# Avk331 - Machine Learning Pathway

**URL:** <http://staging.stemaway.com/t/avk331-machine-learning-pathway/6577>\
**Category:** Machine Learning Pipeline (NLP)Self-Assessments\
**Created:** [September 6, 2020, 1:50pm UTC](http://staging.stemaway.com/t/avk331-machine-learning-pathway/6577 "2020-09-06T13:50:41Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![avk331](https://d3rzmptxz7fqzy.cloudfront.net/letter_avatar_proxy/v4/letter/a/c38d9e/32.png) [@avk331](http://staging.stemaway.com/u/avk331)\
**Post date:** [September 6, 2020, 1:50pm UTC](http://staging.stemaway.com/t/avk331-machine-learning-pathway/6577/1 "2020-09-06T13:50:41Z")

</div>

**NAME:** Ananya Veerendra Kumar (avk331)

**TEAM:** Machine Learning July Team 6

**The things I learned during this internship:**

Technical Areas:

- Web Scraping
- Web driving
- Data pre-processing and augmentation
- Natural Language Processing Algorithms
  - Bag of Words
  - TF-IDF Vectorization
  - BERT
  - DistilBERT

- Machine Learning Classification Models
  - Decision Trees
  - Random Forest Classifier
  - k-NN
  - Logistic Regression

Tools Used:

- Jupyter Notebook (Python)
- Github
- Google Colab
- Slack
- Asana (Project Management)

**Achievements:**

I learnt to perform webscraping on large datasets from the StackOverflow forum using BeautifulSoup and Selenimum libraries and extracted the text and the metadata from each of the posts. I performed the data cleaning steps like removing the stop words and implementing tokenization, lemmatization and stemming. I implemented a BERT model to build a general-purpose text feature extractor. Then used a k-NN classification model to find topics which are similar to the given query. Thus, developed a topic recommendation system which suggests similar topics.

**Meetings Attended:**  
Attended all team meetings
