semantic-link-labs 0.4.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of semantic-link-labs might be problematic. Click here for more details.

Files changed (52) hide show
  1. semantic_link_labs-0.4.1.dist-info/LICENSE +21 -0
  2. semantic_link_labs-0.4.1.dist-info/METADATA +22 -0
  3. semantic_link_labs-0.4.1.dist-info/RECORD +52 -0
  4. semantic_link_labs-0.4.1.dist-info/WHEEL +5 -0
  5. semantic_link_labs-0.4.1.dist-info/top_level.txt +1 -0
  6. sempy_labs/__init__.py +154 -0
  7. sempy_labs/_ai.py +496 -0
  8. sempy_labs/_clear_cache.py +39 -0
  9. sempy_labs/_connections.py +234 -0
  10. sempy_labs/_dax.py +70 -0
  11. sempy_labs/_generate_semantic_model.py +280 -0
  12. sempy_labs/_helper_functions.py +506 -0
  13. sempy_labs/_icons.py +4 -0
  14. sempy_labs/_list_functions.py +1372 -0
  15. sempy_labs/_model_auto_build.py +143 -0
  16. sempy_labs/_model_bpa.py +1354 -0
  17. sempy_labs/_model_dependencies.py +341 -0
  18. sempy_labs/_one_lake_integration.py +155 -0
  19. sempy_labs/_query_scale_out.py +447 -0
  20. sempy_labs/_refresh_semantic_model.py +184 -0
  21. sempy_labs/_tom.py +3766 -0
  22. sempy_labs/_translations.py +378 -0
  23. sempy_labs/_vertipaq.py +893 -0
  24. sempy_labs/directlake/__init__.py +45 -0
  25. sempy_labs/directlake/_directlake_schema_compare.py +110 -0
  26. sempy_labs/directlake/_directlake_schema_sync.py +128 -0
  27. sempy_labs/directlake/_fallback.py +62 -0
  28. sempy_labs/directlake/_get_directlake_lakehouse.py +69 -0
  29. sempy_labs/directlake/_get_shared_expression.py +59 -0
  30. sempy_labs/directlake/_guardrails.py +84 -0
  31. sempy_labs/directlake/_list_directlake_model_calc_tables.py +54 -0
  32. sempy_labs/directlake/_show_unsupported_directlake_objects.py +89 -0
  33. sempy_labs/directlake/_update_directlake_model_lakehouse_connection.py +81 -0
  34. sempy_labs/directlake/_update_directlake_partition_entity.py +64 -0
  35. sempy_labs/directlake/_warm_cache.py +210 -0
  36. sempy_labs/lakehouse/__init__.py +24 -0
  37. sempy_labs/lakehouse/_get_lakehouse_columns.py +81 -0
  38. sempy_labs/lakehouse/_get_lakehouse_tables.py +250 -0
  39. sempy_labs/lakehouse/_lakehouse.py +85 -0
  40. sempy_labs/lakehouse/_shortcuts.py +296 -0
  41. sempy_labs/migration/__init__.py +29 -0
  42. sempy_labs/migration/_create_pqt_file.py +239 -0
  43. sempy_labs/migration/_migrate_calctables_to_lakehouse.py +429 -0
  44. sempy_labs/migration/_migrate_calctables_to_semantic_model.py +150 -0
  45. sempy_labs/migration/_migrate_model_objects_to_semantic_model.py +524 -0
  46. sempy_labs/migration/_migrate_tables_columns_to_semantic_model.py +165 -0
  47. sempy_labs/migration/_migration_validation.py +227 -0
  48. sempy_labs/migration/_refresh_calc_tables.py +129 -0
  49. sempy_labs/report/__init__.py +35 -0
  50. sempy_labs/report/_generate_report.py +253 -0
  51. sempy_labs/report/_report_functions.py +855 -0
  52. sempy_labs/report/_report_rebind.py +131 -0
sempy_labs/_translations.py ADDED
@@ -0,0 +1,378 @@
1
+ import pandas as pd
2
+ from typing import List, Optional, Union
3
+ from sempy._utils._log import log
4
+ import sempy_labs._icons as icons
5
+
6
+
7
+ @log
8
+ def translate_semantic_model(
9
+ dataset: str,
10
+ languages: Union[str, List[str]],
11
+ exclude_characters: Optional[str] = None,
12
+ workspace: Optional[str] = None,
13
+ ):
14
+ """
15
+ Translates names, descriptions, display folders for all objects in a semantic model.
16
+
17
+ Parameters
18
+ ----------
19
+ dataset : str
20
+ Name of the semantic model.
21
+ languages : str, List[str]
22
+ The language code(s) in which to translate the semantic model.
23
+ exclude_characters : str
24
+ A string specifying characters which will be replaced by a space in the translation text when sent to the translation service.
25
+ workspace : str, default=None
26
+ The Fabric workspace name.
27
+ Defaults to None which resolves to the workspace of the attached lakehouse
28
+ or if no lakehouse attached, resolves to the workspace of the notebook.
29
+
30
+ Returns
31
+ -------
32
+
33
+ """
34
+
35
+ from synapse.ml.services import Translate
36
+ from pyspark.sql.functions import col, flatten
37
+ from pyspark.sql import SparkSession
38
+ from ._tom import connect_semantic_model
39
+
40
+ if isinstance(languages, str):
41
+ languages = [languages]
42
+
43
+ dfPrep = pd.DataFrame(
44
+ columns=["Object Type", "Name", "Description", "Display Folder"]
45
+ )
46
+
47
+ with connect_semantic_model(
48
+ dataset=dataset, readonly=False, workspace=workspace
49
+ ) as tom:
50
+
51
+ if exclude_characters is None:
52
+ for o in tom.model.Tables:
53
+ new_data = {
54
+ "Object Type": "Table",
55
+ "Name": o.Name,
56
+ "TName": o.Name,
57
+ "Description": o.Description,
58
+ "TDescription": o.Description,
59
+ "Display Folder": None,
60
+ "TDisplay Folder": None,
61
+ }
62
+ dfPrep = pd.concat(
63
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
64
+ )
65
+ for o in tom.all_columns():
66
+ new_data = {
67
+ "Object Type": "Column",
68
+ "Name": o.Name,
69
+ "TName": o.Name,
70
+ "Description": o.Description,
71
+ "TDescription": o.Description,
72
+ "Display Folder": o.DisplayFolder,
73
+ "TDisplay Folder": o.DisplayFolder,
74
+ }
75
+ dfPrep = pd.concat(
76
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
77
+ )
78
+ for o in tom.all_measures():
79
+ new_data = {
80
+ "Object Type": "Measure",
81
+ "Name": o.Name,
82
+ "TName": o.Name,
83
+ "Description": o.Description,
84
+ "TDescription": o.Description,
85
+ "Display Folder": o.DisplayFolder,
86
+ "TDisplay Folder": o.DisplayFolder,
87
+ }
88
+ dfPrep = pd.concat(
89
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
90
+ )
91
+ for o in tom.all_hierarchies():
92
+ new_data = {
93
+ "Object Type": "Hierarchy",
94
+ "Name": o.Name,
95
+ "TName": o.Name,
96
+ "Description": o.Description,
97
+ "TDescription": o.Description,
98
+ "Display Folder": o.DisplayFolder,
99
+ "TDisplay Folder": o.DisplayFolder,
100
+ }
101
+ dfPrep = pd.concat(
102
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
103
+ )
104
+ else:
105
+ for o in tom.model.Tables:
106
+ oName = o.Name
107
+ oDescription = o.Description
108
+ for s in exclude_characters:
109
+ oName = oName.replace(s, " ")
110
+ oDescription = oDescription.replace(s, " ")
111
+ new_data = {
112
+ "Object Type": "Table",
113
+ "Name": o.Name,
114
+ "TName": oName,
115
+ "Description": o.Description,
116
+ "TDescription": oDescription,
117
+ "Display Folder": None,
118
+ "TDisplay Folder": None,
119
+ }
120
+ dfPrep = pd.concat(
121
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
122
+ )
123
+ for o in tom.all_columns():
124
+ oName = o.Name
125
+ oDescription = o.Description
126
+ oDisplayFolder = o.DisplayFolder
127
+ for s in exclude_characters:
128
+ oName = oName.replace(s, " ")
129
+ oDescription = oDescription.replace(s, " ")
130
+ oDisplayFolder = oDisplayFolder.replace(s, " ")
131
+ new_data = {
132
+ "Object Type": "Column",
133
+ "Name": o.Name,
134
+ "TName": oName,
135
+ "Description": o.Description,
136
+ "TDescription": oDescription,
137
+ "Display Folder": o.DisplayFolder,
138
+ "TDisplay Folder": oDisplayFolder,
139
+ }
140
+ dfPrep = pd.concat(
141
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
142
+ )
143
+ for o in tom.all_measures():
144
+ oName = o.Name
145
+ oDescription = o.Description
146
+ oDisplayFolder = o.DisplayFolder
147
+ for s in exclude_characters:
148
+ oName = oName.replace(s, " ")
149
+ oDescription = oDescription.replace(s, " ")
150
+ oDisplayFolder = oDisplayFolder.replace(s, " ")
151
+ new_data = {
152
+ "Object Type": "Measure",
153
+ "Name": o.Name,
154
+ "TName": oName,
155
+ "Description": o.Description,
156
+ "TDescription": oDescription,
157
+ "Display Folder": o.DisplayFolder,
158
+ "TDisplay Folder": oDisplayFolder,
159
+ }
160
+ dfPrep = pd.concat(
161
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
162
+ )
163
+ for o in tom.all_hierarchies():
164
+ oName = o.Name
165
+ oDescription = o.Description
166
+ oDisplayFolder = o.DisplayFolder
167
+ for s in exclude_characters:
168
+ oName = oName.replace(s, " ")
169
+ oDescription = oDescription.replace(s, " ")
170
+ oDisplayFolder = oDisplayFolder.replace(s, " ")
171
+ new_data = {
172
+ "Object Type": "Hierarchy",
173
+ "Name": o.Name,
174
+ "TName": oName,
175
+ "Description": o.Description,
176
+ "TDescription": oDescription,
177
+ "Display Folder": o.DisplayFolder,
178
+ "TDisplay Folder": oDisplayFolder,
179
+ }
180
+ dfPrep = pd.concat(
181
+ [dfPrep, pd.DataFrame(new_data, index=[0])], ignore_index=True
182
+ )
183
+
184
+ spark = SparkSession.builder.getOrCreate()
185
+ df = spark.createDataFrame(dfPrep)
186
+
187
+ columns = ["Name", "Description", "Display Folder"]
188
+
189
+ for clm in columns:
190
+ columnToTranslate = f"T{clm}"
191
+ translate = (
192
+ Translate()
193
+ .setTextCol(columnToTranslate)
194
+ .setToLanguage(languages)
195
+ .setOutputCol("translation")
196
+ .setConcurrency(5)
197
+ )
198
+
199
+ transDF = (
200
+ translate.transform(df)
201
+ .withColumn("translation", flatten(col("translation.translations")))
202
+ .withColumn("translation", col("translation.text"))
203
+ .select("Object Type", clm, columnToTranslate, "translation")
204
+ )
205
+
206
+ df_panda = transDF.toPandas()
207
+ print(f"{icons.in_progress} Translating {clm}s...")
208
+
209
+ for lang in languages:
210
+ i = languages.index(lang)
211
+ tom.add_translation(language=lang)
212
+ print(f"{icons.in_progress} Translating into the '{lang}' language...")
213
+
214
+ for t in tom.model.Tables:
215
+ if t.IsHidden == False:
216
+ if clm == "Name":
217
+ df_filt = df_panda[
218
+ (df_panda["Object Type"] == "Table")
219
+ & (df_panda["Name"] == t.Name)
220
+ ]
221
+ if len(df_filt) == 1:
222
+ tr = df_filt["translation"].str[i].iloc[0]
223
+ tom.set_translation(
224
+ object=t, language=lang, property="Name", value=tr
225
+ )
226
+ print(
227
+ f"{icons.green_dot} Translation '{tr}' set for the '{lang}' language on the '{t.Name}' table."
228
+ )
229
+ elif clm == "Description" and t.Description is not None:
230
+ df_filt = df_panda[
231
+ (df_panda["Object Type"] == "Table")
232
+ & (df_panda["Description"] == t.Description)
233
+ ]
234
+ if len(df_filt) == 1:
235
+ tr = df_filt["translation"].str[i].iloc[0]
236
+ tom.set_translation(
237
+ object=t,
238
+ language=lang,
239
+ property="Description",
240
+ value=tr,
241
+ )
242
+ for c in t.Columns:
243
+ if c.IsHidden == False:
244
+ if clm == "Name":
245
+ df_filt = df_panda[
246
+ (df_panda["Object Type"] == "Column")
247
+ & (df_panda["Name"] == c.Name)
248
+ ]
249
+ if len(df_filt) == 1:
250
+ tr = df_filt["translation"].str[i].iloc[0]
251
+ tom.set_translation(
252
+ object=c,
253
+ language=lang,
254
+ property="Name",
255
+ value=tr,
256
+ )
257
+ print(
258
+ f"{icons.green_dot} Translation '{tr}' set on the '{c.Name}' column within the {t.Name}' table."
