-
Notifications
You must be signed in to change notification settings - Fork 0
/
DBconnection.py
303 lines (271 loc) · 9.52 KB
/
DBconnection.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
import pymongo
import StreamingApiForUser
import utils
from pymongo import MongoClient
from bson.son import SON
import matplotlib.pylab as plt
from datetime import datetime, timedelta
from dateutil.parser import parse
class DBconnection:
dburl = ""
dbText = ""
collectionString = ""
# url='mongodb://localhost:27017/'
# dbText="WEBSCIENCE"
# collectionString= "twitter_meta_data"
def __init__(self, url, dbText, *args):
self.dburl = url
self.dbText = dbText
if len(args) > 0:
self.collectionString = args[0]
def dbconnect_to_collection(self):
'''
get the collection from database
:return: collection
'''
try:
myclient = pymongo.MongoClient(self.dburl)
db = myclient[self.dbText]
collection = db[self.collectionString]
return collection
except:
print("fail to connect to collection(table)")
def insert_one_item(self, itemDictOne):
'''
insert one data into collection
:param itemDictOne: data (json)
:return:
'''
x = self.dbconnect_to_collection().insert_one(itemDictOne)
if x is not None:
print("insert successfully")
else:
print("insert failed")
def insert_many_item(self, itemDicts):
'''
insert many data into collection
:param itemDicts: data (json)
:return:
'''
x = self.dbconnect_to_collection().insert_one(itemDicts)
# if x is not None:
# # print("insert many successfully")
# else:
# print("insert many failed")
@classmethod
def count(cls,collection):
'''
get the number of data in collection
:param collection:
:return: the number of data
'''
count=0
for elem in collection.find():
count=count+1
return count
@classmethod
def count_all(cls, collection):
'''
count the number of data and divide these data into time period
:param collection:
:return: list
time
'''
list = []
resultslist = []
count = 0
time = []
# starttime = parse(elem["created_at"])
for elem in collection.find():
resultslist.append(elem)
starttime = parse(resultslist[0]["created_at"])
temp = starttime
for elem in collection.find():
nowtime = parse(elem["created_at"])
if (nowtime - temp) < timedelta(minutes=10):
count = count + 1
elif (nowtime - temp) >= timedelta(minutes=10):
list.append(count)
count = 1
temp = nowtime
time.append(str(temp.strftime('%H:%M:%S')))
return list, time
@classmethod
def count_all_google(cls, collection):
'''
count all function for google
:param collection:
:return:
'''
list = []
resultslist = []
count = 0
time = []
# starttime = parse(elem["created_at"])
for elem in collection.find():
resultslist.append(elem)
starttime = parse(resultslist[0]["published"])
temp = starttime
for elem in collection.find():
nowtime = parse(elem["published"])
if -(nowtime - temp) < timedelta(minutes=10):
count = count + 1
elif -(nowtime - temp) >= timedelta(minutes=10):
list.append(count)
count = 1
temp = nowtime
time.append(str(temp.strftime('%H:%M:%S')))
return list, time
@classmethod
def count_twitter_with_geotag(cls, collection):
'''
count the number of geotagged tweets and divide into time slice
:param collection:
:return: time list
'''
list = []
resultslist = []
count = 0
time = []
# starttime = parse(elem["created_at"])
for elem in collection.find():
resultslist.append(elem)
starttime = parse(resultslist[0]["created_at"])
temp = starttime
for elem in collection.find():
nowtime = parse(elem["created_at"])
if elem["geo"] != None:
for e in elem["geo"]:
if (e == "Glasgow" or "glasgow") and (nowtime - temp) < timedelta(minutes=10):
count = count + 1
break
elif e == "Glasgow" or "glasgow" and (nowtime - temp) >= timedelta(minutes=10):
list.append(count)
count = 1
temp = nowtime
time.append(str(temp.strftime('%H:%M:%S')))
break
return list, time
@classmethod
def count_twitter_with_geotag_google(cls, collection):
'''
count geo for google plus
:param collection:
:return:
'''
list = []
resultslist = []
count = 0
# time = []
# starttime = parse(elem["created_at"])
for elem in collection.find():
resultslist.append(elem)
starttime = parse(resultslist[0]["published"])
temp = starttime
for elem in collection.find():
# nowtime = parse(elem["published"])
if "location" in elem:
for e in elem["location"].values():
if (e == "Glasgow" ):
count = count + 1
return count
@classmethod
def count_retweet(cls, collection):
'''
count the retweet number in collection
:param collection:
:return:
'''
list = []
resultslist = []
count = 0
time = []
# starttime = parse(elem["created_at"])
for elem in collection.find():
resultslist.append(elem)
starttime = parse(resultslist[0]["created_at"])
temp = starttime
for elem in collection.find():
nowtime = parse(elem["created_at"])
if elem["retweet_count"] == 0:
continue
elif elem["retweet_count"] != 0 and (nowtime - temp) < timedelta(minutes=10):
count = count + 1
elif elem["retweet_count"] != 0 and (nowtime - temp) >= timedelta(minutes=10):
list.append(count)
count = 1
temp = nowtime
time.append(str(temp.strftime('%H:%M:%S')))
return list, time
@classmethod
def count_quotes(cls, collection):
# count = 0
# for elem in collection.find():
# if "quoted_status" in elem:
# if elem["quoted_status"] == None:
# continue
# else:
# count = count + 1
#
# return count
list = []
resultslist = []
count = 0
time = []
for elem in collection.find():
resultslist.append(elem)
starttime = parse(resultslist[0]["created_at"])
temp = starttime
for elem in collection.find():
nowtime = parse(elem["created_at"])
if "quoted_status" in elem:
if elem["quoted_status"] == None:
continue
elif elem["quoted_status"] != None and (nowtime - temp) < timedelta(minutes=5):
count = count + 1
elif elem["quoted_status"] != None and (nowtime - temp) >= timedelta(minutes=5):
list.append(count)
count = 1
temp = nowtime
time.append(str(temp.strftime('%H:%M:%S')))
return list, time
@classmethod
def redundant_tweets_count(cls, collec1, collec2):
'''
count redundent tweets from two different collections
:param collec1: string
:param collec2: string
:return: print out the same tweets
'''
collection1 = collec1
collection2 = collec2
db = MongoClient().WEBSCIENCE
pipeline = [
{"$unwind": "$text"},
{"$group": {"_id": "$text", "count": {"$sum": 1}}},
{"$sort": SON([("count", -1), ("_id", -1)])}
]
if collection1 == "twitter_REST_search_geo":
a = list(db.twitter_REST_search_geo.aggregate(pipeline))
if collection1 == "Twitter_location_with_tag":
a = list(db.Twitter_location_with_tag.aggregate(pipeline))
if collection1 == "Twitter_location_without_tag":
a = list(db.Twitter_location_without_tag.aggregate(pipeline))
if collection2 == "twitter_REST_search_geo":
b = list(db.twitter_REST_search_geo.aggregate(pipeline))
if collection2 == "Twitter_location_with_tag":
b = list(db.Twitter_location_with_tag.aggregate(pipeline))
if collection2 == "Twitter_location_without_tag":
b = list(db.Twitter_location_without_tag.aggregate(pipeline))
for Aelem in a:
for belem in b:
if Aelem["_id"] == belem["_id"]:
print(belem)
if __name__ == '__main__':
a = DBconnection('mongodb://localhost:27017/', "WEBSCIENCE", "twitter_REST_search_geo")
#if you want to check different figure, please change the function in following code
list, time = DBconnection.count_quotes(a.dbconnect_to_collection())
plt.bar(range(len(list)), list)
plt.xticks(range(len(time)), time)
plt.savefig("countquote.pdf")
plt.show()