The dataset i downloaded from the mentioned dropbox llinks, is different. like for earliest_cr line the values in the video are 'Nov-01' while the value in the dataset is 'Nov-20'. What can be done to avoid this?

It looks like some of the data was inputted in a single year format, this causes programs to assume it means something else. For example Nov-01 becomes Nov-1, which causes it to think it means 11/1/currentyear. Use loan_data['earliest_cr_line'].replace({"^(\d-.*)$": "0\\g<1>", "^(.*)-(\d)$": "0\\g<2>-\\g<1>"}, regex=True, inplace=True) to make the above example Nov-01 again.

Hi Kunjan, Please refer to the credit risk modelling files available here: https://www.dropbox.com/sh/7oslws1xhsm1zbf/AABkdWDKqpdcGmY1NbXAnkrBa?dl=0 Best, The 365 Team

Follow this topic

Kunjan Mehta

Last answered:

06 Aug 2022

Posted on:

27 May 2020

Different dataset for credit risk modelling course

2 answers ( 0 marked as helpful)

365 Team

Instructor

Posted on:

15 Jun 2020

Kat su

Posted on:

06 Aug 2022

Different dataset for credit risk modelling course

Submit an answer