Gainsight/Scripts/API_Tests/find_completed.py

from collections import Counter
import pandas as pd

basecsv = "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/Skuid_MCA125.csv"
lpcsv = "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/skuidlps.csv"

"""
Example multivalue dictionary

dict = {key1: [value1, value2, value3, value4],
        key2: [value5, value6, value 7],
        }

So this could be used for each learning path. In other words:

learning_paths = {'01:Skuid Ethos' : ["Congratulations", "Create", "Skuid Resources"]} etc etc

Ideally, we will add Alexa's "levels" in this dictionary as well. Could we do:

learning_paths = {'Level_1': [{'01:Skuid Ethos' : ["Congratulations", "Create", "Skuid Resources"]},
                              {'02:Composer' : ["Overview", "Get Started with Composer", "Manage Pages"}]
                              {'03:Design System Studio' : ["Get Started with Design Systems", etc etc]},
                  'Level_2': [{'10 - Data' : ["Tips to Optimize", "Smarter Conditions"]},
                              {'11-Components': ["Battle", "Engage"]},
                  ]
                }

How to create this by automation?
"""


def lpLevels(basecsv, lpcsv):
    levels = pd.read_csv(
        lpcsv,
        index_col=1,
    )
    newDf = levels.groupby("Learning Path")
    newDf2 = newDf.apply(lambda x: x["Course Name"].unique())
    learningpaths = newDf2.apply(pd.Series)
    learningpaths.rename_axis(index=0)
    mainFunc(basecsv, learningpaths)
    # print(levels.Level.unique())  # Print only unique values from the Level column


def mainFunc(basecsv, learningpaths):
    # Part 1
    readData = pd.read_csv(
        basecsv,
    )
    group = readData.groupby("Learner Full Name")
    df2 = group.apply(lambda x: x["Course Name"].unique())
    df2 = df2.apply(pd.Series, dtype="string")
    # print(df2)
    # This prints a dataframe with the learner's name as the index column and the courses as adjacent columns

    # Part 2
    courses = learningpaths.set_index(0)
    # print(courses)
    # lp_dict = learningpaths.to_dict("index")
    # courses = lp_dict.values()
    # Part 3
    print(df2.isin(df2))
    # This produces a bunch of T/F in the dataframe. Is the solution to do:
    # for courses in lp_dict, for row(person) in readData
    # if number of True == length/# of values in courses
    # Add to "Finished List"

    # df3 = df2.columns
    # print(df3)
    # for name in df3.items():
    #    print(f"name: {name}")


if __name__ == "__main__":
    # mainFunc(basecsv)
    lpLevels(basecsv, lpcsv)