add niurenshaixuan

niurenshaixuan/README.md

+# 使用方法
+
+修改`main.py`中的`input_file_path`和`output_file_path`
+
+输出的excel中包含`牛人`，`牛人署名顺序`和`疑似牛人`三列。其中疑似牛人的格式为 `疑似牛人名字(疑似牛人在info/new_niuren_format-merged_turing.csv中的索引)`。
+请初步判断是否为牛人。如果认为是牛人，则找李慧老师复核，由李慧老师添加到全局牛人表中。请不要修改全局牛人表。
+
+如果是脚本运行相关的问题，请联系马天云同学。
\ No newline at end of file

niurenshaixuan/main.py

+import os
+import json
+import pandas as pd
+from tqdm import tqdm
+from joblib import Parallel, delayed
+from utils import firstlast2lastfirst, name_in_niuren_list
+
+input_file_path = '测试输入3.xlsx'
+output_file_path = '测试输出3.xlsx'
+
+
+def load_niuren_pool():
+    niuren_pool = pd.read_csv("info/new_niuren_format-merged_turing.csv", encoding='utf-8-sig')
+    niuren_pool_names = niuren_pool["name"].tolist()
+    niuren_pool_names = [name.replace("\xa0", " ") for name in niuren_pool_names]  # 去除空格
+    return niuren_pool_names
+
+
+def load_true_niuren():
+    # 读取 "全局牛人" 工作簿
+    true_niuren = pd.read_excel("info/新表-论文被引用统计-陈老师-截止2025年X月XX日.xlsx", sheet_name="全局牛人")
+
+    true_niuren["别名列表"] = None
+    true_niuren["别名列表"] = true_niuren["别名列表（各种奇奇怪怪的名字格式，比如first name和second name的顺序，以;分隔）"].apply(
+        lambda x: [firstlast2lastfirst(i.strip()) for i in x.split(";") if i!=""] if isinstance(x, str) else []
+    )
+
+    true_niuren_names = []
+    true_niuren_papers = []
+
+    # 构建牛人姓名列表
+    for _, row in true_niuren.iterrows():
+        if row["别名列表"]:
+            true_niuren_names.append([firstlast2lastfirst(row["姓名"])] + row["别名列表"])
+        else:
+            true_niuren_names.append(firstlast2lastfirst(row["姓名"]))
+
+    # 构建牛人论文列表
+    for true_niuren_idx, _ in enumerate(true_niuren_names):
+        paper_file_path = os.path.join("info/niuren_papers", f"{true_niuren_idx+1}.xlsx")
+        if os.path.exists(paper_file_path):
+            papers_df = pd.read_excel(paper_file_path, usecols=[0])
+            papers_list = papers_df.iloc[:, 0].dropna().tolist()
+            papers_list = [paper.lower() for paper in papers_list]
+            true_niuren_papers.append(papers_list)
+        else:
+            true_niuren_papers.append([])
+    return true_niuren_names, true_niuren_papers
+
+
+
+def load_fake_niuren():
+    # 读取 "全局非牛人" 工作簿
+    fake_niuren = pd.read_excel("info/新表-论文被引用统计-陈老师-截止2025年X月XX日.xlsx", sheet_name="全局非牛人")
+
+    fake_niuren_names = []
+    fake_niuren_papers = []
+
+    # 构建非牛人姓名列表
+    for _, row in fake_niuren.iterrows():
+        fake_niuren_names.append(firstlast2lastfirst(row["姓名"]))
+
+    # 构建非牛人论文列表
+    for fake_niuren_idx, _ in enumerate(fake_niuren_names):
+        paper_file_path = os.path.join("info/feiniuren_papers", f"{fake_niuren_idx+1}.xlsx")
+        if os.path.exists(paper_file_path):
+            papers_df = pd.read_excel(paper_file_path, usecols=[0])
+            papers_list = papers_df.iloc[:, 0].dropna().tolist()
+            papers_list = [paper.lower() for paper in papers_list]
+            fake_niuren_papers.append(papers_list)
+        else:
+            fake_niuren_papers.append([])
+    return fake_niuren_names, fake_niuren_papers
+
+
+def check_niuren(authors, title):
+    niuren = []
+    order = []
+    suspected_niuren = []
+
+    niuren_pool_names = load_niuren_pool()
+    true_niuren_names, true_niuren_papers = load_true_niuren()
+    fake_niuren_names, fake_niuren_papers = load_fake_niuren()
+
