def model_train(self):
env = Environment()
data = self.stat()
t_start = timer()
y, X = self.model_prepare_data(data)
seed = 241
scoring = 'accuracy'
n_splits = 4
frac_test_size = 0.25
#Cross-validation
kf = KFold(n_splits=n_splits, shuffle=True, random_state=seed)
#clf = DecisionTreeClassifier(criterion='gini', random_state=seed)
#clf = GradientBoostingClassifier(n_estimators=50)
model = xgb.XGBClassifier(n_estimators=400,
max_depth=24,
colsample=1,
subsample=1,
seed=seed)
cv_scores = cross_val_score(model, X, y, cv=kf)
#eval
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=frac_test_size, random_state=seed)
eval_set = [(X_train, y_train), (X_test, y_test)]
#print(eval_set)
f_eval = 'merror'
# f_eval = 'mlogloss'
model.fit(X_train,
y_train,
eval_metric=f_eval,
eval_set=eval_set,
verbose=False,
early_stopping_rounds=10)
ev_scores = model.evals_result()
cv_mean = np.array(cv_scores.mean())
#ev_mean = np.array(ev_scores['validation_0']['mlogloss']).mean()
ev_mean = np.array(ev_scores['validation_0'][f_eval]).mean()
#Посмотрим важность признаков в модели
#print(model.feature_importances_)
xgb.plot_importance(model)
#plt.bar(range(len(model.feature_importances_)), model.feature_importances_)
plt.show()
#Обучаем модель на всех данных
model.fit(X, y, verbose=False)
#Сохраняем модель на диск
pickle.dump(model, open(env.filename_model_texts(), 'wb'))
#print('CV', cv_scores, 'EV', ev_scores)
print('Cross-validation: mean', cv_mean, 'eval_set mean', ev_mean)
return model
def model_predict(self, df, b_retrain=False):
env = Environment()
y, X = self.model_prepare_data(df, mode='test')
if b_retrain:
model = self.model_train(
) #Если хотим для кажжого теста вновь тренировать модель
else:
#Загружаем ранее тренированную модель с диска
model = pickle.load(open(env.filename_model_texts(), 'rb'))
#Предсказываем
y = model.predict(X)
return y