finish command to generate light db

backend/metagenedb/apps/catalog/factory/function.py

-from factory import DjangoModelFactory, fuzzy
-from faker import Factory
+from factory import DjangoModelFactory, Faker, fuzzy
 
 from metagenedb.apps.catalog import models
 
-from .fuzzy_base import FuzzyLowerText
-
-faker = Factory.create()
 
 SELECTED_SOURCE = [i[0] for i in models.Function.SOURCE_CHOICES]
 EGGNOG_VERSIONS = [i[0] for i in models.EggNOG.VERSION_CHOICES]
 
 
-class BaseFunctionFactory(DjangoModelFactory):
-    function_id = FuzzyLowerText(prefix='function-', length=15)
-
-
-class FunctionFactory(BaseFunctionFactory):
+class FunctionFactory(DjangoModelFactory):
     class Meta:
         model = models.Function
 
+    function_id = Faker('bothify', text='function-####')
     source = fuzzy.FuzzyChoice(SELECTED_SOURCE)
-    function_id = FuzzyLowerText(prefix='function-', length=15)
 
 
-class EggNOGFactory(BaseFunctionFactory):
+class EggNOGFactory(DjangoModelFactory):
+    function_id = Faker('bothify', text='COG####')
+    name = Faker('bothify', text='COG-????????')
+
     class Meta:
         model = models.EggNOG
 
     version = fuzzy.FuzzyChoice(EGGNOG_VERSIONS)
 
 
-class KeggOrthologyFactory(BaseFunctionFactory):
+class KeggOrthologyFactory(DjangoModelFactory):
+    function_id = Faker('bothify', text='K0####')
+
     class Meta:
         model = models.KeggOrthology
 

backend/metagenedb/apps/catalog/factory/gene.py

 from factory import (
-    DjangoModelFactory, RelatedFactory, SubFactory, fuzzy
+    DjangoModelFactory, Faker, RelatedFactory, SubFactory, fuzzy
 )
-from faker import Factory
 
 from metagenedb.apps.catalog import models
 
-from .fuzzy_base import FuzzyLowerText
-from .function import FunctionFactory
+from .function import FunctionFactory, KeggOrthologyFactory, EggNOGFactory
 from .taxonomy import TaxonomyFactory
 
-faker = Factory.create()
-
 GENE_SOURCES = [i[0] for i in models.Gene.SOURCE_CHOICES]
 
 
@@ -18,9 +14,9 @@ class GeneFactory(DjangoModelFactory):
     class Meta:
         model = models.Gene
 
-    gene_id = FuzzyLowerText(prefix='gene-', length=15)
-    name = fuzzy.FuzzyText(prefix='name-', length=15)
-    length = fuzzy.FuzzyInteger(200, 10000)
+    gene_id = Faker('bothify', text='gene-?#?#??-#??#?#')
+    name = Faker('bothify', text='Gene_name-##-????')
+    length = Faker('pyint', min_value=200, max_value=4200)
     source = fuzzy.FuzzyChoice(GENE_SOURCES)
 
 
@@ -36,9 +32,17 @@ class GeneFunctionFactory(DjangoModelFactory):
     function = SubFactory(FunctionFactory)
 
 
+class GeneKeggFactory(GeneFunctionFactory):
+    function = SubFactory(KeggOrthologyFactory)
+
+
+class GeneEggNOGFactory(GeneFunctionFactory):
+    function = SubFactory(EggNOGFactory)
+
+
 class GeneWithKeggFactory(GeneFactory):
-    kegg = RelatedFactory(GeneFunctionFactory, 'gene', function__source='kegg')
+    kegg = RelatedFactory(GeneKeggFactory, 'gene')
 
 
 class GeneWithEggNOGFactory(GeneFactory):
-    eggnog = RelatedFactory(GeneFunctionFactory, 'gene', function__source='eggnog')
+    eggnog = RelatedFactory(GeneEggNOGFactory, 'gene')

backend/metagenedb/apps/catalog/factory/taxonomy.py

@@ -30,6 +30,7 @@ class DbGenerator:
         """
         Tree need to be an OrderedDict from higher to lower level
         """
+        self.last_tax = None
         for rank, desc in tree.items():
             if desc['tax_id'] not in self.created_ids:
                 self.last_tax = TaxonomyFactory.create(

backend/metagenedb/apps/catalog/management/commands/create_light_db.py

 import logging
+from random import randint
 
 from django.core.management.base import BaseCommand
 
+from metagenedb.apps.catalog.factory import GeneFactory, GeneWithEggNOGFactory, GeneWithKeggFactory
 from metagenedb.apps.catalog.factory.taxonomy import generate_simple_db as gen_tax_db
 from metagenedb.apps.catalog.models import (
-    Gene, KeggOrthology, Taxonomy
+    Gene, Function, Taxonomy
+)
+from metagenedb.apps.catalog.management.commands.compute_stats import (
+    ComputeStatistics, ComputeCounts, ComputeGeneLength, ComputeTaxonomyRepartition, ComputeTaxonomyPresence
 )
 
 logging.basicConfig(format='[%(asctime)s] %(levelname)s:%(name)s:%(message)s')
-logger = logging.getLogger(__name__)
-
-
-def create_functions_db():
-    KeggOrthology.objects.all().delete()
-    keggs_to_create = {
-        "K03556": {
-            'name': 'malT',
-            'long_name': "LuxR family transcriptional regulator, maltose regulon positive regulatory protein"
-        },
-        "K02229": {
-            'name': "cobG",
-            'long_name': 'precorrin-3B synthase [EC:1.14.13.83]'
-        }
-    }
-    for kegg_id, values in keggs_to_create.items():
-        KeggOrthology(
-            function_id=kegg_id,
-            name=values.get('name'),
-            long_name=values.get('long_name')
-        ).save()
+logger = logging.getLogger()
+
+
+def empty_db():
+    Gene.objects.all().delete()
+    Taxonomy.objects.all().delete()
+    Function.objects.all().delete()
 
 
 def create_taxonomy_db():
@@ -37,13 +28,30 @@ def create_taxonomy_db():
 
 
 def create_genes_db():
-    pass
+    Gene.objects.all().delete()
+    GeneFactory.create_batch(50)
+    GeneWithEggNOGFactory.create_batch(15)
+    GeneWithKeggFactory.create_batch(12)
+    for tax in Taxonomy.objects.all():
+        GeneFactory.create_batch(randint(1, 10), taxonomy=tax)
+        GeneWithEggNOGFactory.create(taxonomy=tax)
+        GeneWithKeggFactory.create(taxonomy=tax)
+
+
+def compute_stats():
+    ComputeStatistics('all').clean_db()
+    for gene_source in ['all', 'virgo', 'igc']:
+        ComputeCounts(gene_source).all()
+        ComputeGeneLength(gene_source).all()
+        ComputeTaxonomyRepartition(gene_source).all()
+        ComputeTaxonomyPresence(gene_source).all()
 
 
 def create_small_db():
-    create_functions_db()
+    empty_db()
     create_taxonomy_db()
     create_genes_db()
+    compute_stats()
 
 
 class Command(BaseCommand):

backend/metagenedb/apps/catalog/models/taxonomy.py

@@ -62,12 +62,13 @@ class Taxonomy(models.Model):
         Build and save parental hierarchy for an entry
         """
         hierarchy = {}
-        if self.name != 'root' and self.parent is not None:
+        if self.name != 'root':
             hierarchy[self.rank] = {
                 'tax_id': self.tax_id,
                 'name': self.name
             }
-            hierarchy = {**hierarchy, **getattr(self.parent, 'hierarchy', self.parent.build_hierarchy())}
+            if self.parent is not None:
+                hierarchy = {**hierarchy, **getattr(self.parent, 'hierarchy', self.parent.build_hierarchy())}
         self.hierarchy = hierarchy
         self.save()
         return hierarchy

backend/scripts/populate_db/test_import_igc_data.py

@@ -297,12 +297,12 @@ class TestBuildTaxoMapping(APITestCase):
         self.assertDictEqual(self.import_igc_genes.phylum_mapping, expected_phylum_dict)
 
 
-class TestBuildBuildFunctionCatalog(APITestCase):
+class TestBuildFunctionCatalog(APITestCase):
 
     @classmethod
     def setUpTestData(cls):
-        cls.keggs = KeggOrthologyFactory.create_batch(100)
-        cls.eggnogs = EggNOGFactory.create_batch(100)
+        cls.keggs = KeggOrthologyFactory.create_batch(10)
+        cls.eggnogs = EggNOGFactory.create_batch(10)
 
     def setUp(self):
         self.import_igc_genes = ImportIGCGenes('test', 'test_url', 'test_token')