:INFO:Declaring custom model
2022-05-06 16:31:01,760:INFO:Ridge Classifier Imported succesfully
2022-05-06 16:31:01,760:INFO:Cross validation set to False
2022-05-06 16:31:01,760:INFO:Fitting Model
2022-05-06 16:31:01,778:INFO:RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
max_iter=None, normalize=False, random_state=1559,
solver='auto', tol=0.001)
2022-05-06 16:31:01,778:INFO:create_models() succesfully completed......................................
2022-05-06 16:31:01,887:INFO:create_model_container: 26
2022-05-06 16:31:01,887:INFO:master_model_container: 26
2022-05-06 16:31:01,887:INFO:display_container: 3
2022-05-06 16:31:01,888:INFO:[LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False), DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',
max_depth=None, max_features=None, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, presort='deprecated',
random_state=1559, splitter='best'), RidgeClassifier(alpha=1.0, class_weight=None, copy_X=True, fit_intercept=True,
max_iter=None, normalize=False, random_state=1559,
solver='auto', tol=0.001)]
2022-05-06 16:31:01,889:INFO:compare_models() succesfully completed......................................
2022-05-06 16:31:13,713:INFO:Initializing save_model()
2022-05-06 16:31:13,713:INFO:save_model(model=LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=1559, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False), model_name=Logistic_Regression, prep_pipe_=Pipeline(memory=None,
steps=[('dtypes',
DataTypes_Auto_infer(categorical_features=['input_1',
'input_2',
'input_3'],
display_types=True, features_todrop=[],
id_columns=[],
ml_usecase='classification',
numerical_features=[], target='pred',
time_features=[])),
('imputer',
Simple_Imputer(categorical_strategy='not_available',
fill_value_categorical=None,
fill_value_n...
('scaling', 'passthrough'), ('P_transform', 'passthrough'),
('binn', 'passthrough'), ('rem_outliers', 'passthrough'),
('cluster_all', 'passthrough'),
('dummy', Dummify(target='pred')),
('fix_perfect', Remove_100(target='pred')),
('clean_names', Clean_Colum_Names()),
('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),
('dfs', 'passthrough'), ('pca', 'passthrough')],
verbose=False), verbose=True, kwargs={})
2022-05-06 16:31:13,713:INFO:Adding model into prep_pipe
2022-05-06 16:31:13,732:INFO:Logistic_Regression.pkl saved in current working directory
2022-05-06 16:31:13,738:INFO:Pipeline(memory=None,
steps=[('dtypes',
DataTypes_Auto_infer(categorical_features=['input_1',
'input_2',
'input_3'],
display_types=True, features_todrop=[],
id_columns=[],
ml_usecase='classification',
numerical_features=[], target='pred',
time_features=[])),
('imputer',
Simple_Imputer(categorical_strategy='not_available',
fill_value_categorical=None,
fill_value_n...
('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),
('dfs', 'passthrough'), ('pca', 'passthrough'),
['trained_model',
LogisticRegression(C=1.0, class_weight=None, dual=False,
fit_intercept=True, intercept_scaling=1,
l1_ratio=None, max_iter=1000,
multi_class='auto', n_jobs=None,
penalty='l2', random_state=1559,
solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)]],
verbose=False)
2022-05-06 16:31:13,738:INFO:save_model() successfully completed......................................
2022-10-08 04:14:12,515:INFO:Initializing load_model()
2022-10-08 04:14:12,515:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:14:17,203:INFO:Initializing load_model()
2022-10-08 04:14:17,204:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:16:27,783:INFO:Initializing load_model()
2022-10-08 04:16:27,783:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:16:50,515:INFO:Initializing load_model()
2022-10-08 04:16:50,515:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:17:53,020:INFO:Initializing load_model()
2022-10-08 04:17:53,020:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:19:04,317:INFO:Initializing load_model()
2022-10-08 04:19:04,318:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:19:27,972:INFO:Initializing load_model()
2022-10-08 04:19:27,973:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:19:39,955:INFO:Initializing predict_model()
2022-10-08 04:19:39,955:INFO:predict_model(estimator=Pipeline(steps=[('dtypes',
DataTypes_Auto_infer(categorical_features=['input_1',
'input_2',
'input_3'],
ml_usecase='classification',
target='pred')),
('imputer',
Simple_Imputer(categorical_strategy='not_available',
fill_value_categorical=None,
fill_value_numerical=None,
numeric_strategy='mean',
target_variable=None)),
('new_levels1',
New_Catagorical_Levels_in_T...
('binn', 'passthrough'), ('rem_outliers', 'passthrough'),
('cluster_all', 'passthrough'),
('dummy', Dummify(target='pred')),
('fix_perfect', Remove_100(target='pred')),
('clean_names', Clean_Colum_Names()),
('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),
('dfs', 'passthrough'), ('pca', 'passthrough'),
['trained_model',
LogisticRegression(max_iter=1000, random_state=1559)]]), probability_threshold=None, encoded_labels=False, drift_report=False, raw_score=False, round=4, verbose=True, ml_usecase=MLUsecase.CLASSIFICATION, display=None, drift_kwargs=None)
2022-10-08 04:19:39,955:INFO:Checking exceptions
2022-10-08 04:19:39,955:INFO:Preloading libraries
2022-10-08 04:20:06,907:INFO:Initializing load_model()
2022-10-08 04:20:06,907:INFO:load_model(model_name=Logistic_Regression, platform=None, authentication=None, verbose=True)
2022-10-08 04:20:07,004:INFO:Initializing predict_model()
2022-10-08 04:20:07,005:INFO:predict_model(estimator=Pipeline(steps=[('dtypes',
DataTypes_Auto_infer(categorical_features=['input_1',
'input_2',
'input_3'],
ml_usecase='classification',
target='pred')),
('imputer',
Simple_Imputer(categorical_strategy='not_available',
fill_value_categorical=None,
fill_value_numerical=None,
numeric_strategy='mean',
target_variable=None)),
('new_levels1',
New_Catagorical_Levels_in_T...
