# # Importing Packages
import os
import copy
import config
import dota2api
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.naive_bayes import MultinomialNB

%matplotlib inline

# # STEAM Client API Key to access the dota2 api
API_KEY = config.STEAM_API_KEY
api = dota2api.Initialise(API_KEY)

data = pd.read_csv('../data/draft/capmodedata.csv')

data.head(5)

data.columns

# # # Getting Heroes ID according to the name
heroes = api.get_heroes()

heroes_dict = {}
for i in range (len(heroes['heroes'])):
    hero_id = heroes['heroes'][i]['id']
    hero_name = heroes['heroes'][i]['localized_name']
    heroes_dict[hero_id]= hero_name

def change_hero_name(row):
    if row in heroes_dict:
        return heroes_dict[row]
    
columns = [
    '1hero_id', 
    '2hero_id', 
    '3hero_id', 
    '4hero_id', 
    '5hero_id', 
    '6hero_id', 
    '7hero_id', 
    '8hero_id', 
    '9hero_id',
    '10hero_id',
    '11hero_id', 
    '12hero_id', 
    '13hero_id', 
    '14hero_id', 
    '15hero_id', 
    '16hero_id', 
    '17hero_id', 
    '18hero_id', 
    '19hero_id',
    '20hero_id'
    ]
    
for i in range(len(columns)):
    data[columns[i]] = data[columns[i]].apply(change_hero_name)

data.head(5)

max_minutes = (np.max(data['duration'])) / 60
max_minutes

# # Plotting the graph of match played in minutes
data['minutes'] = data['duration'].apply(lambda x: x / 60)

groupby_minute = data.groupby(['minutes']).count()

groupby_minute.index

plt.hist(groupby_minute.index, histtype='bar', color='green')

base1 = data.loc[data['radiant_win'] == True]

len(base1)

base2 = data.loc[data['radiant_win'] == False]

len(base2)

# # Validation
total = len(base1)   len(base2)
print(total)
print(len(data))

# # Plotting the graph for both sides, it seems they are nearly equal (no bias on the sides here)
temp_a = ['radiant', 'dire']
temp_b = [len(base1), len(base2)]

plt.bar(temp_a, temp_b)

ban_1 = data['1hero_id']

ban1_count = data.groupby(data['1hero_id']).size()

plt.rcParams['figure.figsize'] = 22, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(ban1_count.index, ban1_count.values)

ban2_count = data.groupby(data['2hero_id']).size()

plt.rcParams['figure.figsize'] = 20, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(ban2_count.index, ban2_count.values)

ban3_count = data.groupby(data['3hero_id']).size()
plt.rcParams['figure.figsize'] = 20, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(ban3_count.index, ban3_count.values)

ban4_count = data.groupby(data['4hero_id']).size()
plt.rcParams['figure.figsize'] = 20, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(ban4_count.index, ban4_count.values)

heroes_list = []
for i, j in enumerate(heroes_dict):
    hero_name = heroes_dict[j]
    heroes_list.append(hero_name)

total_ban = 10
columns = ['1hero_id', '2hero_id', '3hero_id', '4hero_id', '9hero_id', '10hero_id', '11hero_id', '12hero_id', '17hero_id', '18hero_id']
all_data = pd.DataFrame(columns=columns, index=heroes_list)

# # Sorting alphabetically
all_data.sort_index()

for i in range(total_ban):
    all_data[columns[i]] = data.groupby(data[columns[i]]).size()

all_data

# # For this context, null value is the 0 value (i.e hero is not picked on it's respective phase)
all_data.fillna(value=0)

# # Grouping the heroes for plotting purpose
sum_all_data = all_data.sum(axis=1)

sum_all_data

# # Plotting all the ban values

plt.grid()
plt.plot(sum_all_data.index, sum_all_data.values)
plt.xticks(rotation='vertical')
plt.yticks(np.arange(0, 350000, 50000))

pick1_count = data.groupby(data['5hero_id']).size()
plt.rcParams['figure.figsize'] = 20, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(pick1_count.index, pick1_count.values)

pick2_count = data.groupby(data['6hero_id']).size()
plt.rcParams['figure.figsize'] = 20, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(pick2_count.index, pick2_count.values)

pick3_count = data.groupby(data['7hero_id']).size()
plt.rcParams['figure.figsize'] = 20, 6
plt.xticks(rotation='vertical')
plt.grid()
plt.plot(pick3_count.index, pick3_count.values)

total_pick = 10
columns = ['5hero_id', '6hero_id', '7hero_id', '8hero_id', '13hero_id', '14hero_id', '15hero_id', '16hero_id', '19hero_id', '20hero_id']
pick_all_data = pd.DataFrame(columns=columns, index=heroes_list)

pick_all_data

for i in range(total_pick):
    pick_all_data[columns[i]] = data.groupby(data[columns[i]]).size()

# # As in our context, we fill Null values with 0 (i.e, not picked = 0)
pick_all_data.fillna(0)

sum_all_pick_data = pick_all_data.sum(axis=1)

sum_all_pick_data.head(2)

plt.grid()
plt.plot(sum_all_pick_data.index, sum_all_pick_data.values)
plt.xticks(rotation='vertical')
plt.yticks(np.arange(0, 300000, 50000))

temp = data.loc[data['1team_id'] == 0]
win1 = temp.loc[temp['radiant_win'] == True]
temp2 = data.loc[data['1team_id'] == 1]
win2 = temp2.loc[temp2['radiant_win'] == False]

to_concat_dataframes = [win1, win2]
all_win_data_only_1 = pd.concat(to_concat_dataframes)

temp = data.loc[data['1team_id'] == 0]
win1 = temp.loc[temp['radiant_win'] == False]
temp2 = data.loc[data['1team_id'] == 1]
win2 = temp2.loc[temp2['radiant_win'] == True]

to_concat_dataframes = [win1, win2]
all_win_data_only_2 = pd.concat(to_concat_dataframes)

# # Validation
print(all_win_data_only_1.shape)
print(all_win_data_only_2.shape)
print(all_win_data_only_1.shape[0]   all_win_data_only_2.shape[0])
print(data.shape[0])

all_win_data_only_1.sort_index()

all_win_data_only_2.sort_index()