-
Notifications
You must be signed in to change notification settings - Fork 0
/
transform_created_by_year.py
237 lines (177 loc) · 7.91 KB
/
transform_created_by_year.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
import os
movies = set()
actors = set()
def transformNameBasics() -> None:
"""
nconst primaryName birthYear deathYear primaryProfession knownForTitles
nm0000001 Fred Astaire 1899 1987 soundtrack,actor,miscellaneous tt0053137,tt0050419,tt0045537,tt0072308
nm0000002 Lauren Bacall 1924 2014 actress,soundtrack tt0117057,tt0037382,tt0038355,tt0075213
nm0000003 Brigitte Bardot 1934 N actress,soundtrack,music_department tt0054452,tt0057345,tt0049189,tt0056404
nm0000004 John Belushi 1949 1982 actor,soundtrack,writer tt0078723,tt0080455,tt0077975,tt0072562
"""
with open('data/unzipped/name.basics.tsv', encoding='UTF-8') as f:
line_count = 0
for line in f:
line_count += 1
print ("Founded Entries: " + str(line_count))
#input file
fileTSV = open("data/unzipped/name.basics.tsv", "r", encoding='UTF-8')
# output file
fileTTL = open("data/transformed/name.basic.ttl","w", encoding='UTF-8')
fileTTL.write("@prefix imdb: <http://www.h-da.de/sis/lda/imdb/> .\n")
# head / row names
fileTSV.readline()
for _ in range(0,line_count-1,1):
line = fileTSV.readline()
line = line[:-1]
line = line.split('\t')
if not line[0] in actors:
continue
line[4] = line[4].split(',')
line[5] = line[5].split(',')
output = "imdb:" + line[0] + ' imdb:primaryName' + ' "' + line[1] + '";\n'
if '\\N' not in line[2]:
output = output + 'imdb:birthYear "' + line[2] + '"^^xsd:date;\n'
if '\\N' not in line[3]:
output = output + 'imdb:deathYear "' + line[3] + '"^^xsd:date;\n'
if line[4][0] != '\\' and line[4][0] != '' and line[4][0] != '\\N' and line[4][0] != None:
job = 'imdb:primaryProfession '
for j in line[4]:
job = job + 'imdb:' + j + ',\n'
job = job[:-2]
job = job + ';\n'
output = output + job
if line[5][0] != '\\' and line[5][0] != '' and line[5][0] != '\\N' and line[5][0] != None:
knownFor = 'imdb:knownForTitles '
for k in line[5]:
knownFor = knownFor + 'imdb:' + k + ',\n'
knownFor = knownFor[:-2]
knownFor = knownFor + '.\n'
output = output + knownFor
output = output[:-2]
output = output + '.\n'
fileTTL.write(output)
fileTSV.close()
fileTTL.close()
def transformTitleBasics() -> None:
"""
tconst titleType primaryTitle originalTitle isAdult startYear endYear runtimeMinutes genres
tt0000001 short Carmencita Carmencita 0 1894 N 1 Documentary,Short
tt0000002 short Le clown et ses chiens Le clown et ses chiens 0 1892 N 5 Animation,Short
tt0000003 short Pauvre Pierrot Pauvre Pierrot 0 1892 N 4 Animation,Comedy,Romance
tt0000004 short Un bon bock Un bon bock 0 1892 N 12 Animation,Short
"""
with open('data/unzipped/title.basics.tsv', encoding='UTF-8') as f:
line_count = 0
for line in f:
line_count += 1
print ("Founded Entries: " + str(line_count))
# input file
fileTSV = open("data/unzipped/title.basics.tsv", "r", encoding='UTF-8')
# output file
fileTTL = open("data/transformed/title.basics.ttl","w", encoding='UTF-8')
fileTTL.write("@prefix imdb: <http://www.h-da.de/sis/lda/imdb/> .\n")
# head / row names
fileTSV.readline()
for _ in range(0,line_count-1,1):
line = fileTSV.readline()
line = line[:-1]
line = line.split('\t')
try:
year = int(line[5])
if year < 1950 or year > 1959:
continue
movies.add(line[0])
except:
pass
line[8] = line[8].split(',')
output = "imdb:" + line[0] + ' imdb:titleType' + ' "' + line[1] + '";\n'
#if '\\N' not in line[2]:
# output = output + 'imdb:primaryTitle "' + line[2] + '";\n'
if '\\N' not in line[3]:
line[3] = line[3].replace('"','\\"')
output = output + 'imdb:originalTitle "' + line[3] + '";\n'
#if '\\N' not in line[4]:
# output = output + 'imdb:isAdult ' + line[4] + '^^xsd:integer;\n'
if '\\N' not in line[5]:
output = output + 'imdb:startYear "' + line[5] + '"^^xsd:date;\n'
if '\\N' not in line[6]:
output = output + 'imdb:endYear "' + line[6] + '"^^xsd:date;\n'
if '\\N' not in line[7]:
output = output + 'imdb:runtimeMinutes "' + line[7] + '"^^xsd:integer;\n'
if line[8][0] != '\\' and line[8][0] != '' and line[8][0] != '\\N' and line[8][0] != None:
genre = 'imdb:genres '
for g in line[8]:
genre = genre + 'imdb:' + g + ',\n'
genre = genre[:-2]
genre = genre + '.\n'
output = output + genre
output = output[:-2]
output = output + '.\n'
fileTTL.write(output)
fileTSV.close()
fileTTL.close()
def transformTitlePrincipals() -> None:
"""
tconst ordering nconst category job characters
tt0000001 1 nm1588970 self N ["Self"]
tt0000001 2 nm0005690 director N N
tt0000001 3 nm0374658 cinematographer director of photography N
tt0000002 1 nm0721526 director N N
"""
with open('data/unzipped/title.principals.tsv', encoding='UTF-8') as f:
line_count = 0
for line in f:
line_count += 1
print ("Founded Entries: " + str(line_count))
# input file
fileTSV = open("data/unzipped/title.principals.tsv", "r", encoding='UTF-8')
# output file
fileTTL = open("data/transformed/title.principals.ttl","w", encoding='UTF-8')
fileTTL.write("@prefix imdb: <http://www.h-da.de/sis/lda/imdb/> .\n")
fileTTL.write("@prefix principals: <http://www.h-da.de/sis/lda/imdb/principals/> .\n")
# head / row names
fileTSV.readline()
for _ in range(0,line_count-1,1):
line = fileTSV.readline()
line = line[:-1]
line = line.split('\t')
if not line[0] in movies:
continue
actors.add(line[2])
# line[4] = line[4].split(',')
output = "imdb:" + line[0] + ' imdb:hasInvolved' + ' imdb:' + line[2] + ';\n'
if '\\N' not in line[3]:
output = output + 'imdb:category ' + 'imdb:' + line[3] + ';\n'
if '\\N' not in line[4]:
line[4] = line[4].replace('"','\\"')
output = output + 'imdb:job' + ' "' + line[4] + '";\n'
if line[5][0] != '\\' and line[5][0] != '' and line[5][0] != '\\N' and line[5][0] != None:
line[5] = eval(line[5])
characters = 'imdb:characters '
for c in line[5]:
c = c.replace('"','\\"')
characters = characters + '"' + c + '",\n'
characters = characters[:-2]
characters = characters + ';\n'
output = output + characters
output = output[:-2]
output = output + '.\n'
fileTTL.write(output)
fileTSV.close()
fileTTL.close()
if __name__ == '__main__':
outputFolder = 'data/transformed/'
if not os.path.exists(outputFolder):
os.makedirs(outputFolder)
print("Start title.basics")
transformTitleBasics()
print("Finish title.basics")
print()
print("Start title.principals")
transformTitlePrincipals()
print("End title.principals")
print()
print("Start name.basics")
transformNameBasics()
print("Finish name.basics")