Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: added field type inside drift data #142

Merged
merged 3 commits into from
Jul 26, 2024
Merged

feat: added field type inside drift data #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6f3a194
feat: added field type inside drift data
maocorte Jul 26, 2024
23c270e
Merge branch 'main' into be_add_field_type_on_drift
maocorte Jul 26, 2024
48b780b
updated demo data
maocorte Jul 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions api/app/models/metrics/drift_dto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
from pydantic import BaseModel, ConfigDict
from pydantic.alias_generators import to_camel

from app.models.inferred_schema_dto import FieldType
from app.models.job_status import JobStatus


Expand All @@ -23,6 +24,7 @@ class FeatureDriftCalculation(BaseModel):

class FeatureMetrics(BaseModel):
feature_name: str
field_type: FieldType
drift_calc: FeatureDriftCalculation

model_config = ConfigDict(populate_by_name=True, alias_generator=to_camel)
Expand Down
3 changes: 3 additions & 0 deletions api/tests/commons/db_mock.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -475,14 +475,17 @@ def get_sample_current_dataset(
'featureMetrics': [
{
'featureName': 'gender',
'fieldType': 'categorical',
'driftCalc': {'type': 'CHI2', 'value': 0.87, 'hasDrift': True},
},
{
'featureName': 'city',
'fieldType': 'categorical',
'driftCalc': {'type': 'CHI2', 'value': 0.12, 'hasDrift': False},
},
{
'featureName': 'age',
'fieldType': 'numerical',
'driftCalc': {'type': 'KS', 'value': 0.92, 'hasDrift': True},
},
]
Expand Down
24 changes: 12 additions & 12 deletions init-data/init_db.sql
View file
Open in desktop

Large diffs are not rendered by default.

12 changes: 6 additions & 6 deletions init-data/mirror_files.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,12 +7,12 @@
/usr/bin/mc mb myminio/test-bucket

# Copy files from the project root to the correct paths in the MinIO bucket
/usr/bin/mc cp /data/binary_classification/reference-income.csv myminio/test-bucket/e02f2aed-cd29-4703-8faf-2dcab9fc668e/reference/ee43cc3d-d71c-43f2-be0b-55da73d509c5/
/usr/bin/mc cp /data/binary_classification/current1-income.csv myminio/test-bucket/e02f2aed-cd29-4703-8faf-2dcab9fc668e/current/63b173f8-6150-41f5-8a6b-a1e08a3a7c12/
/usr/bin/mc cp /data/multiclass-classification/3_classes_reference.csv myminio/test-bucket/756204a0-a6ba-44c2-b287-ca828e2b2441/reference/dd84c147-f6aa-4584-a2dc-3ca4cd00917b/
/usr/bin/mc cp /data/multiclass-classification/3_classes_current1.csv myminio/test-bucket/756204a0-a6ba-44c2-b287-ca828e2b2441/current/658f7c87-b557-4611-a29e-9ae0ae42ded7/
/usr/bin/mc cp /data/regression/regression_abalone_reference.csv myminio/test-bucket/6c48c7e1-442b-4c48-a218-95d07f40a805/reference/12fbe35a-3530-4e26-b53b-ee12dc47a874/
/usr/bin/mc cp /data/regression/regression_abalone_current1.csv myminio/test-bucket/6c48c7e1-442b-4c48-a218-95d07f40a805/current/03616777-0b1e-47ed-b1ad-273dc51d467d/
/usr/bin/mc cp /data/binary_classification/reference-income.csv myminio/test-bucket/e02f2aed-cd29-4703-8faf-2dcab9fc668e/reference/db15546e-16a3-4482-8317-323d66dbe409/
/usr/bin/mc cp /data/binary_classification/current1-income.csv myminio/test-bucket/e02f2aed-cd29-4703-8faf-2dcab9fc668e/current/b73334fb-aac0-400c-9103-fe894e13bd95/
/usr/bin/mc cp /data/multiclass-classification/3_classes_reference.csv myminio/test-bucket/756204a0-a6ba-44c2-b287-ca828e2b2441/reference/d8cb36a9-2f8b-4e45-bab0-aeaa259a9f46/
/usr/bin/mc cp /data/multiclass-classification/3_classes_current1.csv myminio/test-bucket/756204a0-a6ba-44c2-b287-ca828e2b2441/current/dda74c14-91de-4ae8-a432-3a2f8ccdd153/
/usr/bin/mc cp /data/regression/regression_abalone_reference.csv myminio/test-bucket/6c48c7e1-442b-4c48-a218-95d07f40a805/reference/6ae1390e-656a-45aa-acd4-6f6b38e6acf4/
/usr/bin/mc cp /data/regression/regression_abalone_current1.csv myminio/test-bucket/6c48c7e1-442b-4c48-a218-95d07f40a805/current/edb6ed6c-6e2d-44fa-8a60-40540aec9c03/

# Exit the script
exit 0
3 changes: 3 additions & 0 deletions sdk/radicalbit_platform_sdk/models/dataset_drift.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@
from pydantic import BaseModel, ConfigDict
from pydantic.alias_generators import to_camel

from radicalbit_platform_sdk.models.field_type import FieldType


class DriftAlgorithm(str, Enum):
KS = 'KS'
Expand All @@ -21,6 +23,7 @@ class FeatureDriftCalculation(BaseModel):

class FeatureDrift(BaseModel):
feature_name: str
field_type: FieldType
drift_calc: FeatureDriftCalculation

model_config = ConfigDict(populate_by_name=True, alias_generator=to_camel)
Expand Down
6 changes: 6 additions & 0 deletions sdk/tests/apis/model_current_dataset_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
CurrentRegressionModelQuality,
Drift,
DriftAlgorithm,
FieldType,
JobStatus,
ModelType,
RegressionDataQuality,
Expand Down Expand Up @@ -166,14 +167,17 @@ def test_drift_ok(self):
"featureMetrics": [
{
"featureName": "gender",
"fieldType": "categorical",
"driftCalc": {"type": "CHI2", "value": 0.87, "hasDrift": true}
},
{
"featureName": "city",
"fieldType": "categorical",
"driftCalc": {"type": "CHI2", "value": 0.12, "hasDrift": false}
},
{
"featureName": "age",
"fieldType": "numerical",
"driftCalc": {"type": "KS", "value": 0.92, "hasDrift": true}
}
]
Expand All @@ -187,10 +191,12 @@ def test_drift_ok(self):

assert len(drift.feature_metrics) == 3
assert drift.feature_metrics[1].feature_name == 'city'
assert drift.feature_metrics[1].field_type == FieldType.categorical
assert drift.feature_metrics[1].drift_calc.type == DriftAlgorithm.CHI2
assert drift.feature_metrics[1].drift_calc.value == 0.12
assert drift.feature_metrics[1].drift_calc.has_drift is False
assert drift.feature_metrics[2].feature_name == 'age'
assert drift.feature_metrics[2].field_type == FieldType.numerical
assert drift.feature_metrics[2].drift_calc.type == DriftAlgorithm.KS
assert drift.feature_metrics[2].drift_calc.value == 0.92
assert drift.feature_metrics[2].drift_calc.has_drift is True
Expand Down