Adding file analysis.py
David Blume commited on 2018-01-20 20:49:06
Showing 1 changed files, with 186 additions and 0 deletions.
- analysis.py 0000000..012e8f6
| ... | ... |
@@ -0,0 +1,186 @@ |
| 1 |
+#!/usr/bin/env python |
|
| 2 |
+ |
|
| 3 |
+import yaml |
|
| 4 |
+import sys |
|
| 5 |
+import os |
|
| 6 |
+import time |
|
| 7 |
+import traceback |
|
| 8 |
+import exceptions |
|
| 9 |
+import math |
|
| 10 |
+import bisect |
|
| 11 |
+ |
|
| 12 |
+debug = True |
|
| 13 |
+ |
|
| 14 |
+ |
|
| 15 |
+def get_standard_deviation(l): |
|
| 16 |
+ """ returns the standard deviation of the iterable l """ |
|
| 17 |
+ mean = sum(l) / len(l) |
|
| 18 |
+ squares_of_diffs = map(lambda x: pow(x - mean, 2), l) |
|
| 19 |
+ mean_of_squares = sum(squares_of_diffs) / len(squares_of_diffs) |
|
| 20 |
+ return math.sqrt(mean_of_squares) |
|
| 21 |
+ |
|
| 22 |
+ |
|
| 23 |
+def unique(seq, idfun=None): |
|
| 24 |
+ if idfun is None: |
|
| 25 |
+ def idfun(x): return x |
|
| 26 |
+ seen = {}
|
|
| 27 |
+ result = [] |
|
| 28 |
+ for item in seq: |
|
| 29 |
+ marker = idfun(item) |
|
| 30 |
+ if marker in seen: continue |
|
| 31 |
+ seen[marker] = 1 |
|
| 32 |
+ result.append(item) |
|
| 33 |
+ return result |
|
| 34 |
+ |
|
| 35 |
+ |
|
| 36 |
+def Process_comments_for_feed(yaml_items): |
|
| 37 |
+ time_blocks = [[], [], [], [], [], [], [], []] |
|
| 38 |
+ for i in yaml_items: |
|
| 39 |
+ time_posted = i['orig_posted'] |
|
| 40 |
+ comment_times = i['comment_times'] |
|
| 41 |
+ comments = i['comments'] |
|
| 42 |
+ comment_times_indices = [(t - time_posted) / 1800 for t in comment_times] |
|
| 43 |
+ for j in range(len(comments)): |
|
| 44 |
+ if comment_times_indices[j] > 7 or comment_times_indices[j] < 0: |
|
| 45 |
+ continue |
|
| 46 |
+ time_blocks[comment_times_indices[j]].append(comments[j]) |
|
| 47 |
+ |
|
| 48 |
+ stats = [] |
|
| 49 |
+ for time_block in time_blocks: |
|
| 50 |
+ mean = sum(time_block) / len(time_block) |
|
| 51 |
+ squares_of_diffs = map(lambda x: pow(x - mean, 2), time_block) |
|
| 52 |
+ mean_of_squares = sum(squares_of_diffs) / len(squares_of_diffs) |
|
| 53 |
+ std_dev = math.sqrt(mean_of_squares) |
|
| 54 |
+ stats.append((mean, std_dev)) |
|
| 55 |
+ return stats |
|
| 56 |
+ |
|
| 57 |
+ |
|
| 58 |
+def Remove_outliers(time_blocks): |
|
| 59 |
+ """remove 6% of the values as outliers (3% from each side).""" |
|
| 60 |
+ for block in time_blocks: |
|
| 61 |
+ pairs_to_remove = 0 |
|
| 62 |
+ if len(block) > 66: |
|
| 63 |
+ pairs_to_remove = int(len(block) * 0.03) |
|
| 64 |
+ elif len(block) > 19: |
|
| 65 |
+ pairs_to_remove = 1 |
|
| 66 |
+ |
|
| 67 |
+ while pairs_to_remove > 0: |
|
| 68 |
+ block.pop() |
|
| 69 |
+ block.pop(0) |
|
| 70 |
+ pairs_to_remove -= 1 |
|
| 71 |
+ |
|
| 72 |
+ |
|
| 73 |
+def Calculate_median_mean_stddev(time_blocks): |
|
| 74 |
+ stats = [] |
|
| 75 |
+ for block in time_blocks: |
|
| 76 |
+ # Calculate the median |
|
| 77 |
+ count = len(block) |
|
| 78 |
+ median = 0.0 |
|
| 79 |
+ if count % 2: |
|
| 80 |
+ median = float(block[count/2]) |
|
| 81 |
+ elif count > 0: |
|
| 82 |
+ median = (block[count / 2 - 1] + block[count / 2]) / 2.0 |
|
| 83 |
+ |
|
| 84 |
+ # Calculate the mean and standard deviation |
|
| 85 |
+ if count > 0: |
|
| 86 |
+ mean = sum(block) / float(len(block)) |
|
| 87 |
+ squares_of_diffs = map(lambda x: pow(x - mean, 2), block) |
|
| 88 |
+ mean_of_squares = sum(squares_of_diffs) / len(squares_of_diffs) |
|
| 89 |
+ else: |
|
| 90 |
+ mean = 0 |
|
| 91 |
+ mean_of_squares = 0 |
|
| 92 |
+ std_dev = math.sqrt(mean_of_squares) |
|
| 93 |
+ stats.append((median, mean, std_dev)) |
|
| 94 |
+ return stats |
|
| 95 |
+ |
|
| 96 |
+ |
|
| 97 |
+def Process_feed(yaml_items, metric, metric_times): |
|
| 98 |
+ weekend_time_blocks = [[], [], [], [], [], [], [], []] |
|
| 99 |
+ weekday_time_blocks = [[], [], [], [], [], [], [], []] |
|
| 100 |
+ for i in yaml_items: |
|
| 101 |
+ time_posted = i['orig_posted'] |
|
| 102 |
+ wday = time.localtime(time_posted).tm_wday |
|
| 103 |
+ value_times = i[metric_times] |
|
| 104 |
+ values = i[metric] |
|
| 105 |
+ value_times_indices = [(t - time_posted) / 1800 for t in value_times] |
|
| 106 |
+ for j in range(len(values)): |
|
| 107 |
+ if value_times_indices[j] > 7 or value_times_indices[j] < 0: |
|
| 108 |
+ continue |
|
| 109 |
+ if wday == 5 or wday == 6: |
|
| 110 |
+ bisect.insort(weekend_time_blocks[value_times_indices[j]], values[j]) |
|
| 111 |
+ else: |
|
| 112 |
+ bisect.insort(weekday_time_blocks[value_times_indices[j]], values[j]) |
|
| 113 |
+ |
|
| 114 |
+ Remove_outliers(weekend_time_blocks) |
|
| 115 |
+ Remove_outliers(weekday_time_blocks) |
|
| 116 |
+ |
|
| 117 |
+ weekend_stats = Calculate_median_mean_stddev(weekend_time_blocks) |
|
| 118 |
+ weekday_stats = Calculate_median_mean_stddev(weekday_time_blocks) |
|
| 119 |
+ |
|
| 120 |
+ return weekend_stats, weekday_stats |
|
| 121 |
+ |
|
| 122 |
+ |
|
| 123 |
+if __name__=='__main__': |
|
| 124 |
+ start_time = time.time() |
|
| 125 |
+ progress_text = [] |
|
| 126 |
+ |
|
| 127 |
+ try: |
|
| 128 |
+ localdir = os.path.abspath(os.path.dirname(sys.argv[0])) |
|
| 129 |
+ # |
|
| 130 |
+ # Read in techcrunch.yaml |
|
| 131 |
+ # |
|
| 132 |
+ # [ { 'title' : 'Title Text',
|
|
| 133 |
+ # 'link' : u'http://techcrunch.com/2010/08/17/google-buzz-who-to-follow/', |
