# Cwong4000 - Machine Learning Pathway

**URL:** <https://stemaway.com/t/cwong4000-machine-learning-pathway/5487>\
**Category:** Machine Learning Pipeline (NLP)Self-Assessments\
**Created:** [August 4, 2020, 12:34am UTC](https://stemaway.com/t/cwong4000-machine-learning-pathway/5487 "2020-08-04T00:34:57Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![cwong4000](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/c/afd275/32.png) [@cwong4000](https://stemaway.com/u/cwong4000)\
**Post date:** [August 4, 2020, 12:34am UTC](https://stemaway.com/t/cwong4000-machine-learning-pathway/5487/1 "2020-08-04T00:34:57Z")

</div>

Week 1 and 2  
**Concise overview of things learned. Break it up into Technical Area, Tools, Soft Skills**  
_Technical Area:_ Worked on webscraping, learned about data annotation tools  
_Tools:_ Selenium, Python, Data Annotation software  
_Soft Skills:_ Team communication

**Three achievement highlights**  
Researched about LightTag text annotation software, worked on creating a webscraper, learned more about data annotation.

**List of meetings/ training attended including social team events**  
All team meetings thus far.

**Goals for the upcoming week**  
Finish collecting data using the webscraper, possibly work on training classification model.

**Detailed statement of tasks done. State each task, hurdles faced if any and how you solved the hurdle. You need to clearly mark whether the hurdles were solved with the help of training webinars, some help from project leads or significant help from project leads.**  
I did research on the text annotation software LightTag and wrote a report about it, detailing its features and functions. Not much difficulty here, but I used the sample report provided by leads as a guide for my report.  
I worked on making a webscraper for the AI stackexchange forum. It will work for smaller sets of data, but working on trying to get the scraper to work without getting blocked by the website for larger data sets. I used the colab shared by team leads to aid in writing the code for the webscraper. Will work to finish soon and collect the required data.

---

<div class="post-metadata">

**Author:** ![cwong4000](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/c/afd275/32.png) [@cwong4000](https://stemaway.com/u/cwong4000)\
**Post date:** [August 17, 2020, 5:10am UTC](https://stemaway.com/t/cwong4000-machine-learning-pathway/5487/2 "2020-08-17T05:10:32Z")

</div>

Week 3  
**Concise overview of things learned. Break it up into Technical Area, Tools, Soft Skills**  
_Technical Area:_ Worked on understanding and building a model  
_Tools:_ Word2Vec  
_Soft Skills:_ Team communication

**Achievement highlights**  
Finished collecting data with webscraper, worked on understanding and implementing Word2Vec Model.

**List of meetings/ training attended including social team events**  
All team meetings so far.

**Goals for the upcoming week**  
Implementing the model for the dataset collected as a team, and then working with the machine learning model.

**Detailed statement of tasks done. State each task, hurdles faced if any and how you solved the hurdle. You need to clearly mark whether the hurdles were solved with the help of training webinars, some help from project leads or significant help from project leads.**  
Finished collecting the required data. Not much hurdles faced but the code took a long time to run.  
Started working on the Word2Vec model using the Skip Gram method in a tutorial. Resources were given by the project leads to understand this better.