('binn', 'passthrough'), ('rem_outliers', 'passthrough'),
('cluster_all', 'passthrough'),
('dummy', Dummify(target='pred')),
('fix_perfect', Remove_100(target='pred')),
('clean_names', Clean_Colum_Names()),
('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),
('dfs', 'passthrough'), ('pca', 'passthrough'),
['trained_model',
LogisticRegression(max_iter=1000, random_state=1559)]]), probability_threshold=None, encoded_labels=False, drift_report=False, raw_score=False, round=4, verbose=True, ml_usecase=MLUsecase.CLASSIFICATION, display=None, drift_kwargs=None)
2022-10-08 04:20:07,005:INFO:Checking exceptions
2022-10-08 04:20:07,005:INFO:Preloading libraries
backend/smart_assistant/notebook.ipynb 0 → 100644
View file @ 2fbef0f4
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "invisible-penguin",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pycaret.classification import *"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "removed-affect",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>input_1</th>\n",
" <th>input_2</th>\n",
" <th>input_3</th>\n",
" <th>pred</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>57.99879</td>\n",
" <td>46.27261</td>\n",
" <td>99.97455</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>51.99879</td>\n",
" <td>90.99575</td>\n",
" <td>46.27261</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>98.87455</td>\n",
" <td>90.99261</td>\n",
" <td>86.27225</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>91.24879</td>\n",
" <td>20.34575</td>\n",
" <td>42.27261</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>51.99879</td>\n",
" <td>93.99575</td>\n",
" <td>46.27261</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>922</th>\n",
" <td>96.53788</td>\n",
" <td>54.73844</td>\n",
" <td>17.69907</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>923</th>\n",
" <td>44.53781</td>\n",
" <td>88.37842</td>\n",
" <td>66.92945</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>924</th>\n",
" <td>69.38968</td>\n",
" <td>22.95433</td>\n",
" <td>59.82559</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>925</th>\n",
" <td>67.09695</td>\n",
" <td>54.56414</td>\n",
" <td>53.96752</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>926</th>\n",
" <td>32.12081</td>\n",
" <td>80.49886</td>\n",
" <td>30.47048</td>\n",
" <td>5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>927 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" input_1 input_2 input_3 pred\n",
"0 57.99879 46.27261 99.97455 0\n",
"1 51.99879 90.99575 46.27261 1\n",
"2 98.87455 90.99261 86.27225 2\n",
"3 91.24879 20.34575 42.27261 3\n",
"4 51.99879 93.99575 46.27261 4\n",
".. ... ... ... ...\n",
"922 96.53788 54.73844 17.69907 3\n",
"923 44.53781 88.37842 66.92945 1\n",
"924 69.38968 22.95433 59.82559 1\n",
"925 67.09695 54.56414 53.96752 2\n",
"926 32.12081 80.49886 30.47048 5\n",
"\n",
"[927 rows x 4 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('data/data.csv')\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "needed-eleven",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"#T_081c1_row44_col1{\n",
" background-color: lightgreen;\n",
" }</style><table id=\"T_081c1_\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Description</th> <th class=\"col_heading level0 col1\" >Value</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
" <td id=\"T_081c1_row0_col0\" class=\"data row0 col0\" >session_id</td>\n",
" <td id=\"T_081c1_row0_col1\" class=\"data row0 col1\" >1559</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
" <td id=\"T_081c1_row1_col0\" class=\"data row1 col0\" >Target</td>\n",
" <td id=\"T_081c1_row1_col1\" class=\"data row1 col1\" >pred</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
" <td id=\"T_081c1_row2_col0\" class=\"data row2 col0\" >Target Type</td>\n",
" <td id=\"T_081c1_row2_col1\" class=\"data row2 col1\" >Multiclass</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
" <td id=\"T_081c1_row3_col0\" class=\"data row3 col0\" >Label Encoded</td>\n",
" <td id=\"T_081c1_row3_col1\" class=\"data row3 col1\" >0: 0, 1: 1, 2: 2, 3: 3, 4: 4, 5: 5</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
" <td id=\"T_081c1_row4_col0\" class=\"data row4 col0\" >Original Data</td>\n",
" <td id=\"T_081c1_row4_col1\" class=\"data row4 col1\" >(927, 4)</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n",
" <td id=\"T_081c1_row5_col0\" class=\"data row5 col0\" >Missing Values</td>\n",
" <td id=\"T_081c1_row5_col1\" class=\"data row5 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n",
" <td id=\"T_081c1_row6_col0\" class=\"data row6 col0\" >Numeric Features</td>\n",
" <td id=\"T_081c1_row6_col1\" class=\"data row6 col1\" >0</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n",
" <td id=\"T_081c1_row7_col0\" class=\"data row7 col0\" >Categorical Features</td>\n",
" <td id=\"T_081c1_row7_col1\" class=\"data row7 col1\" >3</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n",
" <td id=\"T_081c1_row8_col0\" class=\"data row8 col0\" >Ordinal Features</td>\n",
" <td id=\"T_081c1_row8_col1\" class=\"data row8 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n",
" <td id=\"T_081c1_row9_col0\" class=\"data row9 col0\" >High Cardinality Features</td>\n",
" <td id=\"T_081c1_row9_col1\" class=\"data row9 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row10\" class=\"row_heading level0 row10\" >10</th>\n",
" <td id=\"T_081c1_row10_col0\" class=\"data row10 col0\" >High Cardinality Method</td>\n",
" <td id=\"T_081c1_row10_col1\" class=\"data row10 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row11\" class=\"row_heading level0 row11\" >11</th>\n",
" <td id=\"T_081c1_row11_col0\" class=\"data row11 col0\" >Transformed Train Set</td>\n",
" <td id=\"T_081c1_row11_col1\" class=\"data row11 col1\" >(648, 479)</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row12\" class=\"row_heading level0 row12\" >12</th>\n",
" <td id=\"T_081c1_row12_col0\" class=\"data row12 col0\" >Transformed Test Set</td>\n",
" <td id=\"T_081c1_row12_col1\" class=\"data row12 col1\" >(279, 479)</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row13\" class=\"row_heading level0 row13\" >13</th>\n",
" <td id=\"T_081c1_row13_col0\" class=\"data row13 col0\" >Shuffle Train-Test</td>\n",
" <td id=\"T_081c1_row13_col1\" class=\"data row13 col1\" >True</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row14\" class=\"row_heading level0 row14\" >14</th>\n",
" <td id=\"T_081c1_row14_col0\" class=\"data row14 col0\" >Stratify Train-Test</td>\n",
" <td id=\"T_081c1_row14_col1\" class=\"data row14 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row15\" class=\"row_heading level0 row15\" >15</th>\n",
" <td id=\"T_081c1_row15_col0\" class=\"data row15 col0\" >Fold Generator</td>\n",
" <td id=\"T_081c1_row15_col1\" class=\"data row15 col1\" >StratifiedKFold</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row16\" class=\"row_heading level0 row16\" >16</th>\n",
" <td id=\"T_081c1_row16_col0\" class=\"data row16 col0\" >Fold Number</td>\n",
" <td id=\"T_081c1_row16_col1\" class=\"data row16 col1\" >10</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row17\" class=\"row_heading level0 row17\" >17</th>\n",
" <td id=\"T_081c1_row17_col0\" class=\"data row17 col0\" >CPU Jobs</td>\n",
" <td id=\"T_081c1_row17_col1\" class=\"data row17 col1\" >-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row18\" class=\"row_heading level0 row18\" >18</th>\n",
" <td id=\"T_081c1_row18_col0\" class=\"data row18 col0\" >Use GPU</td>\n",
" <td id=\"T_081c1_row18_col1\" class=\"data row18 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row19\" class=\"row_heading level0 row19\" >19</th>\n",
" <td id=\"T_081c1_row19_col0\" class=\"data row19 col0\" >Log Experiment</td>\n",
" <td id=\"T_081c1_row19_col1\" class=\"data row19 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row20\" class=\"row_heading level0 row20\" >20</th>\n",
" <td id=\"T_081c1_row20_col0\" class=\"data row20 col0\" >Experiment Name</td>\n",
" <td id=\"T_081c1_row20_col1\" class=\"data row20 col1\" >clf-default-name</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row21\" class=\"row_heading level0 row21\" >21</th>\n",
" <td id=\"T_081c1_row21_col0\" class=\"data row21 col0\" >USI</td>\n",
" <td id=\"T_081c1_row21_col1\" class=\"data row21 col1\" >e8b1</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row22\" class=\"row_heading level0 row22\" >22</th>\n",
" <td id=\"T_081c1_row22_col0\" class=\"data row22 col0\" >Imputation Type</td>\n",
" <td id=\"T_081c1_row22_col1\" class=\"data row22 col1\" >simple</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row23\" class=\"row_heading level0 row23\" >23</th>\n",
" <td id=\"T_081c1_row23_col0\" class=\"data row23 col0\" >Iterative Imputation Iteration</td>\n",
" <td id=\"T_081c1_row23_col1\" class=\"data row23 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row24\" class=\"row_heading level0 row24\" >24</th>\n",
" <td id=\"T_081c1_row24_col0\" class=\"data row24 col0\" >Numeric Imputer</td>\n",
" <td id=\"T_081c1_row24_col1\" class=\"data row24 col1\" >mean</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row25\" class=\"row_heading level0 row25\" >25</th>\n",
" <td id=\"T_081c1_row25_col0\" class=\"data row25 col0\" >Iterative Imputation Numeric Model</td>\n",
" <td id=\"T_081c1_row25_col1\" class=\"data row25 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row26\" class=\"row_heading level0 row26\" >26</th>\n",
" <td id=\"T_081c1_row26_col0\" class=\"data row26 col0\" >Categorical Imputer</td>\n",
" <td id=\"T_081c1_row26_col1\" class=\"data row26 col1\" >constant</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row27\" class=\"row_heading level0 row27\" >27</th>\n",
" <td id=\"T_081c1_row27_col0\" class=\"data row27 col0\" >Iterative Imputation Categorical Model</td>\n",
" <td id=\"T_081c1_row27_col1\" class=\"data row27 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row28\" class=\"row_heading level0 row28\" >28</th>\n",
" <td id=\"T_081c1_row28_col0\" class=\"data row28 col0\" >Unknown Categoricals Handling</td>\n",
" <td id=\"T_081c1_row28_col1\" class=\"data row28 col1\" >least_frequent</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row29\" class=\"row_heading level0 row29\" >29</th>\n",
