# coding: utf-8
# pylint: disable = invalid-name, C0111
import json
import lightgbm as lgb
import pandas as pd
from sklearn.metrics import mean_squared_error
import numpy as np 

# load or create your dataset
print('Load data...')
df_train = pd.read_csv('cardata.csv', header=None, sep=',')
df_test = pd.read_csv('testcardata.csv', header=None, sep=',')

y_train = df_train[2].values
print(y_train)

y_test = df_test[2].values
X_train = df_train.drop(2, axis=1).values
X_test = df_test.drop(2, axis=1).values

# create dataset for lightgbm
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)

# specify your configurations as a dict
params = {
    'task': 'train',
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'metric': {'l2'},
    'num_leaves': 31,
    'learning_rate': 0.05,
    #'feature_fraction': 0.9,
    #'bagging_fraction': 0.8,
    'bagging_freq': 5, 'min_data' : 1,
    'verbose': 0 
}

print('Start training...')
# train
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=20,
                valid_sets=lgb_eval,
                early_stopping_rounds=5)

print('Save model...')
# save model to file
gbm.save_model('model.txt')

print('Start predicting...')
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)

# eval
print(y_pred)