kaushalsalvatore / boston-price-prediction Goto Github PK

This is machine learning web app that use to predict Boston house price accroding to given paramenter in data set.

• https://boston-price-prediction.onrender.com/

• Data Collection
• Data Analysis
• Data Visualization
• Feature Engineering
• Feature Selection
• Model Building
• Model Evalution
• Hyper Parameter Tunning
• Creating Pickle file
• Web App using Flask
• Deployment

    from sklearn.datasets import load_boston

• Number of Instances: 506
• Number of Attributes: 13 numeric/categorical predictive.

• CRIM: per capita crime rate by town
• ZN: proportion of residential land zoned for lots over 25,000 sq.ft.
• INDUS: proportion of non-retail business acres per town
• CHAS: Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)
• NOX: nitric oxides concentration (parts per 10 million)
• RM: average number of rooms per dwelling
• AGE: proportion of owner-occupied units built prior to 1940
• DIS: weighted distances to five Boston employment centres
• RAD: index of accessibility to radial highways
• TAX: full-value property-tax rate per $10,000
• PTRATIO: pupil-teacher ratio by town
• B: 1000(Bk - 0.63)^2 where Bk is the proportion of black people by town
• LSTAT: % lower status of the population

python packages: Pandas, Numpy, Scikit-learn, matplotlib ,seaborn

ML Algorithms: LinearRegression

Framework: Flask

frontend: Html, CSS

Clone the project

  git clone https://github.com/KaushalSalvatore/Boston-Price-Prediction.git

Install dependencies

  pip install -r requirements. txt

Start the local server

  Python index.py or index.py

To deploy this project on github use this following command in the project folder.

Initializing a new repository

  git init

A gitignore file specifies intentionally untracked files that Git should ignore.

  touch .gitignore

Add all the files

  git add .

Check file status

  git status

Commit all the file on git

  git commit -m "your message"

Push all the code on github

  git push <your_branch_name>

Push code

  git push -u origin <your_branch_name>

Push code forcefully

  git push origin <your_branch_name> --force

• Dockerfile: first create a docker file that is a text document that contains all the commands a user could call on the command line to assemble an image.
• FROM python:3.8.17 (to create a blank base image)
• COPY . /app (allows us to copy a file or folder from the host system into the docker image)
• WORKDIR /app (define the working directory of a Docker container at any given time)
• RUN pip install -r requirements.txt (execute any commands in a new layer on top of the current image and commit the results)
• EXPOSE 8000 (tells Docker that a container listens for traffic on the specified port.)
• CMD python index.py (specifies the instruction that is to be executed when a Docker container starts.)

  Create a docker image 
  docker build -t kaushalpandey/boston-price-prediction .

  run docker image  
  docker run -p 8000:8000 boston-price-prediction	

  docker login
  docker build -t boston-price-prediction .

  push to docker hub
  docker push kaushalpandey/flask-helloworld:latest

  pull docker image
  docker pull kaushalpandey/boston-price-prediction:latest

• LinearRegression
• coefficients
• intercept
• Assumptions
• mean squared error
• Mean absolute error
• R square
• Adjusted r square

if you have any suggetion and feedback and need any kind of project related help reach me out at linkedin