import json
import os
import json
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from tqdm import tqdm

# 读取评估结果文件
def load_evaluation_results(file_path):
    with open(file_path, 'r') as f:
        data = json.load(f)
    return data

# 计算每种打分的平均值
def calculate_average_scores(results):
    jaccard_scores = []
    cosine_scores = []
    deepseek_scores = []

    for result in results:
        jaccard_scores.append(result['jaccard_score'])
        cosine_scores.append(result['cosine_score'])
        deepseek_scores.append(result['deepseek_score'])

    avg_jaccard_score = sum(jaccard_scores) / len(jaccard_scores)
    avg_cosine_score = sum(cosine_scores) / len(cosine_scores)
    avg_deepseek_score = sum(deepseek_scores) / len(deepseek_scores)

    return {
        'avg_jaccard_score': avg_jaccard_score,
        'avg_cosine_score': avg_cosine_score,
        'avg_deepseek_score': avg_deepseek_score
    }

# 保存平均打分结果
def save_average_scores(avg_scores, output_path):
    with open(output_path, 'w') as f:
        json.dump(avg_scores, f, indent=4)

if __name__ == "__main__":
    file_path = 'data/iu_xray/iu_xray/evaluation_results.json'
    output_path = 'data/iu_xray/iu_xray/average_scores.json'

    evaluation_results = load_evaluation_results(file_path)
    avg_scores = calculate_average_scores(evaluation_results)
    print(avg_scores)
    # save_average_scores(avg_scores, output_path)
    # print(f"Average scores saved to {output_path}")