| Index: trunk/tools/editor_trends/analyses/plugins/ppi_editor_productivity.py |
| — | — | @@ -29,43 +29,34 @@ |
| 30 | 30 | |
| 31 | 31 | edits = editor['character_count'] |
| 32 | 32 | username = editor['username'] |
| 33 | | - x = 0 |
| 34 | 33 | try: |
| 35 | 34 | added = edits['2010']['11']['0']['added'] |
| 36 | | - x += 1 |
| 37 | 35 | except KeyError: |
| 38 | | - added = 2 |
| 39 | | -# try: |
| 40 | | -# removed = edits['2010']['11']['0']['removed'] |
| 41 | | -# x += 1 |
| 42 | | -# except KeyError: |
| 43 | | -# removed = 0 |
| | 36 | + added = 0 |
| | 37 | + try: |
| | 38 | + removed = edits['2010']['11']['0']['removed'] |
| | 39 | + except KeyError: |
| | 40 | + removed = 0 |
| 44 | 41 | |
| 45 | | - |
| 46 | 42 | key = datetime(2010, 11, 30) |
| 47 | 43 | if added > 0: |
| 48 | 44 | var.add(key, added, {'username': username, 'added': 'added'}) |
| 49 | | -# if removed > 0: |
| 50 | | -# var.add(key, removed, {'username': username, 'removed': 'removed'}) |
| 51 | | -# var.add(key, x, {'username': username, 'total': 'total'}) |
| | 45 | + if removed > 0: |
| | 46 | + var.add(key, removed, {'username': username, 'removed': 'removed'}) |
| 52 | 47 | |
| 53 | | - y = 0 |
| 54 | 48 | try: |
| 55 | 49 | added = edits['2010']['12']['0']['added'] |
| 56 | | - y += 1 |
| 57 | 50 | except KeyError: |
| 58 | | - added = 4 |
| 59 | | -# try: |
| 60 | | -# removed = edits['2010']['12']['0']['removed'] |
| 61 | | -# y += 1 |
| 62 | | -# except KeyError: |
| 63 | | -# removed = 0 |
| | 51 | + added = 0 |
| | 52 | + try: |
| | 53 | + removed = edits['2010']['12']['0']['removed'] |
| | 54 | + except KeyError: |
| | 55 | + removed = 0 |
| 64 | 56 | |
| 65 | 57 | key = datetime(2010, 12, 31) |
| 66 | 58 | if added > 0: |
| 67 | 59 | var.add(key, added, {'username': username, 'added': 'added'}) |
| 68 | | -# if removed > 0: |
| 69 | | -# var.add(key, removed, {'username': username, 'removed': 'removed'}) |
| 70 | | -# var.add(key, y, {'username': username, 'total': 'total'}) |
| | 60 | + if removed > 0: |
| | 61 | + var.add(key, removed, {'username': username, 'removed': 'removed'}) |
| 71 | 62 | |
| 72 | 63 | return var |
| Index: trunk/tools/editor_trends/analyses/analyzer.py |
| — | — | @@ -153,18 +153,20 @@ |
| 154 | 154 | |
| 155 | 155 | |
| 156 | 156 | ppills = rts.number_of_processes |
| 157 | | - while ppills > 0: |
| 158 | | - try: |
| 159 | | - res = result.get() |
| 160 | | - if res == True: |
| 161 | | - pbar.update(pbar.currval + 1) |
| 162 | | - else: |
| 163 | | - ppills -= 1 |
| 164 | | - var = res |
| 165 | | - print 'ppills: %s' % ppills |
| 166 | | - except Empty: |
| 167 | | - pass |
| 168 | | - |
| | 157 | + while True: |
| | 158 | + while ppills > 0: |
| | 159 | + try: |
| | 160 | + res = result.get() |
| | 161 | + if res == True: |
| | 162 | + pbar.update(pbar.currval + 1) |
| | 163 | + else: |
| | 164 | + ppills -= 1 |
| | 165 | + var = res |
| | 166 | + print ppills |
| | 167 | + except Empty: |
| | 168 | + pass |
| | 169 | + break |
| | 170 | + print 'Waiting for tasks...' |
| 169 | 171 | tasks.join() |
| 170 | 172 | |
| 171 | 173 | var = reconstruct_observations(var) |
| Index: trunk/tools/editor_trends/analyses/adhoc/ppi_quality.py |
| — | — | @@ -1,3 +1,17 @@ |
| | 2 | +#!/usr/bin/python |
| | 3 | +# -*- coding: utf-8 -*- |
| | 4 | +''' |
| | 5 | +Copyright (C) 2010 by Diederik van Liere (dvanliere@gmail.com) |
| | 6 | +This program is free software; you can redistribute it and/or |
| | 7 | +modify it under the terms of the GNU General Public License version 2 |
| | 8 | +as published by the Free Software Foundation. |
| | 9 | +This program is distributed in the hope that it will be useful, |
| | 10 | +but WITHOUT ANY WARRANTY; without even the implied warranty of |
| | 11 | +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. |
| | 12 | +See the GNU General Public License for more details, at |
| | 13 | +http://www.fsf.org/licenses/gpl.html |
| | 14 | +''' |
| | 15 | + |
| 2 | 16 | __author__ = '''\n'''.join(['Diederik van Liere (dvanliere@gmail.com)']) |
| 3 | 17 | __email__ = 'dvanliere at gmail dot com' |
| 4 | 18 | __date__ = '2011-05-17' |
| — | — | @@ -106,6 +120,10 @@ |
| 107 | 121 | |
| 108 | 122 | |
| 109 | 123 | def normalize_dataset(vars, obs): |
| | 124 | + ''' |
| | 125 | + This function rescales a dataset by dividing the observation by the standard |
| | 126 | + deviation (which results in a Z-score) |
| | 127 | + ''' |
| 110 | 128 | editors = obs.keys() |
| 111 | 129 | data = [] |
| 112 | 130 | for var in vars: |
| — | — | @@ -142,6 +160,7 @@ |
| 143 | 161 | max_d = max(data.keys()) |
| 144 | 162 | match = data[max_d] |
| 145 | 163 | matches.append((ppi_editor, match)) |
| | 164 | + #remove match to make sure that every matched pair is unique |
| 146 | 165 | for editor in distances: |
| 147 | 166 | try: |
| 148 | 167 | distances[editor].pop(match) |
| Index: trunk/tools/editor_trends/js_scripts/ppi_quality.js |
| — | — | @@ -0,0 +1,126 @@ |
| | 2 | +var editors = new Array();
|
| | 3 | +// Editors from December 2010
|
| | 4 | +editors[0] = "IR393.sae211";
|
| | 5 | +editors[1] = "Marian Sokolski";
|
| | 6 | +editors[2] = "SoAuthentic";
|
| | 7 | +editors[3] = "IR393davis";
|
| | 8 | +editors[4] = "Mulforel";
|
| | 9 | +editors[5] = "IR393ANDRICA";
|
| | 10 | +editors[6] = "Richharriott";
|
| | 11 | +editors[7] = "Prahalika";
|
| | 12 | +editors[8] = "IR393.awc211";
|
| | 13 | +editors[9] = "IR393TheSituation";
|
| | 14 | +editors[10] = "IR393harrisonkatz";
|
| | 15 | +editors[11] = "Kcahlber";
|
| | 16 | +editors[12] = "Elangate";
|
| | 17 | +editors[13] = "GWcontributor";
|
| | 18 | +editors[14] = "Dounoannick";
|
| | 19 | +editors[15] = "IR393DEME";
|
| | 20 | +editors[16] = "Teklegam";
|
| | 21 | +editors[17] = "Lbellows";
|
| | 22 | +editors[18] = "Coogan630";
|
| | 23 | +editors[19] = "Clairestum";
|
| | 24 | +editors[20] = "Hawkinjw";
|
| | 25 | +editors[21] = "Labrador70";
|
| | 26 | +editors[22] = "Seaver02";
|
| | 27 | +editors[23] = "Loflinrm";
|
| | 28 | +editors[24] = "Kcsl";
|
| | 29 | +editors[25] = "Farleyeye";
|
| | 30 | +editors[26] = "Eva YFL";
|
| | 31 | +editors[27] = "IR393Sadar";
|
| | 32 | +editors[28] = "Creyjons";
|
| | 33 | +editors[29] = "Okeland";
|
| | 34 | +editors[30] = "Amongst no roses";
|
| | 35 | +editors[31] = "Legin-gross-drawkcab";
|
| | 36 | +editors[32] = "Air3drew";
|
| | 37 | +editors[33] = "Owesetar";
|
| | 38 | +editors[34] = "Jmsheats";
|
| | 39 | +editors[35] = "Pearycrates";
|
| | 40 | +editors[36] = "Rabesque";
|
| | 41 | +editors[37] = "Hathornt";
|
| | 42 | +editors[38] = "Gsrogers";
|
| | 43 | +editors[39] = "Surfertk";
|
| | 44 | +editors[40] = "Evansza1";
|
| | 45 | +editors[41] = "Snyde2bd";
|
| | 46 | +editors[42] = "Ace of Raves";
|
| | 47 | +editors[43] = "IR393DrewGolding";
|
| | 48 | +editors[44] = "Rothboy2";
|
| | 49 | +editors[45] = "Ironman340";
|
| | 50 | +editors[46] = "Elhugheszete";
|
| | 51 | +editors[47] = "JanTan825";
|
| | 52 | +editors[48] = "New Potato Caboose";
|
| | 53 | +editors[49] = "Irishmeadow";
|
| | 54 | +editors[50] = "Tannerbk";
|
| | 55 | +editors[51] = "Luckbethislady";
|
| | 56 | +editors[52] = "1Ridwan";
|
| | 57 | +editors[53] = "Policydude";
|
| | 58 | +editors[54] = "Bmw 1986";
|
| | 59 | +editors[55] = "IR393ldc211";
|
| | 60 | +editors[56] = "Atb2393";
|
| | 61 | +editors[57] = "Goldstein2020";
|
| | 62 | +editors[58] = "Srayburn";
|
| | 63 | +editors[59] = "Yawloco";
|
| | 64 | +editors[60] = "Al-Jahweri";
|
| | 65 | +editors[61] = "Speon";
|
| | 66 | +editors[62] = "IR393aes";
|
| | 67 | +editors[63] = "Dohanian89";
|
| | 68 | +editors[64] = "Tessitjp";
|
| | 69 | +editors[65] = "Nerdpenguin";
|
| | 70 | +editors[66] = "Mikewuh";
|
| | 71 | +editors[67] = "Naj87";
|
| | 72 | +editors[68] = "Harrimel";
|
| | 73 | +editors[69] = "Contribute10";
|
| | 74 | +editors[70] = "Ramacu";
|
| | 75 | +editors[71] = "Kaloryth";
|
| | 76 | +editors[72] = "Qiaochina";
|
| | 77 | +editors[73] = "CBCrookham";
|
| | 78 | +editors[74] = "Saxa228";
|
| | 79 | +editors[75] = "Adw7";
|
| | 80 | +editors[76] = "Jraytram";
|
| | 81 | +editors[77] = "Indigoandcerise";
|
| | 82 | +editors[78] = "Clafoutis";
|
| | 83 | +editors[79] = "Klhrdy";
|
| | 84 | +editors[80] = "TomSannicandro";
|
| | 85 | +editors[81] = "Wkrantz";
|
| | 86 | +editors[82] = "Padmin22";
|
| | 87 | +editors[83] = "Alexvonzu";
|
| | 88 | +editors[84] = "Klcai";
|
| | 89 | +editors[85] = "Bridoc";
|
| | 90 | +editors[86] = "Feuchtcc";
|
| | 91 | +editors[87] = "Karthik Jagadeesh";
|
