-
Notifications
You must be signed in to change notification settings - Fork 8
/
jobs_metadata.yml
518 lines (463 loc) · 27.1 KB
/
jobs_metadata.yml
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
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
# Jobs details below. Common job params listed at the bottom of this file.
jobs:
examples/ex0_extraction_job.py:
description: "Sample API extraction job, pulling public wikipedia data."
api_inputs: {'path': 'https://raw.githubusercontent.com/wikimedia-research/Discovery-Hiring-Analyst-2016/master/events_log.csv.gz'}
output: {'path':'{{base_path}}/wiki_example/input/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
frequency: '@once'
spark_boot: False
examples/ex1_sql_job.sql:
description: "shows sql job, easiest when sql is enough"
py_job: 'jobs/generic/sql_pandas_job.py'
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/wiki_example_sql/output_ex1_sql_pandas/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
dependencies: [examples/ex0_extraction_job.py]
spark_boot: False
frequency: '@daily'
start_date: '{today}T07:00:00+00:00'
emails: ['[email protected]']
examples/ex7_pandas_job.py:
description: "job loading and processing data with pandas. No spark involved."
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas', 'read_kwargs':{}}
output: {'path':'{{base_path}}/wiki_example/output_ex7_pandas/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas', 'save_kwargs':{'sep':'|'}}
dependencies: [examples/ex0_extraction_job.py]
frequency: '@once'
airflow.default_args.retries: 3
airflow.default_args.retry_delay: 'timedelta(minutes=5)'
spark_boot: False
examples/ex1_sql_spark_job:
description: "shows sql job, using spark, for large datasets."
py_job: 'jobs/generic/sql_spark_job.py'
sql_file: 'jobs/examples/ex1_sql_job.sql'
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example_sql/output_ex1_sql_spark/{{now}}/', 'type':'csv'}
dependencies: [examples/ex0_extraction_job.py]
repartition: 1
frequency: '@once'
emails: ['[email protected]']
examples/ex1_frameworked_job.py:
description: "shows frameworked pyspark ops, same as ex1_sql_job but gives access to spark ops to expand on sql."
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex1_frameworked/{{now}}/', 'type':'csv'}
dependencies: [examples/ex0_extraction_job.py]
frequency: 1 day
start_date: "{today}T07:00:00+00:00"
emails: ['[email protected]']
job_using_generic_template:
description: "to show how to reuse existing job code"
py_job: 'jobs/examples/ex1_frameworked_job.py'
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex1_frameworked_p2/{{now}}/', 'type':'csv'}
dependencies: [examples/ex0_extraction_job.py]
examples/ex1_raw_job.py:
frequency: 24h
emails: ['[email protected]']
examples/ex2_frameworked_job.py:
description: "more complex version of ex1_frameworked_job"
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex2/{{now}}/', 'type':'csv'}
frequency: 1 day
start_date: "{today}T07:00:00+00:00"
emails: ['[email protected]']
examples/ex3_incremental_job.py:
description: "focus on incremental loading and dropping"
inputs:
processed_events: {'path':"{{base_path}}/wiki_example/output_ex3_dep/{{latest}}/", 'type':'csv', 'inc_field': 'timestamp_obj'}
output: {'path':'{{base_path}}/wiki_example/output_ex3_inc/incremental_build_v1/', 'type':'csv', 'inc_field': 'other_timestamp'}
dependencies: [examples/ex3_incremental_prep_job.py]
frequency: 24h
emails: ['[email protected]']
examples/ex3_incremental_prep_job.py:
description: "shows computation of dependency as necessary for ex3_incremental_job"
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex3_dep/{{now}}/', 'type':'csv'}
frequency: 24h
emails: ['[email protected]']
examples/ex4_dependency1_job.py:
description: "shows dependency"
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex4_dep1/{{now}}/', 'type':'csv'}
examples/ex4_dependency2_job.py:
description: "shows dependency without specifying inputs path since it is pulled from upstream."
inputs:
some_events: {'path':'{{base_path}}/wiki_example/output_ex4_dep1/{{latest}}/', 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/wiki_example/output_ex4_dep2/{{now}}/dataset.csv', 'df_type':'pandas', 'type':'csv'}
dependencies: [examples/ex4_dependency1_job.py]
examples/ex4_dependency3_job.sql:
description: "shows dependency with sql"
py_job: 'jobs/generic/sql_pandas_job.py'
inputs:
some_events: {'path':'{{base_path}}/wiki_example/output_ex4_dep2/{{latest}}/', 'type':'csv', 'df_type':'pandas', 'from':'examples/ex4_dependency2_job.py'} # 'path' not needed when run as dependency
output: {'path':'{{base_path}}/wiki_example/output_ex4_dep3/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
dependencies: [examples/ex4_dependency2_job.py, examples/ex4_dependency1_job.py]
spark_boot: False
examples/ex4_dependency4_job.py:
description: "shows dependency"
inputs:
some_events: {'path':'{{base_path}}/wiki_example/output_ex4_dep3/{{latest}}/', 'type':'csv', 'from':'examples/ex4_dependency3_job.sql'}
output: {'path':'{{base_path}}/wiki_example/output_ex4_dep4/{{now}}/', 'type':'csv'}
dependencies: [examples/ex4_dependency3_job.sql]
examples/ex5_copy_to_oracle_job.py:
description: "shows frameworked pyspark ops, same as ex1_sql_job but gives access to spark ops to expand on sql."
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex5_copy_to_oracle/{{now}}/', 'type':'csv'}
copy_to_oracle: {'creds': 'oracle', 'table': 'sandbox.test_ex5_pyspark_job'}
examples/ex5_copy_to_redshift_job.py:
description: "shows frameworked pyspark ops, same as ex1_sql_job but gives access to spark ops to expand on sql."
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex5_copy_to_oracle/{{now}}/', 'type':'csv'}
copy_to_redshift: {'creds': 'some_redshift_cred_section', 'table': '{schema}.test_ex5_pyspark_job'}
examples/ex6_mysql_job.py:
description: "requires mysql instance running"
api_inputs: {'api_creds': 'some_mysql_cred_section', 'note':'API Job that relies on creds from conf/connections.cfg'}
output: {'path':'{{base_path}}/mysql_example/output_ex6_mysql/{{now}}/', 'type':'csv'}
examples/job_with_no_output:
description: "shows job with no output (still requiring table as output but not dumped to disk)"
py_job: 'jobs/examples/ex1_frameworked_job.py'
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'n/a', 'type':'None'}
examples/job_with_more_resources:
description: "To show how to change the machine specs and size of the cluster. See ec2_instance_master and emr_core_instances params below"
py_job: 'jobs/examples/ex1_frameworked_job.py'
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex1_frameworked_p3/{{now}}/', 'type':'csv'}
ec2_instance_master: 'm5.4xlarge'
ec2_instance_slaves: 'm5.4xlarge'
emr_core_instances: 3
emr_applications: [{'Name': 'Hadoop'}, {'Name': 'Spark'}, {'Name': 'Livy'}, {'Name': 'JupyterHub'}]
examples/ex7_pandas_with_sql_job.py:
description: "job loading and processing data with pandas. No spark involved."
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas', 'read_kwargs':{}}
output: {'path':'{{base_path}}/wiki_example/output_ex7_pandas_with_sql/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas', 'save_kwargs':{'sep':'|'}}
spark_boot: False
examples/ex7_hybrid_pandas_spark_job.py:
description: "Job processing in pandas, loading and dropping done with spark."
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex7_hybrid_pandas_spark/{{now}}/', 'type':'csv'}
examples/ex8_koalas_job.py:
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex8_koalas/{{now}}/', 'type':'csv'}
examples/ex9_redshift_job.py:
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex9_redshift/{{now}}/', 'type':'csv'}
copy_to_redshift: {'creds': 'some_redshift_cred_section', 'table': '{schema}.test_ex9_redshift'}
examples/ex9_mysql_job.py:
db_inputs: {'creds': 'some_mysql_cred_section', 'note':'API Job that relies on creds from conf/connections.cfg'}
output: {'path':'{{base_path}}/wiki_example/output_ex9_mysql/{{now}}/', 'type':'csv'}
examples/ex9_mysql_framework_load_job:
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'type':'mysql', 'db_table': 'some_schema.some_table', 'creds': 'some_mysql_cred_section', 'note':'creds defined in conf/connections.cfg'}
output: {'path':'{{base_path}}/db_example/output_ex9_mysql_direct/{{now}}/', 'type':'csv'}
load_connectors: all
enable_db_push: True
examples/ex9_clickhouse_job.py:
db_inputs: {'creds': 'some_clickhouse_cred_section', 'note':'API Job that relies on creds from conf/connections.cfg'}
output: {'path':'{{base_path}}/db_example/output_ex9_clickhouse/{{now}}/', 'type':'csv'}
examples/ex9_clickhouse_framework_load_job:
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'type':'clickhouse', 'db_table': 'some_schema.some_table', 'creds': 'some_clickhouse_cred_section', 'note':'creds defined in conf/connections.cfg'}
output: {'path':'{{base_path}}/db_example/output_ex9_clickhouse_direct/{{now}}/', 'type':'csv'}
copy_to_clickhouse: {'creds': 'some_clickhouse_cred_section', 'table': 'public.test_push_arthur'}
load_connectors: all
enable_db_push: True
examples/ex10_excel_load_job:
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input_excel/parts.xlsx", 'type':'xlsx', 'df_type':'pandas', 'read_kwargs':{'engine': 'openpyxl', 'sheet_name': 0, 'header': 1}} # for xls files, use 'type':'xls' and 'engine': 'xlrd'
output: {'path':'{{base_path}}/load_example/excel/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/copy_local_to_cloud_job:
description: "Copy data from local to cloud. To be executed from local only."
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input/", 'type':'csv'}
output: {'path':'{{base_path}}/load_example/test_files/{{now}}/', 'type':'csv'}
base_path: 's3a://mylake-dev/pipelines_data'
aws_config_file: conf/aws_config.cfg
aws_setup: dev
load_connectors: all
examples/copy_cloud_to_local_job:
description: "Copy data from cloud to local. Not loading file content. To be run locally."
py_job: jobs/generic/copy_raw_job.py
inputs:
files_to_copy: {'path':"{{base_path}}/load_example/test_files/", 'glob':'*/*.csv', 'type':'other'}
output: {'path':'./data/load_example/test_files/{{now}}/'}
base_path: 's3://mylake-dev/pipelines_data'
aws_config_file: conf/aws_config.cfg
aws_setup: dev
spark_boot: False
examples/ex11_run_gpu_for_deeplearning.py:
description: ""
inputs:
training_set: {'path':'{{base_path}}/gen_ai/finetuned_albert/raw/{{latest}}/', 'type':'csv', 'df_type':'pandas'} # file available in repo in ./tests/fixtures/data_sample/gen_ai/text_classification.csv
output: {'path':'{{base_path}}/load_example/test_files/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
ec2_instance_master: 'g4dn.xlarge' # access to this GPU instance may requires special request to AWS.
emr_core_instances: 0
examples/wordcount_frameworked_job.py:
description: "shows raw pyspark rdd ops in framework, same as wordcount_raw_job"
inputs:
lines: {'path':"{{base_path}}/wordcount_example/input/sample_text.txt", 'type':'txt'}
output: {'path':'{{base_path}}/wordcount_example/output_frameworked/{{now}}/', 'type':'txt'}
dependencies: [] # list here if any
frequency: 24h
emails: ['[email protected]']
examples/run_jobs:
description: "shows a job meant to run several dependencies at once. The job itself takes no input and generates no output."
