# Tupham - Machine Learning (Level 1) Pathway

**URL:** <https://stemaway.com/t/tupham-machine-learning-level-1-pathway/8812>\
**Category:** Machine Learning Pipeline (NLP) (CE) 2021\
**Created:** [July 9, 2021, 11:35pm UTC](https://stemaway.com/t/tupham-machine-learning-level-1-pathway/8812 "2021-07-09T23:35:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![tupham](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/t/c38d9e/32.png) [@tupham](https://stemaway.com/u/tupham)\
**Post date:** [July 9, 2021, 11:35pm UTC](https://stemaway.com/t/tupham-machine-learning-level-1-pathway/8812/1 "2021-07-09T23:35:40Z")

</div>

Module 1 Self-Assessment

**Technical Area:**

- Familiarized myself with the basic understanding of Machine learning and NLP
- Learned how web scraping is achieved by using Beautiful Soup
- Reviewed basic knowledge of Python through the book “Automate the Boring Stuff with Python” and practiced with HackerRank
- Reviewed basic Linear algebra and calculus from Udemy courses

**Tools/Libraries:**

- Python, Pycharm
- Jupyter Notebook
- BeautifulSoup, Pandas
- Visual Studio Code
- Git/GitHub

**Soft Skills:**

- Learned project management tools like Jira, GSuite to communicate with teammates

**Achievement Highlights:**

- Followed online tutorials and attempted to scrape data from a school website with Python & BeautifulSoup
- Navigated through Discourse forums in order to get familiar with the platform.

**Tasks:**

- Downloaded multiple tools and libraries
- Watched the NLP Basics webinars and get familiar with ML concepts and a typical ML project workflow

---

<div class="post-metadata">

**Author:** ![tupham](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/t/c38d9e/32.png) [@tupham](https://stemaway.com/u/tupham)\
**Post date:** [July 24, 2021, 6:40am UTC](https://stemaway.com/t/tupham-machine-learning-level-1-pathway/8812/2 "2021-07-24T06:40:03Z")

</div>

**Module 2 Self-Assessment: Weeks 3 & 4**

Overview of Things Learned:

**Technical Area:**

- Chose a Discourse platform with our team → Pytorch community

- Learned how to use selenium webdriver from the resources provided by teammates

- Familiarized myself with minimal knowledge about HTML as applied to web scraping

- Practiced to scrape data from the forum and extract elements such as category, topics, etc.

**Tools:**

- VSCode

- Python, HTML

- Jupyter Notebooks

- BeautifulSoup, Selenium, Requests

- GitHub

**Soft Skills:**

- Communicate with teammates on Discord and attended all team meetings

**Achievement Highlights:**

- Learned how to scrape the data from the Pytorch forum with the help of code examples from Sara

- Was able to scrape the data using BeautifulSoup, Requests library and stored it in a csv file

- Performed basic EDA and data cleaning

**Upcoming Goals:**

- Push the module 2 code to the team GitHub

- Start learning with resources from Module 3