Skip to content

Workflow

The Workflow class lets you configure & run jobs and query existing jobs related to this workflow.

Create a new workflow:

workflow = project.create_workflow(name="new_workflow")

Use an existing workflow:

workflow = up42.initialize_workflow(workflow_id="7fb2ec8a-45be-41ad-a50f-98ba6b528b98")

Source code in up42/workflow.py
 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
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
class Workflow:
    """
    The Workflow class lets you configure & run jobs and query existing jobs related
    to this workflow.

    Create a new workflow:
    ```python
    workflow = project.create_workflow(name="new_workflow")
    ```

    Use an existing workflow:
    ```python
    workflow = up42.initialize_workflow(workflow_id="7fb2ec8a-45be-41ad-a50f-98ba6b528b98")
    ```
    """

    def __init__(
        self,
        auth: Auth,
        project_id: str,
        workflow_id: str,
        workflow_info: Optional[dict] = None,
    ):
        self.auth = auth
        self.project_id = project_id
        self.workflow_id = workflow_id
        if workflow_info is not None:
            self._info = workflow_info
        else:
            self._info = self.info

    def __repr__(self):
        return (
            f"Workflow(name: {self._info['name']}, workflow_id: {self.workflow_id}, "
            f"description: {self._info['description']}, createdAt: {self._info['createdAt']}, "
            f"project_id: {self.project_id}"
        )

    @property
    def info(self) -> dict:
        """
        Gets and updates the workflow metadata information.
        """
        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
            f"{self.workflow_id}"
        )
        response_json = self.auth._request(request_type="GET", url=url)
        self._info = response_json["data"]
        return self._info

    @property
    def workflow_tasks(self) -> Dict[str, str]:
        """
        Gets the building blocks of the workflow as a dictionary with `task_name:block-version`.
        """
        logging.getLogger("up42.workflow").setLevel(logging.CRITICAL)
        workflow_tasks = self.get_workflow_tasks(basic=True)
        logging.getLogger("up42.workflow").setLevel(logging.INFO)
        return workflow_tasks  # type: ignore

    def get_compatible_blocks(self) -> dict:
        """
        Gets all compatible blocks for the current workflow. If the workflow is empty
        it will provide all data blocks, if the workflow already has workflow tasks, it
        will provide the compatible blocks for the last workflow task in the workflow.

        Currently no data blocks can be attached to other data blocks.
        """
        tasks: dict = self.get_workflow_tasks(basic=True)  # type: ignore
        if not tasks:
            logger.info("The workflow is empty, returning all data blocks.")

            logging.getLogger("up42.tools").setLevel(logging.CRITICAL)
            data_blocks = Tools(auth=self.auth).get_blocks(
                block_type="data", basic=True
            )
            logging.getLogger("up42.tools").setLevel(logging.INFO)
            return data_blocks  # type: ignore

        last_task = list(tasks.keys())[-1]
        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/{self.workflow_id}/"
            f"compatible-blocks?parentTaskName={last_task}"
        )
        response_json = self.auth._request(request_type="GET", url=url)
        compatible_blocks = response_json["data"]["blocks"]
        compatible_blocks = {
            block["name"]: block["blockId"] for block in compatible_blocks
        }
        return compatible_blocks

    def get_workflow_tasks(self, basic: bool = False) -> Union[List, dict]:
        """
        Get the workflow-tasks of the workflow (Blocks in a workflow are called workflow_tasks).

        Args:
            basic: If selected returns a simplified task-name : block-version dict.

        Returns:
            The workflow task info.
        """
        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
            f"{self.workflow_id}/tasks"
        )

        response_json = self.auth._request(request_type="GET", url=url)
        tasks = response_json["data"]
        logger.info(f"Got {len(tasks)} tasks/blocks in workflow {self.workflow_id}.")

        if basic:
            return {task["name"]: task["blockVersionTag"] for task in tasks}
        else:
            return tasks

    def _construct_full_workflow_tasks_dict(
        self, input_tasks: Union[List]
    ) -> List[dict]:
        """
        Constructs the full workflow task definition from a simplified version.
        Accepts blocks ids, block names, block display names & combinations of them.

        Args:
            input_tasks: List of block names, block ids, or block display names.

        Returns:
            The full workflow task definition.

        Example:
            ```python
            input_tasks = ["sobloo-s2-l1c-aoiclipped",
                           "tiling"]
            ```

            ```python
            input_tasks = ["a2daaab4-196d-4226-a018-a810444dcad1",
                           "4ed70368-d4e1-4462-bef6-14e768049471"]
            ```

            ```python
            input_tasks = ["Sentinel-2 L1C MSI AOI clipped",
                           "Raster Tiling"]
            ```
        """
        full_input_tasks_definition = []

        # Get public + custom blocks.
        logging.getLogger("up42.tools").setLevel(logging.CRITICAL)
        blocks: dict = Tools(auth=self.auth).get_blocks(basic=False)  # type: ignore
        logging.getLogger("up42.tools").setLevel(logging.INFO)

        # Get ids of the input tasks, regardless of the specified format.
        blocks_id_name = {block["id"]: block["name"] for block in blocks}
        blocks_name_id = {block["name"]: block["id"] for block in blocks}
        blocks_displaynames_id = {block["displayName"]: block["id"] for block in blocks}

        input_tasks_ids = []
        for task in input_tasks:
            if task in list(blocks_id_name.keys()):
                input_tasks_ids.append(task)
            elif task in list(blocks_name_id.keys()):
                input_tasks_ids.append(blocks_name_id[task])
            elif task in list(blocks_displaynames_id.keys()):
                input_tasks_ids.append(blocks_displaynames_id[task])
            else:
                raise ValueError(
                    f"The specified input task {task} does not match any "
                    f"available block."
                )

        # Add first task, the data block.
        data_task = {
            "name": f"{blocks_id_name[input_tasks_ids[0]]}:1",
            "parentName": None,
            "blockId": input_tasks_ids[0],
        }
        full_input_tasks_definition.append(data_task)
        previous_task_name = data_task["name"]

        # All following (processing) blocks.
        for block_id in input_tasks_ids[1:]:
            # Check if multiple of the same block are in the input tasks definition,
            # so that is does not get skipped as it has the same id.
            counts = Counter([x["blockId"] for x in full_input_tasks_definition])
            try:
                count_block = int(counts[block_id]) + 1
            except KeyError:
                count_block = 1

            next_task = {
                "name": f"{blocks_id_name[block_id]}:{count_block}",
                "parentName": previous_task_name,
                "blockId": block_id,
            }
            full_input_tasks_definition.append(next_task)
            previous_task_name = next_task["name"]
        return full_input_tasks_definition

    def add_workflow_tasks(self, input_tasks: Union[List[str], List[dict]]) -> None:
        # pylint: disable=line-too-long
        """
        Adds or overwrites workflow tasks in a workflow on UP42.

        Args:
            input_tasks: The blocks to be added to the workflow. Can be a list of the
                block names, block ids (use `up42.get_blocks()`) or block display names
                (The names shown on the [UP42 marketplace](https://marketplace.up42.com).

        !!! Info
            With block names or block display names, the most recent version of a block
            will be added. Using block ids specifies a specific version of a block.

        Examples:
            ```python
            # Block names
            input_tasks = ["sentinelhub-s2", "tiling"]
            ```

            ```python
            # Block Display names
            input_tasks = ["Sentinel-2 Level 2 (BOA) AOI clipped",
                           "Raster Tiling"]
            ```

            ```python
            # Block Ids
            input_tasks = ['018dfb34-fc19-4334-8125-14fd7535f979',
                           '4ed70368-d4e1-4462-bef6-14e768049471']
            ```

        !!! Info "Using Custom Blocks"
            To use a custom block in your workspace, you need to provide the custom block
            id directly in the [full workflow definition](https://docs.up42.com/going-further/api-walkthrough.html#creating-the-the-second-task-processing-block-addition)
            (dict of block id, block name and parent block name). See example below.

        Examples:
            ```python
            # Full workflow definition
            input_tasks = [{'name': 'sentinelhub-s2:1',
                            'parentName': None,
                            'blockId': '018dfb34-fc19-4334-8125-14fd7535f979'},
                           {'name': 'tiling:1',
                            'parentName': 'sentinelhub-s2:1',
                            'blockId': '4ed70368-d4e1-4462-bef6-14e768049471'}]
            ```
        """
        # Construct proper task definition from simplified input.
        if isinstance(input_tasks[0], str) and not isinstance(input_tasks[0], dict):
            input_tasks = self._construct_full_workflow_tasks_dict(input_tasks)

        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
            f"{self.workflow_id}/tasks/"
        )
        self.auth._request(request_type="POST", url=url, data=input_tasks)
        logger.info(f"Added tasks to workflow: {input_tasks}")

    def get_parameters_info(self) -> dict:
        """
        Gets infos about the workflow parameters of each block in the current workflow
        to make it easy to construct the desired parameters.

        Returns:
            Workflow parameters info json.
        """
        workflow_parameters_info = {}
        workflow_tasks = self.get_workflow_tasks()
        for task in workflow_tasks:
            task_name = task["name"]
            task_default_parameters = task["block"]["parameters"]
            workflow_parameters_info[task_name] = task_default_parameters
        return workflow_parameters_info

    def _get_default_parameters(self) -> dict:
        """
        Gets the default parameters for the workflow that can be directly used to
        run a job. Excludes geometry operation and geometry of the data block.
        """
        default_workflow_parameters = {}

        logger.setLevel(logging.CRITICAL)
        workflow_tasks = self.get_workflow_tasks()
        logger.setLevel(logging.INFO)
        for task in workflow_tasks:
            task_name = task["name"]
            task_parameters = task["block"]["parameters"]

            default_task_parameters = {}

            for param_name, param_values in task_parameters.items():
                if "default" in param_values and param_values["default"] is not None:
                    default_task_parameters[param_name] = param_values["default"]

            default_workflow_parameters[task_name] = default_task_parameters
        return default_workflow_parameters

    def construct_parameters(
        self,
        geometry: Union[
            dict,
            Feature,
            FeatureCollection,
            geojson_Polygon,
            list,
            GeoDataFrame,
            Polygon,
        ] = None,
        geometry_operation: Optional[str] = None,
        start_date: Optional[Union[str, datetime]] = None,
        end_date: Optional[Union[str, datetime]] = None,
        limit: Optional[int] = None,
        scene_ids: Optional[list] = None,
        assets: Optional[List[Asset]] = None,
    ) -> dict:
        """
        Constructs workflow input parameters with a specified aoi, the default input parameters, and
        optionally limit and order-ids. Further parameter editing needs to be done manually
        via dict.update({key:value}).

        Args:
            geometry: One of Dict, FeatureCollection, Feature, List,
                GeoDataFrame, shapely.geometry.Polygon. All assume EPSG 4326.
            geometry_operation: Desired operation, One of "bbox", "intersects", "contains".
            limit: Maximum number of expected results.
            start_date: Query period starting day as iso-format string or datetime object,
                e.g. "YYYY-MM-DD" or "YYYY-MM-DDTHH:MM:SS".
            end_date: Query period ending day as iso-format or datetime object,
                e.g. "YYYY-MM-DD" or "YYYY-MM-DDTHH:MM:SS".
            scene_ids: List of scene_ids, if given ignores all other parameters except geometry.
            assets: Optional, can be used to incorporate existing assets in Storage (result
                of Orders for instance) into new workflows.

        Returns:
            Dictionary of constructed input parameters.
        """
        input_parameters = self._get_default_parameters()
        try:
            data_block_name = list(input_parameters.keys())[0]
        except IndexError as e:
            raise ValueError("The Workflow has no workflow tasks.") from e

        if assets is not None:
            # Needs to be handled in this function(not run_job) as it is only
            # relevant for the data block.
            asset_ids = [asset.asset_id for asset in assets if asset.source == "BLOCK"]
            if not asset_ids:
                raise ValueError(
                    "None of the assets are usable in a workflow since the source is not `BLOCK`."
                )
            input_parameters[data_block_name] = {"asset_ids": asset_ids}
        else:
            if limit is not None:
                input_parameters[data_block_name]["limit"] = limit

            if scene_ids is not None:
                if not isinstance(scene_ids, list):
                    scene_ids = [scene_ids]
                input_parameters[data_block_name]["ids"] = scene_ids
                input_parameters[data_block_name]["limit"] = len(scene_ids)
                input_parameters[data_block_name].pop("time")
            elif start_date is not None or end_date is not None:
                time_period = format_time_period(
                    start_date=start_date, end_date=end_date
                )
                input_parameters[data_block_name]["time"] = time_period

            if geometry is not None:
                aoi_fc = any_vector_to_fc(
                    vector=geometry,
                )
                aoi_feature = fc_to_query_geometry(
                    fc=aoi_fc,
                    geometry_operation=geometry_operation,  # type: ignore
                )

                input_parameters[data_block_name][geometry_operation] = aoi_feature
        return input_parameters

    def construct_parameters_parallel(
        self,
        geometries: List[
            Union[
                dict,
                Feature,
                geojson_Polygon,
                Polygon,
            ]
        ] = None,
        interval_dates: List[Tuple[str, str]] = None,
        scene_ids: List[str] = None,
        limit_per_job: int = 1,
        geometry_operation: str = "intersects",
    ) -> List[dict]:
        """
        Maps a list of geometries and a list of time series into a list
        of input parameters of a workflow. If you pass 2 geometries and 1 time
        interval this will result in 2 x 1 input parameters.

        Args:
            geometries: List of unit geometries to map with times.
            interval_dates: List of tuples of start and end dates,
                i.e. `("2014-01-01","2015-01-01")`.
            scene_ids: List of scene ids. Will be mapped 1:1 to each job.
                All other arguments are ignored except geometries if passed.
            limit_per_job: Limit passed to be passed to each individual job parameter.
            geometry_operation: Geometry operation to be passed to each job parameter.

        Returns:
            List of dictionary of constructed input parameters.
        """
        # TODO: Rename arguments
        result_params = []
        # scene_ids mapped to geometries
        if scene_ids is not None and geometries is not None:
            for geo in geometries:
                for scene_id in scene_ids:
                    params = self.construct_parameters(
                        geometry=geo,
                        scene_ids=[scene_id],
                        geometry_operation=geometry_operation,
                    )
                    result_params.append(params)

        # interval_dates mapped to geometries
        elif interval_dates is not None and geometries is not None:
            for geo in geometries:
                for start_date, end_date in interval_dates:
                    params = self.construct_parameters(
                        geometry=geo,
                        geometry_operation=geometry_operation,
                        start_date=start_date,
                        end_date=end_date,
                        limit=limit_per_job,
                    )
                    result_params.append(params)

        # only scene_ids
        elif scene_ids is not None:
            for scene_id in scene_ids:
                result_params.append(
                    self.construct_parameters(
                        geometry=None,
                        scene_ids=[scene_id],
                    )
                )
        else:
            raise ValueError(
                "Please provides geometries and scene_ids, geometries"
                "and time_interval or scene_ids."
            )

        return result_params

    def estimate_job(self, input_parameters: Union[dict, str, Path] = None) -> dict:
        """
        Estimation of price and duration of the workflow for the provided input parameters.

        Args:
            input_parameters: Either json string of workflow parameters or filepath to json.

        Returns:
            A dictionary of estimation for each task in the workflow.
        """
        if input_parameters is None:
            raise ValueError(
                "Select the job_parameters, use workflow.construct_parameters()!"
            )

        workflow_tasks = self.workflow_tasks
        block_names = [task_name.split(":")[0] for task_name in workflow_tasks.keys()]
        input_tasks = self._construct_full_workflow_tasks_dict(block_names)
        for task in input_tasks:
            task["blockVersionTag"] = workflow_tasks[task["name"]]

        estimation = Estimation(
            auth=self.auth, input_parameters=input_parameters, input_tasks=input_tasks
        ).estimate()

        min_credits, max_credits, min_duration, max_duration = [], [], [], []
        for e in estimation.values():
            min_credits.append(e["blockConsumption"]["credit"]["min"])
            max_credits.append(e["blockConsumption"]["credit"]["max"])
            min_credits.append(e["machineConsumption"]["credit"]["min"])
            max_credits.append(e["machineConsumption"]["credit"]["max"])

            min_duration.append(e["machineConsumption"]["duration"]["min"])
            max_duration.append(e["machineConsumption"]["duration"]["max"])

        logger.info(
            f"Estimated: {sum(min_credits)}-{sum(max_credits)} Credits, "
            f"Duration: {int(sum(min_duration) / 60)}-{int(sum(max_duration) / 60)} min."
        )

        return estimation

    def _helper_run_job(
        self,
        input_parameters: Union[Dict, str, Path] = None,
        test_job=False,
        track_status: bool = False,
        name: str = None,
    ) -> "Job":
        """
        Helper function to create and run a new real or test job.

        Args:
            input_parameters: Either json string of workflow parameters or filepath to json.
            test_job: If set, runs a test query (search for available imagery based on your data parameters).
            track_status: Automatically attaches workflow.track_status which queries
                the job status every 30 seconds.
            name: The job name. Optional, by default the workflow name is assigned.

        Returns:
            The spawned real or test job object.
        """
        if input_parameters is None:
            raise ValueError(
                "Select the job_parameters, use workflow.construct_parameters()!"
            )

        if isinstance(input_parameters, (str, Path)):
            with open(input_parameters) as src:
                input_parameters = json.load(src)
            logger.info("Loading job parameters from json file.")

        if test_job:
            input_parameters = input_parameters.copy()  # type: ignore
            input_parameters.update({"config": {"mode": "DRY_RUN"}})  # type: ignore
            logger.info("+++++++++++++++++++++++++++++++++")
            logger.info("Running this job as Test Query...")
            logger.info("+++++++++++++++++++++++++++++++++")

        logger.info(f"Selected input_parameters: {input_parameters}")

        if name is None:
            name = self._info["name"]
        name = f"{name}_py"  # Temporary recognition of python API usage.
        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/"
            f"workflows/{self.workflow_id}/jobs?name={name}"
        )
        response_json = self.auth._request(
            request_type="POST", url=url, data=input_parameters  # type: ignore
        )
        job_json = response_json["data"]
        logger.info(f"Created and running new job: {job_json['id']}.")
        job = Job(
            self.auth,
            job_id=job_json["id"],
            project_id=self.project_id,
        )

        if track_status:
            job.track_status()
        return job

    def _helper_run_parallel_jobs(
        self,
        input_parameters_list: List[dict] = None,
        max_concurrent_jobs: int = 10,
        test_job: bool = False,
        name: str = None,
    ) -> "JobCollection":
        """
        Helper function to create and run parallel real or test jobs.

        Args:
            input_parameters_list: List of dictionary of input parameters.
            max_concurrent_jobs: Maximum number of parallel jobs that can be triggered.
            test_job: If set, runs a test query (search for available imagery based on your data parameters).
            name: The job name. Optional, by default the workflow name is assigned.

        Returns:
            The spawned real or test job object.

        Raises:
            ValueError: When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.
        """
        if input_parameters_list is None:
            raise ValueError(
                "Provide the job parameters via `input_parameters_list`."
                " You can use workflow.construct_parallel_parameters()!"
            )

        if test_job:
            input_parameters_list = copy.deepcopy(input_parameters_list)
            for input_parameters in input_parameters_list:
                input_parameters.update({"config": {"mode": "DRY_RUN"}})  # type: ignore
                logger.info("+++++++++++++++++++++++++++++++++")
                logger.info("Running this job as Test Query...")
                logger.info("+++++++++++++++++++++++++++++++++")

        if name is None:
            name = self._info["name"]

        jobs_list = []
        job_nr = 0

        if max_concurrent_jobs > self.max_concurrent_jobs:
            logger.error(
                f"Maximum concurrent jobs {max_concurrent_jobs} greater "
                f"than project settings {self.max_concurrent_jobs}. "
                "Use project.update_project_settings to change this value."
            )
            raise ValueError("Too many concurrent jobs!")

