gitea_admin/sientia-dataops-model-manager
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SIENTIAPDE-1241: Fixed formatting and linted code

Browse Source
This commit is contained in:
Kou-Kinoshita
2025-10-30 10:38:29 -03:00
parent 17a551d6f9
commit a5c0cb6e47
5 changed files with 161 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/utils/repository/test_storage_repository.py
View File

@@ -1,7 +1,7 @@
"""Unit tests for StorageRepository class."""
from io import BytesIO
from unittest.mock import MagicMock, Mock, patch
from unittest.mock import Mock, patch
import pytest
from botocore.exceptions import ClientError
@@ -462,4 +462,3 @@ def test_fetch_file_logs_file_size(mock_boto3, mock_logger, storage_config):
# Verify logging includes file size
log_calls = [str(call) for call in mock_logger.info.call_args_list]
assert any('12345 bytes' in str(call) for call in log_calls)

116
tests/utils/repository/test_training_repository.py
View File

@@ -496,12 +496,14 @@ class TestTrain:
):
"""Test basic training workflow."""
# Mock load_data to return a DataFrame
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
# Mock split_train_test to return train/test splits
@@ -540,12 +542,14 @@ class TestTrain:
"""Test training with scaler enabled."""
sample_params.use_scaler = True
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
@@ -567,12 +571,14 @@ class TestTrain:
"""Test training with shuffle enabled."""
sample_params.shuffle = True
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
@@ -581,7 +587,7 @@ class TestTrain:
y_test = pd.Series([25, 30], name='target')
mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
result = training_repo.train(sample_csv_data, sample_params)
training_repo.train(sample_csv_data, sample_params)
# Verify split was called with shuffle=True
call_kwargs = mock_split_train_test.call_args[1]
@@ -595,12 +601,14 @@ class TestTrain:
"""Test training with different train size."""
sample_params.train_size = 70
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
@@ -609,7 +617,7 @@ class TestTrain:
y_test = pd.Series([25, 30], name='target')
mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
result = training_repo.train(sample_csv_data, sample_params)
training_repo.train(sample_csv_data, sample_params)
# Verify split was called with train_size=0.7
call_kwargs = mock_split_train_test.call_args[1]
@@ -622,12 +630,14 @@ class TestTrain:
):
"""Test that ValueError is raised when transformed data is empty."""
# Mock load_data to return empty DataFrame
mock_df = pd.DataFrame({
'var1': [],
'var2': [],
'var3': [],
'target': [],
})
mock_df = pd.DataFrame(
{
'var1': [],
'var2': [],
'var3': [],
'target': [],
}
)
mock_load_data.return_value = mock_df
with pytest.raises(ValueError, match='Data view is empty after transformation'):
@@ -645,12 +655,14 @@ class TestTrain:
sample_csv_data,
):
"""Test that training success is logged."""
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
@@ -676,12 +688,14 @@ class TestTrain:
sample_params.line_separator = ';'
sample_params.decimal_separator = ','
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
@@ -701,12 +715,14 @@ class TestTrain:
self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
):
"""Test that TrainModelResult contains all expected fields."""
mock_df = pd.DataFrame({
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
})
mock_df = pd.DataFrame(
{
'var1': [1, 2, 3, 4, 5],
'var2': [2, 3, 4, 5, 6],
'var3': [3, 4, 5, 6, 7],
'target': [10, 15, 20, 25, 30],
}
)
mock_load_data.return_value = mock_df
x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})