Stefan Jansen
Stefan Jansen

Stefan is Founder & Lead Data Scientist at Applied Artificial Intelligence.

Stefan has applied data science to business, investment and policy decisions since for over 15 years. He has built an early warning system for financial crises, and worked as advisor to Central Banks and the World Bank before moving into fintech. He is founder and lead data scientist at Applied Artificial Intelligence, and instructor at General Assembly.

See More
  • Lore Dirick

    Lore Dirick

Course Description

If you want to apply your new 'Python for Data Science' skills to real-world financial data, then this course will give you some very valuable tools. First, you will learn how to get data out of Excel into pandas and back. Then, you will learn how to pull stock prices from various online APIs like Google or Yahoo! Finance, macro data from the Federal Reserve, and exchange rates from OANDA. Finally, you will learn how to calculate returns for various time horizons, analyze stock performance by sector for IPOs, and calculate and summarize correlations.

  1. 1

    Importing stock listing data from Excel


    In this chapter, you will learn how to import, clean and combine data from Excel workbook sheets into a pandas DataFrame. You will also practice grouping data, summarizing information for categories, and visualizing the result using subplots and heatmaps. You will use data on companies listed on the stock exchanges NASDAQ, NYSE, and AMEX with information on company name, stock symbol, last market capitalization and price, sector or industry group, and IPO year. In Chapter 2, you will build on this data to download and analyze stock price history for some of these companies.

  2. Importing financial data from the web

    This chapter introduces online data access to Google Finance and the Federal Reserve Data Service through the `pandas` `DataReader`. You will pull data, perform basic manipulations, combine data series, and visualize the results.

  3. Summarizing your data and visualizing the result

    In this chapter, you will learn how to capture key characteristics of individual variables in simple metrics. As a result, it will be easier to understand the distribution of the variables in your data set: Which values are central to, or typical of your data? Is your data widely dispersed, or rather narrowly distributed around some mid point? Are there outliers? What does the overall distribution look like?

  4. Aggregating and describing your data by category

    This chapter introduces the ability to group data by one or more categorical variables, and to calculate and visualize summary statistics for each caategory. In the process, you will learn to compare company statistics for different sectors and IPO vintages, analyze the global income distribution over time, and learn how to create various statistical charts from the seaborn library.