-
Notifications
You must be signed in to change notification settings - Fork 27
/
get_operations.py
246 lines (184 loc) · 5.5 KB
/
get_operations.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
import importlib
import json
import os
import sys
import datalabs # noqa
from datalabs.features.featurize import general # noqa
def findDecorators(target):
import ast # noqa
import inspect
res = {}
def visit_FunctionDef(node):
res[node.name] = [ast.dump(e) for e in node.decorator_list]
V = ast.NodeVisitor()
V.visit_FunctionDef = visit_FunctionDef
V.visit(compile(inspect.getsource(target), "?", "exec", ast.PyCF_ONLY_AST))
return res
def parse_dec_ast(info):
dec_class_type = info.split("func=Name(id='")[-1].split("',")[0]
if dec_class_type.find("_") != -1:
dec_class_type = dec_class_type.split("_")[-1]
arg_keys = []
for x in info.split("keyword(arg='")[1:]:
arg_keys.append(x.split("', value=")[0])
arg_values = []
for x in info.split("value=Str(s='")[1:]:
arg_values.append(x.split("'))")[0])
new_dict = dict(zip(arg_keys, arg_values))
res = {"class_type": dec_class_type, "args": new_dict}
return res
ALL_FUNCS = []
"""
featurize.general
"""
from featurize import general # noqa
funcs = findDecorators(general)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
# featurize.summarization
from featurize import summarization # noqa
funcs = findDecorators(summarization)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
"""
edit.general
"""
from edit import general # noqa
funcs = findDecorators(general)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
"""
edit.general.plugins
"""
dir_operations = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
"src/datalabs/operations/edit/plugins/general/",
)
sys.path.append(dir_operations)
# print(dir_operations)
for file_name in os.listdir(dir_operations):
if not file_name.endswith(".py") and file_name != "__pycache__":
# print(f"{file_name}.transformation.{file_name}")
my_module = importlib.import_module(f"{file_name}.transformation")
# extract metadata information given the module: "my_module:
funcs = findDecorators(my_module)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
"""
preprocess.general
"""
from preprocess import general # noqa
funcs = findDecorators(general)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
"""
aggregate.general
"""
from aggregate import general # noqa
funcs = findDecorators(general)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
# aggregate.summarization
from aggregate import summarization # noqa
funcs = findDecorators(summarization)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
# aggregate.sequence_labeling
from aggregate import sequence_labeling # noqa
funcs = findDecorators(sequence_labeling)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
# aggregate.text_matching
from aggregate import text_matching # noqa
funcs = findDecorators(text_matching)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
# aggregate.text_classification
from aggregate import text_classification # noqa
funcs = findDecorators(text_classification)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
ALL_FUNCS.append(func_metadata)
# ------------------------- prompt ------------------
# aggregate.sequence_labeling
from prompt import topic_classification # noqa
funcs = findDecorators(topic_classification)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
print(func_metadata)
ALL_FUNCS.append(func_metadata)
from prompt import summarization # noqa
funcs = findDecorators(summarization)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
print(func_metadata)
ALL_FUNCS.append(func_metadata)
from prompt import sentiment_classification # noqa
funcs = findDecorators(sentiment_classification)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
print(func_metadata)
ALL_FUNCS.append(func_metadata)
from prompt import natural_language_inference # noqa
funcs = findDecorators(natural_language_inference)
for k, v in funcs.items():
if len(v) == 0:
continue
info = v[0]
func_metadata = parse_dec_ast(info)
print(func_metadata)
ALL_FUNCS.append(func_metadata)
for k in ALL_FUNCS:
print(k)
with open("./docs/Resources/operations_info/operations_info.json", "w") as f:
json.dump(ALL_FUNCS, f, indent=4)
# json_string = json.dumps(ALL_FUNCS, indent = 4)
# print(json_string)