EDA-on-PREMIER-LEAGUE

⚽ Premier League EDA (Exploratory Data Analysis)

This project performs Exploratory Data Analysis (EDA) on a Premier League dataset to uncover insights about team performance, player stats, match outcomes, and more. The analysis helps identify trends, outliers, and relationships across seasons.

📌 Table of Contents

• About the Project
• Dataset
• Objectives
• Technologies Used
• Key Insights
• Visualizations
• Future Work
• Author

---

📝 About the Project

The Premier League is one of the most watched football leagues in the world. This project uses EDA techniques to:

• Understand player and team performance
• Analyze match statistics
• Discover season-level patterns
• Explore correlations and trends

---

📂 Dataset

The dataset used contains information such as:

• Match results (Home/Away goals, winners)
• Team stats (Possession, Shots, Fouls, etc.)
• Player performance (Goals, Assists, Cards)
• Seasonal summaries

Dataset Source: https://drive.google.com/file/d/1jB20GritU6nWHU2zNYsWM2DuEJIzz8FI/view?usp=sharing

---

🎯 Objectives

• Clean and preprocess the data
• Generate descriptive statistics
• Identify key trends and patterns
• Visualize relationships using plots and graphs
• Draw conclusions to support decision-making in football analytics

---

💻 Technologies Used

• Python 🐍
• Pandas 📊
• NumPy 🔢
• Matplotlib 📈
• Seaborn 🌊
• Google Colab 📓

---

📊 Key Insights (Example Highlights)

After performing thorough EDA and visualizing various aspects of the Premier League dataset, here are the major insights obtained:

📈 1. Correlation Heatmap

• Strong positive correlation between shots on target and goals scored, indicating shooting accuracy plays a key role.
• A mild negative correlation between fouls committed and points earned, suggesting that disciplined teams often perform better.

📦 2. Boxplots

• Goals scored have a few significant outliers — indicating occasional high-scoring matches or standout players.
• Yellow cards are more consistently distributed, with most teams falling within a typical range, but a few overly aggressive teams stand out.

🏟️ 3. Home vs Away Performance

• Home teams tend to win more matches than away teams, confirming the traditional home advantage trend.
• Away teams have slightly fewer goals on average.

🧍 4. Player-Level Analysis

• Top goal scorers also lead in shots taken and minutes played, highlighting the importance of regular playtime.
• A few players accumulate high assists with fewer goals, indicating their role as creative playmakers.

🛑 5. Defensive Statistics

• Teams with higher clearances and tackles often finish mid-table — showing that strong defense alone may not ensure top position.
• Goalkeepers' saves were highest in lower-ranked teams, indicating defensive pressure and fewer clean sheets.

---

📸 Visualizations

Here are a few visualizations used in the project:

• 📊 Goals scored per season (Bar chart)
• 🥧 Win distribution by team (Pie chart)
• 🔥 Heatmap of feature correlations
• 🧍 Top 10 goal scorers (Horizontal bar chart)

---

🚀 Future Work

• Include data from more seasons
• Add xG (Expected Goals) and advanced metrics
• Perform predictive modeling (e.g., match outcome prediction)
• Dashboard creation using Plotly or Power BI

---

👤 Author

Somtirtha Chakraborty
🔗 LinkedIn
📫 Gmail