Weather Type Prediction Model using Machine Learning

This project is a Weather Type Classification model built using the “Weather Type Classification” dataset from Kaggle.

Key Features:

Exploratory Data Analysis & Visualization (boxplots, distributions for temperature, humidity, wind speed, precipitation, cloud cover, etc.)

Data Preprocessing: Encoding categorical variables (season, location, cloud cover), scaling, handling outliers

Machine Learning model (e.g., Random Forest or similar classifier) to predict weather types: Rainy, Sunny, Cloudy, Snowy

Interactive input: Users enter real-time values (temperature, humidity, wind speed, precipitation, etc.) to get instant prediction + recommendation (e.g., agricultural advice)

Error handling and clear output messages

Implementation:

Developed in Python using Jupyter Notebook. Libraries: pandas, numpy, scikit-learn, matplotlib, seaborn. Includes full pipeline: data loading → preprocessing → training → prediction interface.

Work Images/Files (Suggestions – upload up to 20):

Screenshots of data visualizations (boxplots, histograms)

Confusion matrix or classification report (if evaluated)

Prediction cell output during runtime

Feature/target overview from slides

Final recommendation example (e.g., “Heavy rain – avoid planting today”)