My Guided Project: Clean And Analyze Employee Exit Surveys

Please I need an honest feedback regarding this guided project.

Basics (8).ipynb (135.6 KB)

Click here to view the jupyter notebook file in a new tab

1 Like

Hi @lukeayobami56

I have gone through your work and honestly I loved the way you have presented your work. Analyzing Employee Exit Survey hasn’t become easy to many me included, hope this wasn’t your case. Congratulations indeed for the good work. Have got few suggestions;

  • In cell [8] I think it would be better if you indicated why you have used the na_values parameter , if you keenly checked the comments you have just pointed out that you are reading the dete_survey csv files again.
  • In cell [19] I can see you have used vectorization to extract the years
# Extracting The Years Using Vectorized String Methods.
dete_resignations['cease_date'] = dete_resignations['cease_date'].str.split('/').str[-1]
dete_resignations['cease_date'] = dete_resignations['cease_date'].astype('float')

As an alternative , you can also use the regex just in one line code . have a look;

dete_resignations['cease_date'] =dete_resignations['cease_date'].astype('str')str.extract(r"(\d+\/(\d+)").astype("float")
  • Also in cell [29] when combining the data, you have indicated in the markdown cell that you are combining the data sets but coming to code cell you added as well a new column institute. This may create a different meaning that is, one may assume that before combining the datasets you need to add specific columns to the given dataframe. Though you have explained the entire working, below the given code cell, I think the best way was to separate the two task, adding the new column and then combining the datasets or rather include detailed information of the two task in the markdown cell.

Consider above as humble suggestions , Happy learning!

1 Like

Thanks so much for your honest suggestion.