Python 3: Web Scraping and Machine Learning - 2 HALF DAY CLASSES

Python 3: Web Scraping and Machine Learning - 2 HALF DAY CLASSES


Learning Objectives

Topics Include

Acquiring Data from Websites (“Web Scraping”)

  • Automate corporate due diligence and data gathering by designing programs to download publicly available information from websites
  • Aggregate alternative data from industry websites
  • Create programs for competitor analysis and price comparisons
  • Review API’s and Python packages used for web scraping, such as Requests, Urllib and Beautiful
  • Soup to parse downloaded data into a format that can be analyzed and visualized
  • Automate user interactions with websites using Selenium package
  • Extract financial data from Yahoo Finance, EDGAR and other sources
  • Learn to import data from various types of websites (HTML, JSON, XML, PDFs)

Machine Learning (ML) & AI Applications

  • Overview popular Machine Learning algorithms and how companies are leveraging Python’s ML packages
  • Use advanced language processing packages for natural language processing (NLP) to extract key information from new articles and press releases
  • Review the NLTK and SpaCy packages used for NLP
  • Use image processing packages to extract text and key information from images

Automaton, Visualization and Best Practices

  • Tips for moving and creating folders on the fly and importing data from multiple source files
  • Automate extracting and cleaning tables from PDF files
  • Build powerful visualizations using more advanced visualization packages such as Bokeh, Seaborn, and Plotly
  • Create interactive dashboards and charts using Dash and Streamlit packages
  • Explore the integration of Python with Power BI, Microsoft’s powerful dashboarding and visualization tool