# -*- coding: utf-8 -*-
"""
Created on Mon Mar 15 13:51:09 2021

@author: ganjar
"""

import pandas as pd
import glob
if __name__ == '__main__':    
    
    path = r'seoul hourly' # use your path
    all_files = glob.glob(path + "/*.csv")

    li = []

    for filename in all_files:
        print(filename)
        df = pd.read_csv(filename, sep = ',', encoding= 'ISO-8859-1')
        li.append(df)

    frame = pd.concat(li, axis=0, ignore_index=True)
    
    
    frame["date_time"]= pd.to_datetime(frame.iloc[:, 1])
    
    df_ori = frame.groupby(pd.Grouper(key='date_time',freq='H')).size().reset_index(name='count')
    df_ori = df_ori.sort_values(by='date_time') 
    
    df_ori['hour'] = df_ori['date_time'].dt.hour
    df_ori['day_week'] = df_ori['date_time'].dt.dayofweek
    df_ori['month'] = df_ori['date_time'].dt.month
    df_ori['week'] = df_ori['date_time'].dt.week
    #df_ori['year'] = df_ori['date_time'].dt.year

    df_ori.to_csv ('seoul hourly/2020_hourly.csv', index = False, header=True)
    
    '''
    pd.options.display.max_columns=None
    df = pd.read_csv('seoul hourly/공공자전거 대여이력 정보_2020.05.csv', sep = ',', encoding= 'ISO-8859-1')
    df["date_time"]= pd.to_datetime(df.대여일시)
    df_ori = df.groupby(pd.Grouper(key='date_time',freq='H')).size().reset_index(name='count')
    df_ori['hour'] = df_ori['date_time'].dt.hour
    df_ori['day_week'] = df_ori['date_time'].dt.dayofweek
    df_ori['month'] = df_ori['date_time'].dt.month
    df_ori['week'] = df_ori['date_time'].dt.week
    df_ori['year'] = df_ori['date_time'].dt.year

    #df_ori.to_csv ('seoul hourly/2020.04.csv', index = False, header=True)
    '''