GitHunt
AN

anjaliy11/NLP_

💬 A hands-on collection of Jupyter notebooks exploring essential Natural Language Processing (NLP) concepts including tokenization, stop words, Bag of Words, TF-IDF, POS tagging, NER, SpaCy pipelines, stemming, lemmatization, and word embeddings with FastText and Gensim.

fasttext-embeddingsgensimmachine-learningnamed-entity-recognitionnlppythonspacy-pipelinestemming-and-lemmatizationtext-classificationword2vecwordvectors

NLP_

🧠 Natural Language Processing Concepts – Notebook Implementations

This repository is a curated collection of Jupyter notebooks demonstrating foundational and intermediate Natural Language Processing (NLP) concepts using real-world libraries such as SpaCy, NLTK, Scikit-learn, Gensim, and FastText.

The notebooks are structured to support learning, experimentation, and practical application of key NLP building blocks including tokenization, POS tagging, NER, embeddings, and text classification.

📌 Contents

Notebook Description
tokenizer.ipynb Introduction to tokenization using SpaCy
stop_words.ipynb Removing stop words from text
Bag_Of_Words.ipynb Building Bag-of-Words representations
bag_of_n_grams.ipynb N-gram generation and vectorization
tf-IDF.ipynb Computing TF-IDF vectors using Scikit-learn
stemming&lemmatization.ipynb Stemming and Lemmatization comparison (NLTK vs SpaCy)
POS_tagging.ipynb Part-of-Speech tagging using SpaCy
NER.ipynb Named Entity Recognition with SpaCy
spacy.ipynb Overview of core SpaCy functionalities
spacy_lang_processing_pipeline.ipynb Constructing custom NLP pipelines in SpaCy
fasttext_classification.ipynb Text classification using FastText word embeddings
gensim_word_vectors_text_classification.ipynb Word2Vec embedding-based classification using Gensim
news_clasification_spacy_word_vectors.ipynb News text classification using SpaCy word vectors

🛠️ Technologies

  • Python 3.8+
  • Jupyter Notebook
  • SpaCy
  • NLTK
  • Scikit-learn
  • Gensim
  • FastText (via Gensim or Facebook)

🧪 Getting Started

1. Clone the repository

git clone https://github.com/anjaliy11/NLP_.git
cd NLP_

2. Create a virtual environment (optional but recommended)
python -m venv venv
source venv/bin/activate        # Windows: venv\Scripts\activate

3. Install dependencies
pip install -r requirements.txt

4. Run Jupyter
jupyter notebook
---

## 📦 Dependencies
spacy
nltk
gensim
scikit-learn
matplotlib
jupyter
Then run:
python -m spacy download en_core_web_sm

---

 ## 🎯 Use Cases
💡 Education and training on NLP fundamentals

🔍 Rapid prototyping of NLP preprocessing pipelines

📊 Experimentation with vectorization and classification techniques

🤖 Baseline development for text classification tasks

Languages

Jupyter Notebook100.0%

Contributors

AN
Created July 28, 2025
Updated July 28, 2025