In this project, I dip my toes into NLP by exploring the basic functionality of the nltk toolkit and IBM Tone Analyzer. Since I do not have much experience in NLP, I used this project to learn about tokenizing texts, stripping them of their stopwords, plotting the frequency of words in a text, and analyzing text via the IBM Tone Analyzer.

The program can be run via the command "python nlp_practice.py" in the terminal. The program will read two separate text files containing different texts, tokenize the texts, remove all English stopwords according to nltk.corpus, print the 20 most frequently used words (excluding stopwords), and analyze the two texts via the IBM Tone Analyzer. To run the program, please replace the api_key and url with your IBM credentials.