" <td id=\"T_081c1_row29_col0\" class=\"data row29 col0\" >Normalize</td>\n",
" <td id=\"T_081c1_row29_col1\" class=\"data row29 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row30\" class=\"row_heading level0 row30\" >30</th>\n",
" <td id=\"T_081c1_row30_col0\" class=\"data row30 col0\" >Normalize Method</td>\n",
" <td id=\"T_081c1_row30_col1\" class=\"data row30 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row31\" class=\"row_heading level0 row31\" >31</th>\n",
" <td id=\"T_081c1_row31_col0\" class=\"data row31 col0\" >Transformation</td>\n",
" <td id=\"T_081c1_row31_col1\" class=\"data row31 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row32\" class=\"row_heading level0 row32\" >32</th>\n",
" <td id=\"T_081c1_row32_col0\" class=\"data row32 col0\" >Transformation Method</td>\n",
" <td id=\"T_081c1_row32_col1\" class=\"data row32 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row33\" class=\"row_heading level0 row33\" >33</th>\n",
" <td id=\"T_081c1_row33_col0\" class=\"data row33 col0\" >PCA</td>\n",
" <td id=\"T_081c1_row33_col1\" class=\"data row33 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row34\" class=\"row_heading level0 row34\" >34</th>\n",
" <td id=\"T_081c1_row34_col0\" class=\"data row34 col0\" >PCA Method</td>\n",
" <td id=\"T_081c1_row34_col1\" class=\"data row34 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row35\" class=\"row_heading level0 row35\" >35</th>\n",
" <td id=\"T_081c1_row35_col0\" class=\"data row35 col0\" >PCA Components</td>\n",
" <td id=\"T_081c1_row35_col1\" class=\"data row35 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row36\" class=\"row_heading level0 row36\" >36</th>\n",
" <td id=\"T_081c1_row36_col0\" class=\"data row36 col0\" >Ignore Low Variance</td>\n",
" <td id=\"T_081c1_row36_col1\" class=\"data row36 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row37\" class=\"row_heading level0 row37\" >37</th>\n",
" <td id=\"T_081c1_row37_col0\" class=\"data row37 col0\" >Combine Rare Levels</td>\n",
" <td id=\"T_081c1_row37_col1\" class=\"data row37 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row38\" class=\"row_heading level0 row38\" >38</th>\n",
" <td id=\"T_081c1_row38_col0\" class=\"data row38 col0\" >Rare Level Threshold</td>\n",
" <td id=\"T_081c1_row38_col1\" class=\"data row38 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row39\" class=\"row_heading level0 row39\" >39</th>\n",
" <td id=\"T_081c1_row39_col0\" class=\"data row39 col0\" >Numeric Binning</td>\n",
" <td id=\"T_081c1_row39_col1\" class=\"data row39 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row40\" class=\"row_heading level0 row40\" >40</th>\n",
" <td id=\"T_081c1_row40_col0\" class=\"data row40 col0\" >Remove Outliers</td>\n",
" <td id=\"T_081c1_row40_col1\" class=\"data row40 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row41\" class=\"row_heading level0 row41\" >41</th>\n",
" <td id=\"T_081c1_row41_col0\" class=\"data row41 col0\" >Outliers Threshold</td>\n",
" <td id=\"T_081c1_row41_col1\" class=\"data row41 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row42\" class=\"row_heading level0 row42\" >42</th>\n",
" <td id=\"T_081c1_row42_col0\" class=\"data row42 col0\" >Remove Multicollinearity</td>\n",
" <td id=\"T_081c1_row42_col1\" class=\"data row42 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row43\" class=\"row_heading level0 row43\" >43</th>\n",
" <td id=\"T_081c1_row43_col0\" class=\"data row43 col0\" >Multicollinearity Threshold</td>\n",
" <td id=\"T_081c1_row43_col1\" class=\"data row43 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row44\" class=\"row_heading level0 row44\" >44</th>\n",
" <td id=\"T_081c1_row44_col0\" class=\"data row44 col0\" >Remove Perfect Collinearity</td>\n",
" <td id=\"T_081c1_row44_col1\" class=\"data row44 col1\" >True</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row45\" class=\"row_heading level0 row45\" >45</th>\n",
" <td id=\"T_081c1_row45_col0\" class=\"data row45 col0\" >Clustering</td>\n",
" <td id=\"T_081c1_row45_col1\" class=\"data row45 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row46\" class=\"row_heading level0 row46\" >46</th>\n",
" <td id=\"T_081c1_row46_col0\" class=\"data row46 col0\" >Clustering Iteration</td>\n",
" <td id=\"T_081c1_row46_col1\" class=\"data row46 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row47\" class=\"row_heading level0 row47\" >47</th>\n",
" <td id=\"T_081c1_row47_col0\" class=\"data row47 col0\" >Polynomial Features</td>\n",
" <td id=\"T_081c1_row47_col1\" class=\"data row47 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row48\" class=\"row_heading level0 row48\" >48</th>\n",
" <td id=\"T_081c1_row48_col0\" class=\"data row48 col0\" >Polynomial Degree</td>\n",
" <td id=\"T_081c1_row48_col1\" class=\"data row48 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row49\" class=\"row_heading level0 row49\" >49</th>\n",
" <td id=\"T_081c1_row49_col0\" class=\"data row49 col0\" >Trignometry Features</td>\n",
" <td id=\"T_081c1_row49_col1\" class=\"data row49 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row50\" class=\"row_heading level0 row50\" >50</th>\n",
