So, I have multiple files - one contains tables with all people who submitted a type form with their original answers, others are lists that contain updated answers between the people in the team who asked the customers later on. The identical parts are the emails and the phone numbers. Any ideas how I should make some basic statistics between those clients? For example how do I have their before/after answers next to each others? Also, some of those clients were lost, others were validated, I'd like to do probabilities of how many clients that have, let's say, 100m2 of surface and Electric heaters are lost, how many are validated, etc, etc. Sorry if this is a bit messy, I am not sure how to exploit this data. Thank you !
I would suggest to first merge these datasets. If you are using python, R or some programming language, depending on their format, you can do it using simple commands. Of course maybe you would need to clean them first (for example rename the columns). For python and R you can do it like this:
https://stackoverflow.com/questions/6709151/how-do-i-combine-two-data-frames-based-on-two-columnshttps://stackoverflow.com/questions/37697195/how-to-merge-two-data-frames-based-on-particular-column-in-pandas-python
https://stackoverflow.com/questions/6709151/how-do-i-combine-two-data-frames-based-on-two-columns
If you have small datasets you can do this manually on excel.
Afterwards, from my understanding you want to perform simple statistical analysis. I would start with some frequency tables, summaries (mean, SD etc) of the continuous variables and some plots (histograms and barplots).
Dan Li Use the tidyverse library, read in the files, and use an inner join, specifying that the join must be using the email and phone number columns, e.g. by=c('email','phone number'). That will at least bring your data together and further you can compare the before and after answers side by side.
Best!!
AN
- Badges
- Science topic
- Similar topics
- Filing