- Learned more about overview concepts of Machine learning and some machine learning algorithms by watching the lecture videos
- Learned about fundamental ideas about NLP and some networks like Vanilla Neural Networks, Recurrent Neural Networks (RNNS), and Long Short-Term Memory Networks (LSTM)
- Learned about web scraping and data mining
- Got a good overview of ML better from Kunal Singh’s video
- Understood application of ML better via sorting IMDB movie example.
- Got an idea about crawling, scraping, and NLP.
- Learn Python better
Achievements and tasks:
- Learned about concepts of Machine Learning and web scraping
- Got all of the required material installed (Python libraries, VS Code)
- Built virtual environment
- Learned a lot of new stuff about git and git-hub
- Scraping data using BeautifulSoup
- Cleaning the data
- Familiarized me with data preprocessing and data cleaning
- Learned how the requests library allows users to directly interact with HTML websites
- Used requests, Pandas, and BeautifulSoup to scrape data and then convert it into a CSV file
- Google Colab
- Python Libraries (BeautifulSoup, Pandas, Requests)
- Discourse (CarTalk Forum)
- Data preprocessing
- Successfully scraped the data from the CarTalk forum (on discourse)
- Convert data into CSV using the pandas library
- Understood how to use BeautifulSoup to scrape data
- Learned different concepts from Youtube videos and the resources on EDA, etc.
- Created a new Google Colab
- Scraped data from: CarTalk forum
- Converted data into a CSV file using pandas library
- Used Selenium Webdriver to scrape websites I found
- Used Pandas to play around with and clean/organize data
- Learned about basic recommender systems
- Learned how to better Google information to help me in my learning process
- Found videos and forums that helped improve my understanding of machine learning concepts and the tools I was using
- Downloaded and learned about Selenium’s purpose/uses, watched a few tutorials
- Created a basic recommender system, using cosine similarity
- Used different embeddings with machine learning models to see classification results of data
Tasks and Hurdles
- Made a simple recommender system using cosine similarity, it took me some time but I had it recommend similar posts through similar titles.
- I tried training and testing different classification models, and I struggled in getting accurate results.