https://github.com/nav3005/dl-2-section-1
Project to implement Creation and Extraction of Datasets and summarize those Datasets using Python Libraries such as NLTK, Gensim, Pandas
https://github.com/nav3005/dl-2-section-1
Last synced: about 1 year ago
JSON representation
Project to implement Creation and Extraction of Datasets and summarize those Datasets using Python Libraries such as NLTK, Gensim, Pandas
- Host: GitHub
- URL: https://github.com/nav3005/dl-2-section-1
- Owner: Nav3005
- Created: 2024-09-08T12:32:35.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-08T14:32:55.000Z (almost 2 years ago)
- Last Synced: 2024-12-27T12:27:02.533Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 17.6 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Blog Generation Project
## Section 1: Introduction and Dataset Creation
## Overview
This section is the first part of the DL-2 project, aimed at creating a dataset and fine-tuning a model to generate blog content from given summaries. It builds on concepts from DL Part 1 but can be followed independently.
## Key Components
1. **Dataset Creation:** We create a dataset using the Medium Articles dataset from Kaggle, which includes titles, summaries, and full content of articles.
2. **Extractive Summarization:** We use NLTK and Gensim to generate summaries by selecting the most important sentences from the articles.
3. **Implementation:** Code snippets are provided to help generate summaries and save them into a CSV file.
## How to Use
1. Download the Medium Articles dataset from Kaggle.
2. Follow the steps to generate summaries using the provided Python code.
3. Save the summaries and corresponding articles into a CSV file for use in the next section.
## Requirements
- Python 3.x
- NLTK
- Gensim
- Pandas
- Kaggle API key