|
Download README.md from neelnsoni13/genderverification: direct link, hf CLI and curl.
- Browser
- Download file 3.76 kB
-
https://huggingface.co/neelnsoni13/genderverification/resolve/main/README.md
- Command line
-
hf download hf://neelnsoni13/genderverification/README.md
-
curl -L -o README.md https://huggingface.co/neelnsoni13/genderverification/resolve/main/README.md
3.76 kB
| license: mit | |
| ## πΈ **Application Screenshot** | |
| ## <a href="https://ibb.co/JjhspDnr"><img src="https://i.ibb.co/ZzZMgqdc/Screenshot-2025-02-11-231313.png" alt="Screenshot-2025-02-11-231313" border="0" /></a> | |
| ## π **How It Works (End-to-End)** | |
| ### 1. **Data Preparation** | |
| - The dataset `gender.xlsx` contains names and their corresponding genders (Male/Female). | |
| - The `Gender` column is mapped to numerical values: | |
| - **Male (M)** is mapped to `1` | |
| - **Female (F)** is mapped to `0` | |
| ### 2. **Feature Extraction (TF-IDF Vectorization)** | |
| - The names are converted to **TF-IDF vectors** using character n-grams (1 to 3 characters). | |
| - This helps the model learn important patterns in names. | |
| ### 3. **Model Training** | |
| - A **Neural Network** is built using **Keras Sequential API**: | |
| - Dense layers with **ReLU activation** | |
| - **Batch Normalization** and **Dropout layers** to prevent overfitting | |
| - Output layer with **Sigmoid activation** for binary classification | |
| - The model is trained with **callbacks** like early stopping and learning rate reduction. | |
| ### 4. **Saving the Model and Vectorizer** | |
| - The trained model is saved as `gender_prediction_model_Improve.h5` | |
| - The TF-IDF vectorizer is saved as `tfidf_vectorizer_Improve.joblib` | |
| ### 5. **Streamlit Application** | |
| - Loads the pre-trained model and vectorizer. | |
| - Accepts user input (name) and predicts gender. | |
| - Displays the predicted gender in a clean UI. | |
| --- | |
| ## π **Project File Structure** | |
| ``` | |
| . | |
| βββ TrainImprove.py # Training script for the model | |
| βββ ml-st1.py # Streamlit app for gender prediction | |
| βββ gender.xlsx # Dataset with names and gender | |
| βββ gender_prediction_model_Improve.h5 # Saved Keras model | |
| βββ tfidf_vectorizer_Improve.joblib # Saved TF-IDF vectorizer | |
| βββ screenshot.png # Screenshot of the app UI | |
| ``` | |
| --- | |
| ## π **How to Run the Project** | |
| ### 1. **Clone the Repository** | |
| ```bash | |
| $ git clone <repository-url> | |
| $ cd <repository-folder> | |
| ``` | |
| ### 2. **Install Dependencies** | |
| ```bash | |
| $ pip install -r requirements.txt | |
| ``` | |
| ### 3. **Train the Model (Optional)** | |
| If you want to retrain the model, run the training script: | |
| ```bash | |
| $ python TrainImprove.py | |
| ``` | |
| ### 4. **Run the Streamlit Application** | |
| ```bash | |
| $ python -m streamlit run ml-st.py | |
| ``` | |
| ### 5. **Access the App** | |
| Open your browser and go to: [http://localhost:8501](http://localhost:8501) | |
| --- | |
| ## π‘ **How the Code Works** | |
| ### **Training (TrainImprove.py)** | |
| 1. **Data Loading:** Reads the dataset from `gender.xlsx`. | |
| 2. **Preprocessing:** Converts names to TF-IDF vectors. | |
| 3. **Model Building:** Defines a neural network with regularization. | |
| 4. **Model Training:** Trains the model with early stopping. | |
| 5. **Saving Artifacts:** Stores the trained model (`.h5`) and vectorizer (`.joblib`). | |
| ### **Application (final.py)** | |
| 1. **Load Model and Vectorizer:** Loads the pre-trained model and TF-IDF vectorizer. | |
| 2. **User Input:** Accepts a name input from the user. | |
| 3. **Prediction:** Transforms the name using TF-IDF and makes a prediction. | |
| 4. **Output:** Displays the predicted gender (Male/Female) in the app. | |
| --- | |
| ## π¦ **Dependencies** | |
| - Python 3.x | |
| - TensorFlow | |
| - Scikit-learn | |
| - Pandas | |
| - Streamlit | |
| Install them using: | |
| ```bash | |
| $ pip install tensorflow scikit-learn pandas streamlit joblib | |
| ``` | |
| --- | |
| ## π¨ **Future Enhancements** | |
| - Improve the UI design. | |
| - Include more diverse datasets for better generalization. | |
| - Add confidence scores for predictions. | |
| - Deploy the app online for public access. | |
| --- | |
| ## π€ **Contributing** | |
| Feel free to fork the project and submit a pull request for improvements. | |
| --- | |
| ## π **License** | |
| This project is licensed under the MIT License. | |
| </html> |