| | 92 | +editors[88] = "Smj39";
|
| | 93 | +editors[89] = "Xavier Peniche";
|
| | 94 | +editors[90] = "Ka Yaffa";
|
| | 95 | +editors[91] = "Jysg23";
|
| | 96 | +editors[92] = "Wsko.ko";
|
| | 97 | +editors[93] = "Psyoon";
|
| | 98 | +editors[94] = "Wvhoya";
|
| | 99 | +editors[95] = "Act25";
|
| | 100 | +editors[96] = "Hpl1981";
|
| | 101 | +editors[97] = "Jacqueline F";
|
| | 102 | +editors[98] = "IR393.cfc211";
|
| | 103 | +editors[99] = "Joko123nm";
|
| | 104 | +editors[100] = "Kmac1986";
|
| | 105 | +editors[101] = "Amfarr21";
|
| | 106 | +editors[102] = "IR393Anjan";
|
| | 107 | +
|
| | 108 | +
|
| | 109 | +var date1 = new Date();
|
| | 110 | +date1.setFullYear(2010,12,31);
|
| | 111 | +d = {"date1": date1};
|
| | 112 | +
|
| | 113 | +var editors = {"IR393.sae211": d,"Marian Sokolski": d,"SoAuthentic": d,"IR393davis": d,"Mulforel": d,"IR393ANDRICA": d,"Richharriott": d,"Prahalika": d,"IR393.awc211": d,"IR393TheSituation": d,"IR393harrisonkatz": d,"Kcahlber": d,"Elangate": d,"GWcontributor": d,"Dounoannick": d,"IR393DEME": d,"Teklegam": d,"Lbellows": d,"Coogan630": d,"Clairestum": d,"Hawkinjw": d,"Labrador70": d,"Seaver02": d,"Loflinrm": d,"Kcsl": d,"Farleyeye": d,"Eva YFL": d,"IR393Sadar": d,"Creyjons": d,"Okeland": d,"Amongst no roses": d,"Legin-gross-drawkcab": d,"Air3drew": d,"Owesetar": d,"Jmsheats": d,"Pearycrates": d,"Rabesque": d,"Hathornt": d,"Gsrogers": d,"Surfertk": d,"Evansza1": d,"Snyde2bd": d,"Ace of Raves": d,"IR393DrewGolding": d,"Rothboy2": d,"Ironman340": d,"Elhugheszete": d,"JanTan825": d,"New Potato Caboose": d,"Irishmeadow": d,"Tannerbk": d,"Luckbethislady": d,"1Ridwan": d,"Policydude": d,"Bmw 1986": d,"IR393ldc211": d,"Atb2393": d,"Goldstein2020": d,"Srayburn": d,"Yawloco": d,"Al-Jahweri": d,"Speon": d,"IR393aes": d,"Dohanian89": d,"Tessitjp": d,"Nerdpenguin": d,"Mikewuh": d,"Naj87": d,"Harrimel": d,"Contribute10": d,"Ramacu": d,"Kaloryth": d,"Qiaochina": d,"CBCrookham": d,"Saxa228": d,"Adw7": d,"Jraytram": d,"Indigoandcerise": d,"Clafoutis": d,"Klhrdy": d,"TomSannicandro": d,"Wkrantz": d,"Padmin22": d,"Alexvonzu": d,"Klcai": d,"Bridoc": d,"Feuchtcc": d,"Karthik Jagadeesh": d,"Smj39": d,"Xavier Peniche": d,"Ka Yaffa": d,"Jysg23": d,"Wsko.ko": d,"Psyoon": d,"Wvhoya": d,"Act25": d,"Hpl1981": d,"Jacqueline F": d,"IR393.cfc211": d,"Joko123nm": d,"Kmac1986": d,"Amfarr21": d,"IR393Anjan": d};
|
| | 114 | +
|
| | 115 | +for (var username in editors) {
|
| | 116 | + for (var obsdate in editors[username]) {
|
| | 117 | + print(obsdate);
|
| | 118 | + }
|
| | 119 | +}
|
| | 120 | + print(username);
|
| | 121 | + //var reverts = db.enwiki_editors_dataset.findOne({"username": username}, {"revert_count": 1});
|
| | 122 | + //for (obsdate in editors[username]) {
|
| | 123 | + //month = date.getMonth();
|
| | 124 | + //year = date.getYear();
|
| | 125 | + // print(month, year);
|
| | 126 | + // }
|
| | 127 | +} |
| \ No newline at end of file |
| Index: trunk/tools/editor_trends/etl/variables.py |
| — | — | @@ -254,6 +254,7 @@ |
| 255 | 255 | past_revert['reverted_contributor'] = -1 |
| 256 | 256 | return past_revert |
| 257 | 257 | |
| | 258 | + |
| 258 | 259 | def is_revision_reverted(hash_cur, hashes): |
| 259 | 260 | ''' |
| 260 | 261 | Determine whether an edit was reverted or not based on md5 hashes |
| — | — | @@ -314,7 +315,7 @@ |
| 315 | 316 | ''' |
| 316 | 317 | This function determines the xml_namespace version |
| 317 | 318 | ''' |
| 318 | | - for elem in siteinfo : |
| | 319 | + for elem in siteinfo: |
| 319 | 320 | if elem.tag.endswith('sitename'): |
| 320 | 321 | xml_namespace = elem.tag |
| 321 | 322 | pos = xml_namespace.find('sitename') |
| Index: trunk/tools/editor_trends/etl/extracter.py |
| — | — | @@ -133,7 +133,7 @@ |
| 134 | 134 | '''
|
| 135 | 135 | This function determines the title of an article and the
|
| 136 | 136 | namespace to which it belongs. Then, if the namespace is one
|
| 137 | | - which we are interested set parse to True so that we start
|
| | 137 | + which we are interested in set parse to True so that we start
|
| 138 | 138 | parsing this article, else it will skip this article.
|
| 139 | 139 | '''
|
| 140 | 140 | title = variables.parse_title(elem)
|
| Index: trunk/tools/editor_trends/etl/transformer.py |
| — | — | @@ -179,6 +179,7 @@ |
| 180 | 180 | dc = cleanup_datacontainer(dc, {}) |
| 181 | 181 | return dc |
| 182 | 182 | |
| | 183 | + |
| 183 | 184 | def calculate_cum_edits(edits): |
| 184 | 185 | cum_edit_count_main_ns = 0 |
| 185 | 186 | cum_edit_count_other_ns = 0 |
| — | — | @@ -191,6 +192,7 @@ |
| 192 | 193 | |
| 193 | 194 | return cum_edit_count_main_ns, cum_edit_count_other_ns |
| 194 | 195 | |
| | 196 | + |
| 195 | 197 | def determine_articles_workedon(edits, first_year, final_year): |
| 196 | 198 | ''' |
| 197 | 199 | This function creates a list of article_ids that an editor has worked on in |
| Index: trunk/tools/editor_trends/kaggle/training.py |
| — | — | @@ -1,25 +1,83 @@ |
| | 2 | +#!/usr/bin/python |
| | 3 | +# -*- coding: utf-8 -*- |
| | 4 | +''' |
| | 5 | +Copyright (C) 2010 by Diederik van Liere (dvanliere@gmail.com) |
| | 6 | +This program is free software; you can redistribute it and/or |
| | 7 | +modify it under the terms of the GNU General Public License version 2 |
| | 8 | +as published by the Free Software Foundation. |
| | 9 | +This program is distributed in the hope that it will be useful, |
| | 10 | +but WITHOUT ANY WARRANTY; without even the implied warranty of |
| | 11 | +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. |
| | 12 | +See the GNU General Public License for more details, at |
| | 13 | +http://www.fsf.org/licenses/gpl.html |
| | 14 | +''' |
| | 15 | + |
| | 16 | +__author__ = '''\n'''.join(['Diederik van Liere (dvanliere@gmail.com)', ]) |
| | 17 | +__email__ = 'dvanliere at gmail dot com' |
| | 18 | +__date__ = '2011-04-12' |
| | 19 | +__version__ = '0.1' |
| | 20 | + |
| 2 | 21 | import codecs |
| 3 | 22 | import os |
| | 23 | +from datetime import datetime |
| | 24 | +import json |
| 4 | 25 | |
| | 26 | +location = '/home/diederik/wikimedia/en/wiki/kaggle_prediction' |
| | 27 | +files = os.listdir(location) |
| | 28 | +files.reverse() |
| | 29 | +dataset = codecs.open('training.tsv', 'w', 'utf-8') |
| | 30 | +t0 = datetime.now() |
| | 31 | +max_size = 2147483648 |
| | 32 | +titles = {} |
| | 33 | +ids = set() |
| | 34 | +size = 0 |
| | 35 | +cnt_obs = 0 |
| | 36 | +max_size_reached = False |
| 5 | 37 | |
| | 38 | +for filename in files: |
| | 39 | + if not filename.startswith('comments') and not filename.startswith('articles'): |
| | 40 | + fh = codecs.open(os.path.join(location, filename)) |
| | 41 | + if max_size_reached == True: |
| | 42 | + break |
| | 43 | + for line in fh: |
| | 44 | + line = line.strip() |
| | 45 | + line = line.split('\t') |
| | 46 | + if len(line) != 12: |
| | 47 | + continue |
| | 48 | + if line[10] == '1': |
| | 49 | + continue |
| | 50 | + username = line[3].lower() |
| | 51 | + if username.endswith('bot'): |
| | 52 | + #line[10] = '1' |
| | 53 | + continue |
| | 54 | + cnt_obs += 1 |
| | 55 | + title_id = line[1] |
| | 56 | + ids.add(line[2]) |
| | 57 | + title = line.pop(5) |
| | 58 | + titles[title_id] = title |
| | 59 | + line.append('\n') |
| | 60 | + line = '\t'.join(line) |
| | 61 | + size += len(line) |
| | 62 | + if size > max_size: |
| | 63 | + max_size_reached = True |
| | 64 | + dataset.write(line.decode('utf-8')) |
| 6 | 65 | |
| 7 | | -location = '/home/diederik/wikimedia/wikilytics/en/wiki/txt' |
| 8 | | -files = os.listdir(location) |
| | 66 | +dataset.close() |
| 9 | 67 | |
| 10 | | -output = codecs.open('training.txt', 'w', 'utf-8') |
| | 68 | +fh = codecs.open('titles.tsv', 'w', 'utf-8') |
| | 69 | +for id, title in titles.iteritems(): |
| | 70 | + fh.write('%s\t%s\n' % (id, title.decode('utf-8'))) |
| | 71 | +fh.close() |
| 11 | 72 | |
| 12 | | -for filename in files: |
| 13 | | - fh = codecs.open(os.path.join(location, filename)) |
| 14 | | - for line in fh: |
| 15 | | - line = line.strip() |
| 16 | | - line = line.split('\t') |
| 17 | | - if len(line) != 13: |
| 18 | | - continue |
| 19 | | - username = line[12].lower() |
| 20 | | - if username.endswith('bot'): |
| 21 | | - line[5] = 1 |
| 22 | | - line = '\t'.join(line) |
| 23 | | - output.write(line) |
| 24 | | - |
| 25 | | - |
| 26 | | -output.close() |
| \ No newline at end of file |
| | 73 | +fh = codecs.open('ids.json', 'w', 'utf-8') |
| | 74 | +json.dump(ids, fh) |
| | 75 | +#for id in ids: |
| | 76 | +#fh.write('%s\n' % (id.decode('utf-8'))) |
| | 77 | +#fh.write('%s\n' % (json.du) |
| | 78 | +fh.close() |
| | 79 | + |
| | 80 | +t1 = datetime.now() |
| | 81 | +print 'Descriptives:\n' |
| | 82 | +print 'Number of editors: %s' % len(ids) |
| | 83 | +print 'Number of edits: %s' % cnt_obs |
| | 84 | +print 'It took %s to construct the Kaggle training set' % (t1 - t0) |
| Index: trunk/tools/editor_trends/classes/storage.py |
| — | — | @@ -86,7 +86,7 @@ |
| 87 | 87 | '''Find multiple observations in a collection''' |
| 88 | 88 | |
| 89 | 89 | @abstractmethod |
| 90 | | - def find_one(self, key, value): |
| | 90 | + def find_one(self, key, value, var=False): |
| 91 | 91 | '''Find a single observation in a collection''' |
| 92 | 92 | |
| 93 | 93 | @abstractmethod |
| — | — | @@ -145,7 +145,7 @@ |
| 146 | 146 | |
| 147 | 147 | def update(self, key, value, data): |
| 148 | 148 | assert isinstance(data, dict), 'You need to feed me dictionaries.' |
| 149 | | - self.db[self.collection].update({key: value}, data, upsert=True) |
| | 149 | + self.db[self.collection].update({key: value}, {'$set': data}) |
| 150 | 150 | |
| 151 | 151 | def find(self, key=None, qualifier=None): |
| 152 | 152 | if qualifier == 'min': |
| — | — | @@ -154,14 +154,24 @@ |
| 155 | 155 | elif qualifier == 'max': |
| 156 | 156 | return self.db[self.collection].find({ |
| 157 | 157 | key : {'$ne' : False}}).sort(key, pymongo.DESCENDING).limit(1)[0] |
| | 158 | + elif qualifier: |
| | 159 | + return self.db[self.collection].find({key : qualifier}) |
| 158 | 160 | elif key != None: |
| 159 | 161 | return self.db[self.collection].find({}, fields=[key]) |
| 160 | 162 | else: |
| 161 | 163 | return self.db[self.collection].find() |
| 162 | 164 | |
| 163 | | - def find_one(self, key, value): |
| 164 | | - return self.db[self.collection].find_one({key: value}) |
| | 165 | + def find_one(self, key, value, vars=None): |
| | 166 | + if vars: |
| | 167 | + #if you only want to retrieve a specific variable(s) then you need to |
| | 168 | + #specify vars, if vars is None then you will get the entire BSON object |
| | 169 | + vars = vars.split(',') |
| | 170 | + vars = dict([(var, 1) for var in vars]) |
| | 171 | + return self.db[self.collection].find_one({key: value}, vars) |
| | 172 | + else: |
| | 173 | + return self.db[self.collection].find_one({key: value}) |
| 165 | 174 | |
| | 175 | + |
| 166 | 176 | def drop_collection(self): |
| 167 | 177 | self.db.drop_collection(self.collection) |
| 168 | 178 | |
| Index: trunk/tools/editor_trends/classes/analytics.py |
| — | — | @@ -92,7 +92,6 @@ |
| 93 | 93 | project and then calls the plugin that does the actual mapping. |
| 94 | 94 | ''' |
| 95 | 95 | db = storage.init_database(self.rts.storage, self.rts.dbname, self.rts.editors_dataset) |
| 96 | | - x = 0 |
| 97 | 96 | while True: |
| 98 | 97 | try: |
| 99 | 98 | editor_id = self.tasks.get(block=False) |