Created
June 28, 2016 14:15
-
-
Save Lazhari/4ca45d52478ea979703940075c895baf to your computer and use it in GitHub Desktop.
Reading CSV file -- Python
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
DATADIR = "" | |
DATAFILE = "beatles-diskography.csv" | |
SEPARATOR = "," | |
def parse_file(datafile): | |
data = [] | |
header= [] | |
with open(datafile, "rb") as f: | |
for i, line in enumerate(f): | |
line = line.replace('\n', '') | |
if i==0: | |
header = line.split(SEPARATOR) | |
else: | |
row = dict(zip(header, line.split(SEPARATOR))) | |
data.append(row) | |
return data | |
def test(): | |
# a simple test of your implemetation | |
datafile = os.path.join(DATADIR, DATAFILE) | |
d = parse_file(datafile) | |
firstline = {'Title': 'Please Please Me', 'UK Chart Position': '1', 'Label': 'Parlophone(UK)', 'Released': '22 March 1963', 'US Chart Position': '-', 'RIAA Certification': 'Platinum', 'BPI Certification': 'Gold'} | |
tenthline = {'Title': '', 'UK Chart Position': '1', 'Label': 'Parlophone(UK)', 'Released': '10 July 1964', 'US Chart Position': '-', 'RIAA Certification': '', 'BPI Certification': 'Gold'} | |
assert d[0] == firstline | |
assert d[9] == tenthline | |
test() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment