import numpy as np
import pandas as pd



##载入数据
ht = pd.read_csv('all/historical_transactions.csv', dtype={'city_id': np.int16, 'installments': np.int8, 'merchant_category_id': np.int16, 'month_lag': np.int8, 'purchase_amount': np.float32, 'category_2': np.float16, 'state_id': np.int8, 'subsector_id':np.int8})
nt = pd.read_csv('all/new_merchant_transactions.csv', dtype={'city_id': np.int16, 'installments': np.int8, 'merchant_category_id': np.int16, 'month_lag': np.int8, 'purchase_amount': np.float32, 'category_2': np.float16, 'state_id': np.int8, 'subsector_id':np.int8})
train = pd.read_csv('all/train.csv')
test = pd.read_csv('all/test.csv')

##数据清洗
def tidy_data(df):
    df['category_2'].fillna(0, inplace=True)
    df['category_3'].fillna('D', inplace=True)
    df['installments'].clip(-1, 12, inplace=True)# 有outliers，统一规定范围
    mode_mer = df['merchant_id'].mode().iloc[0]# 通过每张卡对应店铺的众数对merchant_id插补
    df.sort_values('card_id', inplace=True)
    group = df.groupby('card_id')['merchant_id'].apply(lambda x:x.fillna(x.mode().iloc[0] if len(x.mode())>0 else mode_mer))
    df.drop('merchant_id', axis=1, inplace=True)
    df['merchant_id'] = group.values
    return df

ht = tidy_data(ht)
nt = tidy_data(nt)


##特征工程
def new_data(df):  
    df['purchase_date'] = pd.to_datetime(df['purchase_date'], format='%Y-%m-%d %H:%M:%S')
    df['month'] = df['purchase_date'].dt.month
    df['month'] = df['month'].astype(np.int8)
    df['day'] = df['purchase_date'].dt.day
    df['day'] = df['day'].astype(np.int8)
    df['week'] = df['purchase_date'].dt.week
    df['week'] = df['week'].astype(np.int8)
    df['dayofweek'] = df['purchase_date'].dt.dayofweek
    df['dayofweek'] = df['dayofweek'].astype(np.int8)
    df['hour'] = df['purchase_date'].dt.hour
    df['hour'] = df['hour'].astype(np.int8)
    
    df['is_weekend'] = 0
    df.loc[df['dayofweek'].isin([5, 6]), ['is_weekend']] = 1
    df['is_weekend'] = df['is_weekend'].astype(np.int8)
    df['day_interval'] = 0
    df.loc[(0 < df['hour']) & (df['hour'] < 9), ['day_interval']] = 1
    df.loc[(8 < df['hour']) & (df['hour'] < 17), ['day_interval']] = 2
    df['day_interval'] = df['day_interval'].astype(np.int8)
    
    df['authorized_flag'] = df['authorized_flag'].map({'Y': 1, 'N':0})
    df['authorized_flag'] = df['authorized_flag'].astype(np.int8)
    df['category_1'] = df['category_1'].map({'Y': 1, 'N':0})
    df['category_1'] = df['category_1'].astype(np.int8)
    
    df['days_to_now'] = (datetime.datetime.today()-df['purchase_date']).dt.days
    df['days_to_now'] = df['days_to_now'].astype(np.int16)
    df['month_diff'] = df['days_to_now']//30
    df['month_diff'] += df['month_lag']
    df['month_diff'] = df['month_diff'].astype(np.int8)
    return df

def cal_amount(df, var, prefix=None):
    g = df.groupby(['card_id', var])['purchase_amount'].mean().unstack(var)
    g.fillna(0, inplace=True)
    columns_names = [] 
    if prefix:
        for i in g.columns.values:
            new_name = prefix + '_' + var + '_' + str(i) + '_' +'amt'
            columns_names.append(new_name)
    else:
        for i in g.columns.values:
            new_name = var + '_' + str(i) + '_' +'amt'
            columns_names.append(new_name)
    g.columns = columns_names
    g.reset_index(inplace=True)
    return g

ht = new_data(ht)
nt = new_data(nt)

