test_explorer.py

#!/usr/bin/env python3
"""
Test script to verify basic functionality of the Dataset Explorer
"""

import sys
import pandas as pd
import numpy as np
from dataset_explorer import DatasetExplorer
from PyQt5.QtWidgets import QApplication
from PyQt5.QtTest import QTest
from PyQt5.QtCore import Qt


def test_dataset_loading():
    """Test loading and basic operations"""
    print("Testing dataset loading and basic operations...")
    
    # Create a test application
    app = QApplication(sys.argv)
    explorer = DatasetExplorer()
    
    # Load sample data directly
    try:
        explorer.dataset = pd.read_csv('sample_data.csv')
        explorer.filtered_dataset = explorer.dataset.copy()
        explorer.update_column_combos()
        explorer.update_preview()
        explorer.update_statistics()
        print("✓ Dataset loaded successfully")
        print(f"  - Rows: {len(explorer.dataset)}")
        print(f"  - Columns: {len(explorer.dataset.columns)}")
    except Exception as e:
        print(f"✗ Failed to load dataset: {e}")
        return False
    
    # Test statistics calculation
    try:
        stats_text = explorer.stats_text.toPlainText()
        assert len(stats_text) > 0, "Statistics text is empty"
        print("✓ Statistics calculated successfully")
    except Exception as e:
        print(f"✗ Failed to calculate statistics: {e}")
        return False
    
    # Test filtering
    try:
        original_count = len(explorer.filtered_dataset)
        explorer.column_combo.setCurrentText('Department')
        explorer.operator_combo.setCurrentText('==')
        explorer.filter_value.setText('Engineering')
        explorer.apply_filter()
        filtered_count = len(explorer.filtered_dataset)
        assert filtered_count < original_count, "Filter did not reduce dataset size"
        print(f"✓ Filtering works (reduced from {original_count} to {filtered_count} rows)")
        
        # Reset filter
        explorer.reset_filter()
        assert len(explorer.filtered_dataset) == original_count, "Reset filter failed"
        print("✓ Reset filter works")
    except Exception as e:
        print(f"✗ Failed filtering test: {e}")
        return False
    
    # Test column combo boxes
    try:
        assert explorer.column_combo.count() > 0, "Column combo is empty"
        assert explorer.x_column_combo.count() > 0, "X column combo is empty"
        assert explorer.y_column_combo.count() > 0, "Y column combo is empty"
        print("✓ Column combo boxes populated")
    except Exception as e:
        print(f"✗ Failed column combo test: {e}")
        return False
    
    print("\n✓ All tests passed!")
    app.quit()
    return True


def test_data_types():
    """Test that the sample data has correct types"""
    print("\nTesting data types in sample dataset...")
    
    try:
        df = pd.read_csv('sample_data.csv')
        
        # Check for numeric columns
        numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
        print(f"✓ Numeric columns: {numeric_cols}")
        
        # Check for categorical columns
        cat_cols = df.select_dtypes(include=['object']).columns.tolist()
        print(f"✓ Categorical columns: {cat_cols}")
        
        # Verify expected columns exist
        expected_cols = ['Name', 'Age', 'Gender', 'Salary', 'Department', 'Experience']
        for col in expected_cols:
            assert col in df.columns, f"Expected column {col} not found"
        print(f"✓ All expected columns present")
        
        return True
    except Exception as e:
        print(f"✗ Data type test failed: {e}")
        return False


if __name__ == '__main__':
    success = True
    
    # Run tests
    success = test_data_types() and success
    success = test_dataset_loading() and success
    
    if success:
        print("\n" + "="*50)
        print("ALL TESTS PASSED!")
        print("="*50)
        sys.exit(0)
    else:
        print("\n" + "="*50)
        print("SOME TESTS FAILED!")
        print("="*50)
        sys.exit(1)