import json
import datetime
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from collections import Counter, OrderedDict


all_files = ['season-0910.csv',
            'season-1011.csv',
            'season-1112.csv',
            'season-1213.csv',
            'season-1314.csv',
            'season-1415.csv',
            'season-1516.csv',
            'season-1617.csv',
            'season-1718.csv',
            'season-1819.csv']

year_list = [2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018]
df = pd.concat((pd.read_csv("archive\\"+f) for f in all_files))
df['Date'] = pd.to_datetime(df['Date'])

festive = []
normal = []
for year in year_list:
    festive.append(df[(df['Date'] >= pd.to_datetime(datetime.date(year, 12, 1))) & (df['Date'] <= pd.to_datetime(datetime.date(year+1, 1, 31)))])
    normal.append(df[(df['Date'] >= pd.to_datetime(datetime.date(year, 1, 31))) & (df['Date'] <= pd.to_datetime(datetime.date(year, 12, 1)))])
    # ignoring before Christmas 2009 b/c cba

festive_df = pd.concat(games for games in festive)
normal_df = pd.concat(games for games in normal)

def get_cs(df):

    clean_sheets = []
    for _, row in df.iterrows():
        if row['FTHG'] == 0:
            clean_sheets.append(row['AwayTeam'])
        if row['FTAG'] == 0:
            clean_sheets.append(row['HomeTeam'])
    return clean_sheets

festive_clean_sheets = get_cs(festive_df)
normal_clean_sheets = get_cs(normal_df)

print("Festive CS: {}%".format((len(festive_clean_sheets) / festive_df.shape[0]) * 100 ))
print("Normal CS: {}%".format((len(normal_clean_sheets) / normal_df.shape[0]) * 100 ))