File: transform_in_parallel_code.rst

package info (click to toggle)
python-ruffus 2.6.3%2Bdfsg-4
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 20,828 kB
  • ctags: 2,843
  • sloc: python: 15,745; makefile: 180; sh: 14
file content (366 lines) | stat: -rw-r--r-- 15,208 bytes parent folder | download | duplicates (6)
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
.. include:: ../../global.inc
.. include:: manual_chapter_numbers.inc

.. _new_manual.transform_in_parallel.code:

######################################################################################################
|new_manual.transform_in_parallel.chapter_num|: Python Code for More on ``@transform``-ing data
######################################################################################################

.. seealso::


    * :ref:`Manual Table of Contents <new_manual.table_of_contents>`
    * :ref:`@transform syntax in detail <decorators.transform>`
    * Back to |new_manual.transform_in_parallel.chapter_num|: :ref:`More on @transform-ing data and @originate <new_manual.transform_in_parallel>`

*******************************************
Producing several items / files per job
*******************************************

    ::

        from ruffus import *

        #---------------------------------------------------------------
        #   Create pairs of input files
        #
        first_task_params = [
                             ['job1.a.start', 'job1.b.start'],
                             ['job2.a.start', 'job2.b.start'],
                             ['job3.a.start', 'job3.b.start'],
                            ]

        for input_file_pairs in first_task_params:
            for input_file in input_file_pairs:
                open(input_file, "w")


        #---------------------------------------------------------------
        #
        #   first task
        #
        @transform(first_task_params, suffix(".start"),
                                [".output.1",
                                 ".output.extra.1"],
                               "some_extra.string.for_example", 14)
        def first_task(input_files, output_file_pair,
                        extra_parameter_str, extra_parameter_num):
            for output_file in output_file_pair:
                with open(output_file, "w"):
                    pass


        #---------------------------------------------------------------
        #
        #   second task
        #
        @transform(first_task, suffix(".output.1"), ".output2")
        def second_task(input_files, output_file):
            with open(output_file, "w"): pass


        #---------------------------------------------------------------
        #
        #       Run
        #
        pipeline_run([second_task])

=============================
Resulting Output
=============================

        ::

            >>> pipeline_run([second_task])
                Job  = [[job1.a.start, job1.b.start] -> [job1.a.output.1, job1.a.output.extra.1], some_extra.string.for_example, 14] completed
                Job  = [[job2.a.start, job2.b.start] -> [job2.a.output.1, job2.a.output.extra.1], some_extra.string.for_example, 14] completed
                Job  = [[job3.a.start, job3.b.start] -> [job3.a.output.1, job3.a.output.extra.1], some_extra.string.for_example, 14] completed
            Completed Task = first_task
                Job  = [[job1.a.output.1, job1.a.output.extra.1] -> job1.a.output2] completed
                Job  = [[job2.a.output.1, job2.a.output.extra.1] -> job2.a.output2] completed
                Job  = [[job3.a.output.1, job3.a.output.extra.1] -> job3.a.output2] completed
            Completed Task = second_task



*******************************************
Defining tasks function out of order
*******************************************

    .. code-block:: python
       :emphasize-lines: 22

        from ruffus import *

        #---------------------------------------------------------------
        #   Create pairs of input files
        #
        first_task_params = [
                             ['job1.a.start', 'job1.b.start'],
                             ['job2.a.start', 'job2.b.start'],
                             ['job3.a.start', 'job3.b.start'],
                            ]

        for input_file_pairs in first_task_params:
            for input_file in input_file_pairs:
                open(input_file, "w")



        #---------------------------------------------------------------
        #
        #   second task defined first
        #
        #   task name string wrapped in output_from(...)
        @transform(output_from("first_task"), suffix(".output.1"), ".output2")
        def second_task(input_files, output_file):
            with open(output_file, "w"): pass


        #---------------------------------------------------------------
        #
        #   first task
        #
        @transform(first_task_params, suffix(".start"),
                                [".output.1",
                                 ".output.extra.1"],
                               "some_extra.string.for_example", 14)
        def first_task(input_files, output_file_pair,
                        extra_parameter_str, extra_parameter_num):
            for output_file in output_file_pair:
                with open(output_file, "w"):
                    pass


        #---------------------------------------------------------------
        #
        #       Run
        #
        pipeline_run([second_task])


=============================
Resulting Output
=============================

        .. code-block:: pycon

            >>> pipeline_run([second_task])
                Job  = [[job1.a.start, job1.b.start] -> [job1.a.output.1, job1.a.output.extra.1], some_extra.string.for_example, 14] completed
                Job  = [[job2.a.start, job2.b.start] -> [job2.a.output.1, job2.a.output.extra.1], some_extra.string.for_example, 14] completed
                Job  = [[job3.a.start, job3.b.start] -> [job3.a.output.1, job3.a.output.extra.1], some_extra.string.for_example, 14] completed
            Completed Task = first_task
                Job  = [[job1.a.output.1, job1.a.output.extra.1] -> job1.a.output2] completed
                Job  = [[job2.a.output.1, job2.a.output.extra.1] -> job2.a.output2] completed
                Job  = [[job3.a.output.1, job3.a.output.extra.1] -> job3.a.output2] completed
            Completed Task = second_task

.. _new_manual.transform.multiple_dependencies.code:

*******************************************
Multiple dependencies
*******************************************

    .. code-block:: python
       :emphasize-lines: 58

        from ruffus import *
        import time
        import random

        #---------------------------------------------------------------
        #   Create pairs of input files
        #
        first_task_params = [
                             ['job1.a.start', 'job1.b.start'],
                             ['job2.a.start', 'job2.b.start'],
                             ['job3.a.start', 'job3.b.start'],
                            ]
        second_task_params = [
                             ['job4.a.start', 'job4.b.start'],
                             ['job5.a.start', 'job5.b.start'],
                             ['job6.a.start', 'job6.b.start'],
                            ]

        for input_file_pairs in first_task_params + second_task_params:
            for input_file in input_file_pairs:
                open(input_file, "w")



        #---------------------------------------------------------------
        #
        #   first task
        #
        @transform(first_task_params, suffix(".start"),
                                [".output.1",
                                 ".output.extra.1"],
                               "some_extra.string.for_example", 14)
        def first_task(input_files, output_file_pair,
                        extra_parameter_str, extra_parameter_num):
            for output_file in output_file_pair:
                with open(output_file, "w"):
                    pass
            time.sleep(random.random())



        #---------------------------------------------------------------
        #
        #   second task
        #
        @transform(second_task_params, suffix(".start"),
                                [".output.1",
                                 ".output.extra.1"],
                               "some_extra.string.for_example", 14)
        def second_task(input_files, output_file_pair,
                        extra_parameter_str, extra_parameter_num):
            for output_file in output_file_pair:
                with open(output_file, "w"):
                    pass
            time.sleep(random.random())


        #---------------------------------------------------------------
        #
        #   third task
        #
        #       depends on both first_task() and second_task()
        @transform([first_task, second_task], suffix(".output.1"), ".output2")
        def third_task(input_files, output_file):
            with open(output_file, "w"): pass


        #---------------------------------------------------------------
        #
        #       Run
        #
        pipeline_run([third_task], multiprocess = 6)

=============================
Resulting Output
=============================

    .. code-block:: pycon

        >>> pipeline_run([third_task], multiprocess = 6)
            Job  = [[job3.a.start, job3.b.start] -> [job3.a.output.1, job3.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job6.a.start, job6.b.start] -> [job6.a.output.1, job6.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job1.a.start, job1.b.start] -> [job1.a.output.1, job1.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job4.a.start, job4.b.start] -> [job4.a.output.1, job4.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job5.a.start, job5.b.start] -> [job5.a.output.1, job5.a.output.extra.1], some_extra.string.for_example, 14] completed
        Completed Task = second_task
            Job  = [[job2.a.start, job2.b.start] -> [job2.a.output.1, job2.a.output.extra.1], some_extra.string.for_example, 14] completed
        Completed Task = first_task
            Job  = [[job1.a.output.1, job1.a.output.extra.1] -> job1.a.output2] completed
            Job  = [[job2.a.output.1, job2.a.output.extra.1] -> job2.a.output2] completed
            Job  = [[job3.a.output.1, job3.a.output.extra.1] -> job3.a.output2] completed
            Job  = [[job4.a.output.1, job4.a.output.extra.1] -> job4.a.output2] completed
            Job  = [[job5.a.output.1, job5.a.output.extra.1] -> job5.a.output2] completed
            Job  = [[job6.a.output.1, job6.a.output.extra.1] -> job6.a.output2] completed
        Completed Task = third_task


*******************************************
Multiple dependencies after @follows
*******************************************

    .. code-block:: python
        :emphasize-lines: 31

        from ruffus import *
        import time
        import random

        #---------------------------------------------------------------
        #   Create pairs of input files
        #
        first_task_params = [
                             ['job1.a.start', 'job1.b.start'],
                             ['job2.a.start', 'job2.b.start'],
                             ['job3.a.start', 'job3.b.start'],
                            ]
        second_task_params = [
                             ['job4.a.start', 'job4.b.start'],
                             ['job5.a.start', 'job5.b.start'],
                             ['job6.a.start', 'job6.b.start'],
                            ]

        for input_file_pairs in first_task_params + second_task_params:
            for input_file in input_file_pairs:
                open(input_file, "w")



        #---------------------------------------------------------------
        #
        #   first task
        #
        @transform(first_task_params, suffix(".start"),
                                [".output.1",
                                 ".output.extra.1"],
                               "some_extra.string.for_example", 14)
        def first_task(input_files, output_file_pair,
                        extra_parameter_str, extra_parameter_num):
            for output_file in output_file_pair:
                with open(output_file, "w"):
                    pass
            time.sleep(random.random())



        #---------------------------------------------------------------
        #
        #   second task
        #
        @follows("first_task")
        @transform(second_task_params, suffix(".start"),
                                [".output.1",
                                 ".output.extra.1"],
                               "some_extra.string.for_example", 14)
        def second_task(input_files, output_file_pair,
                        extra_parameter_str, extra_parameter_num):
            for output_file in output_file_pair:
                with open(output_file, "w"):
                    pass
            time.sleep(random.random())


        #---------------------------------------------------------------
        #
        #   third task
        #
        #       depends on both first_task() and second_task()
        @transform([first_task, second_task], suffix(".output.1"), ".output2")
        def third_task(input_files, output_file):
            with open(output_file, "w"): pass


        #---------------------------------------------------------------
        #
        #       Run
        #
        pipeline_run([third_task], multiprocess = 6)

=======================================================================================
Resulting Output: ``first_task`` completes before ``second_task``
=======================================================================================

    .. code-block:: pycon

        >>> pipeline_run([third_task], multiprocess = 6)
            Job  = [[job2.a.start, job2.b.start] -> [job2.a.output.1, job2.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job3.a.start, job3.b.start] -> [job3.a.output.1, job3.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job1.a.start, job1.b.start] -> [job1.a.output.1, job1.a.output.extra.1], some_extra.string.for_example, 14] completed
        Completed Task = first_task
            Job  = [[job4.a.start, job4.b.start] -> [job4.a.output.1, job4.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job6.a.start, job6.b.start] -> [job6.a.output.1, job6.a.output.extra.1], some_extra.string.for_example, 14] completed
            Job  = [[job5.a.start, job5.b.start] -> [job5.a.output.1, job5.a.output.extra.1], some_extra.string.for_example, 14] completed
        Completed Task = second_task
            Job  = [[job1.a.output.1, job1.a.output.extra.1] -> job1.a.output2] completed
            Job  = [[job2.a.output.1, job2.a.output.extra.1] -> job2.a.output2] completed
            Job  = [[job3.a.output.1, job3.a.output.extra.1] -> job3.a.output2] completed
            Job  = [[job4.a.output.1, job4.a.output.extra.1] -> job4.a.output2] completed
            Job  = [[job5.a.output.1, job5.a.output.extra.1] -> job5.a.output2] completed
            Job  = [[job6.a.output.1, job6.a.output.extra.1] -> job6.a.output2] completed