notebook.community

Edit and run

発電量データを30分単位に変更する





In [1]:



    


# データ加工・処理・分析モジュール
import numpy as np
import pandas as pd



    











In [2]:



    


# train_kwhをエクセル等で開くとdatetimeが指数表示に直される可能性がある
# その場合うまくいかないので201201010120の形になってることを確認する必要あり
output_data = pd.read_csv('train_kwh.tsv', delimiter = '\t')



    











In [3]:



    


def set_time(dataframe, col_name):
    '''
    to_datetimeを使うための前処理
    '''
    dataframe[col_name] = dataframe[col_name].map(lambda x : transform_time(x))
    return dataframe



    











In [4]:



    


def transform_time(x):
    '''
    set_time内で使う関数
    to_datetimeで24時をサポートしないので00に変更する処理
    '''
    str_x = str(x)
    res = ''
    if str(x)[8:10] == '24':
        res = str_x[0:4] + '-' + str_x[4:6] + '-' + str_x[6:8] + ' 00:'+str_x[10:12] 
    else:
        res = str_x[0:4] + '-' + str_x[4:6] + '-' + str_x[6:8] + ' '+ str_x[8:10] +':'+str_x[10:12]
    return res



    











In [5]:



    


# datetimeの行をpd.Timestampのインスタンスに変更
output_data = set_time(output_data, 'datetime')
output_data['datetime'] = output_data['datetime'].map(lambda x : pd.to_datetime(x))

# 30分ごとに集計
output_data.set_index('datetime').groupby(pd.TimeGrouper(freq='1800s', closed='left')).sum()



    


















    
Out[5]:











  
    

      
      SOLA01
      SOLA02
      SOLA03
    

    

      datetime
      
      
      
    

  
  
    

      2012-01-01 00:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 00:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 01:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 01:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 02:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 02:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 03:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 03:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 04:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 04:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 05:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 05:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 06:00:00
      0
      0.0
      NaN
    

    

      2012-01-01 06:30:00
      0
      0.0
      NaN
    

    

      2012-01-01 07:00:00
      15
      0.0
      NaN
    

    

      2012-01-01 07:30:00
      180
      340.0
      NaN
    

    

      2012-01-01 08:00:00
      527
      840.0
      NaN
    

    

      2012-01-01 08:30:00
      670
      1110.0
      NaN
    

    

      2012-01-01 09:00:00
      904
      1680.0
      NaN
    

    

      2012-01-01 09:30:00
      911
      1730.0
      NaN
    

    

      2012-01-01 10:00:00
      1705
      2920.0
      NaN
    

    

      2012-01-01 10:30:00
      1754
      3090.0
      NaN
    

    

      2012-01-01 11:00:00
      1696
      2900.0
      NaN
    

    

      2012-01-01 11:30:00
      1908
      3300.0
      NaN
    

    

      2012-01-01 12:00:00
      1756
      3160.0
      NaN
    

    

      2012-01-01 12:30:00
      1665
      2770.0
      NaN
    

    

      2012-01-01 13:00:00
      1805
      2980.0
      NaN
    

    

      2012-01-01 13:30:00
      1381
      2080.0
      NaN
    

    

      2012-01-01 14:00:00
      1143
      1910.0
      NaN
    

    

      2012-01-01 14:30:00
      944
      1680.0
      NaN
    

    

      ...
      ...
      ...
      ...
    

    

      2015-12-31 09:00:00
      464
      670.0
      470.0
    

    

      2015-12-31 09:30:00
      644
      720.0
      2160.0
    

    

      2015-12-31 10:00:00
      1589
      1500.0
      2450.0
    

    

      2015-12-31 10:30:00
      1612
      2020.0
      2630.0
    

    

      2015-12-31 11:00:00
      1776
      2650.0
      2780.0
    

    

      2015-12-31 11:30:00
      1510
      1310.0
      2870.0
    

    

      2015-12-31 12:00:00
      1923
      2620.0
      2870.0
    

    

      2015-12-31 12:30:00
      2244
      2990.0
      2780.0
    

    

      2015-12-31 13:00:00
      2041
      2620.0
      2610.0
    

    

      2015-12-31 13:30:00
      1737
      1300.0
      2380.0
    

    

      2015-12-31 14:00:00
      1574
      1500.0
      2060.0
    

    

      2015-12-31 14:30:00
      746
      1040.0
      1640.0
    

    

      2015-12-31 15:00:00
      353
      720.0
      1140.0
    

    

      2015-12-31 15:30:00
      134
      440.0
      630.0
    

    

      2015-12-31 16:00:00
      57
      130.0
      180.0
    

    

      2015-12-31 16:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 17:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 17:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 18:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 18:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 19:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 19:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 20:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 20:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 21:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 21:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 22:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 22:30:00
      0
      0.0
      0.0
    

    

      2015-12-31 23:00:00
      0
      0.0
      0.0
    

    

      2015-12-31 23:30:00
      0
      0.0
      0.0
    

  



70128 rows × 3 columns



















In [ ]:

Content source: gciteam6/xgboost

Similar notebooks:

notebook.community | gallery | about