/nlp-in-practice

Starter code to solve real world text data problems. Includes: Gensim Word2Vec, phrase embeddings, Text Classification with Logistic Regression, word count with pyspark, simple text preprocessing, pre-trained embeddings and more.

Primary LanguageJupyter Notebook

NLP-IN-PRACTICE

Use these NLP, Text Mining and Machine Learning code samples and tools to solve real world text data problems.

Notebooks / Source

Links in the first column take you to the subfolder/repository with the source code.

Task Related Article Source Type Description
Large Scale Phrase Extraction phrase2vec article python script Extract phrases for large amounts of data using PySpark. Annotate text using these phrases or use the phrases for other downstream tasks.
Word Cloud for Jupyter Notebook and Python Web Apps word_cloud article python script + notebook Visualize top keywords using word counts or tfidf
Gensim Word2Vec (with dataset) word2vec article notebook How to work correctly with Word2Vec to get desired results
Reading files and word count with Spark spark article python script How to read files of different formats using PySpark with a word count example
Extracting Keywords with TF-IDF and SKLearn (with dataset) tfidf article notebook How to extract interesting keywords from text using TF-IDF and Python's SKLEARN
Text Preprocessing text preprocessing article notebook A few code snippets on how to perform text preprocessing. Includes stemming, noise removal, lemmatization and stop word removal.
TFIDFTransformer vs. TFIDFVectorizer tfidftransformer and tfidfvectorizer usage article notebook How to use TFIDFTransformer and TFIDFVectorizer correctly and the difference between the two and what to use when.
Accessing Pre-trained Word Embeddings with Gensim Pre-trained word embeddings article notebook How to access pre-trained GloVe and Word2Vec Embeddings using Gensim and an example of how these embeddings can be leveraged for text similarity
Text Classification in Python (with news dataset) Text classification with Logistic Regression article notebook Get started with text classification. Learn how to build and evaluate a text classifier for news classification using Logistic Regression.
CountVectorizer Usage Examples How to Correctly Use CountVectorizer? An In-Depth Look article notebook Learn how to maximize the use of CountVectorizer such that you are not just computing counts of words, but also preprocessing your text data appropriately as well as extracting additional features from your text dataset.
HashingVectorizer Examples HashingVectorizer Vs. CountVectorizer article notebook Learn the differences between HashingVectorizer and CountVectorizer and when to use which.
CBOW vs. SkipGram Word2Vec: A Comparison Between CBOW, SkipGram & SkipGramSI article notebook A quick comparison of the three embeddings architecture.

Notes

Contact

This repository is maintained by Kavita Ganesan. Connect with me on LinkedIn or Twitter.