I'm a data enthusiast passionate about transforming raw data into compelling stories through advanced analytics and visualization techniques. I specialize in exploring intricate datasets and applying machine learning to uncover hidden insights.
One of my most exciting projects delves into the world of Indian Premier League (IPL), analyzing match outcomes, player performances, and team strategies over 15 seasons (2008–2022). This project combines my love for data science and cricket!
Let’s connect, collaborate, and create! 😊
- Programming Languages: Python, SQL
- Libraries/Tools: NumPy, pandas, seaborn, matplotlib, scikit-learn, XGBoost, statsmodels, plotly
- Expertise: Data Visualization, Predictive Modeling, Exploratory Data Analysis (EDA)
- Interests: Data Science, Storytelling with Data, Sports Analytics
- Fun Fact: Whether it's predicting match outcomes or analyzing player stats, I bring the same enthusiasm to data science as I do while cheering for my favorite IPL team!
This project dives into the rich history of the Indian Premier League (IPL), analyzing match data, player performances, and team strategies over 15 seasons (2008-2022). Using statistical methods, data visualizations, and predictive modeling, it uncovers insights about the most successful teams, players, and match trends.
- Languages: Python
- Libraries: NumPy, pandas, seaborn, matplotlib, plotly, scikit-learn, statsmodels
- Exploratory Data Analysis (EDA):
- Analyze match outcomes, team performance, and player statistics.
- Trends in winning margins, toss decisions, and home vs. away results.
- Visualizations:
- Bar plots, heatmaps, and interactive charts to highlight key patterns.
- Predictive Modeling:
- Build machine learning models to predict match winners and player performances.
- Insights:
- Identified the most impactful players and consistent teams across seasons.
The dataset contains match records from the IPL's inception in 2008 to 2022, including:
- Match outcomes and details (winner, venue, toss decision).
- Player performance (runs, wickets, strike rates, economy rates).
- Team statistics across all seasons.
Dataset Source: Kaggle: IPL Complete Dataset (2008-2022)
- Clone the repository:
git clone https://github.com/SumanthUdupi/IPL-Aalysis.git
- Install dependencies:
pip install -r requirements.txt
- Open
ipl-analysis.ipynbin Jupyter Notebook. - Run the cells to view EDA, visualizations, and predictions.
- Patrick B1912 for compiling the IPL dataset.
- Kaggle community for resources and inspiration.