https://github.com/r-mahesh45/resume-text-classification-and-data-visualization
ð Text Classification for Resumes: Conducted Exploratory Data Analysis (EDA) on a vast collection of resumes ð. Organized the data using Bag of Words (BoW) and TF-IDF techniques ð§ . Built and evaluated multiple models, with Logistic Regression delivering standout performance ðŊ. Created Word Clouds ðĨïļ and Histograms ð to visualize document wor
https://github.com/r-mahesh45/resume-text-classification-and-data-visualization
data datacleaning extract-transform-load feature-extraction nlp nltk-tokenizer text-mining text-processing
Last synced: 8 months ago
JSON representation
ð Text Classification for Resumes: Conducted Exploratory Data Analysis (EDA) on a vast collection of resumes ð. Organized the data using Bag of Words (BoW) and TF-IDF techniques ð§ . Built and evaluated multiple models, with Logistic Regression delivering standout performance ðŊ. Created Word Clouds ðĨïļ and Histograms ð to visualize document wor
- Host: GitHub
- URL: https://github.com/r-mahesh45/resume-text-classification-and-data-visualization
- Owner: R-Mahesh45
- Created: 2024-06-15T06:21:03.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-03T21:53:27.000Z (10 months ago)
- Last Synced: 2024-12-03T22:29:30.148Z (10 months ago)
- Topics: data, datacleaning, extract-transform-load, feature-extraction, nlp, nltk-tokenizer, text-mining, text-processing
- Language: Jupyter Notebook
- Homepage:
- Size: 10.5 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
---
# ð **Resume Classification Application**
### ð ïļ Developed By: **Mahesh Rathod**
Welcome to the **Resume Classification Application**, an intelligent tool for analyzing resumes and predicting job profiles with skill extraction! ð---
## ðŊ **Features**
- ð **Upload resumes**: Accepts multiple file types (`.pdf` and `.docx`).
- ð§ **Skill Extraction**: Automatically extracts relevant skills from resumes.
- ð **Job Profile Prediction**: Uses machine learning models to classify resumes into job profiles.
- ð **Interactive Interface**: Built with **Streamlit** for easy interaction.---
## ð **How It Works**
1. **Upload**: Drag and drop your resume(s) in `.pdf` or `.docx` format.
2. **Processing**:
- The application preprocesses the resume text.
- Skills are extracted, and the text is classified using a trained ML model.
3. **Output**:
- Displays uploaded file details.
- Shows extracted skills and the predicted job profile in a clean table format.---
## ð ïļ **Libraries Used**
This application uses several powerful libraries for text processing and machine learning:- **Text Processing**:
- `nltk` ðŠķ
- `spaCy` ð
- `docx2txt` ð
- `pdfplumber` ð
- **Data Handling**:
- `pandas` ð
- `numpy` ðĒ
- **Machine Learning**:
- `sklearn` ðĪ
- `pickle` ðĶ
- **Visualization**:
- `matplotlib` ð## ðĶ **Installation**
1. Clone the repository:
```bash
git clone
cd
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Run the application:
```bash
streamlit run app.py
```---
## ðĄïļ **Security Measures**
- Handles sensitive resume data securely.
- Ensures no data is stored locally after processing.
---## ð **Future Enhancements**
- ðĪ Integrate support for more file formats.
- ð Deploy the application online for global access.
- ð Improve classification accuracy with deep learning models.
- ð Add multi-language resume processing.---
## ð§ **Contact Us**
For any queries or contributions, feel free to reach out:
**Email**: `maheshrathod2236@gmail.com`