Skip to content

lab-hyper-tuning-lab-5 #558

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
michaelgrasshopper wants to merge 1 commit into
base: main
Choose a base branch
from
Open

lab-hyper-tuning-lab-5 #558

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
91 changes: 83 additions & 8 deletions lab-hyper-tuning.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,11 +221,29 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"#feature scaling\n",
"spaceship = spaceship.dropna().reset_index(drop=True)\n",
"spaceship['Cabin'] = spaceship['Cabin'].str.split('/').str[0]\n",
"spaceship = spaceship.drop(columns=['PassengerId', 'Name'])\n",
"spaceship = pd.get_dummies(spaceship, drop_first=True)\n",
"y = spaceship['Transported_True']\n",
"X = spaceship.drop(columns=['Transported_True'])\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n",
"print(f\"X_train shape: {X_train.shape}\")\n",
"print(f\"X_test shape: {X_test.shape}\")\n",
"\n",
"#feature selection\n",
"from sklearn.preprocessing import StandardScaler\n",
"scaler = StandardScaler()\n",
"X_train_scaled = scaler.fit_transform(X_train)\n",
"X_test_scaled = scaler.transform(X_test)\n",
"X_train_scaled = pd.DataFrame(X_train_scaled, columns=X_train.columns, index=X_train.index)\n",
"X_test_scaled = pd.DataFrame(X_test_scaled, columns=X_test.columns, index=X_test.index)\n",
"X_train_scaled.head()"
]
},
{
Expand All @@ -241,7 +259,26 @@
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"param_grid = {\n",
" 'n_estimators': [100, 200, 300],\n",
" 'learning_rate': [0.01, 0.05, 0.1, 0.2],\n",
" 'max_depth': [2, 3, 4],\n",
" 'min_samples_split': [2, 5, 10],\n",
" 'subsample': [0.8, 1.0]\n",
"}\n",
"\n",
"gb = GradientBoostingClassifier(random_state=42)\n",
"grid_search = GridSearchCV(\n",
" estimator=gb,\n",
" param_grid=param_grid,\n",
" cv=5,\n",
" scoring='accuracy',\n",
" n_jobs=-1,\n",
" verbose=1\n",
")\n",
"grid_search.fit(X_train, y_train)\n",
"print(f\"Best parameters: {grid_search.best_params_}\")\n",
"print(f\"Best cross-validation accuracy: {grid_search.best_score_:.4f}\")"
]
},
{
Expand All @@ -253,11 +290,18 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"best_gb = grid_search.best_estimator_\n",
"y_pred_best = best_gb.predict(X_test)\n",
"accuracy = accuracy_score(y_test, y_pred_best)\n",
"print(f\"Tuned Gradient Boosting Test Accuracy: {accuracy:.4f}\")\n",
"print(\"\\nClassification Report:\")\n",
"print(classification_report(y_test, y_pred_best))\n",
"print(\"Confusion Matrix:\")\n",
"print(confusion_matrix(y_test, y_pred_best))"
]
},
{
Expand Down Expand Up @@ -287,7 +331,15 @@
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"from sklearn.ensemble import GradientBoostingClassifier\n",
"from sklearn.model_selection import GridSearchCV\n",
"param_grid = {\n",
" 'n_estimators': [100, 200, 300],\n",
" 'learning_rate': [0.01, 0.05, 0.1, 0.2],\n",
" 'max_depth': [2, 3, 4],\n",
" 'min_samples_split': [2, 5, 10],\n",
" 'subsample': [0.8, 1.0]\n",
"}"
]
},
{
Expand All @@ -302,7 +354,20 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"source": [
"gb = GradientBoostingClassifier(random_state=42)\n",
"grid_search = GridSearchCV(\n",
" estimator=gb,\n",
" param_grid=param_grid,\n",
" cv=5,\n",
" scoring='accuracy',\n",
" n_jobs=-1,\n",
" verbose=2\n",
")\n",
"grid_search.fit(X_train, y_train)\n",
"print(f\"Best parameters: {grid_search.best_params_}\")\n",
"print(f\"Best cross-validation accuracy: {grid_search.best_score_:.4f}\")"
]
},
{
"cell_type": "markdown",
Expand All @@ -316,7 +381,17 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"source": [
"from sklearn.metrics import accuracy_store, classification_report, confusion_matrix\n",
"best_model = grid_search.best_estimator_\n",
"y_pred = best_model.predict(X_test)\n",
"accuracy = accuracy_score(y_test, y_pred)\n",
"print(f\"Test Accuracy: {accuracy:.4f}\")\n",
"print(\"\\nClassification Report:\")\n",
"print(classification_report(y_test, y_pred))\n",
"print(\"Confusion Matrix:\")\n",
"print(confusion_matrix(y_test, y_pred))"
]
}
],
"metadata": {
Expand Down