verify_pipeline.py

import pandas as pd
import sys
import os

# Add the project root to sys.path
sys.path.append(os.getcwd())

from app import analyze_dataset, load_example

class MockFile:
    def __init__(self, path):
        self.name = path

print("Generating example dataset...")
example_path = load_example()
print(f"Example dataset created at: {example_path}")

print("Running pipeline...")
mock_file = MockFile(example_path)

try:
    results = analyze_dataset(mock_file)
    
    # Unpack results to verify types
    overview_md, overview_df, insights, chart, anomalies_md, anomalies_df, questions = results
    
    print("Pipeline finished successfully.")
    print(f"Overview MD Length: {len(overview_md)}")
    print(f"Overview DF Shape: {overview_df.shape if hasattr(overview_df, 'shape') else 'None'}")
    print(f"Insights: {insights[:50]}...")
    print(f"Chart Object: {type(chart)}")
    print(f"Anomalies MD Length: {len(anomalies_md)}")
    print(f"Anomalies DF Shape: {anomalies_df.shape if hasattr(anomalies_df, 'shape') else 'None'}")
    print(f"Questions: {questions[:50]}...")
    
except Exception as e:
    print(f"Pipeline Failed: {e}")
    import traceback
    traceback.print_exc()

# Cleanup
if os.path.exists(example_path):
    os.remove(example_path)