import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

hyp_rows = [{'id': 'h-155f0b0c', 'title': 'LRRK2 Volume Sensor Hijacking Drives Metabolic Dysregulation via SIRT1/PGC1α Suppression', 'type': 'mechanistic', 'disease': 'neurodegeneration', 'composite_score': 0.666, 'confidence_score': 0.42, 'evidence_for': "{'pmid': '33805527', 'claim': 'LRRK2 at the crossroad of aging and PD shows age-dependent mitochondrial dysfunction'}; {'pmid': 'NOSTRING', 'claim': 'STRING shows LRRK2 functionally connected to SIRT1-PPARGC1A axis (scor", 'evidence_against': "{'pmid': '35235774', 'claim': 'The NADPARK phase I trial of nicotinamide riboside in PD patients showed safety but limited efficacy signals, suggesting NAD+ supplementation alone is insufficient for disease modification'"}]
hyp_df = pd.DataFrame(hyp_rows)
hyp_df

if len(hyp_df):
    ranked = hyp_df.sort_values('composite_score')
    fig, ax = plt.subplots(figsize=(9, max(4, len(ranked) * 0.45)))
    ax.barh(ranked['title'], ranked['composite_score'], color='#26a69a')
    ax.set_xlabel('Composite score')
    ax.set_title('Scored hypotheses')
    ax.grid(axis='x', alpha=0.25)
    plt.tight_layout(); plt.show()

dims = ['confidence_score', 'novelty_score', 'feasibility_score', 'impact_score', 'mechanistic_plausibility_score', 'clinical_relevance_score', 'data_availability_score', 'reproducibility_score', 'druggability_score', 'safety_profile_score']
labels = ['LRRK2 Volume Sensor Hijacking Drives Metabolic D']
matrix = np.array([[0.42, 0.75, 0.6, 0.58, 0.55, 0.0, 0.7, 0.68, 0.52, 0.72]])
if matrix.size:
    fig, ax = plt.subplots(figsize=(10, max(4, len(labels) * 0.4)))
    im = ax.imshow(matrix, cmap='viridis', aspect='auto', vmin=0, vmax=1)
    ax.set_xticks(range(len(dims)))
    ax.set_xticklabels([d.replace('_score','').replace('_',' ').title() for d in dims], rotation=45, ha='right', fontsize=8)
    ax.set_yticks(range(len(labels)))
    ax.set_yticklabels(labels, fontsize=7)
    ax.set_title('Hypothesis scoring dimensions')
    plt.colorbar(im, ax=ax, shrink=0.8)
    plt.tight_layout(); plt.show()
else:
    print('No score matrix available')

lit_rows = []
if lit_rows:
    pd.DataFrame(lit_rows)
else:
    print('No PubMed literature rows returned')

debate_info = {'num_rounds': 4, 'quality_score': 0.85}
edge_data = []
print('Debate:', debate_info)
if edge_data:
    display(pd.DataFrame(edge_data))
else:
    print('No KG edges recorded for this analysis')