import numpy as np
import pandas as pd
from datetime import datetime
!pip install pycountry
!pip install folium

df = pd.read_csv('Forbes Richest Atheletes (Forbes Richest Athletes 1990-2020).csv')
df.head()

# Creating a copy of the original dataframe-df
df1 = df.copy()
df1.drop('S.NO',axis=1, inplace=True)
df1.info()

# Convert string to datetime64
df1['Year'] = df1['Year'].apply(pd.to_datetime, format='%Y')

# Set Date column as the index column
df1['year'] = pd.DatetimeIndex(df1['Year']).year
df1.set_index('year', inplace=True)
df1.drop('Year', axis=1, inplace=True)

# Converting the sport column to uppercase
df1['Sport'] = df1['Sport'].str.upper()
df1.head()

data_2020 = df1[df1.index == 2020]
data_2020.head()

trace = go.Bar(
    x = data_2020['earnings ($ million)'],
    y = data_2020['Name'],
    orientation='h',
    marker = dict(color='blue',
                  line=dict(color='black', width=1))
)

data = [trace]

layout = go.Layout(barmode = "group",title="World's Highest-Paid Athletes in 2020",width=800, height=500, 
                       xaxis= dict(title='No of times ranked higest'),
                       yaxis=dict(autorange="reversed"),
                       showlegend=False)
fig = go.Figure(data = data, layout = layout)
iplot(fig)

top_paid_each_year = df1[df1['Current Rank'] == 1].sort_values(by='year', ascending=False)
top_paid_each_year.head()

z = top_paid_each_year[['Name', 'Sport', 'Nationality', 'earnings ($ million)']]
z.style.background_gradient(cmap='Reds')

counts_top = top_paid_each_year['Name'].value_counts().to_frame()
trace = go.Bar(
    y = counts_top.index,
    x = counts_top['Name'],
    orientation='h',
    marker = dict(color='blue',
                  line=dict(color='black', width=1))
)

data = [trace]
layout = go.Layout(barmode = 'group', title='Athlete earing the most maximum numbe of times', width=800, height=500,
                   xaxis = dict(title='No of times ranked higest'),
                   yaxis = dict(autorange='reversed'),
                   showlegend=False)

fig = go.Figure(data = data, layout = layout)
iplot(fig)

counts_top = top_paid_each_year['Nationality'].value_counts().to_frame()


trace = go.Bar(
                    x = counts_top.index,
                    y = counts_top['Nationality'] ,
                    orientation='v',
                    marker = dict(color='pink',
                                 line=dict(color='black',width=1)),
                    )
data = [trace]
layout = go.Layout(barmode = "group",title='Country which produces the maximum earners in Sports',width=800, height=500, 
                       xaxis= dict(title='No of times ranked higest'),
                       #yaxis=dict(autorange="reversed"),
                       showlegend=False)
fig = go.Figure(data = data, layout = layout)
iplot(fig)

trace = go.Scatter(
                    x = top_paid_each_year.index,
                    y = top_paid_each_year['earnings ($ million)'] ,
                    orientation='v',
                    marker = dict(color='red',
                                 line=dict(color='royalblue',width=2)),
                    )
data = [trace]
layout = go.Layout(title='How much did the Top Paid Athlete for Each Year, earn? ',width=800, height=500, 
                       xaxis= dict(title='Years'),
                       yaxis=dict(title="Earning in US Dollars(million)"),
                       showlegend=False)
fig = go.Figure(data = data, layout = layout)
iplot(fig)

df['Sport'] = df['Sport'].str.upper() # Converting the text to uppercase
max_sport = df['Sport'].value_counts().to_frame()

trace = go.Bar(
                    y = max_sport.index,
                    x = max_sport['Sport'] ,
                    orientation='h',
                    marker = dict(color='pink',
                                 line=dict(color='black',width=1)),
                    )
data = [trace]
layout = go.Layout(barmode = "group",title='Sport which dominates in earnings',width=800, height=500, 
                       xaxis= dict(title='No of times ranked highest'),
                       yaxis=dict(autorange="reversed"),
                       showlegend=False)
fig = go.Figure(data = data, layout = layout)
iplot(fig)

max_sport = df['Nationality'].value_counts().to_frame()


trace = go.Bar(
                    y = max_sport.index,
                    x = max_sport['Nationality'] ,
                    orientation='h',
                    marker = dict(color='pink',
                                 line=dict(color='black',width=1)),
                    )
data = [trace]
layout = go.Layout(barmode = "group",title='Country which dominates in Sports earningss',width=800, height=500, 
                       xaxis= dict(title='No of times ranked highest'),
                       yaxis=dict(autorange="reversed"),
                       showlegend=False)
fig = go.Figure(data = data, layout = layout)
iplot(fig)

s = df['Name'].value_counts().to_frame()[:5]
s.style.background_gradient(cmap='Reds')  

# People who have appeared once on the list.
names = df['Name'].value_counts().to_frame()
names[names['Name']==1].index

# On scanning the list, we find the name of a sole women athlete- monica seles
monica = df[df['Name'] == 'Monica Seles']
monica.style.set_properties(**{'background-color': 'pink',
                            'color': 'black',
                            'border-color': 'black'})

top_earners_alltime = pd.pivot_table(df, index='Name',values="earnings ($ million)", aggfunc='sum')
top3_earners_all = top_earners_alltime.sort_values(by="earnings ($ million)",ascending=False)[:3]

top3_earners_all.style.background_gradient(cmap='Reds')  

image_path = "th.jpeg"
earnings_plot(df1,'Tiger Woods',image_path,opacity=0.3)

image_path = "fm.jpeg"
earnings_plot(df1,'Floyd Mayweather',image_path,opacity=0.2)