https://github.com/itaynir1/tf-second_car_hand

The code builds a machine learning model to predict the price of second-hand cars. It preprocesses the data, defines a neural network model, and trains it using the training dataset. The model's performance is evaluated, and predictions are made on new car data.
https://github.com/itaynir1/tf-second_car_hand

ipynb kaggle machine-learning machine-learning-algorithms python tensorflow tf

Last synced: 4 months ago
JSON representation

The code builds a machine learning model to predict the price of second-hand cars. It preprocesses the data, defines a neural network model, and trains it using the training dataset. The model's performance is evaluated, and predictions are made on new car data.

• Host: GitHub
• URL: https://github.com/itaynir1/tf-second_car_hand
• Owner: itaynir1
• Created: 2023-07-19T14:56:48.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-07-20T04:43:58.000Z (almost 3 years ago)
• Last Synced: 2025-03-02T04:27:55.004Z (over 1 year ago)
• Topics: ipynb, kaggle, machine-learning, machine-learning-algorithms, python, tensorflow, tf
• Language: Jupyter Notebook
• Homepage: https://github.com/itaynir1/tf-second_car_hand
• Size: 1.54 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
#  SECOND HAND CARS DATA SET

## Regression problem - using `TensorFlow `

### Description:

###  This code is a script for building and training a machine-learning model for predicting the price of second-hand cars.

### This code uses libraries such as TensorFlow, pandas, seaborn, and matplotlib for data processing, visualization, and model building.

### Data preparation is performed by reading a CSV file `("train.csv")` containing car features and labels, and then exploring the data using visualizations.

### The data is normalized using the Normalization layer from TensorFlow. 
 The model architecture is defined using the Sequential API from Keras, consisting of several dense layers with relu activation and a final output layer. 
 The model is compiled with an optimizer (Adam), loss function (MeanAbsoluteError), and metrics (RootMeanSquaredError). 

 The model is trained using the training dataset and validated using the validation dataset. Training history and performance metrics are plotted. 
 
Finally, the trained model is evaluated on the test dataset, and predictions are made on new car data.