Walmart Notes, Skuid script, etc

Scripts/Skuid_LPs/find_completed.py

@@ -2,7 +2,7 @@ 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/skuidlps2.csv"
+lpcsv = "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/skuidlps.csv"
 
 """
 Example multivalue dictionary
@@ -29,28 +29,50 @@ How to create this by automation?
 """
 
 
-def lpLevels(lpcsv):
+def lpLevels(basecsv, lpcsv):
     levels = pd.read_csv(
         lpcsv,
-        index_col=None,
-        header=None,
+        index_col=1,
     )
+    newDf = levels.groupby("Learning Path")
+    learningpaths = 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):
+def mainFunc(basecsv, learningpaths):
+    # Part 1
     readData = pd.read_csv(
         basecsv,
     )
-    #    lp01 = readData[readData["Course Name"] ==
-    #    print(lp01)
-    # people = lp01.groupby(["Email", "Learner Full Name"])["Course Name"].nunique()
-    # print(people)
-    # readData.drop_duplicates(subset="Course Name", keep="first")
-    lvl1 = readData.loc["Course Name"].any()
-    if lvl1.str.contains('Level 1'):
-        emailGroups = readData.groupby(["Email", "Learner Full Name"])["Course Name"].nunique()
-        print(emailGroups)
+    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
+    # learningpaths.set_index(0)
+    # print(courses)
+    lp_dict = learningpaths.to_dict()
+    courses = lp_dict.values()
+    print(courses)
+    # crs = courses
+    # print(crs)
+
+    # Part 3
+    # for course in courses:
+      #  print(df2.isin(course))
+
+    # df3 = df2.columns
+    # print(df3)
+    # for name in df3.items():
+    #    print(f"name: {name}")
+
+    # emailGroups = readData.groupby(["Email", "Learner Full Name"])["Course Name"].nunique()
+    # print(emailGroups)
     # emailGroups = people.to_csv(
     #    "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/outtest2.csv"
     # )
@@ -70,5 +92,5 @@ def mainFunc(basecsv):
 
 
 if __name__ == "__main__":
-    mainFunc(basecsv)
-    # lpLevels(lpcsv)
+    # mainFunc(basecsv)
+    lpLevels(basecsv, lpcsv)