Skip to content

Commit

Permalink
add GradientBoosting 'estimators' Pt.4
Browse files Browse the repository at this point in the history
  • Loading branch information
@thierrymoudiki
thierrymoudiki committed Aug 3, 2024
1 parent 9909ce8 commit c3e1918
Show file tree
Hide file tree
Showing 6 changed files with 200 additions and 257 deletions.
10 changes: 5 additions & 5 deletions .github/workflows/python-publish.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,8 @@ jobs:
- name: Run examples
run: pip install .&&find examples -maxdepth 2 -name "*.py" -exec python3 {} \;

#- name: Publish to PyPI
# uses: pypa/gh-action-pypi-publish@release/v1
# with:
# password: ${{ secrets.PYPI_GLOBAL_UB }}
# repository-url: https://upload.pypi.org/legacy/
- name: Publish to PyPI
uses: pypa/gh-action-pypi-publish@release/v1
with:
password: ${{ secrets.PYPI_GLOBAL_UB }}
repository-url: https://upload.pypi.org/legacy/
190 changes: 190 additions & 0 deletions unifiedbooster/demo/thierrymoudiki_20240803_unifiedbooster.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,190 @@
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"source": [
"!pip install git+https://github.com/thierrymoudiki/unifiedbooster.git --upgrade"
],
"metadata": {
"id": "R9R4-y5Obsqm"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import unifiedbooster as ub\n",
"from sklearn.datasets import load_iris, load_breast_cancer, load_wine\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import accuracy_score\n",
"\n",
"datasets = [load_iris(), load_breast_cancer(), load_wine()]\n",
"\n",
"for dataset in datasets:\n",
"\n",
" X, y = dataset.data, dataset.target\n",
" X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
"\n",
" # Initialize the unified regressor (example with XGBoost)\n",
" regressor1 = ub.GBDTClassifier(model_type='xgboost')\n",
" regressor2 = ub.GBDTClassifier(model_type='catboost')\n",
" regressor3 = ub.GBDTClassifier(model_type='lightgbm')\n",
" regressor4 = ub.GBDTClassifier(model_type='gradientboosting')\n",
"\n",
" # Fit the model\n",
" regressor1.fit(X_train, y_train)\n",
" regressor2.fit(X_train, y_train)\n",
" regressor3.fit(X_train, y_train)\n",
" regressor4.fit(X_train, y_train)\n",
"\n",
" # Predict on the test set\n",
" y_pred1 = regressor1.predict(X_test)\n",
" y_pred2 = regressor2.predict(X_test)\n",
" y_pred3 = regressor3.predict(X_test)\n",
" y_pred4 = regressor4.predict(X_test)\n",
"\n",
" # Evaluate the model\n",
" accuracy1 = accuracy_score(y_test, y_pred1)\n",
" accuracy2 = accuracy_score(y_test, y_pred2)\n",
" accuracy3 = accuracy_score(y_test, y_pred3)\n",
" accuracy4 = accuracy_score(y_test, y_pred4)\n",
" print(\"-------------------------\")\n",
" print(f\"Classification Accuracy xgboost: {accuracy1:.2f}\")\n",
" print(f\"Classification Accuracy catboost: {accuracy2:.2f}\")\n",
" print(f\"Classification Accuracy lightgbm: {accuracy3:.2f}\")\n",
" print(f\"Classification Accuracy gradientboosting: {accuracy4:.2f}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GlNUpp9nb_cT",
"outputId": "f845bb72-3976-47e3-e6a0-61673822fc0c"
},
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"-------------------------\n",
"Classification Accuracy xgboost: 1.00\n",
"Classification Accuracy catboost: 1.00\n",
"Classification Accuracy lightgbm: 1.00\n",
"Classification Accuracy gradientboosting: 1.00\n",
"-------------------------\n",
"Classification Accuracy xgboost: 0.96\n",
"Classification Accuracy catboost: 0.97\n",
"Classification Accuracy lightgbm: 0.96\n",
"Classification Accuracy gradientboosting: 0.96\n",
"-------------------------\n",
"Classification Accuracy xgboost: 0.97\n",
"Classification Accuracy catboost: 1.00\n",
"Classification Accuracy lightgbm: 1.00\n",
"Classification Accuracy gradientboosting: 0.94\n"
]
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "Yjr1cXR2xVoj"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"import unifiedbooster as ub\n",
"from sklearn.datasets import fetch_california_housing, load_diabetes\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import mean_squared_error\n",
"\n",
"\n",
"datasets = [fetch_california_housing(), load_diabetes()]\n",
"\n",
"for dataset in datasets:\n",
"\n",
" # Load dataset\n",
" X, y = dataset.data, dataset.target\n",
"\n",
" # Split dataset into training and testing sets\n",
" X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
"\n",
" # Initialize the unified regressor (example with XGBoost)\n",
" regressor1 = ub.GBDTRegressor(model_type='xgboost')\n",
" regressor2 = ub.GBDTRegressor(model_type='catboost')\n",
" regressor3 = ub.GBDTRegressor(model_type='lightgbm')\n",
" regressor4 = ub.GBDTRegressor(model_type='gradientboosting')\n",
"\n",
" # Fit the model\n",
" regressor1.fit(X_train, y_train)\n",
" regressor2.fit(X_train, y_train)\n",
" regressor3.fit(X_train, y_train)\n",
" regressor4.fit(X_train, y_train)\n",
"\n",
" # Predict on the test set\n",
" y_pred1 = regressor1.predict(X_test)\n",
" y_pred2 = regressor2.predict(X_test)\n",
" y_pred3 = regressor3.predict(X_test)\n",
" y_pred4 = regressor4.predict(X_test)\n",
"\n",
" # Evaluate the model\n",
" mse1 = np.sqrt(mean_squared_error(y_test, y_pred1))\n",
" mse2 = np.sqrt(mean_squared_error(y_test, y_pred2))\n",
" mse3 = np.sqrt(mean_squared_error(y_test, y_pred3))\n",
" mse4 = np.sqrt(mean_squared_error(y_test, y_pred4))\n",
" print(\"-------------------------\")\n",
" print(f\"Regression Root Mean Squared Error xgboost: {mse1:.2f}\")\n",
" print(f\"Regression Root Mean Squared Error catboost: {mse2:.2f}\")\n",
" print(f\"Regression Root Mean Squared Error lightgbm: {mse3:.2f}\")\n",
" print(f\"Regression Root Mean Squared Error gradientboosting: {mse4:.2f}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "u2vdE0mulk8q",
"outputId": "0a29b466-769e-416f-bdbe-3cccd48bf5eb"
},
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"-------------------------\n",
"Regression Root Mean Squared Error xgboost: 0.54\n",
"Regression Root Mean Squared Error catboost: 0.57\n",
"Regression Root Mean Squared Error lightgbm: 0.54\n",
"Regression Root Mean Squared Error gradientboosting: 0.54\n",
"-------------------------\n",
"Regression Root Mean Squared Error xgboost: 54.40\n",
"Regression Root Mean Squared Error catboost: 52.12\n",
"Regression Root Mean Squared Error lightgbm: 53.19\n",
"Regression Root Mean Squared Error gradientboosting: 53.92\n"
]
}
]
}
]
}
Loading

0 comments on commit c3e1918

Please sign in to comment.