Dive into a comprehensive 42-minute workshop on topic modeling in Python, combining Gensim, spaCy, NLTK, and other libraries. Learn to process NIPS papers through six key steps: data loading, preparation, exploratory analysis, modeling and tokenization, LDA model building, and evaluation. Master techniques like punctuation removal, word cloud creation, stop word elimination, bigram and trigram generation, lemmatization, and tokenization. Visualize topics and calculate coherence scores to assess model performance. Access the accompanying GitHub notebook for hands-on practice and follow along with detailed time stamps for each section of the tutorial.
Overview
Syllabus
- Tutorial Starts
- Topic Modeling Intro
- Workshop Environment
- Content location at GitHub
- Dataset used in this workshop
- LDA Intro
- Topic Modeling Use Cases
- 6 Steps in this Workshop
- Step 1: Loading Data
- Step 2: Data Preparation
- Step 2.1: Removing Punctuation
- Step 2.2: Removing digits and word with digits
- Step 2.3: Lowercase all context
- Step 3: EDA
- Step 3.1: Word Cloud
- Step 3.2: Document Term Matrix
- Step 4: Data Modeling
- Step 4.1: Stop words removal
- Step 4.2: Creating Bigram and Trigram
- Step 4.3: Lemmatization
- Step 4.4: Tokenization
- Step 5: LDA Topic Modeling
- Step 6: Topic Modeling Performance and analysis
- Step 6.1: Topic visualization
- Step 6.2: Coherence Score
- Saving notebook to GitHub
- Recap
Taught by
Prodramp
Related Courses
-
Text Data Preprocessing in Python
-
2025 Natural Language Processing in Python for Beginners
-
Natural Language Processing (NLP) in Python with 8 Projects
-
Introduction to NLP and Topic Modeling
-
Natural Language Processing Real World Use-cases in Python
-
Natural Language Processing with Deep NLP in Hindi-Urdu
