BMW Car Market Insights Data Analysis Final Year Project with Source Code

Project Features in this Final Year Project

• BMW used-car market data analysis
• CSV-based dataset loading
• Data cleaning and preparation
• Text column whitespace removal
• Dataset shape inspection
• Data type inspection
• First records preview
• Numerical descriptive statistics
• Categorical frequency analysis
• Missing-value analysis
• Thirteen graphical outputs
• Automatic output_plots folder creation
• Model-wise price analysis
• Year-wise price analysis
• Transmission-wise price comparison
• Fuel-type price comparison
• Mileage versus price analysis
• Engine size versus price analysis
• MPG versus price analysis
• Correlation heatmap
• BMW model popularity analysis
• Listings by manufacturing year
• Label encoding of categorical features
• Train-test split
• Feature scaling
• Random Forest regression model
• Training and testing prediction
• R², RMSE, and MAE evaluation
• Five-fold cross-validation
• Feature importance ranking
• Actual-versus-predicted graph
• Sample car-price prediction output
• Automatic market insights summary
• Fully local command-line execution

Data Analytics / EDA Features in this Final Year Project

• Loads:

  data.csv

• Cleans text values in:

  model
  transmission
  fuelType

• Displays dataset rows and columns
• Displays column names
• Displays non-null counts
• Displays memory usage
• Displays first five records
• Displays numerical summary using describe()
• Analyzes categorical value counts
• Analyzes BMW model frequency
• Analyzes transmission frequency
• Analyzes fuel type frequency
• Checks missing values column-wise
• Displays total missing cell count
• Verifies loaded data types
• Prints final market insights summary

Visualization Features in this Final Year Project

The project generates 13 PNG charts inside:

output_plots/

1. Price Distribution
   File: 01_price_distribution.png
   Chart type: Histogram
   Shows BMW car price distribution with average price line.
2. Average Price by Model
   File: 02_price_by_model.png
   Chart type: Horizontal bar chart
   Compares average selling price of BMW models.
3. Price Distribution by Year
   File: 03_price_vs_year.png
   Chart type: Box plot
   Shows price variation across manufacturing years.
4. Price by Transmission Type
   File: 04_price_by_transmission.png
   Chart type: Box plot
   Compares prices for automatic, manual, semi-auto, and other transmission types.
5. Price by Fuel Type
   File: 05_price_by_fuel_type.png
   Chart type: Box plot
   Compares vehicle prices across petrol, diesel, hybrid, electric, or other fuel categories.
6. Mileage versus Price
   File: 06_mileage_vs_price.png
   Chart type: Scatter plot with trend line
   Studies relationship between mileage and price.
7. Engine Size versus Price
   File: 07_engine_vs_price.png
   Chart type: Scatter plot
   Compares engine size with price, grouped by fuel type.
8. MPG versus Price
   File: 08_mpg_vs_price.png
   Chart type: Scatter plot
   Studies relationship between fuel efficiency and car price.
9. Correlation Heatmap
   File: 09_correlation_heatmap.png
   Chart type: Heatmap
   Displays correlation among numerical variables.
10. BMW Model Popularity
    File: 10_model_popularity.png
    Chart type: Horizontal bar chart
    Shows listing count for each BMW model.
11. Listings by Year
    File: 11_year_distribution.png
    Chart type: Bar chart
    Shows number of vehicle listings by manufacturing year.
12. Feature Importance
    File: 12_feature_importance.png
    Chart type: Horizontal bar chart
    Shows feature contribution in Random Forest price prediction.
13. Actual versus Predicted Price
    File: 13_actual_vs_predicted.png
    Chart type: Scatter plot
    Compares actual test-set prices with predicted prices.

Machine Learning Features in this Final Year Project

• Supervised machine learning regression

• Target variable:

  price

• Input features:

  model
  year
  transmission
  mileage
  fuelType
  tax
  mpg
  engineSize

• Uses Random Forest Regressor
• Categorical encoding using LabelEncoder
• Feature scaling using StandardScaler
• 80% training and 20% testing split
• Random state set to 42 for reproducibility
• Trains model on scaled training data
• Predicts training prices
• Predicts testing prices
• Reports training R² score
• Reports testing R² score
• Reports training RMSE
• Reports testing RMSE
• Reports training MAE
• Reports testing MAE
• Performs five-fold cross-validation
• Calculates feature importance values
• Ranks important price-prediction features
• Generates actual-versus-predicted visualization
• Displays sample prediction table

Random Forest Model Configuration in this Final Year Project

The project uses:

RandomForestRegressor(
    n_estimators=100,
    max_depth=15,
    random_state=42,
    n_jobs=-1
)

Why Random Forest is suitable:

• Handles non-linear relationships
• Works well on structured tabular data
• Learns interactions between vehicle features
• Performs well with mixed encoded feature sets
• Handles noisy patterns better than simple linear models
• Provides feature importance values
• Useful for used-car price prediction demonstrations

Dataset Details in this Final Year Project

Dataset file:

data.csv

Required CSV header:

model,year,price,transmission,mileage,fuelType,tax,mpg,engineSize

Dataset columns:

• model — BMW vehicle model or series
• year — manufacturing or registration year
• price — vehicle selling price
• transmission — transmission type
• mileage — miles already travelled
• fuelType — vehicle fuel category
• tax — annual road tax
• mpg — fuel economy in miles per gallon
• engineSize — engine displacement in litres

Files / Modules Included in this Final Year Project

• main.py — recommended name for the main script
• data.csv — required BMW used-car dataset
• requirements.txt — dependency list
• README.md — project documentation
• output_plots/ — generated charts folder

Recommended structure:

bmw-car-market-insights/
|
|-- main.py
|-- data.csv
|-- requirements.txt
|-- README.md
|
`-- output_plots/

Output Files in this Final Year Project

After successful execution, generated files appear in:

output_plots/

Expected output files:

• 01_price_distribution.png
• 02_price_by_model.png
• 03_price_vs_year.png
• 04_price_by_transmission.png
• 05_price_by_fuel_type.png
• 06_mileage_vs_price.png
• 07_engine_vs_price.png
• 08_mpg_vs_price.png
• 09_correlation_heatmap.png
• 10_model_popularity.png
• 11_year_distribution.png
• 12_feature_importance.png
• 13_actual_vs_predicted.png

These outputs can be used in:

• Project reports
• Presentations
• Research documentation
• Viva demonstrations
• Data analysis assignments
• Portfolio case studies

1. Create project folder:

   bmw-car-market-insights/

2. Place files inside the folder:

   main.py
   data.csv
   requirements.txt
   README.md

3. Open terminal in project folder:

   cd "bmw-car-market-insights"

4. Create virtual environment on Windows:

   python -m venv venv
   venv\Scripts\activate

5. Create virtual environment on macOS/Linux:

   python3 -m venv venv
   source venv/bin/activate

6. Install required packages:

   pip install pandas numpy matplotlib seaborn scikit-learn

7. Or install using requirements file:

   pip install -r requirements.txt

8. Ensure the dataset exists:

   data.csv

9. Run the project on Windows:

   python main.py

10. Run the project on macOS/Linux:

python3 main.py

11. Check generated charts:

output_plots/

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

Credential note:
No admin panel, user login, dealer panel, password, or database authentication is included. The project runs locally as a command-line analytics project.