Cricket Analytics with Python — IPL Data Analysis Project

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# Load datasets
matches = pd.read_csv('matches.csv')
deliveries = pd.read_csv('deliveries.csv')

print(f"Matches: {len(matches)}, Deliveries: {len(deliveries)}")
print(matches.head())

team_wins = matches['winner'].value_counts()
total_matches = matches.groupby('team1').size() + matches.groupby('team2').size()

win_rate = (team_wins / total_matches * 100).sort_values(ascending=False)
print(win_rate.head(10))

# Visualize
plt.figure(figsize=(12,6))
win_rate.head(8).plot(kind='bar', color='skyblue')
plt.title('IPL Win Rate by Team', fontsize=14, fontweight='bold')
plt.ylabel('Win %')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

batting_stats = deliveries.groupby('batsman').agg({
    'batsman_runs': 'sum',
    'match_id': 'nunique'
}).rename(columns={'batsman_runs': 'total_runs', 'match_id': 'matches'})

batting_stats['avg_per_match'] = batting_stats['total_runs'] / batting_stats['matches']
top_scorers = batting_stats.sort_values('total_runs', ascending=False).head(10)

print(top_scorers)

toss_wins = matches.groupby('toss_decision')['winner'].count()
print(f"Bat first wins: {(matches[matches['toss_decision']=='bat']['winner'] == matches[matches['toss_decision']=='bat']['toss_winner']).sum()}")