Predict the price of a car based on different variables such as make and technical specifications
1. For the purpose of obtaining data, the sample data set "Automobile price data (Raw)" has been used in training in order to get the price predictions. 2. Then, the data should be prepared by the process of "data pre-processing", in which all the missing values in the data set are cleaned, so the model can analyze the data correctly. Either the missing values can be removed, or they can be calculated.(depends on the quantity of data). 3. Then, the features (individual measurable properties) have been defined. According to this, each row represents one automobile, and each column is a feature of that automobile. 4. In order to build the model, the subset of the features (make, body-style, wheel-base, engine-size, horsepower, peak-rpm, highway-mpg, price) have been used. 5. Next, a suitable algorithm has to be chosen. Here, we have chosen linear regression model, which is a regression model used to predict price, which is a number. 6. Then, we have to train the model with the prepared data set. For the training purposes, we have used 75% of the data to train the model and hold back 25% for testing. 7. After running this experiment successfully, we have predicted new automobile prices accurately. 8. According to the results, the mean of "price" has been received as 12733.5625, while the mean of "Scored labels" has been received as 12437.776 9. With these results, we can conclude that the chosen model is suitable for the chosen data set, because there is not much difference between the mean values of price and Scored labels. 10. With this, the price of a car can be predicted accurately.