-
Notifications
You must be signed in to change notification settings - Fork 2
/
classification_resources.py
268 lines (227 loc) · 8.18 KB
/
classification_resources.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
#OpenAIRE - Classification of resources according to DCAT
#Classifies the metadata entries for creator, publisher and contributor
#classifies the entries of creator into the classes person (creatorPerson), organisation (creatorOrganization) and agent (creatorOther)
#classifies the entries of publisher into the classes organisation and agent
#classifies the entries of contributor into the classes organisation and agent
import spacy
nlp = spacy.load('en_core_web_sm')
import pandas as pd
df = pd.read_csv("/OpenAire_unclassified.csv")
df['creatorPerson'] = ""
df['creatorOrganization'] = ""
df['creatorOther'] = ""
df['publisherOrganization'] = ""
df['publisherOther'] = ""
df['contributorOrganization'] = ""
df['contributorOther'] = ""
i = 0
while i < len(df.index):
cellvalue = df['creator'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
persons = ""
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "PERSON"):
persons = persons + X.text + ", "
elif (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if persons.endswith(", "):
max_len = len(persons)
unwanted_cut_off = max_len - 2
persons = persons[0:unwanted_cut_off]
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df['creatorPerson'][i] = persons
df['creatorOrganization'][i] = organization
df['creatorOther'][i] = other
i += 1
i = 0
while i < len(df.index):
cellvalue = df['publisher'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df['publisherOrganization'][i] = organization
df['publisherOther'][i] = other
if (cellvaluestr.lower() == "figshare"):
df['publisherOther'][i] = cellvaluestr
if (cellvaluestr.lower() == "zenodo"):
df['publisherOther'][i] = cellvaluestr
i += 1
i = 0
while i < len(df.index):
cellvalue = df['contributor'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df['contributorOrganization'][i] = organization
df['contributorOther'][i] = other
i += 1
df.to_csv('/OpenAire_classified.csv', index=False)
#Wikidata - Classification of resources according to DCAT
#Classifies the metadata entries for author, authorString, publisher and contributor
#classifies the entries of author into the classes person (authorPerson), organisation (authorOrganization) and agent (authorOther)
#classifies the entries of authorString into the classes person (authorStringPerson), organisation (authorStringOrganization) and agent (authorStringOther)
#classifies the entries of publisher into the classes organisation and agent
#classifies the entries of contributor into the classes organisation and agent
import spacy
nlp = spacy.load('en_core_web_sm')
import pandas as pd
df = pd.read_csv("/Wikidata_unclassified.csv")
df["authorPerson"] = ""
df["authorOrganization"] = ""
df["authorOther"] = ""
df["authorStringPerson"] = ""
df["authorStringOrganization"] = ""
df["authorStringOther"] = ""
df["publisherOrganization"] = ""
df["publisherOther"] = ""
df['contributorOrganization'] = ""
df['contributorOther'] = ""
i = 0
while i < len(df.index):
cellvalue = df['author'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
persons = ""
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "PERSON"):
persons = persons + X.text + ", "
elif (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if persons.endswith(", "):
max_len = len(persons)
unwanted_cut_off = max_len - 2
persons = persons[0:unwanted_cut_off]
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df.at[i, 'authorPerson'] = persons
df.at[i, 'authorOrganization'] = organization
df.at[i, 'authorOther'] = other
i += 1
i = 0
while i < len(df.index):
cellvalue = df['authorString'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
persons = ""
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "PERSON"):
persons = persons + X.text + ", "
elif (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if persons.endswith(", "):
max_len = len(persons)
unwanted_cut_off = max_len - 2
persons = persons[0:unwanted_cut_off]
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df.at[i, 'authorStringPerson'] = persons
df.at[i, 'authorStringOrganization'] = organization
df.at[i, 'authorStringOther'] = other
i += 1
i = 0
while i < len(df.index):
cellvalue = df['publisher'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df.at[i, 'publisherOrganization'] = organization
df.at[i, 'publisherOther'] = other
i += 1
i = 0
while i < len(df.index):
cellvalue = df['contributor'][i]
cellvaluestr = str(cellvalue)
doc = nlp(cellvaluestr)
organization = ""
other = ""
for X in doc.ents:
if (X.label_ == "ORG"):
organization = organization + X.text + ", "
else:
other = other + X.text + ", "
if organization.endswith(", "):
max_len = len(organization)
unwanted_cut_off = max_len - 2
organization = organization[0:unwanted_cut_off]
if other.endswith(", "):
max_len = len(other)
unwanted_cut_off = max_len - 2
other = other[0:unwanted_cut_off]
df.at[i, 'contributorOrganization'] = organization
df.at[i, 'contributorOther'] = other
i += 1
df.to_csv("/Wikidata_classified.csv")