Skip to content

Commit

Permalink
add demo notebook
Browse files Browse the repository at this point in the history
  • Loading branch information
@thierrymoudiki
thierrymoudiki committed Aug 1, 2024
1 parent e14b5eb commit c1251f9
Showing 1 changed file with 249 additions and 0 deletions.
249 changes: 249 additions & 0 deletions unifiedbooster/demo/thierrymoudiki_2024_08_01_unifiedbooster.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,249 @@
{
"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": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "R9R4-y5Obsqm",
"outputId": "dc0f73f7-576a-4505-be6e-e19548f92ddd"
},
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting git+https://github.com/thierrymoudiki/unifiedbooster.git\n",
" Cloning https://github.com/thierrymoudiki/unifiedbooster.git to /tmp/pip-req-build-bfnp1r_b\n",
" Running command git clone --filter=blob:none --quiet https://github.com/thierrymoudiki/unifiedbooster.git /tmp/pip-req-build-bfnp1r_b\n",
" Resolved https://github.com/thierrymoudiki/unifiedbooster.git to commit e45d844a6745f244a88f5979c70924ed1afe3860\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: Cython in /usr/local/lib/python3.10/dist-packages (from unifiedbooster==0.1.2) (3.0.10)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from unifiedbooster==0.1.2) (1.3.2)\n",
"Requirement already satisfied: xgboost in /usr/local/lib/python3.10/dist-packages (from unifiedbooster==0.1.2) (2.1.0)\n",
"Requirement already satisfied: lightgbm in /usr/local/lib/python3.10/dist-packages (from unifiedbooster==0.1.2) (4.4.0)\n",
"Collecting catboost (from unifiedbooster==0.1.2)\n",
" Downloading catboost-1.2.5-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.2 kB)\n",
"Requirement already satisfied: graphviz in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (0.20.3)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (3.7.1)\n",
"Requirement already satisfied: numpy>=1.16.0 in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (1.26.4)\n",
"Requirement already satisfied: pandas>=0.24 in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (2.1.4)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (1.13.1)\n",
"Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (5.15.0)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from catboost->unifiedbooster==0.1.2) (1.16.0)\n",
"Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->unifiedbooster==0.1.2) (1.4.2)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->unifiedbooster==0.1.2) (3.5.0)\n",
"Collecting nvidia-nccl-cu12 (from xgboost->unifiedbooster==0.1.2)\n",
" Downloading nvidia_nccl_cu12-2.22.3-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost->unifiedbooster==0.1.2) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost->unifiedbooster==0.1.2) (2024.1)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost->unifiedbooster==0.1.2) (2024.1)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (1.2.1)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (4.53.1)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (1.4.5)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (24.1)\n",
"Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (9.4.0)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost->unifiedbooster==0.1.2) (3.1.2)\n",
"Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly->catboost->unifiedbooster==0.1.2) (9.0.0)\n",
"Downloading catboost-1.2.5-cp310-cp310-manylinux2014_x86_64.whl (98.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.2/98.2 MB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_nccl_cu12-2.22.3-py3-none-manylinux2014_x86_64.whl (190.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.9/190.9 MB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hBuilding wheels for collected packages: unifiedbooster\n",
" Building wheel for unifiedbooster (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for unifiedbooster: filename=unifiedbooster-0.1.2-py3-none-any.whl size=3503 sha256=455d29c6105ffb4aa1251432e78831b2603e9db6bafe6d9e39d97f4526bb9fa9\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-2a9_czka/wheels/ac/dd/dd/e6ca79dfbfe87388d253e5b727d1169c5b2f060bbb3620cd5f\n",
"Successfully built unifiedbooster\n",
"Installing collected packages: nvidia-nccl-cu12, catboost, unifiedbooster\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"torch 2.3.1+cu121 requires nvidia-cublas-cu12==12.1.3.1; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cuda-cupti-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cuda-runtime-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cudnn-cu12==8.9.2.26; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cufft-cu12==11.0.2.54; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-curand-cu12==10.3.2.106; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cusolver-cu12==11.4.5.107; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-cusparse-cu12==12.1.0.106; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-nvtx-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\", which is not installed.\n",
"torch 2.3.1+cu121 requires nvidia-nccl-cu12==2.20.5; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-nccl-cu12 2.22.3 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0mSuccessfully installed catboost-1.2.5 nvidia-nccl-cu12-2.22.3 unifiedbooster-0.1.2\n"
]
}
]
},
{
"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",
"\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",
"\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",
"\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",
" print(f\"Classification Accuracy xgboost: {accuracy1:.2f}\")\n",
" print(f\"Classification Accuracy catboost: {accuracy2:.2f}\")\n",
" print(f\"Classification Accuracy lightgbm: {accuracy3:.2f}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GlNUpp9nb_cT",
"outputId": "65d60559-4f75-4fa6-8a44-f76a277a804d"
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/dask/dataframe/__init__.py:42: FutureWarning: \n",
"Dask dataframe query planning is disabled because dask-expr is not installed.\n",
"\n",
"You can install it with `pip install dask[dataframe]` or `conda install dask`.\n",
"This will raise in a future version.\n",
"\n",
" warnings.warn(msg, FutureWarning)\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Classification Accuracy xgboost: 1.00\n",
"Classification Accuracy catboost: 1.00\n",
"Classification Accuracy lightgbm: 1.00\n",
"Classification Accuracy xgboost: 0.96\n",
"Classification Accuracy catboost: 0.97\n",
"Classification Accuracy lightgbm: 0.96\n",
"Classification Accuracy xgboost: 0.97\n",
"Classification Accuracy catboost: 1.00\n",
"Classification Accuracy lightgbm: 1.00\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import numpy as np"
],
"metadata": {
"id": "s1IzV5uJu9um"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"source": [
"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",
"\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",
"\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",
"\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",
" 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}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "u2vdE0mulk8q",
"outputId": "6220d000-4662-4040-e1a5-f723bd721e2f"
},
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Regression Root Mean Squared Error xgboost: 0.54\n",
"Regression Root Mean Squared Error catboost: 0.58\n",
"Regression Root Mean Squared Error lightgbm: 0.54\n",
"Regression Root Mean Squared Error xgboost: 54.40\n",
"Regression Root Mean Squared Error catboost: 51.72\n",
"Regression Root Mean Squared Error lightgbm: 53.19\n"
]
}
]
}
]
}

0 comments on commit c1251f9

Please sign in to comment.