当我计算一个数据帧以给出另一个数据帧的结果时，我得到 NaN 值。我该如何解决这个问题？

Question

我为我的 DataFrame 对象创建了一个字典。我创建了一个函数来根据 DataFrame 中每周工作的小时数计算工作天数和加班时间。然后，我根据我定义的变量计算每周工作时间，并根据这些答案创建一个新的数据框架。然后我将两个 DataFrame 合并在一起，但结果是错误的，因为相应地合并数据，它通过添加到列表中来合并数据。我该如何解决这个问题？我需要结果 DataFrame 与彼此相邻的数据 DataFrame 相对应。例如，员工 ID 1 每周在远程站点工作 29 小时，工作天数和加班天数不对应。我该如何解决这一切？

import pandas as pd 

data = {
    'Employee_ID': [1, 2, 3, 4, 5], 
    'Employment_Type': ['Remote', 'In-Office', 'Remote', 'Remote', 'Remote'], 
    'Hours_Worked_Per_Week': [29.0, 45.0, 34.0, 25.0, 50.0]
    }

df = pd.DataFrame(data)

def calculate_days_and_overtime(df):
    results = [] 

    for index, row in df.iterrows():
        for index, row in df.iterrows():
            total_hours = row['Hours_Worked_Per_Week']
            regular_hours_per_day = 8 
            days_per_week = 5
            total_regular_hours = days_per_week * regular_hours_per_day
            overtime = max(0, total_hours - total_regular_hours)

            regular_days = min(days_per_week, total_hours // regular_hours_per_day)
            total_hours -= regular_days * regular_hours_per_day

            overtime_days = overtime // regular_hours_per_day
            remaining_overtime_hours = overtime % regular_hours_per_day

            total_days_worked = regular_days + overtime_days + (1 if remaining_overtime_hours else 0)
            
            results.append({
                'Employee_ID'               : row['Employee_ID'],
                'Regular Days'              : regular_days, 
                'Overtime Days'             : overtime_days, 
                'Remaining Overtime Hours'  : remaining_overtime_hours, 
                'Total Days Worked'         : total_days_worked, 
                'Work Location'             : row['Employment_Type']
            })

        return pd.DataFrame(results)
    
results_df = calculate_days_and_overtime(df)
merged_df = pd.concat([df, results_df], ignore_index=True)
merged_df

Answer 1

import pandas as pd

data = {
    'Employee_ID': [1, 2, 3, 4, 5],
    'Employment_Type': ['Remote', 'In-Office', 'Remote', 'Remote', 'Remote'],
    'Hours_Worked_Per_Week': [29.0, 45.0, 34.0, 25.0, 50.0]
}

pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)

df = pd.DataFrame(data)


def calculate_days_and_overtime(df):
    results = []

    for index, row in df.iterrows():

        total_hours = row['Hours_Worked_Per_Week']
        regular_hours_per_day = 8
        days_per_week = 5
        total_regular_hours = days_per_week * regular_hours_per_day
        overtime = max(0, total_hours - total_regular_hours)

        regular_days = min(days_per_week, total_hours // regular_hours_per_day)
        total_hours -= regular_days * regular_hours_per_day

        overtime_days = overtime // regular_hours_per_day
        remaining_overtime_hours = overtime % regular_hours_per_day

        total_days_worked = regular_days + overtime_days + (1 if remaining_overtime_hours else 0)

        results.append({
            'Employee_ID': row['Employee_ID'],
            'Regular Days': regular_days,
            'Overtime Days': overtime_days,
            'Remaining Overtime Hours': remaining_overtime_hours,
            'Total Days Worked': total_days_worked,
            'Work Location': row['Employment_Type']
        })

    return pd.DataFrame(results)


print("=== df ===")
print(df)
results_df = calculate_days_and_overtime(df)
print("=== results_df ===")
print(results_df)
merged_df = pd.merge(df, results_df, on='Employee_ID')
print("=== merged_df ===")
print(merged_df)