-
-
Save selik/6585371 to your computer and use it in GitHub Desktop.
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
| #yelp cluster finder | |
| import re | |
| import collections | |
| def yelp_find(filename,kw): | |
| open_filename = open (filename, "rU") | |
| kw_list=[] | |
| business_dict={} | |
| for line in open_filename: | |
| if kw in line: | |
| print line | |
| kw_list.append(line) | |
| def yelp_find_busid_and_date(filename,kw): | |
| open_filename = open (filename, "rU") | |
| yelp_business_id_and_dates = re.findall('(\d{4}[-/]\d{2}[-/]\d{2})(.+)(\"business_id\"\: \"......................\"\})', open_filename.read()) | |
| for tuple in yelp_business_id_and_dates: | |
| business_id = tuple[2] | |
| date = tuple[0] | |
| print tuple[2]+tuple[0] | |
| #print result | |
| def yelp_cluster_size(filename, kw): | |
| #"this line filters out all reviews with the defined keyword" | |
| #keyword_list =[] | |
| import re | |
| import collections | |
| from collections import defaultdict | |
| business_dict = collections.defaultdict(list) | |
| #for line in filename: | |
| #if keyword in line: | |
| #keyword_list.append(line) | |
| #print line | |
| open_filename = open (filename, "rU") | |
| yelp_business_id_and_dates = re.findall(r'(\d{4}[-/]\d{2}[-/]\d{2})(.+)(\"business_id\"\: \"......................\"\})',open_filename.read()) | |
| for tuple in yelp_business_id_and_dates: | |
| businessid = tuple[2] | |
| date = tuple[0] | |
| business_dict[businessid].append(date) | |
| date_clusters = dict([k,v] for k,v in business_dict.items() if len(v) > 1) | |
| print date_clusters | |
| def days_between_events(filename, numberdays): | |
| import time | |
| import re | |
| import collections | |
| from collections import defaultdict | |
| business_dict = collections.defaultdict(list) | |
| open_filename = open (filename, "rU") | |
| yelp_business_id_and_dates = re.findall(r'(\d{4}[-/]\d{2}[-/]\d{2})(.+)(\"business_id\"\: \"......................\"\})',open_filename.read()) | |
| for tuple in yelp_business_id_and_dates: | |
| businessid = tuple[2] | |
| dates = tuple[0] | |
| #print dates + businessid | |
| for businessid, dates in business_dict.iteritems(): | |
| business_dict[businessid]=sorted(dates) | |
| {businessid:dates for businessid,dates in business_dict.iteritems()if dates[0].day-dates[-1].day<2} | |
| #date_object =datetime.strptime(dates, '(%Y[-/]%m[-/]%d)' | |
| #print date_object | |
| #print result | |
| # | |
| #if __name__ == '__main__': | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment