ChrisPark - Machine Learning (Level 1) Pathway

Certificates Summer 2021 Certificates Machine Learning Pipeline (NLP) (CE) 2021
,
1

Level 1 - Module 3

Things that I learned

Technical Area:

  • Organized the data in an ordered set by using pandas.

  • Used pandas to clean the data and call the saved csv file that contained the data.

  • Used matplotlib.pyplot to graph and visualize the data.

  • Understood the basic mechanics of the recommender system.

Tools:

  • Pandas

  • CSV

  • NumPy

  • Jupyter Notebook

  • matplotlib.pyplot

  • Git / GitHub

Soft Skills:

  • Learned the basics of pandas and how to use it

  • Gained experience with the basic recommender system

  • Learned how to use matplotlib.pyplot and graph the data

Achievements:

  • Successfully cleaned the data and graphed it in a bar chart

  • Gathered the Data that I needed and visualized it in a table

  • Categorized the topics and determined the the Category that has the most topics by graphing it with matplotlib.pyplot

  • Removed special characters from data

  • Successfully visualized the data in various types of graphs and charts

Tasks Completed:

  • Explored the data I Scraped and Graphed

  • Read and watched the tutorials and online videos

  • Created a basic recommender system

3

Level 1 - Module 2

Things that I learned

Technical Area:

  • Learned how to use Beautiful Soup in python
  • Learned how to look at website’s source
  • Learned how Python works
  • Learned how to Web Scrape

Soft Skills:

  • Learned what to look for while looking at a website’s source code.
  • Learned what data should be scraped from the website
  • Learned how Websites are structured
  • Got familiar with Anaconda and my computer’s command prompt

Achievements:

  • Successfully scraped data from one of the forums provided
  • Successfully scraped data from a simpler website
  • Found the elements that I was looking for in the html and converted them into text
  • Cleaned the data by getting rid of the html
  • Organized the data and labled each data that was scraped.
  • Understood how Web scraping worked
  • Understood how the find and find all method worked in beautiful soap 4

Tasks Completed:

  • Scraped one of the forums provided in Stem away
  • Read the tutorial for Web scraping 3 ~ 4 times
  • Explored my data after gathering it and analyzed it
  • Performed basic cleaning to remove html tags from data

Struggles:

  • Had trouble cleaning the data, I used the .text.strip() method just like the tutorial, but it would not print out anything. It printed out the numbers of views and replies in each post but It did not print the title and url(leaved a blank space).
  • I struggled because I never worked with python. I never had any experience in web scraping or anything of the kind, but I figured out by watching many youtube tutorials and the tutorials provided by Stem Away
4

Level 1 - Module 1

Things that I learned

Technical Area:

  • Learned basic Machine learning concepts
  • Learned about beautiful soap
  • Learned how to Web Scrape
  • Learned how to use Git and Git hub

Soft Skills:

  • learned how to code Python
  • learned how to code with Git hub

Achievements:

  • Downloaded Beautiful soap
  • Watched the demo and tutorial provided by Stem away
  • Got a better understanding in python

Tasks Completed:

  • Finished watching all the tutorials and demos
  • Tried to scrape a webpage
  • Installed Beautiful Soap 4 and requests(Libraries needed for web scraping)
5

Level 1 Module 4

Things that I learned

Technical Area:

  • learned how to use simple transformers to train the BERT model
  • learned how to compare an advanced model and a simple ML model by its performance
  • learned how to use Machine Learning to build and dockerize my ML app

Tools:

  • VS code
  • Simple transformers
  • Advanced model(BERT)
  • Simple ML model (Logistic Regression)

Soft Skills:

  • Learned how to train ML models
  • Learned how to use Simple transformers
  • Learned how to deploy flask

Achievements:

  • Trained logistic regression model
  • Successfully trained Bert and xlnet model
  • Cleaned the data set and combined the Bert model with the Logistic regression model