FUN With CSV Files



In [2]:

    
import unicodecsv
import pprint
import csv



In [3]:

    
csv_file_name="enrollments.csv"

Json Import of csv file

Import data in json formate, All data are imported as string



In [4]:

    
enrolment = []

f=open(csv_file_name,'rb')

reader =unicodecsv.DictReader(f)
#reader is a itterater so loop is possible only once
print "type(reader) =",reader

#for each_row in reader:
#    enrolment.append(each_row)
enrolment=list(reader) #shorthand for above two line

#close file
f.close()

print "Total no of row : ",len(enrolment),"\n\n"

#print demo data
pprint.pprint(enrolment[1])









    



type(reader) = <unicodecsv.py2.DictReader instance at 0x03233AD0>
Total no of row :  1640 


{u'account_key': u'448',
 u'cancel_date': u'2014-11-10',
 u'days_to_cancel': u'5',
 u'is_canceled': u'True',
 u'is_udacity': u'True',
 u'join_date': u'2014-11-05',
 u'status': u'canceled'}

Simple import

Import data Row by row



In [5]:

    
data = []
with open(csv_file_name, 'rb') as csvfile:
    reader = csv.reader(csvfile, delimiter=' ', quotechar='|')
    for row in reader:
        data.append(row)

print "Headings :",(data[0])
print"Data :",(data[1])









    



Headings : ['account_key,status,join_date,cancel_date,days_to_cancel,is_udacity,is_canceled']
Data : ['448,canceled,2014-11-10,2015-01-14,65,True,True']

Using Pandas ( Very fast than above two)



In [6]:

    
import pandas as pd



In [7]:

    
enrol = pd.read_csv(csv_file_name)



In [8]:

    
enrol[:5]









    Out[8]:






  
    
      
      account_key
      status
      join_date
      cancel_date
      days_to_cancel
      is_udacity
      is_canceled
    
  
  
    
      0
      448
      canceled
      2014-11-10
      2015-01-14
      65
      True
      True
    
    
      1
      448
      canceled
      2014-11-05
      2014-11-10
      5
      True
      True
    
    
      2
      448
      canceled
      2015-01-27
      2015-01-27
      0
      True
      True
    
    
      3
      448
      canceled
      2014-11-10
      2014-11-10
      0
      True
      True
    
    
      4
      448
      current
      2015-03-10
      NaN
      NaN
      True
      False



In [9]:

    
len(enrol["account_key"].unique()) #unique account keys









    Out[9]:





1302



In [10]:

    
type(enrol)









    Out[10]:





pandas.core.frame.DataFrame



In [ ]:

	account_key	status	join_date	cancel_date	days_to_cancel	is_udacity	is_canceled
0	448	canceled	2014-11-10	2015-01-14	65	True	True
1	448	canceled	2014-11-05	2014-11-10	5	True	True
2	448	canceled	2015-01-27	2015-01-27	0	True	True
3	448	canceled	2014-11-10	2014-11-10	0	True	True
4	448	current	2015-03-10	NaN	NaN	True	False