README.md

metadata

title: WeatherApp.v1
emoji: 🌍
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 3.27.0
app_file: app.py
pinned: false
license: unknown

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Weather Prediction Model Based on User Preferences

This is a machine learning model that predicts the suitability of the weather based on user preferences. The model takes into account various weather features and scores each day based on how well it matches the user's ideal weather conditions.

Features

• Trains a machine learning model based on the user's ideal weather conditions
• Predicts the suitability of the weather on a given day and location
• Provides hourly scores for the day's weather

Requirements

• pandas
• numpy
• scikit-learn
• pickle
• datetime
• tensorflow
• json
• requests
• gradio

To install the requirements, run:

pip install pandas numpy scikit-learn tensorflow json requests gradio

Usage

1. Train the model by providing your ideal max temperature, min temperature, and humidity level.
2. Predict the weather for a given location and day (yesterday, today, or tomorrow) using the trained model.
3. Receive a daily score and hourly scores for the selected day based on your preferences.

Data

The historical weather data is stored in weatherdatafinal.csv. The program uses the Visual Crossing Weather API to fetch real-time weather data for the specified location and day.

Functions

• add_daytime_column(): Adds a daytime column to the dataset by calculating the duration between sunrise and sunset.
• train_model(): Trains the model based on user preferences for ideal max temperature, ideal min temperature, and ideal humidity.
• predict_weather(): Predicts the daily score for the specified location and day based on the trained model.
• main(): Defines the Gradio interface and launches the application.

Author

@egecandrsn