#!/usr/bin/env python
# coding: utf-8

# <a href="https://colab.research.google.com/github/cyrus723/my-first-binder/blob/main/WTA_1st_weeks.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

# ### Source of Data
# # Jeff Sackmann data at https://www.jeffsackmann.com/

# In[1]:


import numpy as np
import pandas as pd


# In[2]:


# Combine data from years 2000-2019
url = 'https://raw.githubusercontent.com/JeffSackmann/tennis_wta/master/'
df_list = [pd.read_csv(url + 'wta_matches_' + str(year) + '.csv') for year in range(2000,2020)]

type(df_list)


# In[3]:


# Player rankings from 2000-2019

rankings_10s = pd.read_csv(url + 'wta_rankings_10s.csv')
rankings_10s.columns = ['week', 'ranking', 'player_id', 'ranking_points', 'tours']

rankings_00s = pd.read_csv(url + 'wta_rankings_00s.csv')
rankings_00s.columns = ['week', 'ranking', 'player_id', 'ranking_points', 'tours']

rankings = pd.concat([rankings_00s, rankings_10s])

rankings.index = range(rankings.shape[0])

rankings


# In[4]:


rankings.info()


# In[5]:


type(rankings['week'])


# In[6]:


# Convert ranking dates to datetime
rankings['week'] = pd.to_datetime(rankings['week'], format = '%Y%m%d')


# In[7]:


player_df = pd.read_csv('https://raw.githubusercontent.com/JeffSackmann/tennis_wta/master/wta_players.csv')
player_df.info()


# In[9]:


joined_df = pd.merge(rankings, player_df, on = 'player_id', how = 'left')


# In[10]:


joined_df.info()


# In[11]:


joined_df.head(100)


# In[12]:


keep_column=['ranking', 'player_id', 'name_first', 'name_last']
df2=joined_df[keep_column]
df2


# In[13]:


df3=df2.loc[(df2['ranking'] ==1)]
df3


# In[14]:


checktosee = df3.groupby(['ranking', 'name_last', 'name_first']).count()
checktosee


# In[15]:


checktosee.info()


# In[16]:


checktosee.index


# In[17]:


checktosee.reset_index(inplace=True)


# In[18]:


checktosee


# In[19]:


checktosee['full_name'] = checktosee['name_first'] + ' ' + checktosee['name_last']


# In[20]:


checktosee2 = checktosee.sort_values(by="player_id", ascending=False )


# In[21]:


import matplotlib.pyplot as plt
import seaborn as sns
get_ipython().run_line_magic('matplotlib', 'inline')


# In[23]:


from google.colab import drive
drive.mount('/content/drive')


# In[32]:


fig, ax = plt.subplots(figsize=(10,6))
plt.bar(checktosee2["full_name"], checktosee2["player_id"], color ='blue',
        width = 0.8)
plt.title("WTA the 1st Ranked Players", size = 25)
plt.ylabel("# of Weeks as the 1st Ranked", size=15)
plt.xlabel("Players", size=15) 
plt.xticks(rotation = 82, size=20)
plt.tight_layout()

#ax.set_ylabel(player_id"])

plt.show()
fig.savefig('/content/drive/My Drive/Colab Notebooks/tennis/Tennis_Predicting-master/womenfirst.png', dpi=500, bbox_inches='tight')


# In[33]:


fig, ax = plt.subplots(figsize=(10,6))
sns.set_style('whitegrid')
#sns.set_palette()
plt.title("WTA the 1st Ranked Players", size = 25)
plt.ylabel("# of Weeks as the 1st Ranked", size=15)
plt.xlabel("Players", size=15) 
plt.xticks(rotation = 82, size=20)
plt.tight_layout()

ax=sns.barplot(x='full_name', y='player_id', data=checktosee2)
ax.set_xticklabels(ax.get_xticklabels(), rotation=90)
ax.set(xlabel='Players', ylabel='# of Weeks Ranked the 1st')


plt.show()
fig.savefig('/content/drive/My Drive/Colab Notebooks/tennis/Tennis_Predicting-master/womenfirst_sns.png', dpi=500, bbox_inches='tight')