# Nicholas\_Miller - Machine Learning Pathway **URL:** \ **Category:** Machine Learning Pipeline (NLP) Self-Assessments\ **Created:** [June 16, 2020, 4:55pm UTC](https://stemaway.com/t/nicholas-miller-machine-learning-pathway/3478 "2020-06-16T16:55:31Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Nicholas\_Miller](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/n/e8a87c/32.png) [@Nicholas\_Miller](https://stemaway.com/u/Nicholas_Miller)\ **Post date:** [June 16, 2020, 4:55pm UTC](https://stemaway.com/t/nicholas-miller-machine-learning-pathway/3478/1 "2020-06-16T16:55:31Z")
**Concise overview of things learned. Break it up into Technical Area, Tools, Soft Skills:** _Technical_: I have learned how to use Selenium with Python to scrape a website and the Pandas library to format it. _Tools_: I have learned how to use organizational tools such as Asana, Slack, and GitHub. _Soft Skills_: I have gained soft skills in team communication and collaboration. **Three achievement highlights:** 1. Successfully scraped Amazon Sellers Form using Selenium. 2. Used Pandas to put scraped data into a dataframe. 3. Effectively collaborated with teammates on tasks. **List of meetings/ training attended including social team events** Team Meetings: 6/1, 6/2, 6/9, 6/13 Webinars: Git Webinar (6/5) Training Sessions: Python Training 1 (6/6) **Goals for the upcoming week. Next self-assessment will be due on the following Tuesday 06/23:** My goals for the next week are to learn about BERT and data cleaning as well as how we will use the data we have gathered to develop a training 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.** _Task 1:_ GSuite, Slack, Asana, and GitHub Setup - _Task 1 Hurdles:_ Complications with the GSuite account not being setup that were solved with the help of the project leads. _Task 2:_ Used selenium and pandas to scrape data from the Amazon Seller Form in the Amazon Custom category. - _Task 2 Hurdles:_ Had trouble selecting specific elements on the webpage. I was able to solve the problem by collaborating with my teammates and pondering on it. _Task 3:_ Exported the scraped data to a CSV file. - _Task 3 Hurdles:_ I was able to complete this task without any notable hurdles. ---
**Author:** ![Nicholas\_Miller](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/n/e8a87c/32.png) [@Nicholas\_Miller](https://stemaway.com/u/Nicholas_Miller)\ **Post date:** [August 4, 2020, 5:12am UTC](https://stemaway.com/t/nicholas-miller-machine-learning-pathway/3478/2 "2020-08-04T05:12:43Z")
**Concise overview of things learned. Break it up into Technical Area, Tools, Soft Skills:** _Technical_ : I learned about Natural Language Processing and the functioning of BERT _Tools_ : I learned DistilBERT and its functions _Soft Skills_ : I further enhanced my teamwork and communication skills **Three achievement highlights:** 1. Successfully gathered all our data and combined it. 2. Learned how to use BERT for NLP. 3. Effectively collaborated with teammates on tasks. **List of meetings/ training attended including social team events** Team Meetings: 6/16, 6/20 Training Sessions: Python Training 2 (6/16) **Goals for the upcoming week. Next self-assessment will be due on the following Tuesday 06/23:** My goals for the next week are to successfully apply DistilBERT to our data resulting in effective classification. **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.** _Task 1:_ Learn about BERT and DistilBERT as well as attempt implementation - _Task 1 Hurdles:_ The usage of BERT and how it worked were at first very confusing to me and entirely new concepts. I overcame this initial confusion by reviewing the recorded lesson and seeking external resources. ---
**Author:** ![Nicholas\_Miller](https://d2nat51eddc6b4.cloudfront.net/letter_avatar_proxy/v4/letter/n/e8a87c/32.png) [@Nicholas\_Miller](https://stemaway.com/u/Nicholas_Miller)\ **Post date:** [August 6, 2020, 8:54pm UTC](https://stemaway.com/t/nicholas-miller-machine-learning-pathway/3478/3 "2020-08-06T20:54:01Z")
**Full Session Assessment:** **Concise overview of things learned. Break it up into Technical Area, Tools, Soft Skills:** _Technical_: Throughout the full session, I have learned how to web scrape and process data as well as implement natural language processing using a pre-trained model and apply a classification model. _Tools_: - Slack - GitHub - Asana - Selenium WebDriver - Pandas Python Library - DistilBERT _Soft Skills_: The soft skills I developed and enhanced were effective communication and collaboration within a team. **Three achievement highlights:** 1. Successfully scraped Amazon Sellers Form using Selenium. 2. Used Pandas to format and process scraped data. 3. Learned and implement DistilBERT in conjunction with a classification model to classify the data. **List of meetings/ training attended including social team events** Team Meetings: 6/1 6/2, 6/9, 6/13, 6/16, 6/20, 6/27, 6/30 Training Sessions / Webinars: Git Webinar (6/5), Python Training 1 (6/6), Python Training 2 (6/16) **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.** _Task 1:_ GSuite, Slack, Asana, and GitHub Setup - _Task 1 Hurdles:_ Complications with the GSuite account not being setup that were solved with the help of the project leads. _Task 2:_ Used selenium and pandas to scrape data from the Amazon Seller Form in the Amazon Custom category. - _Task 2 Hurdles:_ Had trouble selecting specific elements on the webpage. I was able to solve the problem by collaborating with my teammates and pondering on it. _Task 3:_ Exported the scraped data to a CSV file. - _Task 3 Hurdles:_ I was able to complete this task without any notable hurdles. _Task 4:_ Learn about BERT and DistilBERT as well as attempt implementation - _Task 4 Hurdles:_ The usage of BERT and how it worked were at first very confusing to me and entirely new concepts. I overcame this initial confusion by reviewing the recorded lesson and seeking external resources.