This course is intended to give learners and introduction to Natural Language Processing (NLP) and give them the skills they need to enter a Kaggle competition focusing on NLP.

The learners will be introduced to the Natural Language Tool Kit (NLTK), Spacy, and the sklearn machine learning library.

The course is broken down into three sections, being an introduction to NLP, practice projects, and lastly the chance to enter a Kaggle competition.

In the introductory section of this course, the leasrner will be introduced to:-

1. Natural Language Tool Kit (NLTK)

2. Tokenization

3. Frequency distribution

4. Stop words

5. Unigrams, bigrams, trigrams and ngrams

6. Stemming

7. Lemmatization

8. Part of speech tagging

9. Named entity recognition

10. Spacy

11. Chunking

12. Chinking

13. Machine learning

14. Deep learning

In the practice session of the course the learner will work on projects from the sklearn machine learning library, NLTK and spacy:-

1. Countvectorizer

2. Countvectorizer and TfIdfTransformer

3. Difference between vectorizers in sklearn

4. How to use feature hashers in sklearn

5. DictVectorizer

6. Cosine similarity

7. IMDBmovie reviews using NLTK

8. COV19 tweets using spacy and Kaggle Jupyter Notebook

In the final part of the course, Kaggle competition, the learner will be given the opportunity to enter a Kaggle competition:-

1. Disaster tweets competition using sklearn

2. Disaster tweets competition using spacy