Skip to content

2
2023-24-051 Resume_Ranker
Commit fde333ce authored by Sewwandi W.M.C's avatar Sewwandi W.M.C
Browse files
Options

Create gb_ml_model_param_grid.ipynb 

model parameter adjustment
parent 3f346e12
Hide whitespace changes
Inline Side-by-side
Showing with 300 additions and 0 deletions
Function 01/Function 01/Function1/March_Update/SkillPredict/gb_ml_model_param_grid.ipynb 0 → 100644
View file @ fde333ce
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Skills Prediction ML Model - GB Classifier with GridSearchCV"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split, GridSearchCV\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"from sklearn.naive_bayes import MultinomialNB\n",
"from sklearn.svm import SVC\n",
"from sklearn.ensemble import GradientBoostingClassifier\n",
"from sklearn.ensemble import RandomForestRegressor\n",
"from sklearn.pipeline import make_pipeline\n",
"from sklearn.metrics import accuracy_score, classification_report, mean_squared_error\n",
"\n",
"# Load the dataset\n",
"df = pd.read_csv('./Dataset/skills_list_dataset_32.csv', encoding='latin1')\n",
"\n",
"# Map labels to numbers\n",
"label_mapping = {label: idx + 1 for idx, label in enumerate(df['Label'].unique())}\n",
"df['Label'] = df['Label'].map(label_mapping)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"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>Keywords_List</th>\n",
" <th>Label</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>['React', 'ReactJS', 'Frontend', 'Web Developm...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>['React Developer', 'Web Design', 'Responsive ...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>['JavaScript Library', 'Frontend Engineering',...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>['Frontend Engineering', 'JavaScript Framework...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>['Stateful Components', 'Stateless Components'...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Keywords_List Label\n",
"0 ['React', 'ReactJS', 'Frontend', 'Web Developm... 1\n",
"1 ['React Developer', 'Web Design', 'Responsive ... 1\n",
"2 ['JavaScript Library', 'Frontend Engineering',... 1\n",
"3 ['Frontend Engineering', 'JavaScript Framework... 1\n",
"4 ['Stateful Components', 'Stateless Components'... 1"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Label Mapping:\n",
"React: 1\n",
"React Native: 2\n",
"Angular: 3\n",
"PHP: 4\n",
"Java: 5\n",
"HTML/HTML5: 6\n",
"CSS: 7\n",
"Python: 8\n",
"Node.js: 9\n",
"Full-Stack Development: 10\n",
"Mobile App Development (iOS): 11\n",
"Mobile App Development (Android): 12\n",
"JavaScript: 13\n",
"TypeScript: 14\n",
"DevOps: 15\n",
"QA/Testing: 16\n",
"UI: 17\n",
"UX: 18\n",
"UI/UX: 19\n",
"Cloud (AWS, Google, Azure): 20\n",
"Graphics Designing: 21\n",
"VFX Designing: 22\n",
"GitHub/Version Control: 23\n",
"Video Editing: 24\n",
"Project Management: 25\n",
"Problem Solving: 26\n",
"Team Collaboration: 27\n",
"3D Designing: 28\n",
"Leadership: 29\n",
"Animation Editing: 30\n",
"Time Management: 31\n",
"Digital Marketing: 32\n"
]
}
],
"source": [
"# Print the mapping of labels to encoded numbers\n",
"print(\"Label Mapping:\")\n",
"for label, encoded_number in label_mapping.items():\n",
" print(f\"{label}: {encoded_number}\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# Split the data into training and testing sets\n",
"X_train, X_test, y_train, y_test = train_test_split(df['Keywords_List'], df['Label'], test_size=0.2, random_state=42)\n",
"\n",
"# Models\n",
"param_grid = {\n",
" 'gradientboostingclassifier__n_estimators': [50, 100, 150, 200, 300],\n",
" 'gradientboostingclassifier__learning_rate': [0.01, 0.1, 0.2, 0.3],\n",
" 'gradientboostingclassifier__max_depth': [3, 5, 7, 9, 11, None],\n",
"}\n",
"\n",
"model = GridSearchCV(\n",
" make_pipeline(TfidfVectorizer(), GradientBoostingClassifier()),\n",
" param_grid=param_grid,\n",
" scoring='accuracy',\n",
" cv=5\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Best Hyperparameters: {'gradientboostingclassifier__learning_rate': 0.2, 'gradientboostingclassifier__max_depth': 3, 'gradientboostingclassifier__n_estimators': 200}\n",
"Optimized Accuracy: 0.6296296296296297\n",
"Classification Report:\n",
" precision recall f1-score support\n",
"\n",
" 1 0.17 0.50 0.25 4\n",
" 2 0.75 0.60 0.67 5\n",
" 3 1.00 0.86 0.92 7\n",
" 4 1.00 0.90 0.95 10\n",
" 5 1.00 0.67 0.80 3\n",
" 6 1.00 0.80 0.89 5\n",
" 7 0.00 0.00 0.00 5\n",
" 8 0.71 1.00 0.83 5\n",
" 9 1.00 1.00 1.00 3\n",
" 10 0.33 0.25 0.29 4\n",
" 11 0.67 0.40 0.50 5\n",
" 12 0.67 1.00 0.80 2\n",
" 13 0.00 0.00 0.00 3\n",
" 14 0.71 0.83 0.77 6\n",
" 15 0.50 0.33 0.40 6\n",
" 16 0.80 1.00 0.89 4\n",
" 17 0.43 0.60 0.50 5\n",
" 18 0.33 0.25 0.29 4\n",
" 19 1.00 0.50 0.67 2\n",
" 20 0.00 0.00 0.00 0\n",
" 21 0.50 1.00 0.67 3\n",
" 22 0.75 1.00 0.86 3\n",
" 23 1.00 0.57 0.73 7\n",
" 24 0.50 1.00 0.67 2\n",
" 25 0.67 0.50 0.57 4\n",
" 26 0.20 0.33 0.25 3\n",
" 27 0.50 0.50 0.50 4\n",
" 28 1.00 0.50 0.67 2\n",
" 29 0.50 0.50 0.50 2\n",
" 30 1.00 0.71 0.83 7\n",
" 31 0.25 0.25 0.25 4\n",
" 32 0.83 0.83 0.83 6\n",
"\n",
" accuracy 0.63 135\n",
" macro avg 0.62 0.60 0.59 135\n",
"weighted avg 0.67 0.63 0.63 135\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\niwar\\anaconda3\\envs\\resume-ranker\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1471: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"c:\\Users\\niwar\\anaconda3\\envs\\resume-ranker\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1471: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"c:\\Users\\niwar\\anaconda3\\envs\\resume-ranker\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1471: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"c:\\Users\\niwar\\anaconda3\\envs\\resume-ranker\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1471: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"c:\\Users\\niwar\\anaconda3\\envs\\resume-ranker\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1471: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"c:\\Users\\niwar\\anaconda3\\envs\\resume-ranker\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1471: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n"
]
}
],
"source": [
"# Train and evaluate the model\n",
"model.fit(X_train, y_train)\n",
"\n",
"# Get the best parameters and print the results\n",
"best_params = model.best_params_\n",
"print(f\"Best Hyperparameters: {best_params}\")\n",
"\n",
"predictions = model.predict(X_test)\n",
"\n",
"# Use accuracy and classification report\n",
"accuracy = accuracy_score(y_test, predictions)\n",
"classification_report_result = classification_report(y_test, predictions)\n",
"\n",
"print(\"Optimized Accuracy: \", accuracy)\n",
"print(\"Classification Report:\\n\", classification_report_result)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "resume-ranker",
"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": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
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