60 lines
2.2 KiB
Python
60 lines
2.2 KiB
Python
|
from collections import Counter
|
||
|
|
import pandas as pd
|
||
|
|
import glob
|
||
|
|
import re
|
||
|
|
|
||
|
|
basecsv = "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/Skuid_MCA125.csv"
|
||
|
|
directory = "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/LPCSVs/*.csv"
|
||
|
|
lpcsv = "/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/skuidlps.csv"
|
||
|
|
|
||
|
|
# Unfortunately, what this needs is a CSV per learning path/MCA export. That will be painful to run.
|
||
|
|
|
||
|
|
|
||
|
|
def manualFunc(lpcsv, directory):
|
||
|
|
lps = pd.read_csv(lpcsv)
|
||
|
|
lpcourses = lps.groupby(["Learning Path"])["Course Name"]
|
||
|
|
coursenums = lpcourses.nunique()
|
||
|
|
coursenums = coursenums.to_dict()
|
||
|
|
lpnames = coursenums.keys()
|
||
|
|
# print(lpnames)
|
||
|
|
# num = re.match(r"(\d{2})")
|
||
|
|
# for row in coursenums:
|
||
|
|
# print(row)
|
||
|
|
# print(coursenums.keys())
|
||
|
|
# keys() and values() will show the respective columns. Adding the full LP string will show the values.
|
||
|
|
# What if... I do something like
|
||
|
|
# The next step is to compare each of the items in this list with the results of each fname. I wonder if I can do it by regex?
|
||
|
|
lp_dict = {}
|
||
|
|
lp_list = []
|
||
|
|
for fname in glob.glob(directory):
|
||
|
|
readData = pd.read_csv(
|
||
|
|
fname,
|
||
|
|
)
|
||
|
|
emailGroups = readData.groupby(["Email", "Learner Full Name"])[
|
||
|
|
"Course Name"
|
||
|
|
].nunique()
|
||
|
|
peoples = emailGroups.to_dict()
|
||
|
|
num = re.findall(r"(\d{2})", fname)
|
||
|
|
for lp, nums in coursenums.items():
|
||
|
|
file_num = str(num[0])
|
||
|
|
file_num = f"{file_num:02}"
|
||
|
|
lp_num = re.findall(r"(\d{2})", lp)
|
||
|
|
lp_num = str(lp_num[0])
|
||
|
|
if file_num == lp_num:
|
||
|
|
lp_list = []
|
||
|
|
# print(file_num+"+"+lp_num)
|
||
|
|
for person, completions in peoples.items():
|
||
|
|
if completions == nums:
|
||
|
|
lp_list.append(person)
|
||
|
|
ppl_todict = {fname: lp_list}
|
||
|
|
lp_dict.update(ppl_todict)
|
||
|
|
|
||
|
|
final = pd.DataFrame({key: pd.Series(value) for key, value in lp_dict.items()})
|
||
|
|
final.to_csv(
|
||
|
|
"/Users/normrasmussen/Documents/Northpass/Scripts/Skuid_LPs/finaltest3.csv"
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
manualFunc(lpcsv, directory)
|