Python+pypinyin实现将中文姓名拼音转换与搜索

pip install pandas pypinyin

import pandas as pd
from pypinyin import pinyin, Style

data = {
    'name': ['张三', '李四', '王小五', '赵六']
}

df = pd.DataFrame(data)

def get_full_pinyin_and_initials(name):
    """
    将中文姓名转换为：
    1. 全拼
    2. 姓全拼 + 名首字母
    """

    # 全拼（张三 -> zhangsan）
    full_pinyin = ''.join(
        pinyin(name, style=Style.NORMAL)[i][0]
        for i in range(len(name))
    )

    # 姓的全拼
    surname_pinyin = pinyin(name[0], style=Style.NORMAL)[0][0]

    # 名的首字母
    name_initials = pinyin(name[1:], style=Style.FIRST_LETTER)

    initials = surname_pinyin + ''.join(i[0] for i in name_initials)

    return full_pinyin, initials

df[['full_pinyin', 'initials']] = (
    df['name']
    .apply(get_full_pinyin_and_initials)
    .apply(pd.Series)
)

def find_name_by_pinyin(input_pinyin):
    """
    根据拼音或拼音首字母查找姓名
    """

    matched_names = df[
        df['initials'].str.contains(input_pinyin, na=False) |
        df['full_pinyin'].str.contains(input_pinyin, na=False)
    ]

    return matched_names

input_pinyin = "zhangs"
result = find_name_by_pinyin(input_pinyin)

print(result)

import pandas as pd
from pypinyin import pinyin, Style


# 假设你的 DataFrame 是这样的
data = {
    'name': ['张三', '李四', '王小五', '赵六']
}
df = pd.DataFrame(data)


# 定义获取拼音的函数
def get_full_pinyin_and_initials(name):
    # 获取全拼
    full_pinyin = ''.join(pinyin(name, style=Style.NORMAL)[i][0] for i in range(len(name)))

    # 获取姓的拼音和名的首字母
    surname_pinyin = pinyin(name[0], style=Style.NORMAL)[0][0]  # 姓的全拼
    name_initial = pinyin(name[1:], style=Style.FIRST_LETTER)  # 名的首字母
    initials = surname_pinyin + ''.join(n[0] for n in name_initial)

    return full_pinyin, initials


# 应用函数并创建新的列
df[['full_pinyin', 'initials']] = df['name'].apply(get_full_pinyin_and_initials).apply(pd.Series)


# 定义查找姓名的函数
def find_name_by_pinyin(input_pinyin):
    # 查找与输入拼音匹配的姓名
    matched_names = df[df['initials'].str.contains(input_pinyin, na=False) | 
                        df['full_pinyin'].str.contains(input_pinyin, na=False)]
    return matched_names


# 示例：查找拼音
input_pinyin = "zhangs"  # 你想要查找的拼音
result = find_name_by_pinyin(input_pinyin)


# 打印结果
print(result)