import pandas as pd
import datetime as dt
import numpy as np

orders = pd.read_csv('/datasets/data_for_tasks_3.csv', sep=',')
orders['date'] = orders['date'].map(lambda x: dt.datetime.strptime(x, '%d/%m/%Y'))

visitors = pd.read_csv('/datasets/data_for_tasks_3_visitors.csv', sep=',')
visitors['date'] = visitors['date'].map(lambda x: dt.datetime.strptime(x, '%d/%m/%Y'))

print(orders.head(5))
print(visitors.head(5))

datesGroups = orders[['date','group']].drop_duplicates()

ordersAggregated = datesGroups.apply(
    lambda x: orders[np.logical_and(orders['date'] <= x['date'], orders['group'] == x['group'])].agg({
'date' : 'max',
'group' : 'max',
'orderId' : pd.Series.nunique,
'userId' : pd.Series.nunique,
'revenue' : 'sum'}), axis=1).sort_values(by=['date','group'])

visitorsAggregated = datesGroups.apply(
lambda x: visitors[np.logical_and(visitors['date'] <= x['date'], visitors['group'] == x['group'])].agg({
'date' : 'max',
'group' : 'max',
'visitors' : 'sum'}), axis=1).sort_values(by=['date','group'])

cummulativeData = ordersAggregated.merge(visitorsAggregated, left_on=['date', 'group'], right_on=['date', 'group'])
cummulativeData.columns = ['date', 'group', 'orders', 'buyers', 'revenue', 'visitors']

print(cummulativeData.head(5))