Lesson 1 of Coursera's Data Analysis with Python course. Datasets housed in ~/Code/intro_data_anal on local host

unique.py

import os,unicodecsv
# write the csv reader function
def read_csv(filename): # write a function that reads a csv
    with open(filename,'rb') as file_object: # open csv file
        reader = unicodecsv.DictReader(file_object) # dictionary object created
        return list(reader) # creating list of dictionary(reader) objects

enrolled = read_csv('enrollments.csv')
engaged = read_csv('daily_engagement.csv')
submitted = read_csv('project_submissions.csv')


def uniqueness(list_object):
    unique_count = 0
    dummy_accountkey = 0
    for i in range(len(list_object)):
        if list_object[i]['account_key'] != dummy_accountkey: #testing for uniqueness
            dummy_accountkey = list_object[i]['account_key']
            unique_count += 1
    return unique_count, len(list_object)


enrollment_account_key,number_of_rows = uniqueness(enrolled)
print enrollment_account_key,'unique Enrollments account keys.'
print number_of_rows,'total rows in the Enrollments csv file.\n'

submissions_account_key,submissions_number_of_rows = uniqueness(submitted)
print submissions_account_key,'unique Project Submissions account keys.'
print submissions_number_of_rows, 'total rows in the Project Submissions csv file.\n'

# MUST create separate function for engaged BECAUSE the dictionary key is different(<acct> versus <account_key> (August 22,2018))

def uniqueness(list_object):
    count = 0
    dummy_accountkey = 0
    for i in range(len(list_object)):
        if list_object[i]['acct'] != dummy_accountkey:
            dummy_accountkey = list_object[i]['acct']
            count += 1

    return count, len(list_object)

engagement_account_keys,engagement_rows = uniqueness(engaged)
print engagement_account_keys,'unique Engagement account keys.' # unique account keys
print engagement_rows,'total Engagement rows.' # number of rows