lenaromanenko / lyrics_classification Goto Github PK

The goal of the project is to build a text classification model on song lyrics and predict the artist from a piece of text.

Let's copy a piece of text from Frank Sinatra's famous song from a website and check whether the model can predict the singer right.

Result: With a probability of 97%, the model predicts that the singer of the chosen song is Frank Sinatra! 👏

See more results here.

1. Choosing some artists from MetroLyrics.
2. Web Scraping: downloading the URLs of all songs of chosen artists and getting song lyrics using Requests module, RegEx, and BeautifulSoup.
3. Constructing text corpus (a list of strings) and labels.
4. Cleaning the text with the help of Natural Language Toolkit (NLTK) or spaCy. There are both text cleaning methods for NLP in the classification_model.py.
5. Converting a text corpus into a numerical matrix using Bag of Words method (BoW).
6. Normalizing the counts with the Term Frequency and the Inverse Document Frequency (TF-IDF).
7. Applying Naive Bayes algorithm for multinomially distributed data (MultinomialNB). Putting TF-IDF and MultinomialNB in a pipeline.
8. Exporting the code from Jupyter to a Python file and сreating a pipeline for building a CLI.
9. Creating Word Cloud with the most frequent words in songs of chosen artists: