JiazhengXu - Machine Learning (Level 1) Pathway

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

Self-Assessment for first-week Machine learning module 1

Technical Area:

  1. Get familiar with the machine learning workflow, which contains the EDA, pre-processing data, apply learning algorithm to data, and evaluate the model.

  2. Go over the whole process for building a simple movie recommendation system with basic ML knowledge.

  3. Knowing some tech concepts such as Collaborative Filtering, Content-Based Filtering, and Word Embedding. Recall an ML algorithm Cosine Similarity which is a kind of KNN algorithm.

Tools: Install and run the sample code with Beautiful Soup, Selenium, Spacy, Sentence_transformers, and transformers libraries.

Soft Skills:

  1. Practice communication skills with teammates.

  2. Improve the notes management from separate webinars.

Three highlights:

  1. Setup all coding environments such as python library. I am not familiar with Python, so it makes me exciting.

  2. Think deeper into the Machine learning workflow and understand it. I have only learned some basic math knowledge and never experienced ML. Through Kunal and Sara’s video, I know exactly what I need to do in the ML process.

  3. Create a learning group and communicate with the teammates. It’s the first time I need to collaborate with others using English. Fortunately, I build an inspiring team atmosphere.

1 Like
2

Self-Assessment for first-week Machine learning module 2

Technical Area:

  1. Get familiar with web scraping and review the python coding.
  2. Review the DOM structure in HTML and locate them by codes.

Tools:

  1. Jupyter notebook
  2. PyCharm
  3. Develop tool in Chrome and Firefox
  4. Jira software

Soft Skills:

  1. Schedule the meeting time with other teammates.
  2. Host the team-building activities.

Achievement:

  1. Finish one tutorial’s homework to create a web scraper for the job information from indeed.com. Meet some technical difficulties for using python and solve them through the internet by myself.
  2. Solve the timeout problem, which could happen in some posts and lead the program to exit accidentally. Add the logging module in web scraping to trace the possible error.
  3. Successfully scrape all the posts from the PyTorch forum (50000+) and start the data cleaning process.
3

Self-Assessment for first-week Machine learning module 2

Technical Area:

  1. I am learning more python coding techniques through the tutorial.
  2. Deploy the web scraping program in the Google Cloud Platform.
  3. Knowing the different skills in processing textual data.

Tools:

  1. PyCharm
  2. Terminal
  3. Sublime(Handle CSV files)

Soft Skills:

  1. Develop communication skills with team members.
  2. Practice the time management strategy.

Achievement:

  1. Fix the bug in the scraping program and scrape all the data from the website.
  2. Finish the data cleaning process