0716-END0516文件放SED模型（sentence bert elmo ...）

END0516/Code/main.py

+import pandas as pd
+
+import DocSimElmoPlus0516
+import DotProSim
+import PatSimBert0516
+import handler
+
+
+def calculate_similarity(doctors):
+    # 统计医生名称的出现次数
+    name_counts = {}
+    for doctor in doctors:
+        name = doctor['医生名称']
+        if name in name_counts:
+            name_counts[name] += 1
+        else:
+            name_counts[name] = 1
+
+    # 选出大于2次的医生名称
+    selected_names = [name for name, count in name_counts.items() if count > 1]
+
+    # 计算医生对应的相似度
+    similarity_scores = {}
+    for doctor in doctors:
+        name = doctor['医生名称']
+        score = doctor['相似度得分']
+        if name in selected_names:
+            if doctor['医生集'] == 'A':
+                score *= 0.6
+            elif doctor['医生集'] == 'B':
+                score *= 0.3
+            elif doctor['医生集'] == 'C':
+                score *= 0.1
+            if name in similarity_scores:
+                similarity_scores[name] += score
+            else:
+                similarity_scores[name] = score
+
+    # 按相似度降序排序
+    sorted_results = sorted(similarity_scores.items(), key=lambda x: x[1], reverse=True)
+
+    # 仅保留前十个医生
+    return sorted_results[:10]
+    # return sorted_results
+
+
+def calculate_precision(candidates, test_data):
+    total_tests = len(test_data)
+    matched_tests = 0
+
+    for i in range(total_tests):
+        test = test_data[i]
+        for doctor in test:
+            for candidate in candidates[i]:
+                if doctor == candidate[0]:
+                    matched_tests += 1
+                    break
+
+    precision = matched_tests / total_tests if total_tests > 0 else 0
+    return precision
+
+def calculate_average_precision(candidate_set, test_set):
+    total_precision = 0.0
+    relevant_count = 0
+
+    for i in range(len(test_set)):
+        query = test_set[i]
+        candidates = candidate_set[i]
+        position = 0
+
+        for j in range(len(candidates)):
+            position += 1
+            if query in candidates[j]:
+                precision = 1.0 / position
+                total_precision += precision
+                relevant_count += 1
+                break
+
+    if relevant_count > 0:
+        return total_precision / relevant_count
+    else:
+        return 0.0
+
+
+def calculate_coverage(candidate_sets):
+    total_coverage = 0.0
+    candidate_count = 0
+
+    for candidates in candidate_sets:
+        distinct_doctors = set(candidate['医生名称'] for candidate in candidates)
+        coverage = len(distinct_doctors) / 229
+        total_coverage += coverage
+        candidate_count += 1
+
+    if candidate_count > 0:
+        return total_coverage / candidate_count
+    else:
+        return 0.0
+
+
+def main():
+    # 测试集
+    # queries = [
+    #     "不拉不尿，吃啥吐啥，喝啥也吐。",
+    #     "晚餐不消化，腹胀还放屁"
+    # ]
+    # 读取Excel文件
+    df = pd.read_excel('../data/导医测试数据.xlsx', sheet_name='Sheet1')
+
+    # 提取"ask"列数据作为查询列表
+    queries = df['ask'].tolist()
+
+    results_s = []  # 存储所有医生推荐结果的数组
+    results1_s = []  # 存储所有医生推荐前结果的数组
+
+    for query in queries:
+        '''
+        相似问题
+        '''
+        print(f"咨询问题：{query}")
+        # output_values 前50个相似咨询
+        output_values = PatSimBert0516.process_data(query)
+
+        # 存储不同的sentence文本的集合
+        unique_sentences = set()
+        # 遍历输出值列表并进行后续操作
+        for output_struct in output_values:
+            # 排除与查询值相同的数据
+            if output_struct.sentence == query:
+                continue
+            # 将不同的sentence文本添加到集合中
+            unique_sentences.add(output_struct.sentence)
+            # 检查是否已经找到了五种不同的sentence文本
+            if len(unique_sentences) == 5:
+                break
+
+        # 存储与unique_sentences中的sentence相同的数据
+        # matching_data 前5种相似咨询*
+        matching_data = []
+        # 遍历输出值列表并进行后续操作
+        for output_struct in output_values:
+            # 检查当前output_struct的sentence是否与unique_sentences中的值相同
+            if output_struct.sentence in unique_sentences:
+                # 将匹配的数据添加到matching_data列表中