" <td id=\"T_081c1_row50_col0\" class=\"data row50 col0\" >Polynomial Threshold</td>\n",
" <td id=\"T_081c1_row50_col1\" class=\"data row50 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row51\" class=\"row_heading level0 row51\" >51</th>\n",
" <td id=\"T_081c1_row51_col0\" class=\"data row51 col0\" >Group Features</td>\n",
" <td id=\"T_081c1_row51_col1\" class=\"data row51 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row52\" class=\"row_heading level0 row52\" >52</th>\n",
" <td id=\"T_081c1_row52_col0\" class=\"data row52 col0\" >Feature Selection</td>\n",
" <td id=\"T_081c1_row52_col1\" class=\"data row52 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row53\" class=\"row_heading level0 row53\" >53</th>\n",
" <td id=\"T_081c1_row53_col0\" class=\"data row53 col0\" >Feature Selection Method</td>\n",
" <td id=\"T_081c1_row53_col1\" class=\"data row53 col1\" >classic</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row54\" class=\"row_heading level0 row54\" >54</th>\n",
" <td id=\"T_081c1_row54_col0\" class=\"data row54 col0\" >Features Selection Threshold</td>\n",
" <td id=\"T_081c1_row54_col1\" class=\"data row54 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row55\" class=\"row_heading level0 row55\" >55</th>\n",
" <td id=\"T_081c1_row55_col0\" class=\"data row55 col0\" >Feature Interaction</td>\n",
" <td id=\"T_081c1_row55_col1\" class=\"data row55 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row56\" class=\"row_heading level0 row56\" >56</th>\n",
" <td id=\"T_081c1_row56_col0\" class=\"data row56 col0\" >Feature Ratio</td>\n",
" <td id=\"T_081c1_row56_col1\" class=\"data row56 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row57\" class=\"row_heading level0 row57\" >57</th>\n",
" <td id=\"T_081c1_row57_col0\" class=\"data row57 col0\" >Interaction Threshold</td>\n",
" <td id=\"T_081c1_row57_col1\" class=\"data row57 col1\" >None</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row58\" class=\"row_heading level0 row58\" >58</th>\n",
" <td id=\"T_081c1_row58_col0\" class=\"data row58 col0\" >Fix Imbalance</td>\n",
" <td id=\"T_081c1_row58_col1\" class=\"data row58 col1\" >False</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_081c1_level0_row59\" class=\"row_heading level0 row59\" >59</th>\n",
" <td id=\"T_081c1_row59_col0\" class=\"data row59 col0\" >Fix Imbalance Method</td>\n",
" <td id=\"T_081c1_row59_col1\" class=\"data row59 col1\" >SMOTE</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fe592d54370>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cat_features = ['input_1', 'input_2', 'input_3']\n",
"experiment = setup(df, target='pred', categorical_features=cat_features)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "editorial-culture",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
" #T_d9993_ th {\n",
" text-align: left;\n",
" }#T_d9993_row0_col0,#T_d9993_row1_col0,#T_d9993_row2_col0,#T_d9993_row2_col2,#T_d9993_row3_col0,#T_d9993_row4_col0,#T_d9993_row5_col0,#T_d9993_row6_col0,#T_d9993_row7_col0,#T_d9993_row8_col0,#T_d9993_row8_col1,#T_d9993_row8_col2,#T_d9993_row8_col4,#T_d9993_row8_col5,#T_d9993_row9_col0,#T_d9993_row9_col1,#T_d9993_row9_col2,#T_d9993_row9_col3,#T_d9993_row9_col4,#T_d9993_row9_col5,#T_d9993_row10_col0,#T_d9993_row10_col1,#T_d9993_row10_col4,#T_d9993_row10_col5,#T_d9993_row11_col0,#T_d9993_row11_col1,#T_d9993_row11_col2,#T_d9993_row11_col4,#T_d9993_row11_col5,#T_d9993_row12_col0,#T_d9993_row12_col1,#T_d9993_row12_col2,#T_d9993_row12_col4,#T_d9993_row12_col5{\n",
" text-align: left;\n",
" text-align: left;\n",
" }#T_d9993_row0_col1,#T_d9993_row0_col2,#T_d9993_row0_col3,#T_d9993_row0_col4,#T_d9993_row0_col5,#T_d9993_row0_col6,#T_d9993_row0_col7,#T_d9993_row1_col1,#T_d9993_row1_col2,#T_d9993_row1_col3,#T_d9993_row1_col4,#T_d9993_row1_col5,#T_d9993_row1_col6,#T_d9993_row1_col7,#T_d9993_row2_col1,#T_d9993_row2_col3,#T_d9993_row2_col4,#T_d9993_row2_col5,#T_d9993_row2_col6,#T_d9993_row2_col7,#T_d9993_row3_col1,#T_d9993_row3_col2,#T_d9993_row3_col3,#T_d9993_row3_col4,#T_d9993_row3_col5,#T_d9993_row3_col6,#T_d9993_row3_col7,#T_d9993_row4_col1,#T_d9993_row4_col2,#T_d9993_row4_col3,#T_d9993_row4_col4,#T_d9993_row4_col5,#T_d9993_row4_col6,#T_d9993_row4_col7,#T_d9993_row5_col1,#T_d9993_row5_col2,#T_d9993_row5_col3,#T_d9993_row5_col4,#T_d9993_row5_col5,#T_d9993_row5_col6,#T_d9993_row5_col7,#T_d9993_row6_col1,#T_d9993_row6_col2,#T_d9993_row6_col3,#T_d9993_row6_col4,#T_d9993_row6_col5,#T_d9993_row6_col6,#T_d9993_row6_col7,#T_d9993_row7_col1,#T_d9993_row7_col2,#T_d9993_row7_col3,#T_d9993_row7_col4,#T_d9993_row7_col5,#T_d9993_row7_col6,#T_d9993_row7_col7,#T_d9993_row8_col3,#T_d9993_row8_col6,#T_d9993_row8_col7,#T_d9993_row9_col6,#T_d9993_row9_col7,#T_d9993_row10_col2,#T_d9993_row10_col3,#T_d9993_row10_col6,#T_d9993_row10_col7,#T_d9993_row11_col3,#T_d9993_row11_col6,#T_d9993_row11_col7,#T_d9993_row12_col3,#T_d9993_row12_col6,#T_d9993_row12_col7{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: yellow;\n",
" }#T_d9993_row0_col8,#T_d9993_row1_col8,#T_d9993_row3_col8,#T_d9993_row4_col8,#T_d9993_row5_col8,#T_d9993_row6_col8,#T_d9993_row7_col8,#T_d9993_row8_col8,#T_d9993_row9_col8,#T_d9993_row10_col8,#T_d9993_row12_col8{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: lightgrey;\n",
" }#T_d9993_row2_col8,#T_d9993_row11_col8{\n",
" text-align: left;\n",
" text-align: left;\n",
" background-color: yellow;\n",
" background-color: lightgrey;\n",
" }</style><table id=\"T_d9993_\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >Model</th> <th class=\"col_heading level0 col1\" >Accuracy</th> <th class=\"col_heading level0 col2\" >AUC</th> <th class=\"col_heading level0 col3\" >Recall</th> <th class=\"col_heading level0 col4\" >Prec.</th> <th class=\"col_heading level0 col5\" >F1</th> <th class=\"col_heading level0 col6\" >Kappa</th> <th class=\"col_heading level0 col7\" >MCC</th> <th class=\"col_heading level0 col8\" >TT (Sec)</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row0\" class=\"row_heading level0 row0\" >lr</th>\n",
" <td id=\"T_d9993_row0_col0\" class=\"data row0 col0\" >Logistic Regression</td>\n",
" <td id=\"T_d9993_row0_col1\" class=\"data row0 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row0_col2\" class=\"data row0 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row0_col3\" class=\"data row0 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row0_col4\" class=\"data row0 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row0_col5\" class=\"data row0 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row0_col6\" class=\"data row0 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row0_col7\" class=\"data row0 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row0_col8\" class=\"data row0 col8\" >0.0390</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row1\" class=\"row_heading level0 row1\" >dt</th>\n",
" <td id=\"T_d9993_row1_col0\" class=\"data row1 col0\" >Decision Tree Classifier</td>\n",
" <td id=\"T_d9993_row1_col1\" class=\"data row1 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row1_col2\" class=\"data row1 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row1_col3\" class=\"data row1 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row1_col4\" class=\"data row1 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row1_col5\" class=\"data row1 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row1_col6\" class=\"data row1 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row1_col7\" class=\"data row1 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row1_col8\" class=\"data row1 col8\" >0.0590</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row2\" class=\"row_heading level0 row2\" >ridge</th>\n",
" <td id=\"T_d9993_row2_col0\" class=\"data row2 col0\" >Ridge Classifier</td>\n",
" <td id=\"T_d9993_row2_col1\" class=\"data row2 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row2_col2\" class=\"data row2 col2\" >0.0000</td>\n",
" <td id=\"T_d9993_row2_col3\" class=\"data row2 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row2_col4\" class=\"data row2 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row2_col5\" class=\"data row2 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row2_col6\" class=\"data row2 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row2_col7\" class=\"data row2 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row2_col8\" class=\"data row2 col8\" >0.0230</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row3\" class=\"row_heading level0 row3\" >rf</th>\n",
" <td id=\"T_d9993_row3_col0\" class=\"data row3 col0\" >Random Forest Classifier</td>\n",
" <td id=\"T_d9993_row3_col1\" class=\"data row3 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row3_col2\" class=\"data row3 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row3_col3\" class=\"data row3 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row3_col4\" class=\"data row3 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row3_col5\" class=\"data row3 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row3_col6\" class=\"data row3 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row3_col7\" class=\"data row3 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row3_col8\" class=\"data row3 col8\" >0.1360</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row4\" class=\"row_heading level0 row4\" >ada</th>\n",
" <td id=\"T_d9993_row4_col0\" class=\"data row4 col0\" >Ada Boost Classifier</td>\n",
" <td id=\"T_d9993_row4_col1\" class=\"data row4 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row4_col2\" class=\"data row4 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row4_col3\" class=\"data row4 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row4_col4\" class=\"data row4 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row4_col5\" class=\"data row4 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row4_col6\" class=\"data row4 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row4_col7\" class=\"data row4 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row4_col8\" class=\"data row4 col8\" >0.0640</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row5\" class=\"row_heading level0 row5\" >gbc</th>\n",
