Skip to content

Instantly share code, notes, and snippets.

@chetanambi

chetanambi/aikit-xgboost-demo.ipynb

Created April 6, 2022 17:21
Show Gist options
  • Save chetanambi/77830397ec6e5601be569ed4178c0020 to your computer and use it in GitHub Desktop.
Save chetanambi/77830397ec6e5601be569ed4178c0020 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
aikit-xgboost-demo.ipynb
{
"cells": [
{
"cell_type": "markdown",
"id": "1209e45b",
"metadata": {},
"source": [
"# Intel optimized XGBoost"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3a8d37af",
"metadata": {},
"outputs": [],
"source": [
"import xgboost as xgb\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.datasets import fetch_california_housing\n",
"from sklearn.model_selection import train_test_split\n",
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.metrics import accuracy_score"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "87814bfe",
"metadata": {},
"outputs": [],
"source": [
"# Dataset: https://www.kaggle.com/datasets/kamilpytlak/personal-key-indicators-of-heart-disease"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "dd03bdb3",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('heart_2020_cleaned.csv')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "56c3a636",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(319795, 18)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "083bc9b5",
"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>HeartDisease</th>\n",
" <th>BMI</th>\n",
" <th>Smoking</th>\n",
" <th>AlcoholDrinking</th>\n",
" <th>Stroke</th>\n",
" <th>PhysicalHealth</th>\n",
" <th>MentalHealth</th>\n",
" <th>DiffWalking</th>\n",
" <th>Sex</th>\n",
" <th>AgeCategory</th>\n",
" <th>Race</th>\n",
" <th>Diabetic</th>\n",
" <th>PhysicalActivity</th>\n",
" <th>GenHealth</th>\n",
" <th>SleepTime</th>\n",
" <th>Asthma</th>\n",
" <th>KidneyDisease</th>\n",
" <th>SkinCancer</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>No</td>\n",
" <td>16.60</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>3.0</td>\n",
" <td>30.0</td>\n",
" <td>No</td>\n",
" <td>Female</td>\n",
" <td>55-59</td>\n",
" <td>White</td>\n",
" <td>Yes</td>\n",
" <td>Yes</td>\n",
" <td>Very good</td>\n",
" <td>5.0</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>No</td>\n",
" <td>20.34</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>No</td>\n",
" <td>Female</td>\n",
" <td>80 or older</td>\n",
" <td>White</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>Very good</td>\n",
" <td>7.0</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>No</td>\n",
" <td>26.58</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>20.0</td>\n",
" <td>30.0</td>\n",
" <td>No</td>\n",
" <td>Male</td>\n",
" <td>65-69</td>\n",
" <td>White</td>\n",
" <td>Yes</td>\n",
" <td>Yes</td>\n",
" <td>Fair</td>\n",
" <td>8.0</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>No</td>\n",
" <td>24.21</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>No</td>\n",
" <td>Female</td>\n",
" <td>75-79</td>\n",
" <td>White</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>Good</td>\n",
" <td>6.0</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>No</td>\n",
" <td>23.71</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>28.0</td>\n",
" <td>0.0</td>\n",
" <td>Yes</td>\n",
" <td>Female</td>\n",
" <td>40-44</td>\n",
" <td>White</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>Very good</td>\n",
" <td>8.0</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" HeartDisease BMI Smoking AlcoholDrinking Stroke PhysicalHealth \\\n",
"0 No 16.60 Yes No No 3.0 \n",
"1 No 20.34 No No Yes 0.0 \n",
"2 No 26.58 Yes No No 20.0 \n",
"3 No 24.21 No No No 0.0 \n",
"4 No 23.71 No No No 28.0 \n",
"\n",
" MentalHealth DiffWalking Sex AgeCategory Race Diabetic \\\n",
"0 30.0 No Female 55-59 White Yes \n",
"1 0.0 No Female 80 or older White No \n",
"2 30.0 No Male 65-69 White Yes \n",
"3 0.0 No Female 75-79 White No \n",
"4 0.0 Yes Female 40-44 White No \n",
"\n",
" PhysicalActivity GenHealth SleepTime Asthma KidneyDisease SkinCancer \n",
"0 Yes Very good 5.0 Yes No Yes \n",
"1 Yes Very good 7.0 No No No \n",
"2 Yes Fair 8.0 Yes No No \n",
"3 No Good 6.0 No No Yes \n",
"4 Yes Very good 8.0 No No No "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d688fa27",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"No 292422\n",
"Yes 27373\n",
"Name: HeartDisease, dtype: int64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['HeartDisease'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c63e6055",
"metadata": {},
"outputs": [],
"source": [
"df['HeartDisease'] = df['HeartDisease'].map({'Yes': 1, 'No': 0})"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "9e1ceedc",
"metadata": {},
"outputs": [],
"source": [
"cat_cols = df.select_dtypes(include='object').columns.tolist()\n",
"df = pd.get_dummies(df, columns=cat_cols) "
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "165e6fad",
"metadata": {},
"outputs": [],
"source": [
"X, y = df.drop('HeartDisease', axis=1), df['HeartDisease']\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "5f3d26e4",
"metadata": {},
"outputs": [],
"source": [
"xg_reg = xgb.XGBRegressor(objective ='binary:hinge', \n",
" eval_metric='logloss',\n",
" colsample_bytree = 0.3, \n",
" learning_rate = 0.1,\n",
" max_depth = 5, \n",
" alpha = 10, \n",
" n_estimators = 10)\n",
"\n",
"xg_reg.fit(X_train, y_train)\n",
"preds = xg_reg.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "4ed09ae7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.9067780710202754\n"
]
}
],
"source": [
"print(\"Accuracy:\",accuracy_score(y_test, preds))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.7.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment