#coding=utf8

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from xgboost import XGBClassifier
titanic = pd.read_csv('./DataSets/Titanic/train.csv')
X = titanic[['Pclass', 'Age', 'Sex']]
y = titanic['Survived']
X['Age'].fillna(X['Age'].mean(), inplace=True)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=33)
vec = DictVectorizer(separator=False)
X_train = vec.fit_transform(X_train.to_dict(orient='record'))
#print X_train.to_dict(orient='record')
X_test = vec.transform(X_test.to_dict(orient='record'))
xgbc = XGBClassifier()
xgbc.fit(X_train, y_train)
print 'The accuracy of eXtreme Gradient Boosting Classifier on testing set:', xgbc.score(X_test, y_test)

#coding=utf8

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from xgboost import XGBClassifier
from sklearn.model_selection import GridSearchCV
titanic = pd.read_csv('./DataSets/Titanic/train.csv')
X = titanic[['Pclass', 'Age', 'Sex']]
y = titanic['Survived']

X['Age'].fillna(X['Age'].mean(), inplace=True)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=33)
vec = DictVectorizer(separator=False)
X_train = vec.fit_transform(X_train.to_dict(orient='record'))
#print X_train.to_dict(orient='record')
X_test = vec.transform(X_test.to_dict(orient='record'))
xgbc = XGBClassifier()

params = {'max_depth':range(2, 7), 'n_estimators':range(100, 1100, 200), 'learning_rate':[0.05, 0.1, 0.25, 0.5, 1.0]}
gs = GridSearchCV(xgbc, params, n_jobs=-1, cv=5, verbose=1)
gs.fit(X_train, y_train)
#print 'The accuracy of eXtreme Gradient Boosting Classifier on testing set:', gs.score(X_test, y_test)

print gs.best_score_
print gs.best_params_