" <td id=\"T_d9993_row5_col0\" class=\"data row5 col0\" >Gradient Boosting Classifier</td>\n",
" <td id=\"T_d9993_row5_col1\" class=\"data row5 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row5_col2\" class=\"data row5 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row5_col3\" class=\"data row5 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row5_col4\" class=\"data row5 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row5_col5\" class=\"data row5 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row5_col6\" class=\"data row5 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row5_col7\" class=\"data row5 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row5_col8\" class=\"data row5 col8\" >0.3950</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row6\" class=\"row_heading level0 row6\" >et</th>\n",
" <td id=\"T_d9993_row6_col0\" class=\"data row6 col0\" >Extra Trees Classifier</td>\n",
" <td id=\"T_d9993_row6_col1\" class=\"data row6 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row6_col2\" class=\"data row6 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row6_col3\" class=\"data row6 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row6_col4\" class=\"data row6 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row6_col5\" class=\"data row6 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row6_col6\" class=\"data row6 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row6_col7\" class=\"data row6 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row6_col8\" class=\"data row6 col8\" >0.1710</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row7\" class=\"row_heading level0 row7\" >lightgbm</th>\n",
" <td id=\"T_d9993_row7_col0\" class=\"data row7 col0\" >Light Gradient Boosting Machine</td>\n",
" <td id=\"T_d9993_row7_col1\" class=\"data row7 col1\" >0.1852</td>\n",
" <td id=\"T_d9993_row7_col2\" class=\"data row7 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row7_col3\" class=\"data row7 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row7_col4\" class=\"data row7 col4\" >0.0343</td>\n",
" <td id=\"T_d9993_row7_col5\" class=\"data row7 col5\" >0.0579</td>\n",
" <td id=\"T_d9993_row7_col6\" class=\"data row7 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row7_col7\" class=\"data row7 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row7_col8\" class=\"data row7 col8\" >0.0250</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row8\" class=\"row_heading level0 row8\" >svm</th>\n",
" <td id=\"T_d9993_row8_col0\" class=\"data row8 col0\" >SVM - Linear Kernel</td>\n",
" <td id=\"T_d9993_row8_col1\" class=\"data row8 col1\" >0.1698</td>\n",
" <td id=\"T_d9993_row8_col2\" class=\"data row8 col2\" >0.0000</td>\n",
" <td id=\"T_d9993_row8_col3\" class=\"data row8 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row8_col4\" class=\"data row8 col4\" >0.0290</td>\n",
" <td id=\"T_d9993_row8_col5\" class=\"data row8 col5\" >0.0495</td>\n",
" <td id=\"T_d9993_row8_col6\" class=\"data row8 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row8_col7\" class=\"data row8 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row8_col8\" class=\"data row8 col8\" >0.0360</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row9\" class=\"row_heading level0 row9\" >lda</th>\n",
" <td id=\"T_d9993_row9_col0\" class=\"data row9 col0\" >Linear Discriminant Analysis</td>\n",
" <td id=\"T_d9993_row9_col1\" class=\"data row9 col1\" >0.1667</td>\n",
" <td id=\"T_d9993_row9_col2\" class=\"data row9 col2\" >0.4464</td>\n",
" <td id=\"T_d9993_row9_col3\" class=\"data row9 col3\" >0.1500</td>\n",
" <td id=\"T_d9993_row9_col4\" class=\"data row9 col4\" >0.0309</td>\n",
" <td id=\"T_d9993_row9_col5\" class=\"data row9 col5\" >0.0521</td>\n",
" <td id=\"T_d9993_row9_col6\" class=\"data row9 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row9_col7\" class=\"data row9 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row9_col8\" class=\"data row9 col8\" >0.0610</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row10\" class=\"row_heading level0 row10\" >knn</th>\n",
" <td id=\"T_d9993_row10_col0\" class=\"data row10 col0\" >K Neighbors Classifier</td>\n",
" <td id=\"T_d9993_row10_col1\" class=\"data row10 col1\" >0.1543</td>\n",
" <td id=\"T_d9993_row10_col2\" class=\"data row10 col2\" >0.5000</td>\n",
" <td id=\"T_d9993_row10_col3\" class=\"data row10 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row10_col4\" class=\"data row10 col4\" >0.0238</td>\n",
" <td id=\"T_d9993_row10_col5\" class=\"data row10 col5\" >0.0413</td>\n",
" <td id=\"T_d9993_row10_col6\" class=\"data row10 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row10_col7\" class=\"data row10 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row10_col8\" class=\"data row10 col8\" >0.0350</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row11\" class=\"row_heading level0 row11\" >nb</th>\n",
" <td id=\"T_d9993_row11_col0\" class=\"data row11 col0\" >Naive Bayes</td>\n",
" <td id=\"T_d9993_row11_col1\" class=\"data row11 col1\" >0.1543</td>\n",
" <td id=\"T_d9993_row11_col2\" class=\"data row11 col2\" >0.4939</td>\n",
