Skip to content

2
2021-193 User-friendly enhanced machine learning-based railway management system
Commit db02e3a7 authored by Mihiranga G.L.V - IT18500790's avatar Mihiranga G.L.V - IT18500790
Browse files
Options

Upload New File

parent a8a24fab
Show whitespace changes
Inline Side-by-side
Showing with 958 additions and 0 deletions
Railway_Line_Predict.ipynb 0 → 100644
View file @ db02e3a7
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "2c445b47",
"metadata": {},
"outputs": [],
"source": [
"#Import All libraries for Prediction\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from tqdm.notebook import tqdm\n",
"from collections import Counter\n",
"from sklearn import metrics\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import classification_report,confusion_matrix"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "adcb4ca1",
"metadata": {},
"outputs": [],
"source": [
"#Filter Warning messages\n",
"import warnings\n",
"warnings.filterwarnings('ignore')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "2e97a069",
"metadata": {},
"outputs": [],
"source": [
"#Import Passenger's Dataset and Assign that dataset to Variable \n",
"PassData = pd.read_csv(\"Passenger_Travel_Line_Data.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "fae02b53",
"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>Age</th>\n",
" <th>Count</th>\n",
" <th>Country</th>\n",
" <th>GenderNo</th>\n",
" <th>LineNo</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"Empty DataFrame\n",
"Columns: [Age, Count, Country, GenderNo, LineNo]\n",
"Index: []"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"PassData[pd.isnull(PassData).any(axis=1)]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "83755e8a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0 3\n",
"1 1\n",
"2 6\n",
"3 6\n",
"4 1\n",
" ..\n",
"7387 1\n",
"7388 5\n",
"7389 4\n",
"7390 5\n",
"7391 5\n",
"Name: LineNo, Length: 7392, dtype: int64\n"
]
}
],
"source": [
"#Y feature (Line No) Assign to Y variable\n",
"Y = PassData.LineNo.copy()\n",
"print(Y)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3c434d28",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Age Count Country GenderNo\n",
"0 38 7 169 1\n",
"1 33 1 165 1\n",
"2 52 6 186 2\n",
"3 52 8 165 2\n",
"4 33 4 165 1\n",
"... ... ... ... ...\n",
"7387 56 7 9 2\n",
"7388 48 3 165 1\n",
"7389 16 4 77 1\n",
"7390 14 6 165 1\n",
"7391 38 3 77 1\n",
"\n",
"[7392 rows x 4 columns]\n"
]
}
],
"source": [
"#X feature (Passenger age, Passenger Country, Passengers count, Passenger Gender) Assign to Y variable\n",
"X = PassData.drop(['LineNo'], axis=1)\n",
"print(X)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "aa6eb91f",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"1 3611\n",
"2 1941\n",
"6 1263\n",
"5 178\n",
"4 169\n",
"3 168\n",
"7 62\n",
"Name: LineNo, dtype: int64"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Data row count for each line\n",
"PassData['LineNo'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "f8ad1a87",
"metadata": {},
"outputs": [],
"source": [
"def pearson(X,Y):\n",
" correlation_matrix = np.corrcoef(X,Y)\n",
" return correlation_matrix[0,1]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "ff7c07bb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.29489433997181086\n",
"0.12408172469911788\n",
"-0.3019730376888903\n",
"0.001401546695404602\n"
]
}
],
"source": [
"print(pearson(X.Age, Y))\n",
"print(pearson(X.Count, Y))\n",
"print(pearson(X.Country, Y))\n",
"print(pearson(X.GenderNo, Y))"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "865e647a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"8.251627549828065\n",
"0.7795532262240084\n",
"-22.882514934947803\n",
"0.0013326433634917101\n"
]
}
],
"source": [
"print(np.cov(X.Age, Y)[0,1])\n",
"print(np.cov(X.Count, Y)[0,1])\n",
"print(np.cov(X.Country, Y)[0,1])\n",
"print(np.cov(X.GenderNo, Y)[0,1])"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "62dff0f9",
"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>Age</th>\n",
" <th>Count</th>\n",
" <th>Country</th>\n",
" <th>GenderNo</th>\n",
" <th>LineNo</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>38</td>\n",
" <td>7</td>\n",
" <td>169</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>33</td>\n",
" <td>1</td>\n",
" <td>165</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>52</td>\n",
" <td>6</td>\n",
" <td>186</td>\n",
" <td>2</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>52</td>\n",
" <td>8</td>\n",
" <td>165</td>\n",
" <td>2</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>33</td>\n",
" <td>4</td>\n",
" <td>165</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Age Count Country GenderNo LineNo\n",
"0 38 7 169 1 3\n",
"1 33 1 165 1 1\n",
"2 52 6 186 2 6\n",
"3 52 8 165 2 6\n",
"4 33 4 165 1 1"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"PassData.head()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "8ed8fa4a",
"metadata": {},
"outputs": [],
"source": [
"finalFeaturedDataset = PassData[['Age', 'Count','Country','GenderNo']]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "6dcb7e74",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import MinMaxScaler\n",
"scaler = MinMaxScaler(feature_range=(0,1)) \n",
"\n",
"#assign scaler to column:\n",
"PassData = pd.DataFrame(scaler.fit_transform(finalFeaturedDataset), columns=finalFeaturedDataset.columns)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "f707600c",
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.30, random_state=123)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "b689e6a7",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LogisticRegression"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "8deca7e2",
"metadata": {},
"outputs": [],
"source": [
"model = LogisticRegression()\n",
"model.fit(X_train, Y_train)\n",
"\n",
"Y_pred = pd.Series(model.predict(X_test))\n",
"\n",
"Y_test = Y_test.reset_index(drop=True)\n",
"Z = pd.concat([Y_test, Y_pred], axis = 1)\n",
"Z.columns = ['True', 'Prediction']\n",
"\n",
"acc_log = metrics.accuracy_score(Y_test, Y_pred)\n",
"pre_log = metrics.precision_score(Y_test,Y_pred, average='macro')\n",
"recall_log = metrics.recall_score(Y_test,Y_pred, average='macro')\n",
"f1_log = metrics.f1_score(Y_test,Y_pred, average='macro')"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "0177e879",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.6262398557258791\n",
"Precision: 0.24419142446879588\n",
"Recall: 0.26669667105604467\n",
"f1-score: 0.2532355511236177\n"
]
}
],
"source": [
"print(\"Accuracy:\", metrics.accuracy_score(Y_test, Y_pred))\n",
"print(\"Precision:\", metrics.precision_score(Y_test, Y_pred,average='macro'))\n",
"print(\"Recall:\", metrics.recall_score(Y_test, Y_pred,average='macro'))\n",
"print(\"f1-score:\", metrics.f1_score(Y_test,Y_pred, average='macro'))"
]
},
{
"cell_type": "markdown",
"id": "d563d7ef",
"metadata": {},
"source": [
"# Support Vector Machine Algorithm"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "f1b4e2ca",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.svm import SVC, LinearSVC"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "d8de5898",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "09e9c47220984de082d0399855bc1607",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/10 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#X_train, X_test, Y_train, Y_test,Y_pred\n",
"\n",
"linear_svc = LinearSVC()\n",
"for i in tqdm(range(10)):\n",
" linear_svc.fit(X_train, Y_train)\n",
"\n",
"Y_pred = linear_svc.predict(X_test)\n",
"\n",
"acc_linear_svc = metrics.accuracy_score(Y_test, Y_pred)\n",
"pre_linear_svc = metrics.precision_score(Y_test,Y_pred, average='macro')\n",
"recall_linear_svc = metrics.recall_score(Y_test,Y_pred, average='macro')\n",
"f1_linear_svc = metrics.f1_score(Y_test,Y_pred, average='macro')"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "cd61bc74",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.5365193868349865\n",
"Precision: 0.2589134336854379\n",
"Recall: 0.28523216312749744\n",
"f1-score: 0.24436669759464053\n"
]
}
],
"source": [
"print(\"Accuracy:\", metrics.accuracy_score(Y_test, Y_pred))\n",
"print(\"Precision:\", metrics.precision_score(Y_test, Y_pred,average='macro'))\n",
"print(\"Recall:\", metrics.recall_score(Y_test, Y_pred,average='macro'))\n",
"print(\"f1-score:\", metrics.f1_score(Y_test,Y_pred, average='macro'))"
]
},
{
"cell_type": "markdown",
"id": "0e36188a",
"metadata": {},
"source": [
"# Naive Bayes Algorithm"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "64b800fc",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.naive_bayes import GaussianNB"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "b28b868a",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2bbd68e465f24b8191123ad89ba67080",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/10 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#X_train, X_test, Y_train, Y_test,Y_pred\n",
"gaussian = GaussianNB() \n",
"for i in tqdm(range(10)):\n",
" gaussian.fit(X_train, Y_train) \n",
"Y_pred = gaussian.predict(X_test)\n",
"\n",
"acc_gaussian = metrics.accuracy_score(Y_test, Y_pred)\n",
"pre_gaussian = metrics.precision_score(Y_test,Y_pred, average='macro')\n",
"recall_gaussian = metrics.recall_score(Y_test,Y_pred, average='macro')\n",
"f1_gaussian = metrics.f1_score(Y_test,Y_pred, average='macro')"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "229aeefe",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.8214607754733995\n",
"Precision: 0.3975998841137974\n",
"Recall: 0.4016636978863704\n",
"f1-score: 0.3979258465031035\n"
]
}
],
"source": [
"print(\"Accuracy:\", metrics.accuracy_score(Y_test, Y_pred))\n",
"print(\"Precision:\", metrics.precision_score(Y_test, Y_pred,average='macro'))\n",
"print(\"Recall:\", metrics.recall_score(Y_test, Y_pred,average='macro'))\n",
"print(\"f1-score:\", metrics.f1_score(Y_test,Y_pred, average='macro'))"
]
},
{
"cell_type": "markdown",
"id": "651501da",
"metadata": {},
"source": [
"# Decision Tree Algorithm"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "7fb9cf66",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.tree import DecisionTreeClassifier"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "713d1ce9",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "27ac4b63b5d740d5b80bf7557bfc4d04",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/10 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"decision_tree = DecisionTreeClassifier() \n",
"for i in tqdm(range(10)):\n",
" decision_tree.fit(X_train, Y_train) \n",
"Y_pred = decision_tree.predict(X_test)\n",
"\n",
"acc_decision = metrics.accuracy_score(Y_test, Y_pred)\n",
"pre_decision = metrics.precision_score(Y_test,Y_pred, average='macro')\n",
"recall_decision = metrics.recall_score(Y_test,Y_pred, average='macro')\n",
"f1_decision = metrics.f1_score(Y_test,Y_pred, average='macro')"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "d7f314f9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[1091 0 2 4 3 3 2]\n",
" [ 3 544 2 3 4 1 2]\n",
" [ 2 6 39 4 2 1 2]\n",
" [ 3 2 3 28 5 2 3]\n",
" [ 3 4 3 0 39 2 1]\n",
" [ 5 1 2 2 2 359 5]\n",
" [ 6 4 5 2 3 2 2]]\n"
]
}
],
"source": [
"print(confusion_matrix(Y_test, Y_pred))"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "167f968d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.9477006311992786\n",
"Precision: 0.722550436699368\n",
"Recall: 0.7219630680336654\n",
"f1-score: 0.721422594292315\n"
]
}
],
"source": [
"print(\"Accuracy:\", metrics.accuracy_score(Y_test, Y_pred))\n",
"print(\"Precision:\", metrics.precision_score(Y_test, Y_pred,average='macro'))\n",
"print(\"Recall:\", metrics.recall_score(Y_test, Y_pred,average='macro'))\n",
"print(\"f1-score:\", metrics.f1_score(Y_test,Y_pred, average='macro'))"
]
},
{
"cell_type": "markdown",
"id": "9d084280",
"metadata": {},
"source": [
"# Each Model Accuracy Level For Railway Line Predict"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "d2a2e1ea",
"metadata": {
"scrolled": true
},
"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>Model</th>\n",
" <th>Precission</th>\n",
" <th>Recall</th>\n",
" <th>F1-Score</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Accuracy</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0.947701</th>\n",
" <td>Decision Tree</td>\n",
" <td>0.722550</td>\n",
" <td>0.721963</td>\n",
" <td>0.721423</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0.821461</th>\n",
" <td>Naive Bayes</td>\n",
" <td>0.397600</td>\n",
" <td>0.401664</td>\n",
" <td>0.397926</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0.626240</th>\n",
" <td>Logistic Regression</td>\n",
" <td>0.244191</td>\n",
" <td>0.266697</td>\n",
" <td>0.253236</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0.536519</th>\n",
" <td>Support Vector Machines</td>\n",
" <td>0.258913</td>\n",
" <td>0.285232</td>\n",
" <td>0.244367</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model Precission Recall F1-Score\n",
"Accuracy \n",
"0.947701 Decision Tree 0.722550 0.721963 0.721423\n",
"0.821461 Naive Bayes 0.397600 0.401664 0.397926\n",
"0.626240 Logistic Regression 0.244191 0.266697 0.253236\n",
"0.536519 Support Vector Machines 0.258913 0.285232 0.244367"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results = pd.DataFrame({\n",
" 'Model': ['Support Vector Machines', 'Logistic Regression','Naive Bayes', \n",
" 'Decision Tree', ],\n",
" 'Accuracy': [acc_linear_svc, acc_log, \n",
" acc_gaussian, acc_decision],\n",
" 'Precission': [pre_linear_svc, pre_log, \n",
" pre_gaussian, pre_decision],\n",
" 'Recall': [recall_linear_svc, recall_log, \n",
" recall_gaussian, recall_decision],\n",
" 'F1-Score': [f1_linear_svc, f1_log, \n",
" f1_gaussian, f1_decision]})\n",
"\n",
"result_df = results.sort_values(by='Accuracy', ascending=False)\n",
"result_df = result_df.set_index('Accuracy')\n",
"result_df"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "0336f802",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"results= pd.DataFrame({'Model': ['S V M', 'Logistic R','Naive Bayes', \n",
" 'Decision Tree'], 'Score': [acc_linear_svc, acc_log, \n",
" acc_gaussian, acc_decision]})\n",
"\n",
"ax = results.plot.bar(x='Model', y='Score', rot=90)"
]
},
{
"cell_type": "markdown",
"id": "c1656c2c",
"metadata": {},
"source": [
"# Save Final Model (Decision tree model)\n",
"### Decision Tree model is best model for predict best line for passenger"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "9df04086",
"metadata": {},
"outputs": [],
"source": [
"#Save the Decision Tree strained modelusing pickle\n",
"import pickle\n",
"with open('ab_classifier_Decision_Tree', 'wb') as picklefile:\n",
" pickle.dump(decision_tree,picklefile)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "e032de3d",
"metadata": {},
"outputs": [],
"source": [
"with open('ab_classifier_Decision_Tree', 'rb') as training_model:\n",
" model6 = pickle.load(training_model)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "baae73c3",
"metadata": {},
"outputs": [],
"source": [
"def start_questionnaire():\n",
" my_predictors = []\n",
" parameters=['Age', 'Count','Country','GenderNo']\n",
" \n",
" print('Input Passenger Information:')\n",
" age = input(\"Passenger age: >>> \") \n",
" my_predictors.append(age)\n",
" count = input(\"Passenger Count: >>> \") \n",
" my_predictors.append(count)\n",
" country = input(\"Passenger Country: >>> \") \n",
" my_predictors.append(country)\n",
" gender = input(\"Passenger Gender: >>> \")\n",
" my_predictors.append(gender)\n",
" \n",
" my_data = dict(zip(parameters, my_predictors))\n",
" my_df = pd.DataFrame(my_data, index=[0])\n",
" scaler = MinMaxScaler(feature_range=(1,6))\n",
" \n",
" # assign scaler to column:\n",
" my_df_scaled = pd.DataFrame(scaler.fit_transform(my_df), columns=my_df.columns)\n",
" my_y_pred = model6.predict(my_df)\n",
" print('\\n')\n",
" print('Result:')\n",
" print(my_y_pred)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e69255e3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Input Passenger Information:\n"
]
}
],
"source": [
"start_questionnaire()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "012dc3a4",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "c64f4369",
"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": "3.8.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
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