# Uzoman-22 - Machine Learning Pathway

**URL:** <https://stemaway.com/t/uzoman-22-machine-learning-pathway/3447>\
**Category:** Machine Learning Pipeline (NLP) Self-Assessments\
**Created:** [June 16, 2020, 5:20am UTC](https://stemaway.com/t/uzoman-22-machine-learning-pathway/3447 "2020-06-16T05:20:47Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![uzoman-22](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/u/e8a87c/32.png) [@uzoman-22](https://stemaway.com/u/uzoman-22)\
**Post date:** [June 16, 2020, 5:20am UTC](https://stemaway.com/t/uzoman-22-machine-learning-pathway/3447/1 "2020-06-16T05:20:47Z")

</div>

Tues 6/16 Assessment  
Technical Area Learned: Learned how to web scrape in Python, learned how to use Python on command line/terminal, learned how to use Juypter Notebook  
Tools: Specific tools used were BeautifulSoup package, also learned how to use web developer tools on web browsers  
Soft Skills: Communication, maintaining deadlines, general team building

The first achievement I had was learning how to understand web scraping. The second achievement was trying to get the contents from web scraping into a pandas DataFrame. Third achievement is succesfully doing a Juypter Notebook, as I had never really done it before.

Goals for me are to update my dataframe to include contents inside a post, as right now my dataframe only contains topics, tags and url. I would like to do some data cleaning and maybe EDA if time allows, and then learn about NLP and apply it to the dataset.

The main task I did was web scraping. I first had to watch and read lot to understand the general process of web scraping. There were many places to go to learn, and each had different styles, but I eventually settled on mainly using the Python requests package and Beautiful Soup. I was able to get the topic, url, and tags from the website my team chose to scrape, but as I stated, I would like to try and get more early on in the week. I then created a pandas DataFrame out of the columns.

Meetings attended:  
6/8 Weekly Meeting  
6/15 Weekly Meeting  
I also attended many preliminary meetings before teams were assigned

---

<div class="post-metadata">

**Author:** ![uzoman-22](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/u/e8a87c/32.png) [@uzoman-22](https://stemaway.com/u/uzoman-22)\
**Post date:** [June 29, 2020, 8:23pm UTC](https://stemaway.com/t/uzoman-22-machine-learning-pathway/3447/2 "2020-06-29T20:23:58Z")

</div>

Fri 6/26 Assessment  
Technical Area Learned: Learned more about web scraping  
Tools: Specific tools used were BeautifulSoup package  
Soft Skills: Working from behind a deadline

Main achievement was to finish web scraping.

Goals for me are to finish data cleaning and explore text classification

The main task I did was to try and get the text from each post. I at first tried to separate the replies and the main post into different columns, but I could not do this so I had to combine all the text into one column. I don’t know if this will backfire because I’m not completely sure of the text classification process  
Meetings attended:  
6/22 Weekly Meeting  
6/29 Weekly Meeting

---

<div class="post-metadata">

**Author:** ![uzoman-22](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/u/e8a87c/32.png) [@uzoman-22](https://stemaway.com/u/uzoman-22)\
**Post date:** [July 7, 2020, 5:13am UTC](https://stemaway.com/t/uzoman-22-machine-learning-pathway/3447/3 "2020-07-07T05:13:32Z")

</div>

Final Assessment  
Technical Area Learned: Clustering techniques and regex  
Tools: Specific tools used was sklearn  
Soft skills used: Reading and understanding other people’s code

My main achievement was to try to learn the recommendation part, as I didn’t have enough time to get through text classification. There are many methods to recommendation such as K nearest neighbors, neural nets, K means, principal component analysis, and hierarchical clustering.

Meetings attended:  
6/30 Meeting