dipanjanS/text-analytics-with-python

Implements end-to-end NLP pipelines using industry-standard libraries (NLTK, spaCy, Gensim, scikit-learn, Keras, TensorFlow) for tasks ranging from tokenization and feature engineering to topic modeling and deep learning-based embeddings. Covers both classical statistical approaches and modern neural architectures, including transfer learning and supervised/unsupervised sentiment analysis with real-world case studies on movie recommendations and NIPS paper analysis. All code examples are Python 3.x compatible with accompanying datasets and Jupyter notebooks illustrating practical NLP workflows.

1,690 stars. No commits in the last 6 months.