" <td id=\"T_d9993_row11_col3\" class=\"data row11 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row11_col4\" class=\"data row11 col4\" >0.0238</td>\n",
" <td id=\"T_d9993_row11_col5\" class=\"data row11 col5\" >0.0413</td>\n",
" <td id=\"T_d9993_row11_col6\" class=\"data row11 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row11_col7\" class=\"data row11 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row11_col8\" class=\"data row11 col8\" >0.0230</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_d9993_level0_row12\" class=\"row_heading level0 row12\" >qda</th>\n",
" <td id=\"T_d9993_row12_col0\" class=\"data row12 col0\" >Quadratic Discriminant Analysis</td>\n",
" <td id=\"T_d9993_row12_col1\" class=\"data row12 col1\" >0.1420</td>\n",
" <td id=\"T_d9993_row12_col2\" class=\"data row12 col2\" >0.0000</td>\n",
" <td id=\"T_d9993_row12_col3\" class=\"data row12 col3\" >0.1667</td>\n",
" <td id=\"T_d9993_row12_col4\" class=\"data row12 col4\" >0.0203</td>\n",
" <td id=\"T_d9993_row12_col5\" class=\"data row12 col5\" >0.0355</td>\n",
" <td id=\"T_d9993_row12_col6\" class=\"data row12 col6\" >0.0000</td>\n",
" <td id=\"T_d9993_row12_col7\" class=\"data row12 col7\" >0.0000</td>\n",
" <td id=\"T_d9993_row12_col8\" class=\"data row12 col8\" >0.0310</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7fe5b7a67c10>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"top3 = compare_models(n_select = 3)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "documentary-flooring",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Transformation Pipeline and Model Successfully Saved\n"
]
},
{
"data": {
"text/plain": [
"(Pipeline(memory=None,\n",
" steps=[('dtypes',\n",
" DataTypes_Auto_infer(categorical_features=['input_1',\n",
" 'input_2',\n",
" 'input_3'],\n",
" display_types=True, features_todrop=[],\n",
" id_columns=[],\n",
" ml_usecase='classification',\n",
" numerical_features=[], target='pred',\n",
" time_features=[])),\n",
" ('imputer',\n",
" Simple_Imputer(categorical_strategy='not_available',\n",
" fill_value_categorical=None,\n",
" fill_value_n...\n",
" ('feature_select', 'passthrough'), ('fix_multi', 'passthrough'),\n",
" ('dfs', 'passthrough'), ('pca', 'passthrough'),\n",
" ['trained_model',\n",
" LogisticRegression(C=1.0, class_weight=None, dual=False,\n",
" fit_intercept=True, intercept_scaling=1,\n",
" l1_ratio=None, max_iter=1000,\n",
" multi_class='auto', n_jobs=None,\n",
" penalty='l2', random_state=1559,\n",
" solver='lbfgs', tol=0.0001, verbose=0,\n",
" warm_start=False)]],\n",
" verbose=False),\n",
" 'Logistic_Regression.pkl')"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"save_model(top3[0], model_name='Logistic_Regression')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "egyptian-manor",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
backend/smart_assistant/readme.txt 0 → 100644
View file @ 2fbef0f4
pip install tensorflow==2.3.0 gym keras keras-rl2 pycaret flask Flask-Cors
pip install pycaret
pip install numpy==1.18.0
backend/smart_assistant/test.py 0 → 100644
View file @ 2fbef0f4
import EmotionEnv
env = EmotionEnv.EmotionEnv()
env.observation_space.sample()
episodes = 10
for episode in range(1, episodes + 1):
state = env.reset()
done = False
score = 0
while not done:
# env.render()
action = env.action_space.sample()
n_state, reward, done, info = env.step(action)
score += reward
print('Episode:{} Score:{}'.format(episode, score))
backend/smart_assistant/test_2.py 0 → 100644
View file @ 2fbef0f4
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.optimizers import Adam
import EmotionEnv
from rl.agents import DQNAgent
from rl.policy import BoltzmannQPolicy
from rl.memory import SequentialMemory
env = EmotionEnv.EmotionEnv()
states = env.observation_space.shape
actions = env.action_space.n
def build_model(states, actions):
model = Sequential()
model.add(Dense(24, activation='relu', input_shape=states))
model.add(Dense(24, activation='relu'))
model.add(Dense(actions, activation='linear'))
return model
model = build_model(states, actions)
print(model.summary())
def build_agent(model, actions):
policy = BoltzmannQPolicy()
memory = SequentialMemory(limit=50000, window_length=1)
dqn = DQNAgent(model=model, memory=memory, policy=policy,
nb_actions=actions, nb_steps_warmup=10, target_model_update=1e-2)
return dqn
dqn = build_agent(model, actions)
dqn.compile(Adam(lr=1e-3), metrics=['mae'])
dqn.fit(env, nb_steps=50000, visualize=False, verbose=1)
scores = dqn.test(env, nb_episodes=100, visualize=False)
print(np.mean(scores.history['episode_reward']))
dqn.save_weights('dqn_weights.h5f', overwrite=True)
backend/smart_assistant/test_3.py 0 → 100644
View file @ 2fbef0f4
import EmotionEnv
env = EmotionEnv.EmotionEnv()
env.observation_space.sample()
episodes = 10
for episode in range(1, episodes + 1):
state = env.reset()
done = False
score = 0
while not done:
# env.render()
action = env.action_space.sample()
n_state, reward, done, info = env.step(action)
score += reward
print('Episode:{} Score:{}'.format(episode, score))
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment