"""Compute correlation statistics for the paper (hop-based)."""

import json
import numpy as np
from scipy import stats

def main():
    with open(r'C:\Users\alexa\copycat\slipnet_analysis\slipnet.json', 'r') as f:
        data = json.load(f)

    # Extract data points (excluding letter nodes themselves)
    names = []
    depths = []
    hops = []
    is_unreachable = []

    for node in data['nodes']:
        name = node['name']
        depth = node['conceptualDepth']
        path_info = node.get('minPathToLetter', {})
        hop_count = path_info.get('hops')
        nearest = path_info.get('nearestLetter')

        # Skip letter nodes (hops 0)
        if hop_count is not None and hop_count > 0:
            names.append(name)
            depths.append(depth)
            hops.append(hop_count)
            is_unreachable.append(nearest is None)

    # Convert to numpy arrays
    depths = np.array(depths)
    hops = np.array(hops)

    # Compute correlation
    correlation, p_value = stats.pearsonr(depths, hops)
    spearman_corr, spearman_p = stats.spearmanr(depths, hops)

    # Linear regression
    z = np.polyfit(depths, hops, 1)

    # R-squared
    y_pred = np.polyval(z, depths)
    ss_res = np.sum((hops - y_pred) ** 2)
    ss_tot = np.sum((hops - np.mean(hops)) ** 2)
    r_squared = 1 - (ss_res / ss_tot)

    num_unreachable = sum(is_unreachable)
    print(f"Number of nodes analyzed: {len(names)}")
    print(f"Total nodes: {data['nodeCount']}")
    print(f"Letter nodes (excluded): 26")
    print(f"Unreachable nodes (hops = 2*max): {num_unreachable}")
    print()
    print(f"Pearson correlation: r = {correlation:.4f}")
    print(f"Pearson p-value: p = {p_value:.6f}")
    print(f"Spearman correlation: rho = {spearman_corr:.4f}")
    print(f"Spearman p-value: p = {spearman_p:.6f}")
    print(f"R-squared: {r_squared:.4f}")
    print(f"Linear regression: hops = {z[0]:.4f} * depth + {z[1]:.4f}")
    print()
    print(f"Depth range: {min(depths):.1f} - {max(depths):.1f}")
    print(f"Hops range: {min(hops)} - {max(hops)}")
    print(f"Mean depth: {np.mean(depths):.2f}")
    print(f"Mean hops: {np.mean(hops):.2f}")
    print(f"Std depth: {np.std(depths):.2f}")
    print(f"Std hops: {np.std(hops):.2f}")
    print()

    # Distribution of hops
    print("Distribution of hops:")
    for h in sorted(set(hops)):
        count = sum(1 for x in hops if x == h)
        nodes_at_h = [n for n, hp in zip(names, hops) if hp == h]
        print(f"  {h} hops: {count} nodes")

    print()
    print("Data points (sorted by hops, then depth):")
    print(f"{'Node':<30} {'Depth':<10} {'Hops':<10} {'Reachable':<10}")
    print("-" * 60)
    for name, depth, hop, unreachable in sorted(zip(names, depths, hops, is_unreachable), key=lambda x: (x[2], x[1])):
        status = "No" if unreachable else "Yes"
        print(f"{name:<30} {depth:<10.1f} {hop:<10} {status:<10}")

if __name__ == '__main__':
    main()