259
+ )
260
+ elif clm == "Description" and c.Description is not None:
261
+ df_filt = df_panda[
262
+ (df_panda["Object Type"] == "Column")
263
+ & (df_panda["Description"] == c.Description)
264
+ ]
265
+ if len(df_filt) == 1:
266
+ tr = df_filt["translation"].str[i].iloc[0]
267
+ tom.set_translation(
268
+ object=c,
269
+ language=lang,
270
+ property="Description",
271
+ value=tr,
272
+ )
273
+ elif (
274
+ clm == "Display Folder"
275
+ and c.DisplayFolder is not None
276
+ ):
277
+ df_filt = df_panda[
278
+ (df_panda["Object Type"] == "Column")
279
+ & (df_panda["Display Folder"] == c.Description)
280
+ ]
281
+ if len(df_filt) == 1:
282
+ tr = df_filt["translation"].str[i].iloc[0]
283
+ tom.set_translation(
284
+ object=c,
285
+ language=lang,
286
+ property="Display Folder",
287
+ value=tr,
288
+ )
289
+ for h in t.Hierarchies:
290
+ if h.IsHidden == False:
291
+ if clm == "Name":
292
+ df_filt = df_panda[
293
+ (df_panda["Object Type"] == "Hierarchy")
294
+ & (df_panda["Name"] == h.Name)
295
+ ]
296
+ if len(df_filt) == 1:
297
+ tr = df_filt["translation"].str[i].iloc[0]
298
+ tom.set_translation(
299
+ object=h,
300
+ language=lang,
301
+ property="Name",
302
+ value=tr,
303
+ )
304
+ elif clm == "Description" and h.Description is not None:
305
+ df_filt = df_panda[
306
+ (df_panda["Object Type"] == "Hierarchy")
307
+ & (df_panda["Description"] == h.Description)
308
+ ]
309
+ if len(df_filt) == 1:
310
+ tr = df_filt["translation"].str[i].iloc[0]
311
+ tom.set_translation(
312
+ object=h,
313
+ language=lang,
314
+ property="Description",
315
+ value=tr,
316
+ )
317
+ elif (
318
+ clm == "Display Folder"
319
+ and h.DisplayFolder is not None
320
+ ):
321
+ df_filt = df_panda[
322
+ (df_panda["Object Type"] == "Hierarchy")
323
+ & (df_panda["Display Folder"] == h.Description)
324
+ ]
325
+ if len(df_filt) == 1:
326
+ tr = df_filt["translation"].str[i].iloc[0]
327
+ tom.set_translation(
328
+ object=h,
329
+ language=lang,
330
+ property="Display Folder",
331
+ value=tr,
332
+ )
333
+ for ms in t.Measures:
334
+ if ms.IsHidden == False:
335
+ if clm == "Name":
336
+ df_filt = df_panda[
337
+ (df_panda["Object Type"] == "Measure")
338
+ & (df_panda["Name"] == ms.Name)
339
+ ]
340
+ if len(df_filt) == 1:
341
+ tr = df_filt["translation"].str[i].iloc[0]
342
+ tom.set_translation(
343
+ object=ms,
344
+ language=lang,
345
+ property="Name",
346
+ value=tr,
347
+ )
348
+ print(
349
+ f"{icons.green_dot} Translation '{tr}' set on the '{ms.Name}' column within the {t.Name}' table."
350
+ )
351
+ elif clm == "Description" and ms.Description is not None:
352
+ df_filt = df_panda[
353
+ (df_panda["Object Type"] == "Measure")
354
+ & (df_panda["Description"] == ms.Description)
355
+ ]
356
+ if len(df_filt) == 1:
357
+ tr = df_filt["translation"].str[i].iloc[0]
358
+ tom.set_translation(
359
+ object=ms,
360
+ language=lang,
361
+ property="Description",
362
+ value=tr,
363
+ )
364
+ elif (
365
+ clm == "Display Folder" and ms.DisplayFolder is not None
366
+ ):
367
+ df_filt = df_panda[
368
+ (df_panda["Object Type"] == "Measure")
369
+ & (df_panda["Display Folder"] == ms.Description)
370
+ ]
371
+ if len(df_filt) == 1:
372
+ tr = df_filt["translation"].str[i].iloc[0]
373
+ tom.set_translation(
374
+ object=ms,
375
+ language=lang,
376
+ property="Display Folder",
377
+ value=tr,
378
+ )