Aaron Schlegel's Notebook of Interesting Things

The following post walked through how to extract and transform the shelter outcome data to make it tidy and suitable for data analysis. In this post, we perform exploratory data analysis using pandas and seaborn to investigate and visualize the shelter outcomes of cats. The findings that are garnered from the exploratory data analysis step can help tremendously in the model building phase when we need to select the important features of the data.

The Austin Animal Center, the largest no-kill municipal animal shelter in the United States, makes available its shelter animal outcomes dataset as patrt of the City of Austin's Open Data program. This post demonstrates how to extract the data from the City of Austin's Open Data portal using the requests library and convert the resulting JSON to a tabular pandas DataFrame. We will then enrich the data by applying feature engineering to the data to add more information, which should help improve the outcome prediction model.

The Greeks are used as risk measures that represent how sensitive the price of derivatives are to change.

Introduces the call and put option pricing using the Black-Scholes formula and Python implementations.

Discusses calculations of the implied volatility measure in pricing security options with the Black-Scholes model.

Introduces the put-call parity as identified by Hans Stoll in 1969 as well as Python code for computing the put-call parity both numerically and symbolically.

Using petpy and multiprocessing to download 45,000 cat images in 6.5 minutes