Machine Learning Level 1 Module 2 : Vishnupriya Kanuri

Technical Areas Worked on :

  1. Scrapped (and cleaned) the data using BeautifulSoup and Selenium and stored it in csv file

  2. Learnt to navigate Jupyter notebook environment to perform the above task

  3. Used pandas and matplotlib libraries for data analysis and visualization


  • Jupyter Notebook
  • Selenium WebDriver

Soft Skills

  • Developed an understanding of what data to choose and what to discard
  • Practiced adaptability to different libraries

Three Achievement Highlights

  1. Scraped and cleaned data using BeautifulSoup and Selenium
  2. Converted it into a csv file and analysed data using pandas library
  3. Performed EDA using matplotlib
  4. Did some additional research on different ML models that could be used

Detailed Statement of Tasks

  • Scraped the tapas platform ‘Do you create music for your own comics’: Analysed the HTML tags and attributes and scraped data to get some relevant textual information.

Performed Data Visualization: Used pandas to store it into csv file and did some additional cleaning (removing missing values etc) and used Matplotlib to analyse some parameters such as histogram charts of the frequency of the word ‘music’, frequency of the word ‘yes’ and frequency of the word ‘no’ to get a general sense of direction about where the conversation on the platform is going