Data Transformation:

1. Handling Missing Values: Missing values in the Price column were replaced with the mean value of that column.

2. Data Type Conversion: The Battery_life column, originally in string format (e.g., "58 kWh"), was converted to numeric using parse_number() to retain only the numeric portion for analysis.

3. Feature Engineering: A new binary variable, Affordability, was created to indicate whether the Price of an electric vehicle is above or below a specific threshold (e.g., $53,000).

4. Train-Test Split: The dataset was split into training and testing sets to build and evaluate predictive models.

Conclusion:

The price of an electric car varies widely depending on the make, model, battery capacity, range, and other features. After using different statistical analysis methods to predict the features that mostly affect the cost of electric cars among the top companies, we conclude that Top speed, which has been consistent during our analysis, and Efficiency, are the features that positively affect the price vehicle of company such as Tesla and BMW. Also, we found in our analysis that cars that have a higher battery life in our dataset are above the average total price of electric vehicle. However, other characteristics, such as Acceleration and Fast Charge Speed were significantly negative in our dataset, so it did not have an increased impact on the cost of the cars. Eventually, we can also conclude that the features that affect the cost of battery electric vehicles vary depending on the manufacturer. ​

Limitations: ​

This analysis is limited to personal electric vehicles. Commercial electric vehicles are outside of the scope for this project. ​

​