Merge pull request #77 from pepkit/dev

Release 0.2.4

eido/_version.py

@@ -1 +1 @@
-__version__ = "0.2.3"
+__version__ = "0.2.4"

eido/conversion_plugins.py

@@ -42,8 +42,7 @@ def yaml_pep_filter(p, **kwargs) -> Dict[str, str]:
     """
     from yaml import dump
 
-    data = p.config.to_dict()
-    return {"project": dump(data, default_flow_style=False)}
+    return {"project": dump(p.config, default_flow_style=False)}
 
 
 def csv_pep_filter(p, **kwargs) -> Dict[str, str]:
@@ -70,7 +69,7 @@ def processed_pep_filter(p, **kwargs) -> Dict[str, str]:
     samples_as_objects = kwargs.get("samples_as_objects")
     subsamples_as_objects = kwargs.get("subsamples_as_objects")
 
-    prj_repr = p.config.to_dict()
+    prj_repr = p.config
 
     return {
         "project": str(prj_repr),

eido/output_formatters.py

@@ -110,7 +110,7 @@ def _convert_sample_to_row(
             ):
                 value = sample[attribute][sample_index]
             else:
-                value = sample[attribute]
+                value = sample.get(attribute)
 
             sample_row.append(value or "")
 

eido/validation.py

@@ -43,6 +43,10 @@ def _validate_object(obj: Mapping, schema: Union[str, dict], sample_name_colname
                 instance_name = error.instance[sample_name_colname]
             except KeyError:
                 instance_name = "project"
+            except TypeError:
+                instance_name = obj["samples"][error.absolute_path[1]][
+                    sample_name_colname
+                ]
             errors_by_type[error.message].append(
                 {
                     "type": error.message,

requirements/requirements-all.txt

@@ -2,5 +2,5 @@ importlib-metadata; python_version < '3.10'
 jsonschema>=3.0.1
 logmuse>=0.2.5
 pandas
-peppy>=0.40.6
+peppy>=0.40.7
 ubiquerg>=0.5.2

tests/conftest.py

@@ -124,10 +124,25 @@ def save_result_mock(mocker):
 
 
 @pytest.fixture
-def test_file_existence_schema(schemas_path):
+def test_file_existing_schema(schemas_path):
     return os.path.join(schemas_path, "schema_test_file_exist.yaml")
 
 
 @pytest.fixture
-def test_file_existance_pep(peps_path):
-    return os.path.join(peps_path, "test_file_existence", "project_config.yaml")
+def test_file_existing_pep(peps_path):
+    return os.path.join(peps_path, "test_file_existing", "project_config.yaml")
+
+
+@pytest.fixture
+def test_schema_value_check(schemas_path):
+    return os.path.join(schemas_path, "value_check_schema.yaml")
+
+
+@pytest.fixture
+def test_file_value_check(peps_path):
+    return os.path.join(peps_path, "value_check_pep", "project_config.yaml")
+
+
+@pytest.fixture
+def test_multiple_subs(peps_path):
+    return os.path.join(peps_path, "multiple_subsamples", "project_config.yaml")

tests/data/peps/multiple_subsamples/project_config.yaml

@@ -0,0 +1,19 @@
+pep_version: "2.1.0"
+sample_table: sample_table.csv
+subsample_table:
+  - subsample_table1.csv
+  - subsample_table2.csv
+
+sample_modifiers:
+  append:
+    local_files: LOCAL
+    genome: "fg"
+  derive:
+    attributes: [local_files]
+    sources:
+      LOCAL: "../data/{file_path}"
+  imply:
+    - if:
+        identifier: "frog1"
+      then:
+        genome: "frog_frog"

tests/data/peps/multiple_subsamples/sample_table.csv

@@ -0,0 +1,5 @@
+sample_id,protocol,identifier
+frog_1,anySampleType,frog1
+frog_2,anySampleType,frog2
+frog_3,anySampleType,frog3
+frog_4,anySampleType,frog4

tests/data/peps/multiple_subsamples/subsample_table1.csv

@@ -0,0 +1,6 @@
+sample_id,file_path,subsample_name
+frog_1,file/a.txt,a
+frog_1,file/b.txt,b
+frog_1,file/c.txt,c
+frog_2,file/a.txt,a
+frog_2,file/b.txt,b

tests/data/peps/multiple_subsamples/subsample_table2.csv

@@ -0,0 +1,6 @@
+sample_id,random_string,subsample_name
+frog_1,x_x,x
+frog_1,y_y,y
+frog_1,z_z,z
+frog_2,xy_yx,xy
+frog_2,xx_xx,xx

tests/data/peps/value_check_pep/project_config.yaml

@@ -0,0 +1,6 @@
+description: None
+name: encode_prj
+pep_version: 2.0.0
+project_name: value_check_pep
+sample_table: sample_table.csv
+subsample_table: []

tests/data/peps/value_check_pep/sample_table.csv

@@ -0,0 +1,7 @@
+sample_name,file_name,genome,assay,cell_line,target,format_type
+encode_4,ENCFF452DAM.bed.gz,hg38,Histone ChIP-seq,skeletal muscle myoblast,H3K36me3,narrowPeak
+encode_20,ENCFF121AXG.bed.gz,hg38,DNase-seq,RPMI7951,,tssPeak
+encode_21,ENCFF710ECJ.bed.gz,hg38,DNase-seq,RPMI7951,,broadPeak
+encode_22,ENCFF945FZN.bed.gz,hg38,DNase-seq,RPMI7951,,narrowPeak
+encode_23,ENCFF322PQO.bed.gz,hg38,DNase-seq,RPMI7951,,tssPeak
+encode_24,ENCFF322PQO.bed.gz,hg38,DNase-seq,RPMI7951,,tssPeak1

tests/data/schemas/value_check_schema.yaml

@@ -0,0 +1,16 @@
+description: bedboss run-all pep schema
+properties:
+  samples:
+    items:
+      properties:
+        format_type:
+          description: whether the regions are narrow (transcription factor implies
+            narrow, histone mark implies broad peaks)
+          enum:
+          - narrowPeak
+          - broadPeak
+          type: string
+      type: object
+    type: array
+required:
+- samples

tests/test_conversions.py

@@ -1,4 +1,10 @@
-from eido.conversion import *
+from eido.conversion import (
+    run_filter,
+    get_available_pep_filters,
+    pep_conversion_plugins,
+    convert_project,
+)
+import peppy
 
 
 class TestConversionInfrastructure:
@@ -74,3 +80,27 @@ def test_eido_csv_filter_filters_nextflow_taxprofiler_input_correctly(
 
         assert save_result_mock.called
         assert conv_result == {"samples": output_pep_nextflow_taxprofiler}
+
+    def test_multiple_subsamples(self, test_multiple_subs):
+        project = peppy.Project(test_multiple_subs, sample_table_index="sample_id")
+
+        conversion = convert_project(
+            project,
+            "csv",
+        )
+        assert isinstance(conversion["samples"], str)
+        conversion = convert_project(
+            project,
+            "basic",
+        )
+        assert isinstance(conversion["project"], str)
+        conversion = convert_project(
+            project,
+            "yaml",
+        )
+        assert isinstance(conversion["project"], str)
+        conversion = convert_project(
+            project,
+            "yaml-samples",
+        )
+        assert isinstance(conversion["samples"], str)

tests/test_validations.py

@@ -1,7 +1,6 @@
 import urllib
 
 import pytest
-from jsonschema.exceptions import ValidationError
 from peppy import Project
 from peppy.utils import load_yaml
 
@@ -140,9 +139,15 @@ def test_validate_detects_invalid(self, schema_invalid_file_path, remote_pep_cfg
             )
 
     def test_validate_file_existance(
-        self, test_file_existance_pep, test_file_existence_schema
+        self, test_file_existing_pep, test_file_existing_schema
     ):
-        schema_path = test_file_existence_schema
-        prj = Project(test_file_existance_pep)
+        schema_path = test_file_existing_schema
+        prj = Project(test_file_existing_pep)
         with pytest.raises(PathAttrNotFoundError):
             validate_input_files(prj, schema_path)
+
+    def test_validation_values(self, test_schema_value_check, test_file_value_check):
+        schema_path = test_schema_value_check
+        prj = Project(test_file_value_check)
+        with pytest.raises(EidoValidationError):
+            validate_project(project=prj, schema=schema_path)