plotting/urls.py

import pandas as pd
import numpy as np
import ast
import os 
import sys
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
sys.path.append(ROOT_DIR)
from core.paper import Paper

df = pd.read_csv('data/urls.csv', sep="\t")
success = 0
total = 0
papers = [Paper.from_row(row) for _, row in df.iterrows()]

def normalize_url(url):
    return url.strip().lower().rstrip("/")

tp, fp, fn = 0, 0, 0
for paper in papers:
    if (paper.venue == "MICCAI"):
        continue
    
    urls_auto = [normalize_url(u) for u in paper.urls_auto]
    urls_manual = [normalize_url(u) for u in paper.urls_manual]

    auto_set = set(urls_auto)
    manual_set = set(urls_manual)

    tp += len(auto_set & manual_set)
    fp += len(auto_set - manual_set)
    fn += len(manual_set - auto_set)

precision = tp / (tp + fp) if (tp + fp) > 0 else 0
recall = tp / (tp + fn) if (tp + fn) > 0 else 0

print(f"Precision: {precision:.3f}")
print(f"Recall: {recall:.3f}")