intrastat/old/xls_pasrer.py

'''
Created on Feb 14, 2020
@author: deeejas
'''
import pandas as pd

dtypes={'NETWEIGHT': 'int64', 'NETVALUE': 'int64'}
df = pd.read_excel('intrastat.xlsx', dtype=dtypes) #, parse_dates=True, date_parser='DATA'
# df['VSCODE'].dtype = 
# print(df['DATA'])
# print(df['VSCODE'])
# print(df.groupby(['VSCODE',
#                   'ACode', 'Bcode', 'DeliveryTermsCode',
#                   'TransportCode', 'CountryOfOrigin',
#                   'EXP'])['NETVALUE', 'NETWEIGHT'].sum())
# print(df['VSCODE'])
grouped_df = df.groupby(['VSCODE', 'ACode', 'Bcode', 'DeliveryTermsCode',
                  'TransportCode', 'CountryOfOrigin',
                  'EXP', 'SUPPL'])[['NETVALUE', 'NETWEIGHT', 'Q', 'SUPPLVALUE']].sum()
print(grouped_df.index[0][7])
# print(grouped_df.index[1][0])
# print(grouped_df.columns)                  
# for i in range(1, len(grouped_df)+1):
#     print(grouped_df['VSCODE'])
# print(df_gr['NETVAELUE'].sum())
# for columns in df.groupby(['VSCODE', 'EXP']).sum():
#     print(columns.title())