SIENTIAPDE-1645: Remove validate.sh script, add jsonschema dependency, and improve test code readability

2026-08-05 11:23:22 -03:00
parent ebc7e5ce6f
commit 4133e200f7
4 changed files with 38 additions and 207 deletions
--- a/requirements-local.txt
+++ b/requirements-local.txt
@@ -7,4 +7,5 @@ git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.12.0
 git+ssh://git@github.com/Aignosi/sientia-model-library.git@0.8.3
 prometheus-client==0.23.1
 beautifulsoup4==4.12.3
-evidently==0.6.7
+evidently==0.6.7
+jsonschema==4.26.0
--- a/tests/activities/test_training.py
+++ b/tests/activities/test_training.py
@@ -369,7 +369,10 @@ def test_prepare_data_increments_error_counter_and_still_observes_lag_on_failure
    training.observe_lag_sync.assert_called_once()
    training.emit_metric_sync.assert_called_once()
    call_args = training.emit_metric_sync.call_args
-    assert call_args.kwargs['metric_object'] is mm_metrics.SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL
+    assert (
+        call_args.kwargs['metric_object']
+        is mm_metrics.SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL
+    )


 def test_fit_model_observes_lag_on_success(training):
@@ -419,12 +422,16 @@ def test_fit_model_increments_error_counter_on_failure(training):
    training.observe_lag_sync.assert_called_once()
    training.emit_metric_sync.assert_called_once()
    call_args = training.emit_metric_sync.call_args
-    assert call_args.kwargs['metric_object'] is mm_metrics.SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL
+    assert (
+        call_args.kwargs['metric_object'] is mm_metrics.SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL
+    )


@patch('model_manager.activities.training.mm_metrics')
@patch('model_manager.activities.training.mlflow')
-def test_train_model_sets_quality_gauges_after_compute_metrics(mock_mlflow, mock_mm_metrics, training):
+def test_train_model_sets_quality_gauges_after_compute_metrics(
+    mock_mlflow, mock_mm_metrics, training
+):
    tp = TrainModelParams.from_dict(
        {**_minimal_params_dict(), 'model_metadata': {'schemas': {'components': {'schemas': {}}}}}
    )
@@ -473,9 +480,15 @@ def test_train_model_sets_quality_gauges_after_compute_metrics(mock_mlflow, mock

    training.train_model({'metadata': {}, 'train_params': tp.to_dict()})

-    mock_mm_metrics.SIENTIA_TRAINING_MODEL_QUALITY_MSE.labels.return_value.set.assert_called_once_with(0.5)
-    mock_mm_metrics.SIENTIA_TRAINING_MODEL_QUALITY_MAE.labels.return_value.set.assert_called_once_with(0.3)
-    mock_mm_metrics.SIENTIA_TRAINING_MODEL_QUALITY_R2.labels.return_value.set.assert_called_once_with(-0.1)
+    mock_mm_metrics.SIENTIA_TRAINING_MODEL_QUALITY_MSE.labels.return_value.set.assert_called_once_with(
+        0.5
+    )
+    mock_mm_metrics.SIENTIA_TRAINING_MODEL_QUALITY_MAE.labels.return_value.set.assert_called_once_with(
+        0.3
+    )
+    mock_mm_metrics.SIENTIA_TRAINING_MODEL_QUALITY_R2.labels.return_value.set.assert_called_once_with(
+        -0.1
+    )


@patch('model_manager.activities.training.mm_metrics')
--- a/tests/test_metrics.py
+++ b/tests/test_metrics.py
@@ -237,7 +237,10 @@ def test_sientia_training_data_preparation_error_count_total_is_counter():
    from model_manager.metrics import SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL

    assert isinstance(SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL, Counter)
-    assert 'sientia_training_data_preparation_error_count' in SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL._name
+    assert (
+        'sientia_training_data_preparation_error_count'
+        in SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL._name
+    )
    _assert_training_labels(SIENTIA_TRAINING_DATA_PREPARATION_ERROR_COUNT_TOTAL)


@@ -257,7 +260,10 @@ def test_sientia_training_model_fit_error_count_total_is_counter():
    from model_manager.metrics import SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL

    assert isinstance(SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL, Counter)
-    assert 'sientia_training_model_fit_error_count' in SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL._name
+    assert (
+        'sientia_training_model_fit_error_count'
+        in SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL._name
+    )
    _assert_training_labels(SIENTIA_TRAINING_MODEL_FIT_ERROR_COUNT_TOTAL)


@@ -340,9 +346,15 @@ def test_sientia_training_info_is_gauge():
    assert SIENTIA_TRAINING_INFO._name == 'sientia_training_info'

    expected_labels = {
-        'pod_id', 'model_name', 'model_type',
-        'dataset_train_rows', 'dataset_val_rows', 'feature_count',
-        'mse', 'mae', 'r2',
+        'pod_id',
+        'model_name',
+        'model_type',
+        'dataset_train_rows',
+        'dataset_val_rows',
+        'feature_count',
+        'mse',
+        'mae',
+        'r2',
    }
    assert expected_labels == set(SIENTIA_TRAINING_INFO._labelnames)

--- a/validate.sh
+++ b/validate.sh
@@ -1,195 +0,0 @@
-#!/bin/bash
-# Model Manager Code Validation Script
-# This script runs all code quality checks before committing or deploying
-#
-# Usage:
-#   ./validate.sh              # Run all checks including tests (default)
-#   ./validate.sh --no-tests   # Skip unit tests
-#   ./validate.sh --skip-tests # Skip unit tests (alias)
-#   ./validate.sh --only-tests # Run only unit tests
-#   ./validate.sh --fix        # Auto-fix formatting and linting, then run validations (no tests)
-
-set -e  # Exit on any error
-
-# Parse command line arguments
-RUN_TESTS=true
-ONLY_TESTS=false
-FIX_MODE=false
-
-for arg in "$@"; do
-    case $arg in
-        --no-tests|--skip-tests)
-            RUN_TESTS=false
-            shift
-            ;;
-        --only-tests)
-            ONLY_TESTS=true
-            shift
-            ;;
-        --fix)
-            FIX_MODE=true
-            RUN_TESTS=false
-            shift
-            ;;
-        --help|-h)
-            echo "Usage: $0 [OPTIONS]"
-            echo ""
-            echo "Options:"
-            echo "  --no-tests, --skip-tests    Skip unit tests (default: run tests)"
-            echo "  --only-tests                Run only unit tests"
-            echo "  --fix                       Auto-fix formatting and linting, then run validations (no tests)"
-            echo "  --help, -h                  Show this help message"
-            echo ""
-            exit 0
-            ;;
-        *)
-            echo "Unknown option: $arg"
-            echo "Use --help for usage information"
-            exit 1
-            ;;
-    esac
-done
-
-# Colors for output
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-YELLOW='\033[1;33m'
-BLUE='\033[0;34m'
-NC='\033[0m' # No Color
-
-echo -e "${BLUE}╔════════════════════════════════════════════════════════╗${NC}"
-echo -e "${BLUE}║  Model Manager - Code Validation Suite                ║${NC}"
-echo -e "${BLUE}╚════════════════════════════════════════════════════════╝${NC}"
-echo ""
-
-# Handle --fix mode
-if [ "$FIX_MODE" = true ]; then
-    echo -e "${BLUE}🔧 Running auto-fix mode...${NC}"
-    echo ""
-    
-    echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-    echo -e "${BLUE}▶ Auto-fixing code formatting (Ruff)${NC}"
-    echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-    ruff format model_manager/ tests/
-    echo -e "${GREEN}✅ Code formatting applied${NC}"
-    echo ""
-    
-    echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-    echo -e "${BLUE}▶ Auto-fixing linting issues (Ruff)${NC}"
-    echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-    ruff check --fix model_manager/ tests/
-    echo -e "${GREEN}✅ Linting fixes applied${NC}"
-    echo ""
-    
-    echo -e "${YELLOW}ℹ️  Now running validations (without tests)...${NC}"
-    echo ""
-fi
-
-# Handle --only-tests mode
-if [ "$ONLY_TESTS" = true ]; then
-    echo -e "${BLUE}🧪 Running only unit tests...${NC}"
-    echo ""
-fi
-
-if [ "$RUN_TESTS" = false ] && [ "$ONLY_TESTS" = false ]; then
-    echo -e "${YELLOW}ℹ️  Unit tests will be skipped${NC}"
-    echo ""
-fi
-
-# Check if virtual environment is activated
-if [[ -z "${VIRTUAL_ENV}" ]] && [[ -z "${CONDA_DEFAULT_ENV}" ]]; then
-    echo -e "${YELLOW}⚠️  Warning: No virtual environment detected${NC}"
-    echo -e "${YELLOW}   Consider activating your venv/conda environment${NC}"
-    echo ""
-fi
-
-# Function to run a validation step
-run_step() {
-    local step_name=$1
-    local step_command=$2
-    
-    echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-    echo -e "${BLUE}▶ ${step_name}${NC}"
-    echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-    
-    if eval "$step_command"; then
-        echo -e "${GREEN}✅ ${step_name} - PASSED${NC}"
-        echo ""
-        return 0
-    else
-        echo -e "${RED}❌ ${step_name} - FAILED${NC}"
-        echo ""
-        return 1
-    fi
-}
-
-# Track failures
-FAILED_STEPS=()
-
-# Handle --only-tests mode
-if [ "$ONLY_TESTS" = true ]; then
-    # Step 5: Unit Tests (pytest)
-    if ! run_step "Unit Tests (pytest)" "pytest tests/ --cov=model_manager --cov-report=term-missing --cov-report=xml --cov-report=html --cov-fail-under=80 -q"; then
-        FAILED_STEPS+=("Unit Tests")
-    fi
-else
-    # Step 1: Code Formatting Check (Ruff)
-    if ! run_step "1. Code Formatting (Ruff)" "ruff format --check model_manager/ tests/"; then
-        FAILED_STEPS+=("Code Formatting")
-    fi
-
-    # Step 2: Linting (Ruff)
-    if ! run_step "2. Code Linting (Ruff)" "ruff check model_manager/ tests/"; then
-        FAILED_STEPS+=("Linting")
-    fi
-
-    # Step 3: Type Checking (mypy)
-    if ! run_step "3. Type Checking (mypy)" "mypy model_manager/"; then
-        FAILED_STEPS+=("Type Checking")
-    fi
-
-    # Step 4: Security Analysis (Bandit)
-    if ! run_step "4. Security Analysis (Bandit)" "bandit -r model_manager/ -ll -q"; then
-        FAILED_STEPS+=("Security Analysis")
-    fi
-
-    # Step 5: Unit Tests (pytest)
-    if [ "$RUN_TESTS" = true ]; then
-        if ! run_step "5. Unit Tests (pytest)" "pytest tests/ --cov=model_manager --cov-report=term-missing --cov-report=xml --cov-report=html --cov-fail-under=80 -q"; then
-            FAILED_STEPS+=("Unit Tests")
-        fi
-    else
-        echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-        echo -e "${BLUE}▶ 5. Unit Tests (pytest)${NC}"
-        echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
-        echo -e "${YELLOW}⏭️  Unit Tests - SKIPPED${NC}"
-        echo ""
-    fi
-fi
-
-# Summary
-echo -e "${BLUE}╔════════════════════════════════════════════════════════╗${NC}"
-echo -e "${BLUE}║  Validation Summary                                    ║${NC}"
-echo -e "${BLUE}╚════════════════════════════════════════════════════════╝${NC}"
-echo ""
-
-if [ ${#FAILED_STEPS[@]} -eq 0 ]; then
-    echo -e "${GREEN}✅ All validation checks passed!${NC}"
-    echo -e "${GREEN}   Your code is ready for commit/deployment.${NC}"
-    echo ""
-    exit 0
-else
-    echo -e "${RED}❌ Validation failed for the following steps:${NC}"
-    for step in "${FAILED_STEPS[@]}"; do
-        echo -e "${RED}   • ${step}${NC}"
-    done
-    echo ""
-    echo -e "${YELLOW}💡 Tips:${NC}"
-    echo -e "${YELLOW}   • Run 'ruff format model_manager/ tests/' to auto-fix formatting${NC}"
-    echo -e "${YELLOW}   • Run 'ruff check --fix model_manager/ tests/' to auto-fix linting issues${NC}"
-    echo -e "${YELLOW}   • Review mypy errors and add type hints where needed${NC}"
-    echo -e "${YELLOW}   • Check bandit warnings for security issues${NC}"
-    echo -e "${YELLOW}   • Fix failing tests or improve test coverage${NC}"
-    echo ""
-    exit 1
-fi