Using XGBoost in Python

 Code 1

(.env) [boris@fedora34server NUMPY]$ cat  GradientBoosting.py

import xgboost as xgb

from sklearn.metrics import mean_squared_error

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split

from sklearn.datasets import load_boston

import warnings

warnings.filterwarnings("ignore")

boston = load_boston()

data = pd.DataFrame(boston.data)

data.columns = boston.feature_names

X, y = data.iloc[:,:-1],data.iloc[:,-1]

data_dmatrix = xgb.DMatrix(data=X,label=y)

# XGBoost's hyperparameters

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)

xg_reg = xgb.XGBRegressor(objective ='reg:squarederror', colsample_bytree = 0.3, learning_rate = 0.1, max_depth = 5, alpha = 10, n_estimators = 10)

xg_reg.fit(X_train,y_train)

preds = xg_reg.predict(X_test)

rmse = np.sqrt(mean_squared_error(y_test, preds))

print("RMSE: %f" % (rmse))

# k-fold Cross Validation using XGBoost

params = {"objective":"reg:squarederror",'colsample_bytree': 0.3,'learning_rate': 0.1,'max_depth': 5, 'alpha': 10}

cv_results = xgb.cv(dtrain=data_dmatrix, params=params, nfold=3,num_boost_round=50,early_stopping_rounds=10,metrics="rmse", as_pandas=True, seed=123)

print(cv_results.head())

print((cv_results["test-rmse-mean"]).tail(1))

xg_reg = xgb.train(params=params, dtrain=data_dmatrix, num_boost_round=10)

xgb.plot_tree(xg_reg,num_trees=0)

plt.rcParams['figure.figsize'] = [50, 10]

plt.show(block=False)

xgb.plot_importance(xg_reg)

plt.rcParams['figure.figsize'] = [5, 5]

plt.show()

References

https://www.datacamp.com/community/tutorials/xgboost-in-python