py_job: 'jobs/generic/dummy_job.py'
spark_boot: False
dependencies:
- examples/ex0_extraction_job.py
- examples/ex1_sql_job.sql
- examples/ex7_pandas_job.py
examples/ex12_run_scala_job:
description: "Sample spark scala code (compiled into a jar), executed through spark-submit"
jar_job: 'jobs/examples/ex12_scala_job/target/spark_scala_job_2.13-1.0.jar'
scala_job: 'jobs/examples/ex12_scala_job/src/spark_scala_job.scala' # for ref, compilation to be done manually
sbt: 'jobs/examples/ex12_scala_job/build.sbt' # for ref, compilation to be done manually
spark_submit_args: '--verbose'
spark_app_args: '{{base_path}}/wordcount_example/input/sample_text.txt'
load_connectors: none
examples/ex13_register_athena_job:
description: "Job to demo registering data to Athena. Setup to be run locally, while pushing data to cloud and registering data to athena in AWS."
py_job: jobs/examples/ex1_frameworked_job.py
inputs:
some_events: {'path':"./data/wiki_example/input/{{latest}}/", 'type':'csv'}
other_events: {'path':"./data/wiki_example/input/{{latest}}/", 'type':'csv'}
output: {'path':'{{base_path}}/wiki_example/output_ex7_pandas/{{now}}/', 'type':'csv'}
base_path: 's3a://mylake-dev/pipelines_data'
register_to_athena: {'table': 'sandbox.ex1_frameworked'} # implies sandbox schema created, to be done with "CREATE DATABASE sandbox;" in SQL editor
enable_db_push: True
aws_config_file: conf/aws_config.cfg
aws_setup: dev
athena_out: s3://mylake-dev/pipelines_data/athena_data/
load_connectors: all
examples/ex14_json_format1_load_job:
description: "Format with basic json, with rows as lines, without []."
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input_json_format1/dataset.json", 'type':'json', 'df_type':'pandas', 'read_kwargs':{'lines':True}}
output: {'path':'{{base_path}}/load_example/json_format1/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/ex14_json_format2_load_job:
description: "Format with basic valid json, with rows inside brackets, ex [rows_here]."
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input_json_format2/dataset.json", 'type':'json', 'df_type':'pandas'}
output: {'path':'{{base_path}}/load_example/json_format2/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/ex14_json_format3_load_job:
description: "Format with rows inside structure like {'records':[rows_here]}."
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input_json_format3/dataset.json", 'type':'json', 'df_type':'json_pandas'}
output: {'path':'{{base_path}}/load_example/json_format3/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/ex15_copy_job_multi_path.py:
description: "Job to demo loading datasets with the same schemas spread over various folders, following structured path. The job will go through combinations of category and subcategory params defined below to extract datasets."
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input_multipath/{category}/{subcategory}/dataset.csv", 'type':'csv', 'df_type':'pandas', 'load':False}
output: {'path':'{{base_path}}/load_example/multipath/{category}/{subcategory}/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
category: ['catA', 'catB']
subcategory: ['subcatA', 'subcatB']
spark_boot: False
examples/ex16_glob_load_job:
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input/", 'type':'csv', 'glob':'part1*', 'df_type':'pandas'}
output: {'path':'{{base_path}}/load_example/glob_filtering/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/ex17_multimode_params_job:
description: |
Showing how to use multiple, useful for single tenant setup, where base_path need to change for various. see --mode=dev_local,your_extra_tenant below.
usage: python jobs/generic/launcher.py --job_name=examples/ex17_multimode_params_job --mode=dev_local,your_extra_tenant
py_job: jobs/examples/ex7_pandas_job.py
inputs:
some_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas'}
other_events: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas', 'read_kwargs':{}}
output: {'path':'{{base_path}}/wiki_example/output_ex7_pandas/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas', 'save_kwargs':{'sep':'|'}}
spark_boot: False
examples/ex18_placeholder_param_replacement_job:
description: |
Showing use of key replacement in strings parameters, i.e. see {{base_path_in}} and {{base_path_out}} below, automatically replace by value of 'base_path_in' and 'base_path_out' params below.
usage: python jobs/generic/launcher.py --job_name=examples/ex18_placeholder_param_replacement_job
py_job: jobs/examples/ex7_pandas_job.py
inputs:
some_events: {'path':"{{base_path_in}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas'}
other_events: {'path':"{{base_path_in}}/wiki_example/input/{{latest}}/", 'type':'csv', 'df_type':'pandas', 'read_kwargs':{}}
output: {'path':'{{base_path_out}}/wiki_example/output_ex7_pandas/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas', 'save_kwargs':{'sep':'|'}}
base_path_in: './data'
base_path_out: './data_other'
spark_boot: False
examples/ex19_compare_pandas_job:
description: "Showcasing a job to compare 2 datasets"
py_job: jobs/generic/compare_job.py
inputs:
tableA: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'pk':['uuid'], 'type':'csv', 'df_type':'pandas'}
tableB: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'pk':['uuid'], 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/wiki_example/output_ex19_compare/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/ex20_list_files_job:
description: "Job to create a dataset from a file list. Meant to work in aws only."
py_job: jobs/generic/list_files_job.py
inputs:
files: {'path':"{{base_path}}/wiki_example/input/{{latest}}/", 'glob':'*/*.csv', 'type':'other'}
output: {'path':'{{base_path}}/wiki_example/output_ex20_filelist/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
examples/ex21_deploy_airflow_job:
description: "Test deployment to airflow."
py_job: jobs/generic/copy_job.py
inputs:
table_to_copy: {'path':"tests/fixtures/data_sample/wiki_example/input/dataset.csv", 'type':'csv'}
output: {'path':'{{base_path}}/load_example/test_files/{{now}}/dataset.csv', 'type':'csv'}
s3_dags: 's3://mylake-dev/pipelines_metadata/airflow_dags'
local_dags: './airflow_dags/'
spark_boot: False
# wordcount_raw_job: #Job exists but doesn't rely on jobs_metadata entries
# ----- Marketing Jobs --------
marketing/github_accounts_extraction_job.py:
description: "Github API extraction job, pulling account data."
api_inputs: {'creds': 'github'}
inputs:
github_accounts_man: {'path':"./data_manual/github/github_accounts.csv", 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/github/users/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
marketing/github_repos_extraction_job.py:
description: "Github API extraction job, pulling repo data."
api_inputs: {'creds': 'github'}
inputs:
github_accounts: {'path':"{{base_path}}/github/users/{{latest}}/dataset.csv", 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/github/user_repos/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
dependencies: [marketing/github_accounts_extraction_job.py]
spark_boot: False
marketing/github_contributors_extraction_job.py:
description: "Github API extraction job, pulling contributor data."
api_inputs: {'creds': 'github'}
inputs:
repos: {'path':"{{base_path}}/github/user_repos/{{latest}}/dataset.csv", 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/github/contributors/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
dependencies: [marketing/github_repos_extraction_job.py]
spark_boot: False
marketing/github_committers_extraction_job.py:
description: "Github API extraction job, pulling committer data, especially email."
api_inputs: {'creds': 'github'}
inputs:
contributors: {'path':"{{base_path}}/github/contributors/{{latest}}/dataset.csv", 'type':'csv', 'df_type':'pandas'}
output: {'path':'{{base_path}}/github/committers/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
dependencies: [marketing/github_contributors_extraction_job.py]
spark_boot: False
marketing/github_repo_list_extraction_job.py:
description: "Github API extraction job, pulling repo data."
api_inputs: {'creds': 'github'}
output: {'path':'{{base_path}}/github/repos/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
marketing/github_traffic_extraction_job.py:
description: "Github API extraction job, pulling repo data."
inputs:
my_repos: {'path':"./data_manual/github/my_github_repos.csv", 'type':'csv', 'df_type':'pandas'}
api_inputs: {'creds': 'github'}
output: {'path':'{{base_path}}/github/traffic/{{now}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
spark_boot: False
marketing/people_merge_job.py:
description: "Merge people from linkedin, github..."
inputs:
perso: {'path':"./data_manual/people/people.csv", 'type':'csv'}
linkedin: {'path':"./data_manual/linkedin/export/Connections_mod.csv", 'type':'csv'}
output: {'path':'{{base_path}}/people/{now}/', 'type':'csv'}
# ----- Dashboards--------
dashboards/wikipedia_demo_dashboard.ipynb:
description: "Showcase a Dashboard using 'panel', based on dummy wikipedia data (experimental)."
inputs:
ex1_sql: {'path':'{{base_path}}/wiki_example_sql/output_ex1_sql_pandas/{{latest}}/dataset.csv', 'type':'csv', 'df_type':'pandas'}
ex7_pandas: {'path':'{{base_path}}/wiki_example/output_ex7_pandas/{{latest}}/dataset.csv', 'type':'csv', 'df_type':'pandas', 'read_kwargs':{'sep':'|'}}
dependencies:
- examples/ex1_sql_job.sql
- examples/ex7_pandas_job.py
# ----- Params -------
common_params:
all_mode_params:
base_path: '{{root_path}}/pipelines_data' # don't add '/' at the end
s3_dags: '{{root_path}}/pipelines_metadata/airflow_dags' # determines which airflow instance to use.
s3_logs: '{{root_path}}/pipelines_metadata'
connection_file: conf/connections.cfg
redshift_s3_tmp_dir: s3a://dev-spark/tmp_spark/
email_cred_section: some_email_cred_section # Section from "connection_file"
spark_version: '3.5' # options: '2.4', '3.0', '3.4' or '3.5'
k8s_url: 'k8s://https://kubernetes.docker.internal:6443'
k8s_name: 'my-pyspark-job'
k8s_executor_instances: '2'
k8s_namespace: 'a_k8s_namespace'
k8s_image_service: 'a_k8s_image_service'
k8s_upload_path: 's3a://a_k8s_upload_path'
k8s_driver_podTemplateFile: conf/k8s_setup_spark_submit_driver.yaml
k8s_executor_podTemplateFile: conf/k8s_setup_spark_submit_executor.yaml
aws_region: eu-west-1 # TODO: remove this.
k8s_podname: a_podname # TODO: make it nullable so jobs can rerun back to back.
default_aws_modes: 'dev_EMR'
default_local_modes: 'dev_local'
aws_modes: ['dev_EMR','prod_EMR']
mode_specific_params:
prod_EMR:
root_path: s3://mylake-prod # don't add '/' at the end
schema: frontroom
emr_core_instances: 0
aws_config_file: conf/aws_config.cfg
aws_setup: pro
jobs_folder: jobs/
load_connectors: all
enable_db_push: True
save_schemas: False
manage_git_info: True
dev_EMR: # TODO: change to dev_aws
root_path: s3://mylake-dev # don't add '/' at the end
schema: sandbox
emr_core_instances: 0
aws_config_file: conf/aws_config.cfg
aws_setup: dev
jobs_folder: jobs/
load_connectors: all
enable_db_push: False
save_schemas: False
manage_git_info: True
dev_local:
root_path: '.' # don't add '/' at the end
base_path: '{{root_path}}/data' # don't add '/' at the end
schema: sandbox
load_connectors: none
aws_config_file: none
enable_db_push: False
save_schemas: True
manage_git_info: False
your_extra_tenant: # useful for single tenant architecture, with data in separate locations
save_schemas: False
other_param: 'some_value'