{"id":25236794,"url":"https://github.com/hasanulmukit/time-series-forecasting","last_synced_at":"2025-04-05T18:13:30.692Z","repository":{"id":276898998,"uuid":"930672578","full_name":"hasanulmukit/time-series-forecasting","owner":"hasanulmukit","description":"A powerful and interactive web application for forecasting time series data using three robust models: ARIMA, Prophet, and LSTM.","archived":false,"fork":false,"pushed_at":"2025-02-11T02:40:22.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-11T03:26:32.724Z","etag":null,"topics":["arima","forecasting","lstm","prophet","python","time-series"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hasanulmukit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-11T02:38:53.000Z","updated_at":"2025-02-11T02:43:09.000Z","dependencies_parsed_at":"2025-02-11T03:38:07.799Z","dependency_job_id":null,"html_url":"https://github.com/hasanulmukit/time-series-forecasting","commit_stats":null,"previous_names":["hasanulmukit/time-series-forecasting"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanulmukit%2Ftime-series-forecasting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanulmukit%2Ftime-series-forecasting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanulmukit%2Ftime-series-forecasting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hasanulmukit%2Ftime-series-forecasting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hasanulmukit","download_url":"https://codeload.github.com/hasanulmukit/time-series-forecasting/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247378140,"owners_count":20929297,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arima","forecasting","lstm","prophet","python","time-series"],"created_at":"2025-02-11T15:31:54.628Z","updated_at":"2025-04-05T18:13:30.670Z","avatar_url":"https://github.com/hasanulmukit.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Time Series Forecasting App\n\nA powerful and interactive web application for forecasting time series data—specifically stock closing prices—using three robust models: **ARIMA**, **Prophet**, and **LSTM**. The app is built using Streamlit and leverages live data from Yahoo Finance, along with additional datasets available on Kaggle.\n\n## Table of Contents\n\n- [Overview](#overview)\n- [Features](#features)\n- [Tech Stack](#tech-stack)\n- [Data Source](#data-source)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Project Structure](#project-structure)\n- [Customization](#customization)\n- [Future Improvements](#future-improvements)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Overview\n\nThe Time Series Forecasting App is designed to help users explore and forecast stock closing prices using three forecasting models:\n\n- **ARIMA:** A classical time series model that is ideal for linear patterns.\n- **Prophet:** Developed by Facebook, this model is robust to missing data and handles seasonality and trend changes efficiently.\n- **LSTM:** A deep learning model implemented in TensorFlow, capable of capturing complex non-linear patterns in time series data.\n\nUsers can interact with the app via a user-friendly dashboard, configure model parameters, and view both static and interactive charts. Additional features include seasonal decomposition analysis and the ability to download forecast results as a CSV file.\n\n## Features\n\n- **Model Selection:** Choose between ARIMA, Prophet, and LSTM models.\n- **Data Sourcing:** Fetch live stock data from Yahoo Finance.\n- **Customizable Forecast Parameters:** Adjust forecasting periods and model-specific parameters.\n- **Interactive Visualization:** Toggle between static (Matplotlib) and interactive (Plotly) charts.\n- **User-Selectable Date Range:** Zoom in on historical data with user-defined date ranges.\n- **Seasonal Decomposition:** View the trend, seasonal, and residual components of your time series.\n- **Download Forecast:** Export forecast results as a CSV file.\n- **Custom Theming:** Enhanced user interface with custom CSS styling for a polished look.\n\n## Tech Stack\n\n- **Python 3.8+**\n- **Streamlit:** For building interactive web applications.\n- **Pandas \u0026 NumPy:** For data manipulation and numerical operations.\n- **yfinance:** For downloading historical stock data.\n- **Matplotlib \u0026 Plotly:** For data visualization.\n- **Statsmodels:** For ARIMA and seasonal decomposition.\n- **Prophet:** For robust forecasting with trend and seasonality.\n- **TensorFlow \u0026 Keras:** For building and loading LSTM models.\n- **scikit-learn:** For data preprocessing.\n\n## Data Source\n\n- **Yahoo Finance:** The primary source for live stock data is [Yahoo Finance](https://finance.yahoo.com/) via the `yfinance` library.\n- **Kaggle Dataset (Optional):** Alternatively, you can experiment with datasets such as [Historical Stock Prices](https://www.kaggle.com/datasets/rohitsahoo/historical-stock-prices).\n\n## Installation\n\n1. **Clone the Repository:**\n\n   ```bash\n   git clone https://github.com/yourusername/time-series-forecasting-app.git\n   cd time-series-forecasting-app\n   ```\n\n2. Create a Virtual Environment:\n\n   ```bash\n   python -m venv venv\n   ```\n\n3. Activate the virtual environment:\n\n- On Windows:\n  ```bash\n  venv\\Scripts\\activate\n  ```\n- On macOS/Linux:\n  ```bash\n  source venv/bin/activate\n  ```\n\n4.  Install Dependencies:\n\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n### Usage\n\n- Run the App:\n- In your project directory, start the Streamlit app with:\n\n  ```bash\n  streamlit run app.py\n  ```\n\n1. Interact with the Dashboard:\n\n- Use the sidebar to select the ticker, date range, forecast period, and model-specific parameters.\n- Adjust the visualization date range to zoom in on the desired window.\n- View interactive or static charts depending on your selection.\n- Access additional analysis such as seasonal decomposition.\n- Download the forecasted results as a CSV file using the provided download button.\n\n### Project Structure\n\ntime-series-forecasting-app/\n│\n├── app.py # Main Streamlit application file\n├── lstm_model.h5 # Pre-trained LSTM model (if applicable)\n├── scaler.pkl # Preprocessing scaler for LSTM model (if applicable)\n├── requirements.txt # List of required Python packages\n└── README.md # Project documentation (this file)\n\n### Contributing\n\nContributions are welcome! If you have suggestions, bug fixes, or improvements, please open an issue or submit a pull request. Follow these steps:\n\n- Fork the repository.\n- Create a new branch: git checkout -b feature/YourFeatureName\n- Commit your changes: git commit -am 'Add some feature'\n- Push to the branch: git push origin feature/YourFeatureName\n- Open a pull request.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhasanulmukit%2Ftime-series-forecasting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhasanulmukit%2Ftime-series-forecasting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhasanulmukit%2Ftime-series-forecasting/lists"}