Olympic Data Analytics Project with Source Code

• Olympic dataset analysis from 1896 to 2016
• Automated data loading from local CSV
• Kaggle API fallback for dataset download
• Country name enrichment using NOC region mapping
• Exploratory data analysis report
• Dataset shape analysis
• Column data type analysis
• Sample row display
• Descriptive statistics
• Missing value analysis
• Unique athlete, country, sport, and year analysis
• Medal distribution analysis
• Gender participation analysis
• Summer and Winter season distribution analysis
• Six comparative visualization graphs
• Country-wise medal comparison
• Medal trend over time
• Gender comparison using pie and bar charts
• Age distribution analysis by sport
• Country medal heatmap
• Athlete participation growth analysis
• Machine learning medal prediction
• Random Forest binary classifier
• Feature scaling using StandardScaler
• Label encoding for sport and NOC
• Train-test split with stratification
• Accuracy score calculation
• ROC-AUC score calculation
• Classification report generation
• Feature importance analysis
• Confusion matrix visualization
• ROC curve visualization
• Medal forecast module
• Linear regression-based medal trend forecasting
• User-selected forecast year input
• Default forecast years from 2022 to 2031
• Forecast graph generation
• Jupyter Notebook support
• IDLE / script mode support
• Environment-aware plot display
• Output PNG graph generation
• Kaggle dataset helper script
• Legacy batch script support

• Dataset row and column count analysis
• Numeric column summary
• Categorical column summary
• Missing data inspection
• Athlete participation count
• Country participation count
• Sport count analysis
• Year range identification
• Medal count distribution
• Gold, Silver, and Bronze medal analysis
• Male vs female participation analysis
• Summer vs Winter Olympics comparison
• Country-wise medal points calculation
• Olympic participation trend analysis
• Sport-wise age distribution analysis
• Top country medal comparison

• Top 15 countries by medal points using horizontal bar chart
• Total medals awarded per year using line chart
• Summer vs Winter medals over time comparison
• Gender participation share using pie chart
• Medals won by gender using bar chart
• Age distribution of medal winners by sport using box plot
• Top 10 countries × medal type using heatmap
• Athlete participation growth using stacked area chart
• Machine learning confusion matrix
• Machine learning ROC curve
• Medal forecast graph
• All generated charts saved in the output/ folder
• Predicts whether an athlete wins a medal or not
• Uses Random Forest Classifier
• Uses 100 trees with max depth 15
• Uses athlete features such as age, height, weight, sex, sport, and NOC
• Encodes categorical columns
• Handles large dataset through sampling
• Uses 75% training and 25% testing split
• Prints model accuracy
• Prints ROC-AUC score
• Prints classification report
• Displays feature importance
• Generates confusion matrix
• Generates ROC curve
• Supports medal forecast using Linear Regression
• Forecasts total medal count for selected future years

Option 1: Run main Python script

1. Open project folder:

   cd "olympic-data-analysis"

2. Install dependencies:

   pip install -r requirements.txt

3. Place dataset files inside:

   data/

4. Run main project:

   python olympic_analysis_complete.py

5. Close each graph window to continue to the next output.

Option 2: Run Jupyter Notebook

1. Open project folder:

   cd "olympic-data-analysis"

2. Install requirements:

   pip install -r requirements.txt

3. Start Jupyter Notebook:

   python -m jupyter notebook

4. Open:

   olympic_analysis.ipynb

5. Run all cells.

Option 3: Download dataset using Kaggle API

1. Configure Kaggle API token:

   kaggle.json

2. Place it in:

   C:\Users\<YourUsername>\.kaggle\kaggle.json

3. Run:

   python download_dataset.py

This project has no login credentials because it is not a web application.

Credential note:
Kaggle API credentials are optional and only required if the dataset is downloaded automatically through Kaggle API. There are no shared or default Kaggle credentials included in the project.