|
| 134 |
+ # 'author' : u'MG Siegler', |
|
| 135 |
+ # 'orig_posted' : 1282197199 |
|
| 136 |
+ # 'tags' : [ u'Google', u'privacy' ] |
|
| 137 |
+ # 'qualified' : -1 |
|
| 138 |
+ # 'comment_times' : [ 1282197199, 1282197407 ] |
|
| 139 |
+ # 'comments' : [ 0, 15 ] |
|
| 140 |
+ # 'slash_comment_times' : [ 1282197199, 1282197407 ] |
|
| 141 |
+ # 'slash_comments' : [ 0, 5 ] |
|
| 142 |
+ # 'slash_comment_times' : [ 1282197199, 1282197407 ] |
|
| 143 |
+ # 'slash_comments' : [ 0, 3 ] |
|
| 144 |
+ # 'retweet_times' : [ 1282197199, 1282197407 ] |
|
| 145 |
+ # 'retweets' : [ 0, 43 ] |
|
| 146 |
+ # }, |
|
| 147 |
+ # { ... }
|
|
| 148 |
+ # ] |
|
| 149 |
+ # |
|
| 150 |
+ yaml_fullpath = os.path.join(localdir, 'techcrunch.yaml') |
|
| 151 |
+ if os.path.exists(yaml_fullpath): |
|
| 152 |
+ f = file(yaml_fullpath, 'rb') |
|
| 153 |
+ items = yaml.load(f) |
|
| 154 |
+ f.close() |
|
| 155 |
+ else: |
|
| 156 |
+ print "could not open", yaml_fullpath |
|
| 157 |
+ items = [] |
|
| 158 |
+ |
|
| 159 |
+ weekend_stats, weekday_stats = Process_feed(items, 'fb_shares', 'comment_times') |
|
| 160 |
+ |
|
| 161 |
+ # We'll only look at the stats for the time 1:00 to 1:30 after posting. |
|
| 162 |
+ weekend_median, weekend_mean, weekend_sigma = weekend_stats[2] |
|
| 163 |
+ weekend_threshold = weekend_median + (weekend_sigma) |
|
| 164 |
+ median, mean, sigma = weekday_stats[2] |
|
| 165 |
+ threshold = median + (sigma) |
|
| 166 |
+ print "Weekend Median=%1.1f, Mean=%1.1f, Sigma=%1.1f --> Threshold = %1.1f" % (weekend_median, weekend_mean, weekend_sigma, weekend_threshold) |
|
| 167 |
+ print "Weekday Median=%1.1f, Mean=%1.1f, Sigma=%1.1f --> Threshold = %1.1f" % (median, mean, sigma, threshold) |
|
| 168 |
+ for item in items: |
|
| 169 |
+ if item['qualified'] == -1: |
|
| 170 |
+ print "Processing", item['title'].encode('ascii', 'replace')
|
|
| 171 |
+ for i in range(len(item['retweet_times'])): |
|
| 172 |
+ r_time = item['retweet_times'][i] |
|
| 173 |
+ if r_time - item['orig_posted'] < 5400: |
|
| 174 |
+ print "Time %1.1f = %d" % ((r_time - item['orig_posted']) / 1800.0, item['retweets'][i]), |
|
| 175 |
+ if item['retweets'][i] >= threshold: |
|
| 176 |
+ item['qualified'] = i |
|
| 177 |
+ print "NOW QUALIFIES", |
|
| 178 |
+ if r_time - item['orig_posted'] >= 3600: |
|
| 179 |
+ break |
|
| 180 |
|
|
| 181 |
+ |
|
| 182 |
+ except Exception as e: |
|
| 183 |
+ exceptional_text = "An exception occurred: " + str(e.__class__) + " " + str(e) |
|
| 184 |
+ print exceptional_text, ' '.join(progress_text) |
|
| 185 |
+ traceback.print_exc(file=sys.stdout) |
|
| 186 |
+ |
|
| 0 | 187 |