Python program to analyze data from IE. Quantifies non-IT enrollments generated by BAS-SD for other departments on campus.

gen_ed_counter.py

# AO8
# February 16, 2018

import csv
import os
import re

def build_csv():
    """iterates through CSV files in directory to create master gen_ed_data.csv"""
    rows = []
    for filename in os.listdir(directory):
        if filename.endswith(".csv"):
            with open(filename, "r") as f:
                contents = f.readlines()
            for line in contents:
                line = line.split(",")
                rows.append(line)
            for row in rows:
                if "\n" in row[2]:
                    row[2] = re.sub("\n", "", row[2])
            with open("gen_ed_data.csv", "w", newline="") as f:
                writer = csv.writer(f)
                for row in rows:
                    writer.writerow(row)  

def read_csv(filename):
    """opens and reads CSV file to create a list of rows"""
    with open(filename, "r") as f:
        reader = csv.reader(f)
        rows = []
        for row in reader:
            rows.append(row)
        return rows

def convert_to_int(lst):
    """converts row[1] from str to int"""
    for i in lst:
        i[2] = int(i[2])
    return lst

def remove_amper(lst):
    """removes ampersands from course prefixes"""
    for i in lst:
        if "&" in i[0]:
            i[0] = i[0][0:-1] # remove ampersand from course prefix
    return lst

def create_dict(lst):
    """creates a dictionary from a list of rows"""
    d = {}
    for i in lst:
        if i[0] == "IT" or i[0] == "STEPP": # disregards IT and STEPP enrollments
            continue
        elif i[0] in d:
            d[i[0]] += i[2]
        else:
            d[i[0]] = i[2]
    return d

def calc_total_enrollments(lst):
    totals = []
    for i in lst:
        if i[0] == "IT" or i[0] == "STEPP":
            continue
        else:
            totals.append(i[2])
    s = sum(totals)
    return s

def sort_dict(d):
    """sorts dict by values"""
    sorted_d = [(k, d[k]) for k in sorted(d, key=d.get, reverse=True)]
    return sorted_d

def display_gened_info(filename):
    """prints information about the sorted dictionary"""
    r = read_csv(filename)
    a = remove_amper(r)
    c = convert_to_int(a)
    d = create_dict(c)
    s = calc_total_enrollments(c)
    sorted_d = sort_dict(d)

    print("\n***\n")
    for k, v in sorted_d:
        print(f"{k} = {v}")
    print(f"\nBAS in Software Development generated {s} non-IT enrollments\nfor {len(sorted_d)} departments on campus!\n")
    
build_csv()
display_gened_info("gen_ed_data.csv")