Uber Rides Prediction in Machine Learning

Uber rides prediction is a Machine Learning model which predict the uber rides that how much uber rides can do a Uber boy per week based on the different types of features. This model works good with a good accuray (93.47 %). This model trained with a LinearRegression Algorithm with a best accuracy out of other models.

Linear regression is a basic and commonly used type model of predictive analysis. These regression estimates are used to explain the relationship between one dependent variable (Feature) and one or more independent variables (Features).

This model is useful for the safety of the passengers that no uber boy can't do a ride out of limit. If they pickup a passenger out of his limit so company will put a charge on him.

I created a uber rides prediction model with the help of following few steps of Machine Learning like :

1. Define project objectives
2. Data Preprocessing (Data Cleaning , Data Preparation , split into train and test , Feature Scaling).
3. Model Selection
4. Data Collection
5. Data Visualization
6. Model Building
7. Deploy Model

I also deployed a model with the help of python framework flask. Flask is a popular Python web framework, meaning it is a third-party Python library used for developing web applications.

When we fill the fields with inputs and after fill values, when we click on the predict button So it predict that how much rides can uber boy do.

Source code and how to use:

1. Go to my github  and download code : Uber rides prediction

2. After download, Extract the folder where you will get a two folders static and templates , one python file, one dataset file, one jupiter notebook file and our pretrained model.

3. Go into the folder.

4. Open the command prompt and go to the project folder with cd command.

5. Write (python app.py) in your prompt.

6. You get a link like this (http://127.0.0.1:5000/).

7. Paste in the Chrome or any browser.

8. Now you can use the model.

If you want to train your own model then you can again run the jupiter notebook and follow all process.

Demo

Thank You !!!!!!!!!!!!!