Asylbaye - Machine Learning (Level 1) Pathway

Module 1 Self Assessment

Technical area

  • I watched the webinar about web crawling
  • I watched the webinar about git
  • I went over the word embeddings
  • I took some tutorial at google about machine learning

Tools:

  • I started by learning Jupiter notebooks and numpy, I also went over the basics of python. (I took programming classes in C++ before)
  • and learned the basics of beautiful soup
  • I read the articles about pytorch and colab

Soft-Skills

  • at first I was lost so I reached out to Sarah for help.
  • I also found out who are my team leads are and asked them where should I start
  • I joined the discord channel and introduced myself to my teammates

Achievements:

  • I grasped the basics of machine learning
  • I’ve finished the git tutorial and now I feel pretty comfortable with git
  • I implemented my own web scraper

Tasks completed:

  • the first module is all about learning, so I would say the tasks I completed would be that I went over all the links provided in the Module 1 and watched all the videos.
  • I also did my own research on the things that I have trouble with (like BERT)
1 Like

Week 3 and 4: 12th July 2021 Overview of Things Learned:

Technical Area:

  • Understood the logic behind recommender systems and ML algorithms
  • As a team we chose to scrape the Pytorch forum on DiscourseHub
  • Scraped the data from the posts on Pytorch forum
  • Did some basic data cleaning and analysis
  • Learned how HTML tags are organized
  • Learned what python virtual environment is, how to activate it, and why it is useful
  • Learned how to install python modules with pip
  • Learned how to run python code in Colab

Tools:

  • Google Colab
  • Jupyter Notebook
  • Command Line
  • Discord
  • Jira
  • Python Modules like: Pandas, Selenium Webdriver, BeautifulSoup, Requests Library, Re Python Library for Regular expressions
  • Github

Soft Skills:

  • Played fun games with my teammates in order to get to know them more, teambuilding
  • Asked my teammates a lot of questions
  • Learned how to find the information I need on google, especially stackoverflow

Achievements:

  • Did two tutorials on web scrapping and gained a general understanding of how web scraping is done.
  • Learned different data cleaning techniques like Lower Casing, Stemming, Lemmatization, Stopword removal, Normalization, Noise Removal
  • I’ve built my own WebCrawler

Tasks Completed

  • Accepted the invite to the git repo from my team
  • Followed the 2 tutorials that were provided to us on stem-away github page
  • Learned how to save scraped data into a csv file
  • Learned how to open a csv file in colab in order to process the data inside
  • Did basic data analysis and data cleaning on the data I gathered from the Pytorch forum

Meetings attended:

  • I attened the help session with Anubhav on July 22
  • Attended the Friday meeting with my teammates
  • Attended the Monday meeting with my teammates

Goals for the Upcoming Week:

  • Do the tutorials on module 3
  • Upload my work from module 2 to my team’s GitHub repo

Module 3 Self-Assessment Week 5 and 6 26th July 2021- 6th August 2021

Overview of things Learned:

Technical Area:

  • Followed module 3 tutorials
  • Data Cleaning Tools like Lowercasing and removing characters like [^0-9a-z #+_]
  • Data Modeling with Sklearn
  • Trained Basic Machine Learning models with tools like Naive Bayes , Linear SVM, Logistic Regression

Tools:

  • Pandas, numpy, gensim, nltk, sklearn, matplotlib

Soft Skills:

  • Communicating with my teammates about team presentation
  • I’ve attended all team meetings, which are every Friday
  • Time management, I keep track of all the hours I’ve spent doing internship

Goals for the Upcoming Week:

  • Deploy our app as a web application
  • Start on module 4

Self-Assessment for Module 4 Technical Area:

  • Learned about Docker and how to dockerize web apps
  • Advanced machine learning models like: BERT, RoBERTa, DistilBERT, XLNet
  • Followed the tutorials in module 4

Tools:

  • Jupyter Notebooks
  • pandas, sklearn, Simple Transformers, Tokenizers, Re, tarfile)
  • Discord
  • Docker
  • Github
  • Vscode

Soft Skills:

  • Communicated with teammates about final presentation
  • Attended weekly team meetings
  • Asked questions on Discord

Achievements:

  • Learned about machine learning algorithms and how to train them
  • Learned how to dockerize web apps
  • Completed all 4 modules