def normalize_data(src, dest):
print "Processing:", src
visits = read_raw_twitter_data(src)
if len(visits) > 0:
with open(dest, "w") as f:
f.write("user\turl\tfollowers\tfriends\n")
for visit in visits:
if not should_skip_host(visit[1]):
f.write("\t".join(map(str, visit)) + "\n")
def normalize_data(src, dest):
print "Processing:", src
visits = read_raw_aol_data(src)
if len(visits) > 0:
with open(dest, "w") as f:
writer = csv.writer(f, delimiter="\t")
writer.writerow(["User", "URL"])
for visit in visits:
if not should_skip_host(visit[1]):
writer.writerow(list(visit))
def normalize_data(src, dest): print "Processing:", src visits = read_raw_aol_data(src) if len(visits) > 0: with open(dest, "w") as f: writer = csv.writer(f, delimiter="\t") writer.writerow(["User", "URL"]) for visit in visits: if not should_skip_host(visit[1]): writer.writerow(list(visit))
