Skip to content

solved #447

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

solved #447

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
166 changes: 149 additions & 17 deletions lab-hyper-tuning.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -47,7 +47,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 8,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -200,7 +200,7 @@
"4 True "
]
},
"execution_count": 2,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -225,7 +225,73 @@
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"spaceship_clean = spaceship.dropna()\n",
"col_a_borrar = ['PassengerId', 'Name','Cabin']\n",
"spaceship_clean = spaceship_clean.drop(columns=col_a_borrar)\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"spaceship_dumm = pd.get_dummies(spaceship_clean, drop_first=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"y = spaceship_dumm['Transported']\n",
"X = spaceship_dumm.drop(columns=['Transported'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tamaño X_train: (5284, 12)\n",
"Tamaño X_test: (1322, 12)\n"
]
}
],
"source": [
"print(\"Tamaño X_train:\", X_train.shape)\n",
"print(\"Tamaño X_test:\", X_test.shape)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"num_cols = ['Age', 'RoomService', 'FoodCourt', 'ShoppingMall', 'Spa', 'VRDeck']\n",
"\n",
"scaler = StandardScaler()\n",
"\n",
"X_train[num_cols] = scaler.fit_transform(X_train[num_cols])\n",
"\n",
"X_test[num_cols] = scaler.transform(X_test[num_cols])"
]
},
{
Expand All @@ -237,11 +303,25 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.metrics import accuracy_score"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"rf_base = RandomForestClassifier(random_state=42)\n",
"rf_base.fit(X_train, y_train)\n",
"\n",
"y_pred_base = rf_base.predict(X_test)\n",
"\n"
]
},
{
Expand All @@ -253,11 +333,20 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 21,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy del Random Forest Base: 0.7958\n"
]
}
],
"source": [
"#your code here"
"accuracy_base = accuracy_score(y_test, y_pred_base)\n",
"print(f\"Accuracy del Random Forest Base: {accuracy_base:.4f}\")"
]
},
{
Expand All @@ -283,11 +372,11 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"#your code here"
"from sklearn.model_selection import GridSearchCV"
]
},
{
Expand All @@ -302,7 +391,14 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"source": [
"param_grid = {\n",
" 'n_estimators': [50, 100, 200], \n",
" 'max_depth': [5, 10, 20]\n",
"}\n",
"grid_search = GridSearchCV(estimator=rf_base, param_grid=param_grid, cv=5, n_jobs=-1, verbose=2)\n",
"\n"
]
},
{
"cell_type": "markdown",
Expand All @@ -313,15 +409,51 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": []
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Fitting 5 folds for each of 9 candidates, totalling 45 fits\n",
"Los mejores hiperparámetros encontrados fueron: {'max_depth': 10, 'n_estimators': 200}\n"
]
}
],
"source": [
"grid_search.fit(X_train, y_train)\n",
"\n",
"\n",
"mejor_modelo = grid_search.best_estimator_\n",
"\n",
"print(f\"Los mejores hiperparámetros encontrados fueron: {grid_search.best_params_}\")"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy del Random Forest con Grid: 0.8048\n"
]
}
],
"source": [
"y_pred_tuneado = mejor_modelo.predict(X_test)\n",
"\n",
"accuracy_tuneado = accuracy_score(y_test, y_pred_tuneado)\n",
"print(f\"Accuracy del Random Forest con Grid: {accuracy_tuneado:.4f}\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "base",
"language": "python",
"name": "python3"
},
Expand All @@ -335,7 +467,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.13.5"
}
},
"nbformat": 4,
Expand Down