import json
from collections import Counter
import numpy as np
import pandas as pd
import altair as alt
import operator

import warnings
warnings.filterwarnings('ignore')

# loading the events data
events={}
nations = ['Italy','England','Germany','France','Spain','European_Championship','World_Cup']
for nation in nations:
    with open('events/events_%s.json' %nation) as json_data:
        events[nation] = json.load(json_data)
        
# loading the match data
matches={}
nations = ['Italy','England','Germany','France','Spain','European_Championship','World_Cup']
for nation in nations:
    with open('matches/matches_%s.json' %nation) as json_data:
        matches[nation] = json.load(json_data)

# loading the players data
players={}
with open('players.json') as json_data:
    players = json.load(json_data)

# loading the competitions data
competitions={}
with open('competitions.json') as json_data:
    competitions = json.load(json_data)

ev_all_nations = []
for nation in nations:
    for i in range(len(events[nation])):
        ev_all_nations.append(events[nation][i]['eventName'])
count = Counter(ev_all_nations)
total = len(ev_all_nations)

counter = {event: int((count / total) * 100) for event, count in count.items()}
sorted_counter = sorted(counter.items(), key=operator.itemgetter(1), reverse=False)


data = pd.DataFrame(sorted_counter, columns=['Event', 'Percentage'])

brush = alt.selection_interval(encodings=['y'])

max_value = data['Percentage'].max()
tick_values = list(range(0, int(max_value) + 10, 10))

bars = alt.Chart(data).mark_bar().encode(
    y=alt.Y('Event:N', title=None, sort='-x'),
    x=alt.X('Percentage:Q', title='events(%)', axis=alt.Axis(values=tick_values)),
    color=alt.condition(brush, alt.Color('Event:N', legend=None), alt.value('lightgray'))
).add_selection(
    brush
)

average_rule = alt.Chart(data).mark_rule(color='firebrick', strokeWidth=2).encode(
    x='mean(Percentage):Q'
).transform_filter(
    brush
)

average_text = alt.Chart(data).mark_text(
    dx=5, dy=-5, color='firebrick', align='left', fontWeight='bold'
).encode(
    x=alt.X('mean(Percentage):Q', aggregate='mean'),
    text=alt.Text('mean(Percentage):Q', aggregate='mean', format='.1f')
).transform_filter(
    brush
)

chart1 = alt.layer(bars, average_rule, average_text).properties(
    width=600,
    height=500,
    title='Events Distribution'
)

# Display the combined chart
chart1

match_ev_count = {}
for nation in nations:
    for ev in events[nation]:
        if ev['matchId'] not in match_ev_count:
            match_ev_count[ev['matchId']] = 1
        else:
            match_ev_count[ev['matchId']] += 1

data = pd.DataFrame({
    'Event Count': list(match_ev_count.values())
})

event_count_values = list(match_ev_count.values())
min_value = min(event_count_values)
max_value = max(event_count_values)


ticks = list(range((min_value // 200) * 200, (max_value // 200 + 1) * 200, 200))

click = alt.selection_single(encodings=['x'], nearest=True)

hist = alt.Chart(data).mark_bar().encode(
    alt.X('Event Count:Q', bin=alt.Bin(maxbins=20), title='events (n)', axis=alt.Axis(values=ticks)),
    alt.Y('count()', title='frequency (n)'),
    tooltip=[alt.Tooltip('mean(Event Count):Q', title='Mean', format='.2f')]
).properties(
    width=600,
    height=400
).add_selection(
    click
)

mean_rule = alt.Chart(data).transform_filter(
    click
).mark_rule(color='firebrick', size=3).encode(
    x='mean(Event Count):Q',
)

chart2 = alt.layer(hist, mean_rule).properties(
    title='Histogram of Event Counts with Click Interaction and Tooltip'
)

chart2

combined_chart1 = alt.hconcat(
    chart1,
    chart2,
    spacing=10
).resolve_scale(
    color='independent'
)
combined_chart1