Jupyter notebook 2016-12-02-195416.ipynb

Path: 2016-12-02-195416.ipynb

Views: ⁶⁹

Kernel: Python 2 (SageMath)

In [1]:

import unicodecsv
import csv

def read_csv(filename):
    with open('enrollments.csv', 'rb') as f:
        reader = unicodecsv.DictReader(f)
        csv_list = list(reader)
        return csv_list

enroll=read_csv('enrollments.csv')
print 'Enroll: ',enroll[2]

daily_engage=read_csv('daily_engagement.csv')
print 'Daily : ',daily_engage[2]

submissions=read_csv('project_submissions.csv')
print 'Submission: ',submissions[2]

Enroll:  {u'status': u'canceled', u'is_udacity': u'True', u'is_canceled': u'True', u'join_date': u'2015-01-27', u'account_key': u'448', u'cancel_date': u'2015-01-27', u'days_to_cancel': u'0'}
Daily :  {u'status': u'canceled', u'is_udacity': u'True', u'is_canceled': u'True', u'join_date': u'2015-01-27', u'account_key': u'448', u'cancel_date': u'2015-01-27', u'days_to_cancel': u'0'}
Submission:  {u'status': u'canceled', u'is_udacity': u'True', u'is_canceled': u'True', u'join_date': u'2015-01-27', u'account_key': u'448', u'cancel_date': u'2015-01-27', u'days_to_cancel': u'0'}

Fixing Datatypes:

In [2]:

from datetime import datetime as dt

# Takes a date as a string, and returns a Python datetime object. 
# If there is no date given, returns None
def parse_date(date):
    if date == '':
        return None
    else:
        return dt.strptime(date, '%Y-%m-%d')
    
    
    
# Takes a string which is either an empty string or represents an integer,
# and returns an int or None.
def parse_maybe_int(i):
    if i == '':
        return None
    else:
        return int(i)

In [4]:

# Clean up the data types in the enrollments table
for enrollment in enroll:
    print enrollment['cancel_date'] #= parse_date(enrollment['cancel_date'])
    '''
    enrollment['days_to_cancel'] = parse_maybe_int(enrollment['days_to_cancel'])
    enrollment['is_canceled'] = enrollment['is_canceled'] == 'True'
    enrollment['is_udacity'] = enrollment['is_udacity'] == 'True'
    enrollment['join_date'] = parse_date(enrollment['join_date'])
    '''
    
enrollments[0]

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-4-c0a155dd0334> in <module>()
      9     '''
     10 
---> 11 enrollments[0]

NameError: name 'enrollments' is not defined

In [22]:

sage

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-22-0c8a2180ef81> in <module>()
----> 1 sage

NameError: name 'sage' is not defined

In [4]:

import pandas

In [ ]: