MBAAssist Academy

Today we continue with DataTransofmers but with potentially more useful example. What we will do today is enrich a dataframe with data collected online. Particularly, we'll enrich a dataset containing company names with market trasnactions data from Media-Market API: Media-Obsessed Market API Documentation (remote-works-default) | RapidAPI To use the API, you need a rapidAPI account. The API is free for reasonable use (it has a limitation on queries per hour) Firstly, let's get our original dataframe (you can easily create your own, as you only need a list of tickers): df_companies = pd.read_excel(os.path.join(path1, "companies to analyse.xlsx" )) The data then looks like this: What you need to pay attention to: the data needs to have a column with tickers and the tickers are lowercase. If they are not, just transform using df_companies['Ticker'].str.lower(). Then let's get our json data. RapidApi will give you a snipper, which you can just copy to your c...

Old Work on Backpropagation in ML

Just came across some old work that I've done, so want to share and keep it tagged for future references: https://www.wolframcloud.com/objects/summerschool/pages/2017/TetyanaLoskutova_TE Honestly, I've never needed this knowledge in practice but it helped me to understand a course on numerical methods. Not that I have much hope to ever use the knowledge gained in the course on numerical methods...

Anomalies of the Financial Markets

Last time, we brought up the subject of the irrationality of the stock market. Today we're going to talk about even more curious things, things that are known as stock market anomalies. Despite their name, these anomalies happen often or even regularly. 1. The hemline effect Very well known, even if debatable, this effect says that when the long skirt is the centerpiece of the season, the stock market falls. Why? No reason. Just an observation that the fashion for long skirts coincided with the crises, such as the crises of 1987 and 1929. Are you convinced? Blame the couturiers! 2. 56-weeks pattern A little more complicated, this reason explains why there would be a larger liquidation of positions 56 weeks after a rise in the stock market. This increase must be more than 5 percent for 20 consecutive trading days. This trend has been very persistent for the past 40 years. Figure 1. 56-week pattern. Source: Investopedia This time, there is a more logical explanation. When instituti...

Powered by Blogger

Copyright mbaassist.co

Data Transformers in scikit-learn. Part 2

Dividend picks for the week 2021-11-29

Comments

Post a Comment