diff --git a/Imputer/sort_csv.py b/Imputer/sort_csv.py new file mode 100644 index 0000000000000000000000000000000000000000..4972e69b6296c8605c439d85c20fc2664805a35d --- /dev/null +++ b/Imputer/sort_csv.py @@ -0,0 +1,38 @@ +# -*- coding: utf-8 -*- +""" +Created on Fri Feb 26 11:19:34 2021 + +@author: Christoph +""" + +import pandas as pd +import numpy as np + + +data = pd.read_csv('db_dump.csv',delimiter=';') +dumb=data.copy() +relevantData= pd.DataFrame.copy(data[['Streckenvorhersage.ZielortID','Streckenvorhersage.StartortID','Streckenvorhersage.Dauer']]) +helpSeries= pd.DataFrame(np.zeros(relevantData.shape[0])) +#relevantData['day']=helpSeries +#relevantData['month']=helpSeries +#relevantData['year']=helpSeries +relevantData['time']=helpSeries +relevantData['day_index']=helpSeries + +dates= data['Streckenvorhersage.Datum'] +for d in range(dates.shape[0]): + toTest = dates[d] + hours = toTest[11:13] + minutes = toTest[14:16] + seconds = int(toTest[17:19]) + int(hours)*60*60 + int(minutes)*60 + day = toTest[0:2] + month = toTest[3:5] + year = toTest[6:10] + day_index= int(day)+int(month)*31+int(year)*12 + #relevantData.at[d,'month']= month + #relevantData.at[d,'day']=day + #relevantData.at[d,'year']=year + relevantData.at[d,'time']=seconds + relevantData.at[d,'day_index']=day_index + +relevantData.to_csv('data.csv')