November 2019
Intermediate to advanced
346 pages
9h 36m
English
We start by importing pandas and then reading our data into a dataframe (step 1). There are two fields in this data: password and password strength. Password strength consists of three levels of difficulty. We shuffle the data to create more robust training in step 2. In step 3, we split the dataframe via an 80-20 split, and then distribute the features and labels into arrays (step 4). In step 5, we define a function that splits the password strings into characters in order to tokenize passwords into characters, rather than into words. This will allow the classifier to learn fine-grained information about the password dataset. In step 6, we define a pipeline to perform NLP on the characters of a password, followed by using an ...