+                matching_data.append(output_struct)
+
+        results = []  # 存储某一个医生推荐结果的数组
+
+        print("========================医生集A=============================")
+        for dataA in matching_data:
+            print(f"医生集A: name: {dataA.name}, Score: {dataA.score:.4f}")
+            result = {
+                '医生集': 'A',
+                '医生名称': dataA.name,
+                '相似度得分': dataA.score
+            }
+            results.append(result)
+
+        # 找出已采纳的idx
+        min_indices = handler.find_minimum_idx(matching_data)
+        print(f"已采纳的回答idx: {min_indices}")
+
+        '''
+        相似回答 
+        '''
+        target_indices = [x - 1 for x in min_indices]
+        # 日期
+        output_path = '0516'
+        cosine_similarity = DocSimElmoPlus0516.calculate_cosine_similarity(target_indices, output_path)
+
+        # 输出
+        results.append(cosine_similarity)
+
+        '''
+        相似医生 
+        '''
+        doctor_idxs = []
+        for target_indice in min_indices:
+            doctor_idx = handler.find_doctor_id_by_idx(target_indice)
+            doctor_idxs.append(doctor_idx)
+        similar_doctors = DotProSim.find_top_similar_doctors(doctor_idxs)
+        # 打印结果
+        print("================3333333==============")
+        for doctor in similar_doctors:
+            idx = doctor['idx']
+            # print(f"医生 {idx} 的相似医生:")
+            for similar_idx, similarity in doctor['similarities']:
+                name_by_idx = handler.find_doctor_name_by_idx(similar_idx)
+                name_doctor = name_by_idx[0]
+                # print(f"医生集C: name: {name_by_idx}, Score: {similarity:.4f}")
+                result = {
+                    '医生集': 'C',
+                    '医生名称': name_doctor,
+                    '相似度得分': similarity
+                }
+                results.append(result)
+            print()
+
+        # results_1,未处理候选医生集
+        def flatten_list(lst):
+            flattened = []
+            for item in lst:
+                if isinstance(item, list):
+                    flattened.extend(flatten_list(item))
+                else:
+                    flattened.append(item)
+            return flattened
+
+        results_1 = flatten_list(results)
+        results1_s.append(results_1)
+
+        print("----------自动化0624----------")
+        # 输出结果数组
+        for result in results_1:
+            print(f"医生集: {result['医生集']}, 医生名称: {result['医生名称']}, 相似度得分: {result['相似度得分']}")
+
+        '''
+        1.处理候选医生集
+            数组中相同的医生数量>2进入计算
+            A 0.6,B 0.3,C 0.1 = 候选集医生，排名（医生，相似度）
+        2. 计算指标
+            2.1 精准度
+                判断测试数据的的医生是否在候选医生集中，在1不在0，得出测试集的精准度
+            2.2 平均精准度
+                实际有的医生，每一个医生的位置1/位置，平均精度相加*（1/n）
+            2.3 覆盖率
+                ABC集合中的医生涉及到的医生数目m，m/229
+        '''
+        # results_2，输出获选医生结果
+        results_2 = calculate_similarity(results_1)
+        for result in results_2:
+            name = result[0]
+            similarity = result[1]
+            print(f"医生名称: {name}, 相似度: {similarity}")
+
+        print("-----end0625------")
+        results_s.append(results_2)
+        print("-----end0625------")
+
+    with open('results_s.txt', 'w', encoding='utf-8') as file:
+        for result in results_s:
+            result_str = ' '.join(str(item) for item in result)
+            file.write(result_str + '\n')
+
+    # 测试集
+    excel_file = '../data/导医测试数据.xlsx'
+    # sheet_name = 'Sheet1'
+    sheet_name = 'Sheet1'
+    df = pd.read_excel(excel_file, sheet_name=sheet_name)
+    test_data = df['doctor'].tolist()
+    questions = df['ask'].tolist()
+    test_data1 = [[doctor] for doctor in test_data]
+
+    # 精准度
+    precision = calculate_precision(results_s, test_data1)
+    print(f"测试集的准确率: {precision:.2%}")
+
+    # 平均精准度
+    average_precision = calculate_average_precision(results_s, test_data)
+    print(f"平均精准度: {average_precision:.2%}")
+
+    # 覆盖率
+    coverage = calculate_coverage(results1_s)
+    print("医生覆盖率: {:.2%}".format(coverage))
+
+
+if __name__ == "__main__":
+    main()