        # Run all jobs in parallel batches of the max_concurrent_jobs (max. 10.)
        batches = [
            input_parameters_list[pos : pos + max_concurrent_jobs]
            for pos in range(0, len(input_parameters_list), max_concurrent_jobs)
        ]
        for batch in batches:
            batch_jobs = []
            # for params in ten_selected_input_parameters:
            for params in batch:
                logger.info(f"Selected input_parameters: {params}.")

                job_name = (
                    f"{name}_{job_nr}_py"  # Temporary recognition of python API usage.
                )

                url = (
                    f"{self.auth._endpoint()}/projects/{self.project_id}/"
                    f"workflows/{self.workflow_id}/jobs?name={job_name}"
                )
                response_json = self.auth._request(
                    request_type="POST", url=url, data=params
                )
                job_json = response_json["data"]
                logger.info(f"Created and running new job: {job_json['id']}")
                job = Job(
                    self.auth,
                    job_id=job_json["id"],
                    project_id=self.project_id,
                )
                batch_jobs.append(job)
                job_nr += 1

            # Track until all jobs in the batch are finished.
            for job in batch_jobs:
                try:
                    job.track_status(report_time=20)
                except ValueError as e:
                    if str(e) == "Job has failed! See the above log.":
                        logger.warning("Skipping failed job...")
                    else:
                        raise
            jobs_list.extend(batch_jobs)

        job_collection = JobCollection(
            self.auth, project_id=self.project_id, jobs=jobs_list
        )
        return job_collection

    def test_job(
        self,
        input_parameters: Union[Dict, str, Path] = None,
        track_status: bool = False,
        name: str = None,
        get_estimation: bool = False,
    ) -> "Job":
        """
        Create a run a new test job (Test Query). With this test query you will not be
        charged with any data or processing credits, but have a preview of the job result.

        Args:
            input_parameters: Either json string of workflow parameters or filepath to json.
            track_status: Automatically attaches workflow.track_status which queries
                the job status every 30 seconds.
            name: The job name. Optional, by default the workflow name is assigned.

        Returns:
            The spawned test job object.
        """
        if get_estimation:
            self.estimate_job(input_parameters)

        return self._helper_run_job(
            input_parameters=input_parameters,
            test_job=True,
            track_status=track_status,
            name=name,
        )

    def test_jobs_parallel(
        self,
        input_parameters_list: List[dict] = None,
        name: str = None,
        max_concurrent_jobs: int = 10,
    ) -> "JobCollection":
        """
        Create and run test jobs (Test Query) in parallel. With this test query you will not be
        charged with any data or processing credits, but have a preview of the job result.

        Args:
            input_parameters_list: List of dictionary of input parameters
            name: The job name. Optional, by default the workflow name is assigned.
            max_concurrent_jobs: The maximum number of jobs to run in parallel.
                This is defined in the project settings.

        Returns:
            The spawned test JobCollection object.

        Raises:
            ValueError: When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.
        """
        return self._helper_run_parallel_jobs(
            input_parameters_list=input_parameters_list,
            max_concurrent_jobs=max_concurrent_jobs,
            test_job=True,
            name=name,
        )

    def run_job(
        self,
        input_parameters: Union[Dict, str, Path] = None,
        track_status: bool = False,
        name: str = None,
    ) -> "Job":
        """
        Creates and runs a new job.

        Args:
            input_parameters: Either json string of workflow parameters or filepath to json.
            track_status: Automatically attaches workflow.track_status which queries
                the job status every 30 seconds.
            name: The job name. Optional, by default the workflow name is assigned.

        Returns:
            The spawned job object.
        """
        return self._helper_run_job(
            input_parameters=input_parameters, track_status=track_status, name=name
        )

    def run_jobs_parallel(
        self,
        input_parameters_list: Optional[List[dict]] = None,
        name: str = None,
        max_concurrent_jobs: int = 10,
    ) -> "JobCollection":
        """
        Create and run jobs in parallel.

        Args:
            input_parameters_list: List of dictionary of input parameters
            name: The job name. Optional, by default the workflow name is assigned.
            max_concurrent_jobs: The maximum number of jobs to run in parallel. This is defined in the project settings.

        Returns:
            The spawned JobCollection object.

        Raises:
            ValueError: When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.
        """
        jobcollection = self._helper_run_parallel_jobs(
            input_parameters_list=input_parameters_list,
            max_concurrent_jobs=max_concurrent_jobs,
            name=name,
        )
        return jobcollection

    def get_jobs(
        self, return_json: bool = False, test_jobs: bool = True, real_jobs: bool = True
    ) -> Union[JobCollection, List[Dict]]:
        """
        Get all jobs associated with the workflow as a JobCollection or json.

        Args:
            return_json: If true, returns the job info jsons instead of a JobCollection.
            test_jobs: Return test jobs or test queries.
            real_jobs: Return real jobs.

        Returns:
            A JobCollection, or alternatively the jobs info as json.
        """
        url = f"{self.auth._endpoint()}/projects/{self.project_id}/jobs"
        response_json = self.auth._request(request_type="GET", url=url)
        jobs_json = filter_jobs_on_mode(response_json["data"], test_jobs, real_jobs)

        jobs_workflow_json = [
            j for j in jobs_json if j["workflowId"] == self.workflow_id
        ]

        logger.info(
            f"Got {len(jobs_workflow_json)} jobs for workflow "
            f"{self.workflow_id} in project {self.project_id}."
        )
        if return_json:
            return jobs_workflow_json
        else:
            jobs = [
                Job(self.auth, job_id=job["id"], project_id=self.project_id)
                for job in tqdm(jobs_workflow_json)
            ]
            jobcollection = JobCollection(
                auth=self.auth, project_id=self.project_id, jobs=jobs
            )
            return jobcollection

    def update_name(
        self, name: Optional[str] = None, description: Optional[str] = None
    ) -> None:
        """
        Updates the workflow name and description.

        Args:
            name: New name of the workflow.
            description: New description of the workflow.
        """
        properties_to_update = {"name": name, "description": description}
        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
            f"{self.workflow_id}"
        )
        self.auth._request(request_type="PUT", url=url, data=properties_to_update)
        # TODO: Renew info
        logger.info(f"Updated workflow name: {properties_to_update}")

    def delete(self) -> None:
        """
        Deletes the workflow and sets the Python object to None.
        """
        url = (
            f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
            f"{self.workflow_id}"
        )
        self.auth._request(request_type="DELETE", url=url, return_text=False)
        logger.info(f"Successfully deleted workflow: {self.workflow_id}")
        del self

    @property
    def max_concurrent_jobs(self) -> int:
        """
        Gets the maximum number of concurrent jobs allowed by the project settings.
        """
        url = f"{self.auth._endpoint()}/projects/{self.project_id}/settings"
        response_json = self.auth._request(request_type="GET", url=url)
        project_settings = response_json["data"]
        project_settings_dict = {d["name"]: int(d["value"]) for d in project_settings}
        return project_settings_dict["MAX_CONCURRENT_JOBS"]

Functions

info() property

Gets and updates the workflow metadata information.

Source code in up42/workflow.py
70
71
72
73
74
75
76
77
78
79
80
81
@property
def info(self) -> dict:
    """
    Gets and updates the workflow metadata information.
    """
    url = (
        f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
        f"{self.workflow_id}"
    )
    response_json = self.auth._request(request_type="GET", url=url)
    self._info = response_json["data"]
    return self._info

workflow_tasks() property

Gets the building blocks of the workflow as a dictionary with task_name:block-version.

Source code in up42/workflow.py
83
84
85
86
87
88
89
90
91
@property
def workflow_tasks(self) -> Dict[str, str]:
    """
    Gets the building blocks of the workflow as a dictionary with `task_name:block-version`.
    """
    logging.getLogger("up42.workflow").setLevel(logging.CRITICAL)
    workflow_tasks = self.get_workflow_tasks(basic=True)
    logging.getLogger("up42.workflow").setLevel(logging.INFO)
    return workflow_tasks  # type: ignore

get_compatible_blocks()

Gets all compatible blocks for the current workflow. If the workflow is empty it will provide all data blocks, if the workflow already has workflow tasks, it will provide the compatible blocks for the last workflow task in the workflow.

Currently no data blocks can be attached to other data blocks.

Source code in up42/workflow.py
 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
def get_compatible_blocks(self) -> dict:
    """
    Gets all compatible blocks for the current workflow. If the workflow is empty
    it will provide all data blocks, if the workflow already has workflow tasks, it
    will provide the compatible blocks for the last workflow task in the workflow.

    Currently no data blocks can be attached to other data blocks.
    """
    tasks: dict = self.get_workflow_tasks(basic=True)  # type: ignore
    if not tasks:
        logger.info("The workflow is empty, returning all data blocks.")

        logging.getLogger("up42.tools").setLevel(logging.CRITICAL)
        data_blocks = Tools(auth=self.auth).get_blocks(
            block_type="data", basic=True
        )
        logging.getLogger("up42.tools").setLevel(logging.INFO)
        return data_blocks  # type: ignore

    last_task = list(tasks.keys())[-1]
    url = (
        f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/{self.workflow_id}/"
        f"compatible-blocks?parentTaskName={last_task}"
    )
    response_json = self.auth._request(request_type="GET", url=url)
    compatible_blocks = response_json["data"]["blocks"]
    compatible_blocks = {
        block["name"]: block["blockId"] for block in compatible_blocks
    }
    return compatible_blocks

get_workflow_tasks(basic=False)

Get the workflow-tasks of the workflow (Blocks in a workflow are called workflow_tasks).

Parameters:

Name Type Description Default
basic bool

If selected returns a simplified task-name : block-version dict.

False

Returns:

Type Description
Union[List, dict]

The workflow task info.

Source code in up42/workflow.py
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
def get_workflow_tasks(self, basic: bool = False) -> Union[List, dict]:
    """
    Get the workflow-tasks of the workflow (Blocks in a workflow are called workflow_tasks).

    Args:
        basic: If selected returns a simplified task-name : block-version dict.

    Returns:
        The workflow task info.
    """
    url = (
        f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
        f"{self.workflow_id}/tasks"
    )

    response_json = self.auth._request(request_type="GET", url=url)
    tasks = response_json["data"]
    logger.info(f"Got {len(tasks)} tasks/blocks in workflow {self.workflow_id}.")

    if basic:
        return {task["name"]: task["blockVersionTag"] for task in tasks}
    else:
        return tasks

add_workflow_tasks(input_tasks)

Adds or overwrites workflow tasks in a workflow on UP42.

Parameters:

Name Type Description Default
input_tasks Union[List[str], List[dict]]

The blocks to be added to the workflow. Can be a list of the block names, block ids (use up42.get_blocks()) or block display names (The names shown on the UP42 marketplace.

required

Info

With block names or block display names, the most recent version of a block will be added. Using block ids specifies a specific version of a block.

Examples:

# Block names
input_tasks = ["sentinelhub-s2", "tiling"]
# Block Display names
input_tasks = ["Sentinel-2 Level 2 (BOA) AOI clipped",
               "Raster Tiling"]
# Block Ids
input_tasks = ['018dfb34-fc19-4334-8125-14fd7535f979',
               '4ed70368-d4e1-4462-bef6-14e768049471']

Using Custom Blocks

To use a custom block in your workspace, you need to provide the custom block id directly in the full workflow definition (dict of block id, block name and parent block name). See example below.

Examples:

# Full workflow definition
input_tasks = [{'name': 'sentinelhub-s2:1',
                'parentName': None,
                'blockId': '018dfb34-fc19-4334-8125-14fd7535f979'},
               {'name': 'tiling:1',
                'parentName': 'sentinelhub-s2:1',
                'blockId': '4ed70368-d4e1-4462-bef6-14e768049471'}]
Source code in up42/workflow.py
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
def add_workflow_tasks(self, input_tasks: Union[List[str], List[dict]]) -> None:
    # pylint: disable=line-too-long
    """
    Adds or overwrites workflow tasks in a workflow on UP42.

    Args:
        input_tasks: The blocks to be added to the workflow. Can be a list of the
            block names, block ids (use `up42.get_blocks()`) or block display names
            (The names shown on the [UP42 marketplace](https://marketplace.up42.com).

    !!! Info
        With block names or block display names, the most recent version of a block
        will be added. Using block ids specifies a specific version of a block.

    Examples:
        ```python
        # Block names
        input_tasks = ["sentinelhub-s2", "tiling"]
        ```

        ```python
        # Block Display names
        input_tasks = ["Sentinel-2 Level 2 (BOA) AOI clipped",
                       "Raster Tiling"]
        ```

        ```python
        # Block Ids
        input_tasks = ['018dfb34-fc19-4334-8125-14fd7535f979',
                       '4ed70368-d4e1-4462-bef6-14e768049471']
        ```

    !!! Info "Using Custom Blocks"
        To use a custom block in your workspace, you need to provide the custom block
        id directly in the [full workflow definition](https://docs.up42.com/going-further/api-walkthrough.html#creating-the-the-second-task-processing-block-addition)
        (dict of block id, block name and parent block name). See example below.

    Examples:
        ```python
        # Full workflow definition
        input_tasks = [{'name': 'sentinelhub-s2:1',
                        'parentName': None,
                        'blockId': '018dfb34-fc19-4334-8125-14fd7535f979'},
                       {'name': 'tiling:1',
                        'parentName': 'sentinelhub-s2:1',
                        'blockId': '4ed70368-d4e1-4462-bef6-14e768049471'}]
        ```
    """
    # Construct proper task definition from simplified input.
    if isinstance(input_tasks[0], str) and not isinstance(input_tasks[0], dict):
        input_tasks = self._construct_full_workflow_tasks_dict(input_tasks)

    url = (
        f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
        f"{self.workflow_id}/tasks/"
    )
    self.auth._request(request_type="POST", url=url, data=input_tasks)
    logger.info(f"Added tasks to workflow: {input_tasks}")

get_parameters_info()

Gets infos about the workflow parameters of each block in the current workflow to make it easy to construct the desired parameters.

Returns:

Type Description
dict

Workflow parameters info json.

Source code in up42/workflow.py
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
def get_parameters_info(self) -> dict:
    """
    Gets infos about the workflow parameters of each block in the current workflow
    to make it easy to construct the desired parameters.

    Returns:
        Workflow parameters info json.
    """
    workflow_parameters_info = {}
    workflow_tasks = self.get_workflow_tasks()
    for task in workflow_tasks:
        task_name = task["name"]
        task_default_parameters = task["block"]["parameters"]
        workflow_parameters_info[task_name] = task_default_parameters
    return workflow_parameters_info

construct_parameters(geometry=None, geometry_operation=None, start_date=None, end_date=None, limit=None, scene_ids=None, assets=None)

Constructs workflow input parameters with a specified aoi, the default input parameters, and optionally limit and order-ids. Further parameter editing needs to be done manually via dict.update({key:value}).

Parameters:

Name Type Description Default
geometry Union[dict, Feature, FeatureCollection, geojson_Polygon, list, GeoDataFrame, Polygon]

One of Dict, FeatureCollection, Feature, List, GeoDataFrame, shapely.geometry.Polygon. All assume EPSG 4326.

None
geometry_operation Optional[str]

Desired operation, One of "bbox", "intersects", "contains".

None
limit Optional[int]

Maximum number of expected results.

None
start_date Optional[Union[str, datetime]]

Query period starting day as iso-format string or datetime object, e.g. "YYYY-MM-DD" or "YYYY-MM-DDTHH:MM:SS".

None
end_date Optional[Union[str, datetime]]

Query period ending day as iso-format or datetime object, e.g. "YYYY-MM-DD" or "YYYY-MM-DDTHH:MM:SS".

None
scene_ids Optional[list]

List of scene_ids, if given ignores all other parameters except geometry.

None
assets Optional[List[Asset]]

Optional, can be used to incorporate existing assets in Storage (result of Orders for instance) into new workflows.

None

Returns:

Type Description
dict

Dictionary of constructed input parameters.

Source code in up42/workflow.py
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
def construct_parameters(
    self,
    geometry: Union[
        dict,
        Feature,
        FeatureCollection,
        geojson_Polygon,
        list,
        GeoDataFrame,
        Polygon,
    ] = None,
    geometry_operation: Optional[str] = None,
    start_date: Optional[Union[str, datetime]] = None,
    end_date: Optional[Union[str, datetime]] = None,
    limit: Optional[int] = None,
    scene_ids: Optional[list] = None,
    assets: Optional[List[Asset]] = None,
) -> dict:
    """
    Constructs workflow input parameters with a specified aoi, the default input parameters, and
    optionally limit and order-ids. Further parameter editing needs to be done manually
    via dict.update({key:value}).

    Args:
        geometry: One of Dict, FeatureCollection, Feature, List,
            GeoDataFrame, shapely.geometry.Polygon. All assume EPSG 4326.
        geometry_operation: Desired operation, One of "bbox", "intersects", "contains".
        limit: Maximum number of expected results.
        start_date: Query period starting day as iso-format string or datetime object,
            e.g. "YYYY-MM-DD" or "YYYY-MM-DDTHH:MM:SS".
        end_date: Query period ending day as iso-format or datetime object,
            e.g. "YYYY-MM-DD" or "YYYY-MM-DDTHH:MM:SS".
        scene_ids: List of scene_ids, if given ignores all other parameters except geometry.
        assets: Optional, can be used to incorporate existing assets in Storage (result
            of Orders for instance) into new workflows.

    Returns:
        Dictionary of constructed input parameters.
    """
    input_parameters = self._get_default_parameters()
    try:
        data_block_name = list(input_parameters.keys())[0]
    except IndexError as e:
        raise ValueError("The Workflow has no workflow tasks.") from e

    if assets is not None:
        # Needs to be handled in this function(not run_job) as it is only
        # relevant for the data block.
        asset_ids = [asset.asset_id for asset in assets if asset.source == "BLOCK"]
        if not asset_ids:
            raise ValueError(
                "None of the assets are usable in a workflow since the source is not `BLOCK`."
            )
        input_parameters[data_block_name] = {"asset_ids": asset_ids}
    else:
        if limit is not None:
            input_parameters[data_block_name]["limit"] = limit

        if scene_ids is not None:
            if not isinstance(scene_ids, list):
                scene_ids = [scene_ids]
            input_parameters[data_block_name]["ids"] = scene_ids
            input_parameters[data_block_name]["limit"] = len(scene_ids)
            input_parameters[data_block_name].pop("time")
        elif start_date is not None or end_date is not None:
            time_period = format_time_period(
                start_date=start_date, end_date=end_date
            )
            input_parameters[data_block_name]["time"] = time_period

        if geometry is not None:
            aoi_fc = any_vector_to_fc(
                vector=geometry,
            )
            aoi_feature = fc_to_query_geometry(
                fc=aoi_fc,
                geometry_operation=geometry_operation,  # type: ignore
            )

            input_parameters[data_block_name][geometry_operation] = aoi_feature
    return input_parameters

construct_parameters_parallel(geometries=None, interval_dates=None, scene_ids=None, limit_per_job=1, geometry_operation='intersects')

Maps a list of geometries and a list of time series into a list of input parameters of a workflow. If you pass 2 geometries and 1 time interval this will result in 2 x 1 input parameters.

Parameters:

Name Type Description Default
geometries List[Union[dict, Feature, geojson_Polygon, Polygon]]

List of unit geometries to map with times.

None
interval_dates List[Tuple[str, str]]

List of tuples of start and end dates, i.e. ("2014-01-01","2015-01-01").

None
scene_ids List[str]

List of scene ids. Will be mapped 1:1 to each job. All other arguments are ignored except geometries if passed.

None
limit_per_job int

Limit passed to be passed to each individual job parameter.

1
geometry_operation str

Geometry operation to be passed to each job parameter.

'intersects'

Returns:

Type Description
List[dict]

List of dictionary of constructed input parameters.

Source code in up42/workflow.py
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
def construct_parameters_parallel(
    self,
    geometries: List[
        Union[
            dict,
            Feature,
            geojson_Polygon,
            Polygon,
        ]
    ] = None,
    interval_dates: List[Tuple[str, str]] = None,
    scene_ids: List[str] = None,
    limit_per_job: int = 1,
    geometry_operation: str = "intersects",
) -> List[dict]:
    """
    Maps a list of geometries and a list of time series into a list
    of input parameters of a workflow. If you pass 2 geometries and 1 time
    interval this will result in 2 x 1 input parameters.

    Args:
        geometries: List of unit geometries to map with times.
        interval_dates: List of tuples of start and end dates,
            i.e. `("2014-01-01","2015-01-01")`.
        scene_ids: List of scene ids. Will be mapped 1:1 to each job.
            All other arguments are ignored except geometries if passed.
        limit_per_job: Limit passed to be passed to each individual job parameter.
        geometry_operation: Geometry operation to be passed to each job parameter.

    Returns:
        List of dictionary of constructed input parameters.
    """
    # TODO: Rename arguments
    result_params = []
    # scene_ids mapped to geometries
    if scene_ids is not None and geometries is not None:
        for geo in geometries:
            for scene_id in scene_ids:
                params = self.construct_parameters(
                    geometry=geo,
                    scene_ids=[scene_id],
                    geometry_operation=geometry_operation,
                )
                result_params.append(params)

    # interval_dates mapped to geometries
    elif interval_dates is not None and geometries is not None:
        for geo in geometries:
            for start_date, end_date in interval_dates:
                params = self.construct_parameters(
                    geometry=geo,
                    geometry_operation=geometry_operation,
                    start_date=start_date,
                    end_date=end_date,
                    limit=limit_per_job,
                )
                result_params.append(params)

    # only scene_ids
    elif scene_ids is not None:
        for scene_id in scene_ids:
            result_params.append(
                self.construct_parameters(
                    geometry=None,
                    scene_ids=[scene_id],
                )
            )
    else:
        raise ValueError(
            "Please provides geometries and scene_ids, geometries"
            "and time_interval or scene_ids."
        )

    return result_params

estimate_job(input_parameters=None)

Estimation of price and duration of the workflow for the provided input parameters.

Parameters:

Name Type Description Default
input_parameters Union[dict, str, Path]

Either json string of workflow parameters or filepath to json.

None

Returns:

Type Description
dict

A dictionary of estimation for each task in the workflow.

Source code in up42/workflow.py
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
519
520
521
522
523
524
525
526
def estimate_job(self, input_parameters: Union[dict, str, Path] = None) -> dict:
    """
    Estimation of price and duration of the workflow for the provided input parameters.

    Args:
        input_parameters: Either json string of workflow parameters or filepath to json.

    Returns:
        A dictionary of estimation for each task in the workflow.
    """
    if input_parameters is None:
        raise ValueError(
            "Select the job_parameters, use workflow.construct_parameters()!"
        )

    workflow_tasks = self.workflow_tasks
    block_names = [task_name.split(":")[0] for task_name in workflow_tasks.keys()]
    input_tasks = self._construct_full_workflow_tasks_dict(block_names)
    for task in input_tasks:
        task["blockVersionTag"] = workflow_tasks[task["name"]]

    estimation = Estimation(
        auth=self.auth, input_parameters=input_parameters, input_tasks=input_tasks
    ).estimate()

    min_credits, max_credits, min_duration, max_duration = [], [], [], []
    for e in estimation.values():
        min_credits.append(e["blockConsumption"]["credit"]["min"])
        max_credits.append(e["blockConsumption"]["credit"]["max"])
        min_credits.append(e["machineConsumption"]["credit"]["min"])
        max_credits.append(e["machineConsumption"]["credit"]["max"])

        min_duration.append(e["machineConsumption"]["duration"]["min"])
        max_duration.append(e["machineConsumption"]["duration"]["max"])

    logger.info(
        f"Estimated: {sum(min_credits)}-{sum(max_credits)} Credits, "
        f"Duration: {int(sum(min_duration) / 60)}-{int(sum(max_duration) / 60)} min."
    )

    return estimation

test_job(input_parameters=None, track_status=False, name=None, get_estimation=False)

Create a run a new test job (Test Query). With this test query you will not be charged with any data or processing credits, but have a preview of the job result.

Parameters:

Name Type Description Default
input_parameters Union[Dict, str, Path]

Either json string of workflow parameters or filepath to json.

None
track_status bool

Automatically attaches workflow.track_status which queries the job status every 30 seconds.

False
name str

The job name. Optional, by default the workflow name is assigned.

None

Returns:

Type Description
Job

The spawned test job object.

Source code in up42/workflow.py
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
def test_job(
    self,
    input_parameters: Union[Dict, str, Path] = None,
    track_status: bool = False,
    name: str = None,
    get_estimation: bool = False,
) -> "Job":
    """
    Create a run a new test job (Test Query). With this test query you will not be
    charged with any data or processing credits, but have a preview of the job result.

    Args:
        input_parameters: Either json string of workflow parameters or filepath to json.
        track_status: Automatically attaches workflow.track_status which queries
            the job status every 30 seconds.
        name: The job name. Optional, by default the workflow name is assigned.

    Returns:
        The spawned test job object.
    """
    if get_estimation:
        self.estimate_job(input_parameters)

    return self._helper_run_job(
        input_parameters=input_parameters,
        test_job=True,
        track_status=track_status,
        name=name,
    )

test_jobs_parallel(input_parameters_list=None, name=None, max_concurrent_jobs=10)

Create and run test jobs (Test Query) in parallel. With this test query you will not be charged with any data or processing credits, but have a preview of the job result.

Parameters:

Name Type Description Default
input_parameters_list List[dict]

List of dictionary of input parameters

None
name str

The job name. Optional, by default the workflow name is assigned.

None
max_concurrent_jobs int

The maximum number of jobs to run in parallel. This is defined in the project settings.

10

Returns:

Type Description
JobCollection

The spawned test JobCollection object.

Raises:

Type Description
ValueError

When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.

Source code in up42/workflow.py
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
def test_jobs_parallel(
    self,
    input_parameters_list: List[dict] = None,
    name: str = None,
    max_concurrent_jobs: int = 10,
) -> "JobCollection":
    """
    Create and run test jobs (Test Query) in parallel. With this test query you will not be
    charged with any data or processing credits, but have a preview of the job result.

    Args:
        input_parameters_list: List of dictionary of input parameters
        name: The job name. Optional, by default the workflow name is assigned.
        max_concurrent_jobs: The maximum number of jobs to run in parallel.
            This is defined in the project settings.

    Returns:
        The spawned test JobCollection object.

    Raises:
        ValueError: When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.
    """
    return self._helper_run_parallel_jobs(
        input_parameters_list=input_parameters_list,
        max_concurrent_jobs=max_concurrent_jobs,
        test_job=True,
        name=name,
    )

run_job(input_parameters=None, track_status=False, name=None)

Creates and runs a new job.

Parameters:

Name Type Description Default
input_parameters Union[Dict, str, Path]

Either json string of workflow parameters or filepath to json.

None
track_status bool

Automatically attaches workflow.track_status which queries the job status every 30 seconds.

False
name str

The job name. Optional, by default the workflow name is assigned.

None

Returns:

Type Description
Job

The spawned job object.

Source code in up42/workflow.py
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
def run_job(
    self,
    input_parameters: Union[Dict, str, Path] = None,
    track_status: bool = False,
    name: str = None,
) -> "Job":
    """
    Creates and runs a new job.

    Args:
        input_parameters: Either json string of workflow parameters or filepath to json.
        track_status: Automatically attaches workflow.track_status which queries
            the job status every 30 seconds.
        name: The job name. Optional, by default the workflow name is assigned.

    Returns:
        The spawned job object.
    """
    return self._helper_run_job(
        input_parameters=input_parameters, track_status=track_status, name=name
    )

run_jobs_parallel(input_parameters_list=None, name=None, max_concurrent_jobs=10)

Create and run jobs in parallel.

Parameters:

Name Type Description Default
input_parameters_list Optional[List[dict]]

List of dictionary of input parameters

None
name str

The job name. Optional, by default the workflow name is assigned.

None
max_concurrent_jobs int

The maximum number of jobs to run in parallel. This is defined in the project settings.

10

Returns:

Type Description
JobCollection

The spawned JobCollection object.

Raises:

Type Description
ValueError

When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.

Source code in up42/workflow.py
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
def run_jobs_parallel(
    self,
    input_parameters_list: Optional[List[dict]] = None,
    name: str = None,
    max_concurrent_jobs: int = 10,
) -> "JobCollection":
    """
    Create and run jobs in parallel.

    Args:
        input_parameters_list: List of dictionary of input parameters
        name: The job name. Optional, by default the workflow name is assigned.
        max_concurrent_jobs: The maximum number of jobs to run in parallel. This is defined in the project settings.

    Returns:
        The spawned JobCollection object.

    Raises:
        ValueError: When max_concurrent_jobs is greater than max_concurrent_jobs set in project settings.
    """
    jobcollection = self._helper_run_parallel_jobs(
        input_parameters_list=input_parameters_list,
        max_concurrent_jobs=max_concurrent_jobs,
        name=name,
    )
    return jobcollection

get_jobs(return_json=False, test_jobs=True, real_jobs=True)

Get all jobs associated with the workflow as a JobCollection or json.

Parameters:

Name Type Description Default
return_json bool

If true, returns the job info jsons instead of a JobCollection.

False
test_jobs bool

Return test jobs or test queries.

True
real_jobs bool

Return real jobs.

True

Returns:

Type Description
Union[JobCollection, List[Dict]]

A JobCollection, or alternatively the jobs info as json.

Source code in up42/workflow.py
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
def get_jobs(
    self, return_json: bool = False, test_jobs: bool = True, real_jobs: bool = True
) -> Union[JobCollection, List[Dict]]:
    """
    Get all jobs associated with the workflow as a JobCollection or json.

    Args:
        return_json: If true, returns the job info jsons instead of a JobCollection.
        test_jobs: Return test jobs or test queries.
        real_jobs: Return real jobs.

    Returns:
        A JobCollection, or alternatively the jobs info as json.
    """
    url = f"{self.auth._endpoint()}/projects/{self.project_id}/jobs"
    response_json = self.auth._request(request_type="GET", url=url)
    jobs_json = filter_jobs_on_mode(response_json["data"], test_jobs, real_jobs)

    jobs_workflow_json = [
        j for j in jobs_json if j["workflowId"] == self.workflow_id
    ]

    logger.info(
        f"Got {len(jobs_workflow_json)} jobs for workflow "
        f"{self.workflow_id} in project {self.project_id}."
    )
    if return_json:
        return jobs_workflow_json
    else:
        jobs = [
            Job(self.auth, job_id=job["id"], project_id=self.project_id)
            for job in tqdm(jobs_workflow_json)
        ]
        jobcollection = JobCollection(
            auth=self.auth, project_id=self.project_id, jobs=jobs
        )
        return jobcollection

update_name(name=None, description=None)

Updates the workflow name and description.

Parameters:

Name Type Description Default
name Optional[str]

New name of the workflow.

None
description Optional[str]

New description of the workflow.

None
Source code in up42/workflow.py
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
def update_name(
    self, name: Optional[str] = None, description: Optional[str] = None
) -> None:
    """
    Updates the workflow name and description.

    Args:
        name: New name of the workflow.
        description: New description of the workflow.
    """
    properties_to_update = {"name": name, "description": description}
    url = (
        f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
        f"{self.workflow_id}"
    )
    self.auth._request(request_type="PUT", url=url, data=properties_to_update)
    # TODO: Renew info
    logger.info(f"Updated workflow name: {properties_to_update}")

delete()

Deletes the workflow and sets the Python object to None.

Source code in up42/workflow.py
852
853
854
855
856
857
858
859
860
861
862
def delete(self) -> None:
    """
    Deletes the workflow and sets the Python object to None.
    """
    url = (
        f"{self.auth._endpoint()}/projects/{self.project_id}/workflows/"
        f"{self.workflow_id}"
    )
    self.auth._request(request_type="DELETE", url=url, return_text=False)
    logger.info(f"Successfully deleted workflow: {self.workflow_id}")
    del self

max_concurrent_jobs() property

Gets the maximum number of concurrent jobs allowed by the project settings.

Source code in up42/workflow.py
864
865
866
867
868
869
870
871
872
873
@property
def max_concurrent_jobs(self) -> int:
    """
    Gets the maximum number of concurrent jobs allowed by the project settings.
    """
    url = f"{self.auth._endpoint()}/projects/{self.project_id}/settings"
    response_json = self.auth._request(request_type="GET", url=url)
    project_settings = response_json["data"]
    project_settings_dict = {d["name"]: int(d["value"]) for d in project_settings}
    return project_settings_dict["MAX_CONCURRENT_JOBS"]