https://github.com/zeuscoderbe/eda-and-model-fnn

Exploratory analysis and visualization of Australian weather data. Building an FNN neural network to predict the highest temperature of the day
https://github.com/zeuscoderbe/eda-and-model-fnn

deeplearning eda machine-learning

Last synced: about 2 months ago
JSON representation

Exploratory analysis and visualization of Australian weather data. Building an FNN neural network to predict the highest temperature of the day

• Host: GitHub
• URL: https://github.com/zeuscoderbe/eda-and-model-fnn
• Owner: ZeusCoderBE
• Created: 2024-04-22T06:29:00.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-22T06:32:37.000Z (about 1 year ago)
• Last Synced: 2025-02-05T08:51:28.624Z (4 months ago)
• Topics: deeplearning, eda, machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 6.44 MB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Weather Prediction Project

## Purpose

This project aims to analyze weather data and build models to predict weather factors such as maximum temperature and the likelihood of rain tomorrow.

## Project Structure

1. **Python Notebook:** The project utilizes a Python notebook to perform all data analysis and model building tasks. The notebook file is named `Weather_Prediction.ipynb`.

2. **Data:** The dataset used in this project is stored in a CSV file named `weatherAUS.csv`. This dataset contains approximately 10 years of daily weather observations from various locations across Australia, including 145460 records and 23 attributes.

3. **Libraries Used:**

   - NumPy

   - Pandas

   - Matplotlib

   - Seaborn

   - TensorFlow (Keras)

4. **Tasks Covered in the Notebook:**

   - Exploratory Data Analysis (EDA) to understand the dataset's structure, summary statistics, and visualize relationships between variables.

   - Data preprocessing steps such as handling missing values, outlier removal, data standardization, and encoding categorical variables.

   - Building an Artificial Neural Network (ANN) model for regression to predict maximum temperature.

   - Building an ANN model for classification to predict the likelihood of rain tomorrow.

   - Evaluating model performance using metrics such as Mean Squared Error (MSE), R-squared score, Mean Absolute Error (MAE), accuracy, confusion matrix, and ROC curve.

   

5. **Instructions for Running the Notebook:**

   - Ensure that all required libraries are installed in your Python environment.

   - Download the `weatherAUS.csv` dataset and place it in the same directory as the notebook.

   - Open the notebook using Jupyter Notebook or any compatible platform.

   - Execute each cell in the notebook