From a952c08469700542db201ab37a5cd1c921369e06 Mon Sep 17 00:00:00 2001 From: jebus Date: Mon, 27 Oct 2025 22:34:05 +1300 Subject: [PATCH] [Feature] Basic logging of Jobs, Model Evaluation (#169) Co-authored-by: Tim Lorsbach Reviewed-on: https://git.envipath.com/enviPath/enviPy/pulls/169 --- epdb/management/commands/create_ml_models.py | 2 +- epdb/management/commands/update_job_logs.py | 38 +++ epdb/models.py | 85 ++++-- epdb/tasks.py | 121 ++++++++- epdb/templatetags/envipytags.py | 13 + epdb/urls.py | 1 + epdb/views.py | 163 +++++++---- templates/collections/joblog.html | 71 +++++ .../modals/collections/new_model_modal.html | 256 +++++++++--------- .../modals/objects/evaluate_model_modal.html | 21 +- templates/objects/model.html | 2 +- tests/test_enviformer.py | 14 +- tests/test_model.py | 5 +- tests/views/test_model_views.py | 2 +- tests/views/test_pathway_views.py | 2 +- 15 files changed, 556 insertions(+), 240 deletions(-) create mode 100644 epdb/management/commands/update_job_logs.py create mode 100644 templates/collections/joblog.html diff --git a/epdb/management/commands/create_ml_models.py b/epdb/management/commands/create_ml_models.py index 6c59141d..89fbc0ec 100644 --- a/epdb/management/commands/create_ml_models.py +++ b/epdb/management/commands/create_ml_models.py @@ -114,6 +114,6 @@ class Command(BaseCommand): print(f"Training {model_name}") model.build_model() print(f"Evaluating {model_name}") - model.evaluate_model() + model.evaluate_model(False, eval_packages=eval_packages) print(f"Saving {model_name}") model.save() diff --git a/epdb/management/commands/update_job_logs.py b/epdb/management/commands/update_job_logs.py new file mode 100644 index 00000000..a5b17cfa --- /dev/null +++ b/epdb/management/commands/update_job_logs.py @@ -0,0 +1,38 @@ +from datetime import date, timedelta + +from django.core.management.base import BaseCommand +from django.db import transaction + +from epdb.models import JobLog + + +class Command(BaseCommand): + def add_arguments(self, parser): + parser.add_argument( + "--cleanup", + type=int, + default=None, + help="Remove all logs older than this number of days. Default is None, which does not remove any logs.", + ) + + @transaction.atomic + def handle(self, *args, **options): + if options["cleanup"] is not None: + cleanup_dt = date.today() - timedelta(days=options["cleanup"]) + print(JobLog.objects.filter(created__lt=cleanup_dt).delete()) + + logs = JobLog.objects.filter(status="INITIAL") + print(f"Found {logs.count()} logs to update") + updated = 0 + for log in logs: + res = log.check_for_update() + if res: + updated += 1 + + print(f"Updated {updated} logs") + + from django.db.models import Count + + qs = JobLog.objects.values("status").annotate(total=Count("status")) + for r in qs: + print(r["status"], r["total"]) diff --git a/epdb/models.py b/epdb/models.py index 33a0b89b..324fe301 100644 --- a/epdb/models.py +++ b/epdb/models.py @@ -2225,10 +2225,18 @@ class PackageBasedModel(EPModel): self.model_status = self.BUILT_NOT_EVALUATED self.save() - def evaluate_model(self): + def evaluate_model(self, multigen: bool, eval_packages: List["Package"] = None): if self.model_status != self.BUILT_NOT_EVALUATED: raise ValueError(f"Can't evaluate a model in state {self.model_status}!") + if multigen: + self.multigen_eval = multigen + self.save() + + if eval_packages is not None: + for p in eval_packages: + self.eval_packages.add(p) + self.model_status = self.EVALUATING self.save() @@ -2525,7 +2533,6 @@ class RuleBasedRelativeReasoning(PackageBasedModel): package: "Package", rule_packages: List["Package"], data_packages: List["Package"], - eval_packages: List["Package"], threshold: float = 0.5, min_count: int = 10, max_count: int = 0, @@ -2574,10 +2581,6 @@ class RuleBasedRelativeReasoning(PackageBasedModel): for p in rule_packages: rbrr.data_packages.add(p) - if eval_packages: - for p in eval_packages: - rbrr.eval_packages.add(p) - rbrr.save() return rbrr @@ -2632,7 +2635,6 @@ class MLRelativeReasoning(PackageBasedModel): package: "Package", rule_packages: List["Package"], data_packages: List["Package"], - eval_packages: List["Package"], threshold: float = 0.5, name: "str" = None, description: str = None, @@ -2672,10 +2674,6 @@ class MLRelativeReasoning(PackageBasedModel): for p in rule_packages: mlrr.data_packages.add(p) - if eval_packages: - for p in eval_packages: - mlrr.eval_packages.add(p) - if build_app_domain: ad = ApplicabilityDomain.create( mlrr, @@ -2995,7 +2993,6 @@ class EnviFormer(PackageBasedModel): def create( package: "Package", data_packages: List["Package"], - eval_packages: List["Package"], threshold: float = 0.5, name: "str" = None, description: str = None, @@ -3028,10 +3025,6 @@ class EnviFormer(PackageBasedModel): for p in data_packages: mod.data_packages.add(p) - if eval_packages: - for p in eval_packages: - mod.eval_packages.add(p) - # if build_app_domain: # ad = ApplicabilityDomain.create(mod, app_domain_num_neighbours, app_domain_reliability_threshold, # app_domain_local_compatibility_threshold) @@ -3144,10 +3137,18 @@ class EnviFormer(PackageBasedModel): args = {"clz": "EnviFormer"} return args - def evaluate_model(self): + def evaluate_model(self, multigen: bool, eval_packages: List["Package"] = None): if self.model_status != self.BUILT_NOT_EVALUATED: raise ValueError(f"Can't evaluate a model in state {self.model_status}!") + if multigen: + self.multigen_eval = multigen + self.save() + + if eval_packages is not None: + for p in eval_packages: + self.eval_packages.add(p) + self.model_status = self.EVALUATING self.save() @@ -3671,3 +3672,53 @@ class Setting(EnviPathModel): self.public = True self.global_default = True self.save() + + +class JobLogStatus(models.TextChoices): + INITIAL = "INITIAL", "Initial" + SUCCESS = "SUCCESS", "Success" + FAILURE = "FAILURE", "Failure" + REVOKED = "REVOKED", "Revoked" + IGNORED = "IGNORED", "Ignored" + + +class JobLog(TimeStampedModel): + user = models.ForeignKey("epdb.User", models.CASCADE) + task_id = models.UUIDField(unique=True) + job_name = models.TextField(null=False, blank=False) + status = models.CharField( + max_length=20, + choices=JobLogStatus.choices, + default=JobLogStatus.INITIAL, + ) + + done_at = models.DateTimeField(null=True, blank=True, default=None) + task_result = models.TextField(null=True, blank=True, default=None) + + def check_for_update(self): + async_res = self.get_result() + new_status = async_res.state + + TERMINAL_STATES = [ + "SUCCESS", + "FAILURE", + "REVOKED", + "IGNORED", + ] + + if new_status != self.status and new_status in TERMINAL_STATES: + self.status = new_status + self.done_at = async_res.date_done + + if new_status == "SUCCESS": + self.task_result = async_res.result + + self.save() + + return True + return False + + def get_result(self): + from celery.result import AsyncResult + + return AsyncResult(str(self.task_id)) diff --git a/epdb/tasks.py b/epdb/tasks.py index b9845c86..b6f4e6b0 100644 --- a/epdb/tasks.py +++ b/epdb/tasks.py @@ -1,10 +1,13 @@ import logging -from typing import Optional -from celery.utils.functional import LRUCache -from celery import shared_task -from epdb.models import Pathway, Node, EPModel, Setting -from epdb.logic import SPathway +from datetime import datetime +from typing import Callable, Optional +from uuid import uuid4 +from celery import shared_task +from celery.utils.functional import LRUCache + +from epdb.logic import SPathway +from epdb.models import EPModel, JobLog, Node, Package, Pathway, Setting, User logger = logging.getLogger(__name__) ML_CACHE = LRUCache(3) # Cache the three most recent ML models to reduce load times. @@ -16,6 +19,40 @@ def get_ml_model(model_pk: int): return ML_CACHE[model_pk] +def dispatch_eager(user: "User", job: Callable, *args, **kwargs): + try: + x = job(*args, **kwargs) + log = JobLog() + log.user = user + log.task_id = uuid4() + log.job_name = job.__name__ + log.status = "SUCCESS" + log.done_at = datetime.now() + log.task_result = str(x) if x else None + log.save() + + return x + except Exception as e: + logger.exception(e) + raise e + + +def dispatch(user: "User", job: Callable, *args, **kwargs): + try: + x = job.delay(*args, **kwargs) + log = JobLog() + log.user = user + log.task_id = x.task_id + log.job_name = job.__name__ + log.status = "INITIAL" + log.save() + + return x.result + except Exception as e: + logger.exception(e) + raise e + + @shared_task(queue="background") def mul(a, b): return a * b @@ -33,17 +70,55 @@ def send_registration_mail(user_pk: int): pass -@shared_task(queue="model") -def build_model(model_pk: int): +@shared_task(bind=True, queue="model") +def build_model(self, model_pk: int): mod = EPModel.objects.get(id=model_pk) - mod.build_dataset() - mod.build_model() + + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update(status="RUNNING", task_result=mod.url) + + try: + mod.build_dataset() + mod.build_model() + except Exception as e: + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update( + status="FAILED", task_result=mod.url + ) + + raise e + + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update(status="SUCCESS", task_result=mod.url) + + return mod.url -@shared_task(queue="model") -def evaluate_model(model_pk: int): +@shared_task(bind=True, queue="model") +def evaluate_model(self, model_pk: int, multigen: bool, package_pks: Optional[list] = None): + packages = None + + if package_pks: + packages = Package.objects.filter(pk__in=package_pks) + mod = EPModel.objects.get(id=model_pk) - mod.evaluate_model() + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update(status="RUNNING", task_result=mod.url) + + try: + mod.evaluate_model(multigen, eval_packages=packages) + except Exception as e: + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update( + status="FAILED", task_result=mod.url + ) + + raise e + + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update(status="SUCCESS", task_result=mod.url) + + return mod.url @shared_task(queue="model") @@ -52,9 +127,13 @@ def retrain(model_pk: int): mod.retrain() -@shared_task(queue="predict") +@shared_task(bind=True, queue="predict") def predict( - pw_pk: int, pred_setting_pk: int, limit: Optional[int] = None, node_pk: Optional[int] = None + self, + pw_pk: int, + pred_setting_pk: int, + limit: Optional[int] = None, + node_pk: Optional[int] = None, ) -> Pathway: pw = Pathway.objects.get(id=pw_pk) setting = Setting.objects.get(id=pred_setting_pk) @@ -65,6 +144,9 @@ def predict( pw.kv.update(**{"status": "running"}) pw.save() + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update(status="RUNNING", task_result=pw.url) + try: # regular prediction if limit is not None: @@ -89,7 +171,18 @@ def predict( except Exception as e: pw.kv.update({"status": "failed"}) pw.save() + + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update( + status="FAILED", task_result=pw.url + ) + raise e pw.kv.update(**{"status": "completed"}) pw.save() + + if JobLog.objects.filter(task_id=self.request.id).exists(): + JobLog.objects.filter(task_id=self.request.id).update(status="SUCCESS", task_result=pw.url) + + return pw.url diff --git a/epdb/templatetags/envipytags.py b/epdb/templatetags/envipytags.py index c8c92fef..6c250e63 100644 --- a/epdb/templatetags/envipytags.py +++ b/epdb/templatetags/envipytags.py @@ -1,8 +1,21 @@ from django import template +from pydantic import AnyHttpUrl, ValidationError +from pydantic.type_adapter import TypeAdapter register = template.Library() +url_adapter = TypeAdapter(AnyHttpUrl) + @register.filter def classname(obj): return obj.__class__.__name__ + + +@register.filter +def is_url(value): + try: + url_adapter.validate_python(value) + return True + except ValidationError: + return False diff --git a/epdb/urls.py b/epdb/urls.py index 391a2f32..25e18680 100644 --- a/epdb/urls.py +++ b/epdb/urls.py @@ -190,6 +190,7 @@ urlpatterns = [ re_path(r"^indigo/dearomatize$", v.dearomatize, name="indigo_dearomatize"), re_path(r"^indigo/layout$", v.layout, name="indigo_layout"), re_path(r"^depict$", v.depict, name="depict"), + re_path(r"^jobs", v.jobs, name="jobs"), # OAuth Stuff path("o/userinfo/", v.userinfo, name="oauth_userinfo"), ] diff --git a/epdb/views.py b/epdb/views.py index 1f73027a..f2fd8c74 100644 --- a/epdb/views.py +++ b/epdb/views.py @@ -47,6 +47,7 @@ from .models import ( ExternalDatabase, ExternalIdentifier, EnzymeLink, + JobLog, ) logger = logging.getLogger(__name__) @@ -754,8 +755,8 @@ def package_models(request, package_uuid): context["unreviewed_objects"] = unreviewed_model_qs context["model_types"] = { - "ML Relative Reasoning": "ml-relative-reasoning", - "Rule Based Relative Reasoning": "rule-based-relative-reasoning", + "ML Relative Reasoning": "mlrr", + "Rule Based Relative Reasoning": "rbrr", } if s.FLAGS.get("ENVIFORMER", False): @@ -775,69 +776,67 @@ def package_models(request, package_uuid): model_type = request.POST.get("model-type") + # Generic fields for ML and Rule Based + rule_packages = request.POST.getlist("model-rule-packages") + data_packages = request.POST.getlist("model-data-packages") + + # Generic params + params = { + "package": current_package, + "name": name, + "description": description, + "data_packages": [ + PackageManager.get_package_by_url(current_user, p) for p in data_packages + ], + } + if model_type == "enviformer": - threshold = float(request.POST.get(f"{model_type}-threshold", 0.5)) + threshold = float(request.POST.get("model-threshold", 0.5)) + params["threshold"] = threshold - mod = EnviFormer.create(current_package, name, description, threshold) + mod = EnviFormer.create(**params) + elif model_type == "mlrr": + # ML Specific + threshold = float(request.POST.get("model-threshold", 0.5)) + # TODO handle additional fingerprinter + # fingerprinter = request.POST.get("model-fingerprinter") - elif model_type == "ml-relative-reasoning" or model_type == "rule-based-relative-reasoning": - # Generic fields for ML and Rule Based - rule_packages = request.POST.getlist("package-based-relative-reasoning-rule-packages") - data_packages = request.POST.getlist("package-based-relative-reasoning-data-packages") - eval_packages = request.POST.getlist( - "package-based-relative-reasoning-evaluation-packages", [] - ) + params["rule_packages"] = [ + PackageManager.get_package_by_url(current_user, p) for p in rule_packages + ] - # Generic params - params = { - "package": current_package, - "name": name, - "description": description, - "rule_packages": [ - PackageManager.get_package_by_url(current_user, p) for p in rule_packages - ], - "data_packages": [ - PackageManager.get_package_by_url(current_user, p) for p in data_packages - ], - "eval_packages": [ - PackageManager.get_package_by_url(current_user, p) for p in eval_packages - ], - } + # App Domain related parameters + build_ad = request.POST.get("build-app-domain", False) == "on" + num_neighbors = request.POST.get("num-neighbors", 5) + reliability_threshold = request.POST.get("reliability-threshold", 0.5) + local_compatibility_threshold = request.POST.get("local-compatibility-threshold", 0.5) - if model_type == "ml-relative-reasoning": - # ML Specific - threshold = float(request.POST.get(f"{model_type}-threshold", 0.5)) - # TODO handle additional fingerprinter - # fingerprinter = request.POST.get(f"{model_type}-fingerprinter") + params["threshold"] = threshold + # params['fingerprinter'] = fingerprinter + params["build_app_domain"] = build_ad + params["app_domain_num_neighbours"] = num_neighbors + params["app_domain_reliability_threshold"] = reliability_threshold + params["app_domain_local_compatibility_threshold"] = local_compatibility_threshold - # App Domain related parameters - build_ad = request.POST.get("build-app-domain", False) == "on" - num_neighbors = request.POST.get("num-neighbors", 5) - reliability_threshold = request.POST.get("reliability-threshold", 0.5) - local_compatibility_threshold = request.POST.get( - "local-compatibility-threshold", 0.5 - ) + mod = MLRelativeReasoning.create(**params) + elif model_type == "rbrr": + params["rule_packages"] = [ + PackageManager.get_package_by_url(current_user, p) for p in rule_packages + ] - params["threshold"] = threshold - # params['fingerprinter'] = fingerprinter - params["build_app_domain"] = build_ad - params["app_domain_num_neighbours"] = num_neighbors - params["app_domain_reliability_threshold"] = reliability_threshold - params["app_domain_local_compatibility_threshold"] = local_compatibility_threshold - - mod = MLRelativeReasoning.create(**params) - else: - mod = RuleBasedRelativeReasoning.create(**params) - - from .tasks import build_model - - build_model.delay(mod.pk) + mod = RuleBasedRelativeReasoning.create(**params) + elif s.FLAGS.get("PLUGINS", False) and model_type in s.CLASSIFIER_PLUGINS.values(): + pass else: return error( request, "Invalid model type.", f'Model type "{model_type}" is not supported."' ) - return redirect(mod.url) + from .tasks import dispatch, build_model + + dispatch(current_user, build_model, mod.pk) + + return redirect(mod.url) else: return HttpResponseNotAllowed(["GET", "POST"]) @@ -865,6 +864,10 @@ def package_model(request, package_uuid, model_uuid): return JsonResponse({"error": f'"{smiles}" is not a valid SMILES'}, status=400) if classify: + from epdb.tasks import dispatch_eager, predict_simple + + res = dispatch_eager(current_user, predict_simple, current_model.pk, stand_smiles) + pred_res = current_model.predict(stand_smiles) res = [] @@ -909,9 +912,25 @@ def package_model(request, package_uuid, model_uuid): current_model.delete() return redirect(current_package.url + "/model") elif hidden == "evaluate": - from .tasks import evaluate_model + from .tasks import dispatch, evaluate_model + + eval_type = request.POST.get("model-evaluation-type") + + if eval_type not in ["sg", "mg"]: + return error( + request, + "Invalid evaluation type", + f'Evaluation type "{eval_type}" is not supported. Only "sg" and "mg" are supported.', + ) + + multigen = eval_type == "mg" + + eval_packages = request.POST.getlist("model-evaluation-packages") + eval_package_ids = [ + PackageManager.get_package_by_url(current_user, p).id for p in eval_packages + ] + dispatch(current_user, evaluate_model, current_model.pk, multigen, eval_package_ids) - evaluate_model.delay(current_model.pk) return redirect(current_model.url) else: return HttpResponseBadRequest() @@ -1809,9 +1828,9 @@ def package_pathways(request, package_uuid): pw.setting = prediction_setting pw.save() - from .tasks import predict + from .tasks import dispatch, predict - predict.delay(pw.pk, prediction_setting.pk, limit=limit) + dispatch(current_user, predict, pw.pk, prediction_setting.pk, limit=limit) return redirect(pw.url) @@ -1930,10 +1949,16 @@ def package_pathway(request, package_uuid, pathway_uuid): if node_url: n = current_pathway.get_node(node_url) - from .tasks import predict + from .tasks import dispatch, predict + + dispatch( + current_user, + predict, + current_pathway.pk, + current_pathway.prediction_setting.pk, + node_pk=n.pk, + ) - # Dont delay? - predict(current_pathway.pk, current_pathway.setting.pk, node_pk=n.pk) return JsonResponse({"success": current_pathway.url}) return HttpResponseBadRequest() @@ -2705,6 +2730,24 @@ def setting(request, setting_uuid): pass +def jobs(request): + current_user = _anonymous_or_real(request) + context = get_base_context(request) + + if request.method == "GET": + context["object_type"] = "joblog" + context["breadcrumbs"] = [ + {"Home": s.SERVER_URL}, + {"Jobs": s.SERVER_URL + "/jobs"}, + ] + if current_user.is_superuser: + context["jobs"] = JobLog.objects.all().order_by("-created") + else: + context["jobs"] = JobLog.objects.filter(user=current_user).order_by("-created") + + return render(request, "collections/joblog.html", context) + + ########### # KETCHER # ########### diff --git a/templates/collections/joblog.html b/templates/collections/joblog.html new file mode 100644 index 00000000..7075e08e --- /dev/null +++ b/templates/collections/joblog.html @@ -0,0 +1,71 @@ +{% extends "framework.html" %} +{% load static %} +{% load envipytags %} +{% block content %} + +
+
+
+ Jobs +
+
+

+ Job Logs Desc +

+ +
+ +
+

+ + Jobs + +

+
+
+
+ + + + + + + + + + + {% for job in jobs %} + + + + + + + {% if job.task_result and job.task_result|is_url == True %} + + {% elif job.task_result %} + + {% else %} + + {% endif %} + + {% endfor %} + +
IDNameStatusQueuedDoneResult
{{ job.task_id }}{{ job.job_name }}{{ job.status }}{{ job.created }}{{ job.done_at }}Result{{ job.task_result|slice:"40" }}...Empty
+
+
+ + + +
+
+{% endblock content %} diff --git a/templates/modals/collections/new_model_modal.html b/templates/modals/collections/new_model_modal.html index b58a65ed..b5e903b6 100644 --- a/templates/modals/collections/new_model_modal.html +++ b/templates/modals/collections/new_model_modal.html @@ -18,113 +18,117 @@ prediction. You just need to set a name and the packages you want the object to be based on. There are multiple types of models available. For additional information have a look at our - wiki >> + wiki + >> + + + + + - -
- - - {% for obj in meta.readable_packages %} - {% if obj.reviewed %} - - {% endif %} + {% if obj.reviewed %} + + {% endif %} {% endfor %} {% for obj in meta.readable_packages %} - {% if not obj.reviewed %} - - {% endif %} + {% if not obj.reviewed %} + + {% endif %} {% endfor %} - - - - -
- - - - {% if meta.enabled_features.PLUGINS and additional_descriptors %} - - - - {% endif %} - - - -
- {% if meta.enabled_features.APPLICABILITY_DOMAIN %} - -
- -
- - {% endif %}
- -
- - + + +
+ + +
+ + +
+ + +
+ + +
+ + +
+ +
+ {% if meta.enabled_features.APPLICABILITY_DOMAIN %} + +
+ +
+ + {% endif %}
@@ -137,53 +141,47 @@ diff --git a/templates/modals/objects/evaluate_model_modal.html b/templates/modals/objects/evaluate_model_modal.html index a42c68bb..1d4b3801 100644 --- a/templates/modals/objects/evaluate_model_modal.html +++ b/templates/modals/objects/evaluate_model_modal.html @@ -17,10 +17,10 @@ For evaluation, you need to select the packages you want to use. While the model is evaluating, you can use the model for predictions. - - - {% for obj in meta.readable_packages %} {% if obj.reviewed %} @@ -35,7 +35,16 @@ {% endif %} {% endfor %} - + + + + + +
@@ -50,7 +59,7 @@ $(function () { - $("#relative-reasoning-evaluation-packages").selectpicker(); + $("#model-evaluation-packages").selectpicker(); $('#evaluate_model_form_submit').on('click', function (e) { e.preventDefault(); diff --git a/templates/objects/model.html b/templates/objects/model.html index b64bee39..4cf4acd2 100644 --- a/templates/objects/model.html +++ b/templates/objects/model.html @@ -117,7 +117,7 @@ {% endif %} - {% if model.app_domain %} + {% if model.ready_for_prediction and model.app_domain %}

diff --git a/tests/test_enviformer.py b/tests/test_enviformer.py index b81ca2ca..647433fc 100644 --- a/tests/test_enviformer.py +++ b/tests/test_enviformer.py @@ -3,7 +3,7 @@ from datetime import datetime from tempfile import TemporaryDirectory from django.test import TestCase, tag from epdb.logic import PackageManager -from epdb.models import User, EnviFormer, Package, Setting, Pathway +from epdb.models import User, EnviFormer, Package, Setting from epdb.tasks import predict_simple, predict @@ -48,9 +48,7 @@ class EnviFormerTest(TestCase): mod.build_dataset() mod.build_model() - mod.multigen_eval = True - mod.save() - mod.evaluate_model() + mod.evaluate_model(True, eval_packages_objs) mod.predict("CCN(CC)C(=O)C1=CC(=CC=C1)C") @@ -75,11 +73,15 @@ class EnviFormerTest(TestCase): # Test pathway prediction times = [measure_predict(mods[1], self.BBD_SUBSET.pathways[0].pk) for _ in range(5)] - print(f"First pathway prediction took {times[0]} seconds, subsequent ones took {times[1:]}") + print( + f"First pathway prediction took {times[0]} seconds, subsequent ones took {times[1:]}" + ) # Test eviction by performing three prediction with every model, twice. times = defaultdict(list) - for _ in range(2): # Eviction should cause the second iteration here to have to reload the models + for _ in range( + 2 + ): # Eviction should cause the second iteration here to have to reload the models for mod in mods: for _ in range(3): times[mod.pk].append(measure_predict(mod)) diff --git a/tests/test_model.py b/tests/test_model.py index e46046ec..f0355be9 100644 --- a/tests/test_model.py +++ b/tests/test_model.py @@ -30,7 +30,6 @@ class ModelTest(TestCase): self.package, rule_package_objs, data_package_objs, - eval_packages_objs, threshold=threshold, name="ECC - BBD - 0.5", description="Created MLRelativeReasoning in Testcase", @@ -50,9 +49,7 @@ class ModelTest(TestCase): mod.build_dataset() mod.build_model() - mod.multigen_eval = True - mod.save() - mod.evaluate_model() + mod.evaluate_model(True, eval_packages_objs) results = mod.predict("CCN(CC)C(=O)C1=CC(=CC=C1)C") diff --git a/tests/views/test_model_views.py b/tests/views/test_model_views.py index 558277f5..10cbefe2 100644 --- a/tests/views/test_model_views.py +++ b/tests/views/test_model_views.py @@ -6,7 +6,7 @@ from epdb.logic import UserManager from epdb.models import Package, User -@override_settings(MODEL_DIR=s.FIXTURE_DIRS[0] / "models") +@override_settings(MODEL_DIR=s.FIXTURE_DIRS[0] / "models", CELERY_TASK_ALWAYS_EAGER=True) class PathwayViewTest(TestCase): fixtures = ["test_fixtures_incl_model.jsonl.gz"] diff --git a/tests/views/test_pathway_views.py b/tests/views/test_pathway_views.py index 9e64e22f..b5fe99fd 100644 --- a/tests/views/test_pathway_views.py +++ b/tests/views/test_pathway_views.py @@ -6,7 +6,7 @@ from epdb.logic import UserManager, PackageManager from epdb.models import Pathway, Edge -@override_settings(MODEL_DIR=s.FIXTURE_DIRS[0] / "models") +@override_settings(MODEL_DIR=s.FIXTURE_DIRS[0] / "models", CELERY_TASK_ALWAYS_EAGER=True) class PathwayViewTest(TestCase): fixtures = ["test_fixtures_incl_model.jsonl.gz"]