+    for author_idx, author in enumerate(authors):
+        if author == "":
+            continue
+
+        # 作者姓名能否在牛人池中找到
+        name_index = name_in_niuren_list(firstlast2lastfirst(author), niuren_pool_names)
+        if name_index == -1:
+            continue
+
+        # 作者姓名能否在全局牛人中找到
+        true_name_index = name_in_niuren_list(firstlast2lastfirst(author), true_niuren_names)
+        if true_name_index != -1:
+            if title.strip().lower() in true_niuren_papers[true_name_index]:
+                niuren.append(author)
+                order.append(author_idx + 1)
+                continue
+
+        # 作者姓名能否在全局非牛人中找到
+        fake_name_index = name_in_niuren_list(firstlast2lastfirst(author), fake_niuren_names)
+        if fake_name_index != -1:
+            if title.strip().lower() in fake_niuren_papers[fake_name_index]:
+                continue
+        suspected_niuren.append([author, name_index+1])
+
+    niuren_str = ";".join(niuren)
+    order_str = ";".join([str(i) for i in order])
+    suspected_niuren_str = ";".join([f"{name}({index})" for name, index in suspected_niuren])
+    return niuren_str, order_str, suspected_niuren_str
+
+
+def process_row(index, row):
+    authors = row.get('引文作者', '')
+    title = row.get('引文名称', '')
+    if not isinstance(authors, str):
+        return index, "", "", ""
+    authors = [i.strip() for i in authors.split(";") if i!=""]
+    niuren_true, niuren_true_order, suspected_niuren = check_niuren(authors, title)
+    return index, niuren_true, niuren_true_order, suspected_niuren
+
+
+if __name__ == "__main__":
+    # 读取原始 Excel 文件的前两行
+    original_header = pd.read_excel(input_file_path, nrows=2, header=None)
+
+    # 读取数据并跳过前两行
+    input_df = pd.read_excel(input_file_path, skiprows=2)
+
+    # 添加新列
+    input_df['牛人'] = None
+    input_df['牛人署名顺序'] = None
+    input_df['疑似牛人'] = None
+
+
+    results = Parallel(n_jobs=-1)(delayed(process_row)(index, row) for index, row in tqdm(input_df.iterrows()))
+    for index, niuren_true, niuren_true_order, suspected_niuren in results:
+        input_df.at[index, '牛人'] = niuren_true
+        input_df.at[index, '牛人署名顺序'] = niuren_true_order
+        input_df.at[index, '疑似牛人'] = suspected_niuren
+
+    # for index, row in tqdm(input_df.iterrows()):
+    #     index, niuren_true, niuren_true_order, suspected_niuren = process_row(index, row)
+    #     input_df.at[index, '牛人'] = niuren_true
+    #     input_df.at[index, '牛人署名顺序'] = niuren_true_order
+    #     input_df.at[index, '疑似牛人'] = suspected_niuren
+
+
+    max_cols = max(original_header.shape[1], input_df.shape[1])
+
+    # 定义补齐函数
+    def pad_df(df, max_cols):
+        df = df.copy()
+        for i in range(df.shape[1], max_cols):
+            df[i] = ""
+        df = df.iloc[:, :max_cols]  # 限制在max_cols列
+        df.columns = range(max_cols)  # 用数字做列名
+        return df
+
+    # 补齐所有DF
+    original_header_padded = pad_df(original_header, max_cols)
+    input_header = pd.DataFrame([input_df.columns.tolist()])
+    input_header_padded = pad_df(input_header, max_cols)
+    input_data_padded = pad_df(input_df, max_cols)
+
+    # 拼接
+    output_df = pd.concat([original_header_padded, input_header_padded, input_data_padded], ignore_index=True)
+
+    # 保存
+    output_df.to_excel(output_file_path, index=False, header=False)
+    print(f"处理后的数据已保存到 {output_file_path}")
\ No newline at end of file

niurenshaixuan/utils.py

+def firstlast2lastfirst(name):
+    if "," in name:
+        return name
+    # 名人列表中存在一些名字是First Name Last Name的格式，将其转换为Last Name, First Name格式
+    # 例如：'John Doe' -> 'Doe, John'，'M. Jane Smith' -> 'Smith, Jane M.'
+    special_str = [".", "Ms.", "Mr.", "Mrs.", "Dr.", "Prof.", "PhD", "MD", "Jr.", "Sr.", "The", "Honorable"]
+    name_split = name.split(" ")
+    name_split = [item.strip() for item in name_split if item.strip() != ""]
+    name_split = [item for item in name_split if item not in special_str]
+    
+    # Grigory Isaakovich Barenblatt --> Barenblatt, Alexa, Marc Isaakovich
+    
+    if len(name_split) == 2:
+        first_name = name_split[0]
+        last_name = name_split[1]
+        new_name = f"{last_name}, {first_name}"
+    elif len(name_split) == 3:
+        if name_split[0].startswith("(") and name_split[0].endswith(")"):
+            # (Alexander) Philip Dawid
+            first_name = f"{name_split[1]} {name_split[0]}"
+            last_name = f"{name_split[2]}"
+        elif name_split[1].startswith("(") and name_split[1].endswith(")"):
+            # Xinyan (Tracy) Cui --> Cui, Xinyan (Tracy)
+            first_name = f"{name_split[0]} {name_split[1]}"
+            last_name = f"{name_split[2]}"
+        elif name_split[2].startswith("(") and name_split[2].endswith(")"):
+            # Ye Fred (Ying)实际是姓Ye，名Ying，英文名Fred, 需要将其转换为"Ye, Ying Fred"
+            # Zhu Jesse (Jingxu)实际是姓Zhu，名Jingxu，英文名Jesse, 需要将其转换为"Zhu, Jingxu Jesse"
+            first_name = f"{name_split[2][1:-1]} ({name_split[1]})"
+            last_name = f"{name_split[0]}"
+        elif name_split[0].endswith("."):
+            # M. Jane Smith --> Smith, Jane M.
+            # K.W. Michael Siu --> Siu, Michael K.W.
+            first_name = f"{name_split[1]} {name_split[0]}"
+            last_name = name_split[2]
+        elif name_split[1].endswith("."):
+            # Jane M. Smith --> Smith, Jane M.
+            # Pierre J.H. Richardson --> Richardson, Pierre J.H.
+            first_name = f"{name_split[0]} {name_split[1]}"
+            last_name = name_split[2]
+        elif name_split[2].endswith("."):
+            # Wimmer-Schweingruber Robert F. --> Wimmer-Schweingruber, Robert F.
+            # Wilderer Peter A. --> Wilderer, Peter A.
+            first_name = f"{name_split[1]} {name_split[2]}"
+            last_name = f"{name_split[0]}"
+        else:
+            # William Nelson Joy --> Joy, William Nelson
+            # Michael J Carey --> Carey, Michael J
+            # len_3_list.append(" ".join(name_split))
+            first_name = f"{name_split[0]} {name_split[1]}"
+            last_name = name_split[2]
+        
+        new_name = f"{last_name}, {first_name}"
+        # print(f"{name} --> {new_name}")
+    else:
+        # lens greater than 3 这部分名字应该不会跟其他部分名字出现重复
+        last_name = name_split[-1]
+        first_name = " ".join(name_split[:-1])
+        new_name = f"{last_name}, {first_name}"
+        
+    return new_name
+
+
+def name_in_niuren_list(name, niuren_name_list):
+    """
+    判断名字是否在牛人列表中
+    :param name: 名字
+    :param niuren_name_list: 牛人列表
+    :return: 如果在牛人列表中，返回 True，否则返回 False
+    """
+    for idx, niuren_name in enumerate(niuren_name_list):
+        if isinstance(niuren_name, str):
+            if name == niuren_name:
+                return idx
+        elif isinstance(niuren_name, list):
+            if name in niuren_name:
+                return idx
+
+    for idx, niuren_name in enumerate(niuren_name_list):
+        if isinstance(niuren_name, str):
+            if niuren_name.startswith(name):
+                if niuren_name[niuren_name.find(name) + len(name)] == " ":
+                    return idx
+            if name.startswith(niuren_name):
+                if name[name.find(niuren_name) + len(niuren_name)] == " ":
+                    return idx
+        elif isinstance(niuren_name, list):
+            for niuren_name_item in niuren_name:
+                if niuren_name_item.startswith(name):
+                    if niuren_name_item[niuren_name_item.find(name) + len(name)] == " ":
+                        return idx
+                if name.startswith(niuren_name_item):
+                    if name[name.find(niuren_name_item) + len(niuren_name_item)] == " ":
+                        return idx
+    return -1
\ No newline at end of file