Diamond Price Prediction

LINK : https://3141roy-diamondpriceprediction.streamlit.app/

The goal is to predict price of given diamond (Regression Analysis).

There are 10 independent variables (including id):

• id : unique identifier of each diamond
• carat : Carat (ct.) refers to the unique unit of weight measurement used exclusively to weigh gemstones and diamonds.
• cut : Quality of Diamond Cut
• color : Color of Diamond
• clarity : Diamond clarity is a measure of the purity and rarity of the stone, graded by the visibility of these characteristics under 10-power magnification.
• depth : The depth of diamond is its height (in millimeters) measured from the culet (bottom tip) to the table (flat, top surface)
• table : A diamond's table is the facet which can be seen when the stone is viewed face up.
• x : Diamond X dimension
• y : Diamond Y dimension
• x : Diamond Z dimension

Target variable:

• price: Price of the given Diamond.

The data contains oridnal features which require domain knowledge to interpret.

For more information about these ordinal features, Click Here

Source of Dataset

Running the Code

To deploy this project run

Step 1 : Create a virtual env and activate it

Step 2 : Install the dependencies by running

        pip install -r requirements.txt

Step 3 : The project is hosted on Streamlit but to run locally, you can use the command : streamlit run app\app.py

Documentation

This project involves a step by step process of performing all operations that a Machine Learning project requires in a step by step fashion.

We first begin with EDA (Exploratory Data Analysis) and Model Analysis, both of which can be seen in the folder notebooks under EDA.ipynb and Model.ipynb. The dataset used is stored in notebooks\data

Apart from this, we also use a Custom Exception Handler to ensure that the code does not stop unexpectedly during execution and a Logger to to help during debugging process. Both these are present in the src folder itself under the name exception.py and logger.py.

The utils.py is another file in the src folder. It is a utility python executable that has three functions

1. save_object : This functuon is passed with two parameters, the path and the file name and is required to store the files generated during model creation i.e. the pickle files for pre-processing our input and the pickle file for the model itself at the desired location.

2. evaluate_model : This function is used to evaluate and generate report by testing our data against a list of models passed as a parameter to it.

3. load_object : This function is used to load the files from a file path during execution phase when the model is being run

Apart from this we also have a pipeline folder and components folder to automate our processes