import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import ensemble
from sklearn import metrics
##############################################################################
# Load data
data = pd.read_csv('Data for train_0.003D.csv')
y = data.iloc[:,0]
X = data.iloc[:,1:]
offset = int(X.shape[0] * 0.9)
X_train, y_train = X[:offset], y[:offset]
X_test, y_test = X[offset:], y[offset:]
##############################################################################
# Fit regression model
params = {'n_estimators': 500, 'max_depth': 4, 'min_samples_split': 2,
'learning_rate': 0.01, 'loss': 'ls'}
clf = ensemble.GradientBoostingRegressor(**params)
clf.fit(X_train, y_train)
y_pre = clf.predict(X_test)
# Calculate metrics
mse = metrics.mean_squared_error(y_test, y_pre)
print("MSE: %.4f" % mse)
mae = metrics.mean_absolute_error(y_test, y_pre)
print("MAE: %.4f" % mae)
R2 = metrics.r2_score(y_test,y_pre)
print("R2: %.4f" % R2)
##############################################################################
# Plot training deviance
# compute test set deviance
test_score = np.zeros((params['n_estimators'],), dtype=np.float64)
for i, y_pred in enumerate(clf.staged_predict(X_test)):
test_score[i] = clf.loss_(y_test, y_pred)
plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plt.title('Deviance')
plt.plot(np.arange(params['n_estimators']) + 1, clf.train_score_, 'b-',
label='Training Set Deviance')
plt.plot(np.arange(params['n_estimators']) + 1, test_score, 'r-',
label='Test Set Deviance')
plt.legend(loc='upper right')
plt.xlabel('Boosting Iterations')
plt.ylabel('Deviance')
##############################################################################
# Plot feature importance
feature_importance = clf.feature_importances_
# make importances relative to max importance
feature_importance = 100.0 * (feature_importance / feature_importance.max())
sorted_idx = np.argsort(feature_importance)
pos = np.arange(sorted_idx.shape[0]) + .5
plt.subplot(1, 2, 2)
plt.barh(pos, feature_importance[sorted_idx], align='center')
plt.yticks(pos, X.columns[sorted_idx])
plt.xlabel('Relative Importance')
plt.title('Variable Importance')
plt.show()