ticket.py

import os
import pandas as pd
import numpy as np
from pandas import DataFrame

project_path = os.path.dirname(os.path.abspath(__file__))
data_path = os.path.join(project_path, 'data/')

file_row_capacity = os.path.join(data_path, 'row_capacity.csv')
file_tickets_sold = os.path.join(data_path, 'tickets_sold.csv')

row_capacity = pd.read_csv(file_row_capacity)
tickets_sold = pd.read_csv(file_tickets_sold)

ticket_dict = {}
for index, row in tickets_sold.iterrows():
    movie_week = row['calendarweek'] + ":" + row['movie']
    if not movie_week in ticket_dict:
        ticket_dict[movie_week] = {}

    ticket_dict[movie_week].setdefault(row['auditorium_row'], 0)
    ticket_dict[movie_week][row['auditorium_row']] += 1

columns = ['calendarweek', 'movie', 'auditorium_row']
df = DataFrame(columns=columns)
counter = 0
for key, values in ticket_dict.items():
    movie, week = key.split(':')
    df.loc[counter] = [movie, week, values]
    counter += 1
print(df)

row_dict = {}
for index, row in row_capacity.iterrows():
    row_dict[row['auditorium_row']] = row['max_seats_per_row']

# print(row_dict)
for keyrow, valuesrow in row_dict.items():
    for key, values in ticket_dict.items():
        audi_row = values.get(keyrow, -1)
        ticket_dict[key][keyrow] = ( audi_row / valuesrow )

# print(ticket_dict)
columns = ['calendarweek', 'movie', 'auditorium_row']
df1 = DataFrame(columns=columns)
counter = 0
for key, values in ticket_dict.items():
    movie, week = key.split(':')
    df1.loc[counter] = [movie, week, values]
    counter += 1
print(df1)

# print(df1.groupby('calendarweek').aggregate())