'''
Collection of examples for using sklearn interface
==================================================

Created on 1 Apr 2015

@author: Jamie Hall
'''
import pickle
import xgboost as xgb

import numpy as np
from sklearn.model_selection import KFold, train_test_split, GridSearchCV
from sklearn.metrics import confusion_matrix, mean_squared_error
from sklearn.datasets import load_iris, load_digits, fetch_california_housing

rng = np.random.RandomState(31337)

print("Zeros and Ones from the Digits dataset: binary classification")
digits = load_digits(n_class=2)
y = digits['target']
X = digits['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
    xgb_model = xgb.XGBClassifier(n_jobs=1).fit(X[train_index], y[train_index])
    predictions = xgb_model.predict(X[test_index])
    actuals = y[test_index]
    print(confusion_matrix(actuals, predictions))

print("Iris: multiclass classification")
iris = load_iris()
y = iris['target']
X = iris['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
    xgb_model = xgb.XGBClassifier(n_jobs=1).fit(X[train_index], y[train_index])
    predictions = xgb_model.predict(X[test_index])
    actuals = y[test_index]
    print(confusion_matrix(actuals, predictions))

print("California Housing: regression")
X, y = fetch_california_housing(return_X_y=True)
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
    xgb_model = xgb.XGBRegressor(n_jobs=1).fit(X[train_index], y[train_index])
    predictions = xgb_model.predict(X[test_index])
    actuals = y[test_index]
    print(mean_squared_error(actuals, predictions))

print("Parameter optimization")
xgb_model = xgb.XGBRegressor(n_jobs=1)
clf = GridSearchCV(xgb_model,
                   {'max_depth': [2, 4, 6],
                    'n_estimators': [50, 100, 200]}, verbose=1, n_jobs=1)
clf.fit(X, y)
print(clf.best_score_)
print(clf.best_params_)

# The sklearn API models are picklable
print("Pickling sklearn API models")
# must open in binary format to pickle
pickle.dump(clf, open("best_calif.pkl", "wb"))
clf2 = pickle.load(open("best_calif.pkl", "rb"))
print(np.allclose(clf.predict(X), clf2.predict(X)))

# Early-stopping

X = digits['data']
y = digits['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = xgb.XGBClassifier(n_jobs=1)
clf.fit(X_train, y_train, early_stopping_rounds=10, eval_metric="auc",
        eval_set=[(X_test, y_test)])