Question

我已经编写了一些代码，可以根据多种条件模拟熊猫数据框中的值。现在，我只想为df['Use Type']列中的特定值运行此代码。我目前有以下内容：

def l_sim():
    n = 100
    for i in range(n)

       df['RAND'] = np.random.uniform(0, 1, size=df.index.size)

       conditions = [df['RAND'] >= (1 - 0.8062), (df['RAND'] < (1 - 0.8062)) & (df['RAND'] >= 0.1),
                  (df['RAND'] < 0.1) & (df['RAND'] >= 0.05), (df['RAND'] < 0.05) &
                  (df['RAND'] >= 0.025), (df['RAND'] < 0.025) & (df['RAND'] >= 0.0125),
                  (df['RAND'] < 0.0125)]
       choices = ['L0', 'L1', 'L2', 'L3', 'L4', 'L5']
       df['L'] = np.select(conditions, choices)

       conditions = [df['L'] == 'L0', df['L'] == 'L1', df['L'] == 'L2', df['L'] == 'L3',
                  df['L'] == 'L4', df['L'] == 'L5']
       choices = [df['A'] * 0.02, df['A'] * 0.15, df['A'] * 0.20, df['A'] * 0.50,
               df['A'] * 1, df['A'] * 1]
       df['AL'] = np.select(conditions, choices)


 l_sim()

如何仅对具有df.loc[df['Use Type'] == 'Commercial Property']的行运行此代码？

谢谢。

Answer 1

我认为您需要以不同的方式构造代码。但通常，您可以使用df.apply和lambda函数。此模式：

df['L'] = df.apply(lambda row: l_sim(row), axis=1)

我会将您的代码分成三个函数，一个用于df['L']：

def l_logic():
    random_num = np.random.uniform(0, 1)
    conditions = [random_num >= (1 - 0.8062), (random_num < (1 - 0.8062)) & (random_num >= 0.1),
              (random_num < 0.1) & (random_num >= 0.05), (random_num < 0.05) &
              (random_num >= 0.025), (random_num < 0.025) & (random_num >= 0.0125),
              (random_num < 0.0125)]
    choices = ['L0', 'L1', 'L2', 'L3', 'L4', 'L5']
    L = np.select(conditions, choices)

    return L

一个用于df['AL']。由于您在分配之前使用过df[A]，因此将其更改为some_number。

def al_logic(row):
    some_number = 1

    conditions = [row['L'] == 'L0', row['L'] == 'L1', row['L'] == 'L2', row['L'] == 'L3', row['L'] == 'L4', row['L'] == 'L5']

    choices = [some_number * 0.02, some_number * 0.15, some_number * 0.20, some_number * 0.50, some_number * 1, some_number * 1]
    AL = np.select(conditions, choices)

    return AL

仅在row['Use Type'] =='Commercial Property'时创建值的逻辑的第三个：

def l_sim(row):
    if row['Use Type'] == 'Commercial Property':
        if 'L' in row.index:
            return al_logic(row)
        else:
            return l_logic()
    else:
        return 'NaN'

要启动它：

df['L'] = df.apply(lambda row: l_sim(row), axis=1)

df['AL'] = df.apply(lambda row: l_sim(row), axis=1)

Answer 2

假设您的数据框至少有两列“ A”和“使用类型”，例如：

df = pd.DataFrame({'Use Type':['Commercial Property']*3+['other']*2, 'A':1})

然后通过以下方式修改您的功能

def l_sim(df,use_type=None):
    #check if you want to do it ont he whole datafrmae or a specific Use type
    if use_type:
        mask = df['Use Type'] == use_type
    else:
        mask = slice(None)
    # generete the random values
    df.loc[mask,'RAND'] = np.random.uniform(0, 1, size=df[mask].index.size)
    # create conditions (same for both L and AL by the way)
    conditions = [ df['RAND'] >= (1 - 0.8062), (df['RAND'] >= 0.1), (df['RAND'] >= 0.05), 
                  (df['RAND'] >= 0.025), (df['RAND'] >= 0.0125), (df['RAND'] < 0.0125)]
    #choices for the column L and create the column
    choices_L = ['L0', 'L1', 'L2', 'L3', 'L4', 'L5']
    df.loc[mask,'L'] = np.select(conditions, choices_L)[mask]
    #choices for the column AL and create the column
    choices_A = [df['A'] * 0.02, df['A'] * 0.15, df['A'] * 0.20, df['A'] * 0.50,
                 df['A'] * 1, df['A'] * 1]
    df.loc[mask,'AL'] = np.select(conditions, choices_A)[mask]

然后，如果您这样做：

l_sim(df,'Commercial Property')
print (df)
              Use Type  A      RAND    L    AL
0  Commercial Property  1  0.036593   L3  0.50
1  Commercial Property  1  0.114773   L1  0.15
2  Commercial Property  1  0.651873   L0  0.02
3                other  1       NaN  NaN   NaN
4                other  1       NaN  NaN   NaN

和

l_sim(df)
print (df)
              Use Type  A      RAND   L    AL
0  Commercial Property  1  0.123265  L1  0.15
1  Commercial Property  1  0.906185  L0  0.02
2  Commercial Property  1  0.107588  L1  0.15
3                other  1  0.434560  L0  0.02
4                other  1  0.304901  L0  0.02

我删除了循环for，因为我看不到要点，并且像上一个问题的answer一样简化了conditions

根据列中的值运行模拟

2 个答案: