Python_DataFrame-的apply方法的应用示例_pandas

DataFrame

拆分-应用-合并 split-apply-combine 
  apply()   方法是针对某些行或列进行操作的，
  applymap()方法是针对所有元素进行操作的

DataFrame 对象，apply 函数的语法如下：
    DataFrame.apply(func, axis=0, raw=False, result_type=None, args=(), **kwds)
Series 对象，apply 函数的语法如下：
     Series.apply(func, convert_dtype=True, args=(), **kwds)

    args：要传递给函数的额外参数。
    *kwds：要传递给函数的额外关键字参数
	
自定义函数
      定义：第一个参数是 DataFrame的行或者列，第二个参数是可以
      使用：这个函数不带任何括号地传递给apply()方法  其他参数 args=(2,)  
	  
split-apply-combine”（拆分-应用-合并）很好地描述了分组运算的整个过程

代码示例

import os.path
import pandas as pd


def check_effect_detail(data, check_type=1):
    effect_type_list = []
    effect_fields_type_words = ['A', 'B',]
    effect_reason_type_words = ['C', 'D',]
    if check_type == 1:
        effect_key_words = effect_fields_type_words
    else:
        effect_key_words = effect_reason_type_words
    for effect_type in effect_key_words:
        if effect_type in str(data):
            effect_type_list.append(effect_type)
    return effect_type_list


def combine_effect_info(data):
    info = data.iloc[0] + data.iloc[1] + data.iloc[2]
    set_data = set(info)
    out = ' '.join(set_data)
    return out


if __name__ == "__main__":
    input_dir = r"C:\Desktop"
    input_file_nm = r"effect_info.xlsx"
    out_file_nm   = r"effect_judge.xlsx"
    input_file_path = os.path.join(input_dir, input_file_nm)
    out_file_path   = os.path.join(input_dir, out_file_nm)
    # 读取Excel文件
    df = pd.read_excel(input_file_path)
    # 显示数据框内容
    # print(df["班级编号"],df["班级内容"],df["功课内容"],df["功课结论"])
    # Series.apply
    df['班级内容_field'] = df["班级内容"].apply(check_effect_detail, args=(1,))
    df['功课内容_field'] = df["功课内容"].apply(check_effect_detail, args=(1,))
    df['结论内容_field'] = df["功课结论"].apply(check_effect_detail, args=(1,))
    # dataFrame.apply()
    df['field'] = df[['班级内容_field', '功课内容_field', '结论内容_field']].apply(combine_effect_info, axis=1)
    # Series.apply
    df['班级内容_reason'] = df["班级内容"].apply(check_effect_detail, args=(2,))
    df['功课内容_reason'] = df["功课内容"].apply(check_effect_detail, args=(2,))
    df['结论内容_reason'] = df["功课结论"].apply(check_effect_detail, args=(2,))
    # dataFrame.apply()
    df['reason'] = df[['班级内容_reason', '功课内容_reason', '结论内容_reason']].apply(combine_effect_info, axis=1)
    data_out_df = df[["班级编号", "班级内容", "功课内容", "功课结论", "field", "reason"]]
    data_out_df.to_excel(out_file_path, index=False)

参考

数据预处理的示例