SNP Class Materials

1. Comparing Uni And Bi-directional LSTM with GRU (ipynb)

   • Same as Tensorflow Notebook
   • Models: LSTM, BiLSTM, GRU
   • Training and Validation Loss Plots
   • Optimized Code

2. Sentiment Analysis With Deep Learning Using TensorFlow (html)

   • Directories, Viewing Samples, Preprocessing
   • Custom Text Vectorization
   • CNN Model Creation Training & Compilation

3. Sentiment Analysis and Classification of Disaster Tweets (ipynb)

   • EDA
   • Cleansing, Handling Abbreviations
   • Models: Naive Bayes, Logistic, SVC, Decision Tree, Random Forest, MLP, Gradient Boosting, LightGBM

4. Practical 1: NLTK And Text Processing (ipynb)

   • RegEx
   • NLTK, POS Tagging

5. Practical 2: SpaCy And Named Entity Recognition (ipynb)

   • POS Tagging, Phrase Matcher
   • NER, Visualisations, Sentence Segmentation

6. Practical 7: RAKE And YAKE (ipynb)

   • RAKE
   • YAKE link

7. Practicals: Causal Attention Masks (ipynb)

   • Causal Attention Mask

8. Topic Modelling Using SkLearn (ipynb)

   • Latent Semantic Analysis
   • Latent Dirichlet Allocation
   • Wordcloud

9. Sentiment Analysis On Amazon Reviews (html)

   • TF
   • VADER
   • TFIDF, CountVectorizer, N-grams
   • Models: Multinomial NB, Logistic, SVM, Decision Tree, Random Forest
   • Hyperparameter Tuning

10. Word2Vec On News Headlines (ipynb)

    • EDA
    • Theory
    • Model

11. M1 & M2

12. Text Analytics 101 — Word Cloud and Sentiment Analysis

13. https://drive.google.com/drive/u/0/folders/1TVVOaiI05nz5tFKYax2kb-VRteiogmYI

NOTE: HTML FILES HAVE TO BE DOWNLOADED AND OPENED IN CHROME SEPARATELY TO SEE THE WHOLE NOTEBOOK.

NLP Lecture 2

• Tokenization, Stemming, Lemmatization, POS Tagging, Conditional Random Fields, WordNet, Word Sense Disambiguation, Query Expansion

NLP Lecture 3

• WordNet, Psycholinguistical Theory, Lexical Matrix, Sense Disambiguation, Sense Tagging, WSD, Query Expansion

SVD

• Introduction, Math, Measures, Calculations, Lowest-k Approximations, Example, Observation & Inference, Conclusion

Topic Modelling

• Introduction, LDA, Gibbs Sampling