xgboost

xgb.py

import xgboost as xgb
import numpy as np
from sklearn.datasets import make_regression, make_gaussian_quantiles
from sklearn.metrics import mean_squared_error, confusion_matrix
from sklearn.model_selection import train_test_split

#REGRESSION
#generate regression data
X, y, _ = make_regression(n_samples=10000,#number of samples
                                      n_features=10,#number of features
                                      n_informative=7,#number of useful features 
                                      noise=70,#bias and standard deviation of the guassian noise
                                      coef=True,#true coefficient used to generated the data
                                      random_state=0) #set for same data points for each run

#train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3)

#train & prediction
model = xgb.XGBRegressor(n_estimators=1000, max_depth=7, eta=0.1)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

#CLASSIFICATION
#generate classification data
X, y = make_gaussian_quantiles(cov=3.,
                                 n_samples=10000, n_features=2,
                                 n_classes=2, random_state=1)

#train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3)

#train & prediction
model = xgb.XGBClassifier(objective='binary:logistic')
model.fit(X_train, y_train)
y_pred = model.predict(X_test)