使用Python自动处理Excel数据缺失值的完整指南

import pandas as pd

# 读取 Excel 文件
df = pd.read_excel("mx-toys.xlsx")

# 分离数值型和非数值型列
numeric_cols = df.select_dtypes(include=['number']).columns
categorical_cols = df.select_dtypes(exclude=['number']).columns

from sklearn.impute import SimpleImputer

# 创建数值型填充器（均值策略）
numeric_imputer = SimpleImputer(strategy='mean')

# 填充数值列并转换为 DataFrame
df_numeric = pd.DataFrame(
    numeric_imputer.fit_transform(df[numeric_cols]),
    columns=numeric_cols
)

# 创建类别型填充器（众数策略）
categorical_imputer = SimpleImputer(strategy='most_frequent')

# 填充类别列并转换为 DataFrame
df_categorical = pd.DataFrame(
    categorical_imputer.fit_transform(df[categorical_cols]),
    columns=categorical_cols
)

# 合并数值和类别数据
df_cleaned = pd.concat([df_numeric, df_categorical], axis=1)

# 保存为新的 Excel 文件
df_cleaned.to_excel("cleaned_mx-toys.xlsx", index=False)

df = df.dropna(thresh=len(df)*0.5, axis=1)

import missingno as msno
msno.matrix(df).show()

df_categorical.fillna("Unknown", inplace=True)

import pandas as pd
from sklearn.impute import SimpleImputer

def clean_excel_file(file_path, output_path):
    """
    自动处理 Excel 文件中的缺失值：
    1. 数值型列填充均值
    2. 类别型列填充众数
    3. 保存清洗后的数据
    """
    # 读取数据
    df = pd.read_excel(file_path)
    
    # 分离数值和类别列
    numeric_cols = df.select_dtypes(include=['number']).columns
    categorical_cols = df.select_dtypes(exclude=['number']).columns
    
    # 处理数值列
    numeric_imputer = SimpleImputer(strategy='mean')
    df_numeric = pd.DataFrame(
        numeric_imputer.fit_transform(df[numeric_cols]),
        columns=numeric_cols
    )
    
    # 处理类别列
    categorical_imputer = SimpleImputer(strategy='most_frequent')
    df_categorical = pd.DataFrame(
        categorical_imputer.fit_transform(df[categorical_cols]),
        columns=categorical_cols
    )
    
    # 合并数据并保存
    df_cleaned = pd.concat([df_numeric, df_categorical], axis=1)
    df_cleaned.to_excel(output_path, index=False)
    print(f"数据已清洗并保存至 {output_path}")

# 使用示例
clean_excel_file("mx-toys.xlsx", "cleaned_mx-toys.xlsx")