dict_list = {
        'authorized_flag': ['count', 'sum', 'mean'],
        'category_1': ['sum', 'mean'],
        'month_lag': ['max', 'min', 'mean', 'nunique'],
        'month': ['mean', 'nunique'],
        'day': ['mean', 'nunique'],
        'week': ['mean', 'nunique'],
        'dayofweek': ['mean', 'nunique'],
        'hour': ['mean', 'nunique'],
        'is_weekend': ['sum', 'mean'],
        'month_diff': ['mean'],
        'days_to_now':['max', 'min'],
        'installments': ['max', 'min', 'sum', 'mean', 'std', 'nunique'],
        'purchase_amount': ['max', 'min', 'sum', 'mean', 'std'],
        'merchant_id': ['nunique'],
        'merchant_category_id': ['nunique'],
        'subsector_id': ['nunique'],
        'city_id': ['nunique'],
        'state_id': ['nunique']
        }
column_names = []
for key in dict_list.keys():
    for i in dict_list[key]:
        new_name = key + '_' + i
        column_names.append(new_name)
group = ht.groupby('card_id').agg(dict_list)
group.columns = column_names
group['average_days'] = (group['days_to_now_max']-group['days_to_now_min'])/group['authorized_flag_count']
group.reset_index(inplace=True) 

g = cal_amount(ht, 'category_2')
group = pd.merge(group, g, how='left', on='card_id')
g = cal_amount(ht, 'category_3')
group = pd.merge(group, g, how='left', on='card_id')
g = cal_amount(ht, 'is_weekend')
group = pd.merge(group, g, how='left', on='card_id')
g = cal_amount(ht, 'day_interval')
group = pd.merge(group, g, how='left', on='card_id')
g = cal_amount(ht, 'month_lag')
group = pd.merge(group, g, how='left', on='card_id')


dict_list = {
        'authorized_flag': ['count'],
        'category_1': ['sum', 'mean'],
        'month_lag': ['mean', 'nunique'],
        'month': ['max', 'mean', 'nunique'],
        'day': ['mean', 'nunique'],
        'week': ['mean', 'nunique'],
        'dayofweek': ['mean', 'nunique'],
        'hour': ['mean', 'nunique'],
        'is_weekend': ['sum', 'mean'],
        'month_diff': ['mean'],
        'days_to_now':['max', 'min'],
        'installments': ['max', 'min', 'sum', 'mean', 'std', 'nunique'],
        'purchase_amount': ['max', 'min', 'sum', 'mean', 'std'],
        'merchant_id': ['nunique'],
        'merchant_category_id': ['nunique'],
        'subsector_id': ['nunique'],
        'city_id': ['nunique'],
        'state_id': ['nunique']
        }
column_names = []
for key in dict_list.keys():
    for i in dict_list[key]:
        new_name = 'new' + '_' + key + '_' + i
        column_names.append(new_name)
group_new = nt.groupby('card_id').agg(dict_list)
group_new.columns = column_names
group_new['new_average_days'] = (group_new['new_days_to_now_max']-group_new['new_days_to_now_min'])/group_new['new_authorized_flag_count']
group_new.reset_index(inplace=True) 

g = cal_amount(nt, 'category_2', 'new')
group_new = pd.merge(group_new, g, how='left', on='card_id')
g = cal_amount(nt, 'category_3', 'new')
group_new = pd.merge(group_new, g, how='left', on='card_id')
g = cal_amount(nt, 'is_weekend', 'new')
group_new = pd.merge(group_new, g, how='left', on='card_id')
g = cal_amount(nt, 'day_interval', 'new')
group_new = pd.merge(group_new, g, how='left', on='card_id')
g = cal_amount(nt, 'month_lag', 'new')
group_new = pd.merge(group_new, g, how='left', on='card_id')


data = pd.merge(group, group_new, how='left', on='card_id')


##建立模型
train['target'].plot.hist(bins=50)
len(train[train['target'] < -30])
train['first_active_month'] = pd.to_datetime(train['first_active_month'])
train['year'] = train['first_active_month'].dt.year
train['month'] = train['first_active_month'].dt.month
train.drop('first_active_month', axis=1, inplace=True)
train = pd.merge(train, data, how='left', on='card_id')
train_X = train.drop(['target', 'card_id'], axis=1)
train_y = train['target']

test['first_active_month'].fillna('2017-03', inplace=True)
test['first_active_month'] = pd.to_datetime(test['first_active_month'])
test['year'] = test['first_active_month'].dt.year
test['month'] = test['first_active_month'].dt.month
test.drop('first_active_month', axis=1, inplace=True)
test = pd.merge(test, data, how='left', on='card_id')


xgbmodel = xgb.XGBRegressor(
        n_estimators=400,        
        learning_rate=0.01,      
        max_depth=6,            
        min_child_weight=8,     
        gamma=0,                
        subsample=1,            
        colsample_bytree=0.6,   
        reg_alpha=1,
        reg_lambda=10,
        n_jobs=7,
        random_state=123
        )
xgbmodel.fit(train_X, train_y, eval_metric='rmse')