SIENTIAPDE-1255: Add unit tests for the reports module

2025-10-20 22:20:26 -03:00
parent 0de2ece063
commit 089f312575
1 changed files with 361 additions and 0 deletions
--- a/tests/sientia/test_reports.py
+++ b/tests/sientia/test_reports.py
@@ -0,0 +1,361 @@
+import os
+from unittest.mock import MagicMock
+
+import pytest
+from bs4 import BeautifulSoup
+
+from model_manager.sientia import reports
+
+
+@pytest.fixture
+def stub_color_options(monkeypatch):
+    def fake_color_options(**kwargs):
+        return dict(kwargs)
+
+    monkeypatch.setattr(reports, 'ColorOptions', fake_color_options)
+
+
+def test_load_html_from_file_success(tmp_path):
+    sample_file = tmp_path / 'sample.html'
+    sample_file.write_text('<p>Hello</p>', encoding='utf-8')
+
+    content = reports.load_html_from_file(str(sample_file))
+
+    assert content == '<p>Hello</p>'
+
+
+def test_load_html_from_file_missing_file(capsys):
+    result = reports.load_html_from_file('non-existent.html')
+
+    captured = capsys.readouterr()
+    assert result is None
+    assert 'File not found: non-existent.html' in captured.out
+
+
+def test_load_html_from_file_os_error(monkeypatch, capsys):
+    def fake_open(*_args, **_kwargs):
+        raise OSError('boom')
+
+    monkeypatch.setattr('builtins.open', fake_open)
+
+    result = reports.load_html_from_file('path.html')
+
+    captured = capsys.readouterr()
+    assert result is None
+    assert 'Error reading file: boom' in captured.out
+
+
+def test_inject_content_replaces_section():
+    main_html = "<html><body><div id='target'>old</div></body></html>"
+    content = '<span>new</span>'
+
+    result = reports.inject_content(main_html, 'target', content)
+
+    soup = BeautifulSoup(result, 'html.parser')
+    section = soup.find(id='target')
+    assert section is not None
+    assert section.find('span').text == 'new'
+
+
+def test_inject_content_missing_section(capsys):
+    main_html = "<html><body><div id='other'>keep</div></body></html>"
+
+    result = reports.inject_content(main_html, 'missing', '<p>ignored</p>')
+
+    captured = capsys.readouterr()
+    assert "Section with id 'missing' not found" in captured.out
+    soup = BeautifulSoup(result, 'html.parser')
+    assert soup.find(id='other') is not None
+
+
+def test_reports_init_sets_defaults(stub_color_options):
+    report = reports.Reports(reference_data='ref', current_data='cur')
+
+    assert report.metrics == []
+    assert isinstance(report.options, list) and len(report.options) == 1
+    assert report.sections == {}
+    assert report.base_path is None
+
+
+def test_add_data_quality_section_without_run(monkeypatch, stub_color_options):
+    monkeypatch.setattr(reports, 'DatasetSummaryMetric', lambda: 'summary')
+    monkeypatch.setattr(
+        reports,
+        'generate_column_metrics',
+        lambda *args, **kwargs: ('columns', kwargs),
+    )
+    monkeypatch.setattr(reports, 'ConflictTargetMetric', lambda: 'conflict')
+    monkeypatch.setattr(reports, 'DatasetCorrelationsMetric', lambda: 'correlations')
+
+    report = reports.Reports(reference_data='ref', current_data='cur')
+    report.add_data_quality_section(columns=['col'], run=False)
+
+    assert report.metrics[-4:] == [
+        'summary',
+        ('columns', {'columns': ['col'], 'skip_id_column': True}),
+        'conflict',
+        'correlations',
+    ]
+    assert 'data_quality' not in report.sections
+
+
+def test_add_data_quality_section_with_run(monkeypatch, tmp_path, stub_color_options):
+    summary = object()
+    column_metrics = object()
+    conflict = object()
+    correlations = object()
+    monkeypatch.setattr(reports, 'DatasetSummaryMetric', lambda: summary)
+
+    def fake_generate_column_metrics(*_args, **kwargs):
+        return column_metrics
+
+    monkeypatch.setattr(reports, 'generate_column_metrics', fake_generate_column_metrics)
+    monkeypatch.setattr(reports, 'ConflictTargetMetric', lambda: conflict)
+    monkeypatch.setattr(reports, 'DatasetCorrelationsMetric', lambda: correlations)
+
+    report_instance = MagicMock()
+    report_instance.as_dict.return_value = {'result': 'data_quality'}
+    ReportMock = MagicMock(return_value=report_instance)
+    monkeypatch.setattr(reports, 'Report', ReportMock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur', base_path=str(tmp_path))
+    report.add_data_quality_section(columns=['c1'], run=True)
+
+    assert report.metrics[-4:] == [summary, column_metrics, conflict, correlations]
+    assert report.sections['data_quality'] == {'result': 'data_quality'}
+    ReportMock.assert_called_once_with(
+        metrics=[summary, column_metrics, conflict, correlations], options=report.options
+    )
+    report_instance.run.assert_called_once_with(reference_data='ref', current_data='cur')
+    report_instance.save_html.assert_called_once_with(
+        os.path.join(str(tmp_path), 'data_quality.html')
+    )
+
+
+def test_add_data_quality_section_run_without_base_path(monkeypatch, stub_color_options):
+    summary = object()
+    column_metrics = object()
+    conflict = object()
+    correlations = object()
+    monkeypatch.setattr(reports, 'DatasetSummaryMetric', lambda: summary)
+    monkeypatch.setattr(
+        reports,
+        'generate_column_metrics',
+        lambda *args, **kwargs: column_metrics,
+    )
+    monkeypatch.setattr(reports, 'ConflictTargetMetric', lambda: conflict)
+    monkeypatch.setattr(reports, 'DatasetCorrelationsMetric', lambda: correlations)
+
+    report_instance = MagicMock()
+    report_instance.as_dict.return_value = {'result': 'quality'}
+    ReportMock = MagicMock(return_value=report_instance)
+    monkeypatch.setattr(reports, 'Report', ReportMock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur')
+    report.add_data_quality_section(run=True)
+
+    assert report.sections['data_quality'] == {'result': 'quality'}
+    report_instance.save_html.assert_not_called()
+
+
+def test_add_data_drift_section_paths(monkeypatch, tmp_path, stub_color_options):
+    drift_instances = [object(), object(), object()]
+    DataDriftPresetMock = MagicMock(side_effect=drift_instances)
+    monkeypatch.setattr(reports, 'DataDriftPreset', DataDriftPresetMock)
+
+    report_instance = MagicMock()
+    report_instance.as_dict.return_value = {'result': 'data_drift'}
+    ReportMock = MagicMock(return_value=report_instance)
+    monkeypatch.setattr(reports, 'Report', ReportMock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur', base_path=str(tmp_path))
+    report.add_data_drift_section(columns=['c1'], run=False)
+    assert report.metrics[-1] == drift_instances[0]
+    assert 'data_drift' not in report.sections
+
+    report.add_data_drift_section(columns=['c1'], run=True)
+    assert report.sections['data_drift'] == {'result': 'data_drift'}
+    ReportMock.assert_called_with(metrics=[drift_instances[2]], options=report.options)
+    report_instance.run.assert_called_with(reference_data='ref', current_data='cur')
+    report_instance.save_html.assert_called_with(os.path.join(str(tmp_path), 'data_drift.html'))
+
+
+def test_add_data_drift_section_run_without_base_path(monkeypatch, stub_color_options):
+    drift_instances = [object(), object(), object()]
+    DataDriftPresetMock = MagicMock(side_effect=drift_instances)
+    monkeypatch.setattr(reports, 'DataDriftPreset', DataDriftPresetMock)
+
+    report_instance = MagicMock()
+    report_instance.as_dict.return_value = {'result': 'drift'}
+    ReportMock = MagicMock(return_value=report_instance)
+    monkeypatch.setattr(reports, 'Report', ReportMock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur')
+    report.add_data_drift_section(run=True)
+
+    assert report.sections['data_drift'] == {'result': 'drift'}
+    report_instance.save_html.assert_not_called()
+
+
+def test_add_regression_section(monkeypatch, tmp_path, stub_color_options):
+    regression_metrics = [object() for _ in range(7)]
+    monkeypatch.setattr(reports, 'RegressionPerformanceMetrics', lambda: regression_metrics[0])
+    monkeypatch.setattr(reports, 'RegressionDummyMetric', lambda: regression_metrics[1])
+    monkeypatch.setattr(
+        reports, 'RegressionPredictedVsActualScatter', lambda: regression_metrics[2]
+    )
+    monkeypatch.setattr(reports, 'RegressionPredictedVsActualPlot', lambda: regression_metrics[3])
+    monkeypatch.setattr(reports, 'RegressionErrorPlot', lambda: regression_metrics[4])
+    monkeypatch.setattr(reports, 'RegressionAbsPercentageErrorPlot', lambda: regression_metrics[5])
+    monkeypatch.setattr(reports, 'RegressionErrorDistribution', lambda: regression_metrics[6])
+
+    report_instance = MagicMock()
+    report_instance.as_dict.return_value = {'result': 'regression'}
+    ReportMock = MagicMock(return_value=report_instance)
+    monkeypatch.setattr(reports, 'Report', ReportMock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur', base_path=str(tmp_path))
+
+    report.add_regression_section(run=False)
+    assert report.metrics[-7:] == regression_metrics
+    assert 'regression' not in report.sections
+
+    report.add_regression_section(run=True)
+    assert report.sections['regression'] == {'result': 'regression'}
+    ReportMock.assert_called_with(metrics=regression_metrics, options=report.options)
+    report_instance.run.assert_called_with(reference_data='ref', current_data='cur')
+    report_instance.save_html.assert_called_with(os.path.join(str(tmp_path), 'regression.html'))
+
+
+def test_add_regression_section_run_without_base_path(monkeypatch, stub_color_options):
+    regression_metrics = [object() for _ in range(7)]
+    monkeypatch.setattr(reports, 'RegressionPerformanceMetrics', lambda: regression_metrics[0])
+    monkeypatch.setattr(reports, 'RegressionDummyMetric', lambda: regression_metrics[1])
+    monkeypatch.setattr(
+        reports, 'RegressionPredictedVsActualScatter', lambda: regression_metrics[2]
+    )
+    monkeypatch.setattr(reports, 'RegressionPredictedVsActualPlot', lambda: regression_metrics[3])
+    monkeypatch.setattr(reports, 'RegressionErrorPlot', lambda: regression_metrics[4])
+    monkeypatch.setattr(reports, 'RegressionAbsPercentageErrorPlot', lambda: regression_metrics[5])
+    monkeypatch.setattr(reports, 'RegressionErrorDistribution', lambda: regression_metrics[6])
+
+    report_instance = MagicMock()
+    report_instance.as_dict.return_value = {'result': 'reg'}
+    ReportMock = MagicMock(return_value=report_instance)
+    monkeypatch.setattr(reports, 'Report', ReportMock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur')
+    report.add_regression_section(run=True)
+
+    assert report.sections['regression'] == {'result': 'reg'}
+    report_instance.save_html.assert_not_called()
+
+
+def test_set_color_options_appends(monkeypatch):
+    calls = []
+
+    def color_options_mock(**kwargs):
+        calls.append(kwargs)
+        return kwargs
+
+    monkeypatch.setattr(reports, 'ColorOptions', color_options_mock)
+
+    report = reports.Reports(reference_data='ref', current_data='cur')
+    report.set_color_options(primary_color='#111', secondary_color='#222')
+
+    assert len(report.options) == 2
+    assert calls[0]['primary_color'] == '#0F4C81'
+    assert calls[1]['primary_color'] == '#111'
+    assert report.options[1]['secondary_color'] == '#222'
+
+
+def test_save_all_sections_html_requires_base_path(stub_color_options):
+    report = reports.Reports(reference_data='ref', current_data='cur')
+
+    with pytest.raises(ValueError):
+        report.save_all_sections_html('output/report.html')
+
+
+def test_save_all_sections_html_writes_output(tmp_path, stub_color_options):
+    base_dir = tmp_path / 'templates'
+    base_dir.mkdir()
+    (base_dir / 'header.html').write_text(
+        "<html><body><div id='data_drift'></div><div id='data_quality'></div><div id='regression'></div></body></html>",
+        encoding='utf-8',
+    )
+    (base_dir / 'data_drift.html').write_text('<p>Drift</p>', encoding='utf-8')
+    (base_dir / 'data_quality.html').write_text('<p>Quality</p>', encoding='utf-8')
+    (base_dir / 'regression.html').write_text('<p>Regression</p>', encoding='utf-8')
+
+    report = reports.Reports(reference_data='ref', current_data='cur', base_path=str(base_dir))
+    output_path = tmp_path / 'reports' / 'combined.html'
+
+    report.save_all_sections_html(str(output_path))
+
+    assert output_path.exists()
+    content = output_path.read_text(encoding='utf-8')
+    assert '<p>Drift</p>' in content
+    assert '<p>Quality</p>' in content
+    assert '<p>Regression</p>' in content
+
+
+def test_save_all_sections_html_creates_directory(monkeypatch, tmp_path, stub_color_options):
+    base_dir = tmp_path / 'templates'
+    base_dir.mkdir()
+    (base_dir / 'header.html').write_text(
+        "<html><body><div id='data_drift'></div><div id='data_quality'></div><div id='regression'></div></body></html>",
+        encoding='utf-8',
+    )
+    (base_dir / 'data_drift.html').write_text('<p>Drift</p>', encoding='utf-8')
+    (base_dir / 'data_quality.html').write_text('<p>Quality</p>', encoding='utf-8')
+    (base_dir / 'regression.html').write_text('<p>Regression</p>', encoding='utf-8')
+
+    make_dirs_called = []
+    report = reports.Reports(reference_data='ref', current_data='cur', base_path=str(base_dir))
+    output_path = tmp_path / 'nested' / 'report.html'
+    output_dir = str(output_path.parent)
+
+    original_exists = os.path.exists
+    original_makedirs = os.makedirs
+
+    def fake_exists(path):
+        if path == output_dir:
+            return False
+        return original_exists(path)
+
+    def fake_makedirs(path, exist_ok=False):
+        make_dirs_called.append((path, exist_ok))
+        return original_makedirs(path, exist_ok=exist_ok)
+
+    monkeypatch.setattr(os.path, 'exists', fake_exists)
+    monkeypatch.setattr(os, 'makedirs', fake_makedirs)
+
+    report.save_all_sections_html(str(output_path))
+
+    assert make_dirs_called == [(str(output_path.parent), True)]
+
+
+def test_save_all_sections_html_no_directory_needed(monkeypatch, tmp_path, stub_color_options):
+    base_dir = tmp_path / 'templates'
+    base_dir.mkdir()
+    (base_dir / 'header.html').write_text(
+        "<html><body><div id='data_drift'></div><div id='data_quality'></div><div id='regression'></div></body></html>",
+        encoding='utf-8',
+    )
+    (base_dir / 'data_drift.html').write_text('<p>Drift</p>', encoding='utf-8')
+    (base_dir / 'data_quality.html').write_text('<p>Quality</p>', encoding='utf-8')
+    (base_dir / 'regression.html').write_text('<p>Regression</p>', encoding='utf-8')
+
+    mk_calls = []
+
+    def fake_makedirs(path, exist_ok=False):
+        mk_calls.append((path, exist_ok))
+
+    monkeypatch.setattr(os, 'makedirs', fake_makedirs)
+    monkeypatch.chdir(tmp_path)
+
+    report = reports.Reports(reference_data='ref', current_data='cur', base_path=str(base_dir))
+    report.save_all_sections_html('report.html')
+
+    assert mk_calls == []
+    assert (tmp_path / 'report.html').exists()