遍历字典

Question

我有一本字典，我试图在其中循环以在 pandas 数据帧上运行一个函数。该功能允许用户手动选择 GLM 中唯一变量的级别以设置为参考/统一值。该功能在手动运行时起作用。使用字典时出现broadcast 错误。

下面是一些示例代码：

import pandas as pd
import numpy as np

#function below

def rebase1(df, variable1, unity_value):
    """
    rebase the factors according to where the modeler wants the unity to be

    """


    if ('factor_rebased' not in df.columns): df['factor_rebased'] = 0


    base_factor = df[(df['variable'] == variable1) & (df['level'] == unity_value)]['factor'].values


    filters = df['variable'].eq(variable1)
    if filters.any():
        df.loc[filters, 'factor_rebased'] = df.loc[filters, 'factor']/base_factor


#Sample data below
df3 = {'variable': ['intercept', 'CLded_model','CLded_model','CLded_model','CLded_model','CLded_model','CLded_model','CLded_model'
                   ,'married_age','married_age','married_age', 'class_cc', 'class_cc', 'class_cc', 'class_cc', 'class_v_age'
                  ,'class_v_age','class_v_age', 'class_v_age'],
      'level': [None,0,100,200,250,500,750,1000, 60, 61, 62, 100, 1200, 1500, 100
                ,10, 20, 15, 10],
      'value': [None, 460955.7793,955735.0532,586308.4028,12216916.67,48401773.87,1477842.472,14587994.92,10493740.36,36388470.44
                ,31805316.37, 123.4, 4546.50, 439854.23, 2134.4, 2304.5, 2032.30, 159.80, 22],
       'coefficient': [-2.36E-14, 0.00174356,  0.00174356,  0.00174356,  0.00174356,  0.00174356 ,0.00174356 , 0.00174356
                       ,-1.004648e-02, -1.004648e-02,-1.071730e-02,-1.812330e-04,-1.812330e-04,8.727980e-04,1.402564e-03
                      ,-1.681685e-01, -8.442040e-02, -1.812330e-04, -1.465950e-01],
      'factor': [ None, 1.        , 1.1904793 , 1.41724097, 1.54633869,
       2.39116334, 3.69754838, 5.71766211, 0.54728324, 0.5418125 ,
       0.51454483, 0.98203994, 0.80454402, 3.70319885, 1.15056877,
       0.1860602 , 0.18481351, 0.9972852 , 0.23085857]}




results = pd.DataFrame(df3)
results['factor'] = np.exp(results['level']*results['coefficient'])
results

#dictionary to loop through

unity_value = {'CLded_model':500, 'married_age':61, 'class_cc':1200, 'class_v_age':10}

#trying to run the loop

for key, values in unity_value.items():
    rebase1(results, key, values)

以下是错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-487-0be11e7c9811> in <module>
      2 
      3 for key, values in unity_value.items():
----> 4     rebase1(results, key, values)

<ipython-input-486-4c3fb8398702> in rebase1(df, variable1, unity_value)
     19     filters = df['variable'].eq(variable1)
     20     if filters.any():
---> 21         df.loc[filters, 'factor_rebased'] = df.loc[filters, 'factor']/base_factor
     22 
     23     # why return? You already update df['factor_rebased']

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\ops.py in wrapper(left, right)
   1067             rvalues = rvalues.values
   1068 
-> 1069         result = safe_na_op(lvalues, rvalues)
   1070         return construct_result(left, result,
   1071                                 index=left.index, name=res_name, dtype=None)

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\ops.py in safe_na_op(lvalues, rvalues)
   1031         try:
   1032             with np.errstate(all='ignore'):
-> 1033                 return na_op(lvalues, rvalues)
   1034         except Exception:
   1035             if is_object_dtype(lvalues):

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\ops.py in na_op(x, y)
   1010 
   1011         try:
-> 1012             result = expressions.evaluate(op, str_rep, x, y, **eval_kwargs)
   1013         except TypeError:
   1014             if isinstance(y, (np.ndarray, ABCSeries, pd.Index)):

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\computation\expressions.py in evaluate(op, op_str, a, b, use_numexpr, **eval_kwargs)
    203     use_numexpr = use_numexpr and _bool_arith_check(op_str, a, b)
    204     if use_numexpr:
--> 205         return _evaluate(op, op_str, a, b, **eval_kwargs)
    206     return _evaluate_standard(op, op_str, a, b)
    207 

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\computation\expressions.py in _evaluate_numexpr(op, op_str, a, b, truediv, reversed, **eval_kwargs)
    118 
    119     if result is None:
--> 120         result = _evaluate_standard(op, op_str, a, b)
    121 
    122     return result

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\computation\expressions.py in _evaluate_standard(op, op_str, a, b, **eval_kwargs)
     63         _store_test_result(False)
     64     with np.errstate(all='ignore'):
---> 65         return op(a, b)
     66 
     67 

ValueError: operands could not be broadcast together with shapes (4,) (2,)

Answer 1

这是因为您的配对：('class_v_age', 10) 在数据框中出现了两次，并且：

base_factor = df[(df['variable'] == variable1) & (df['level'] == unity_value)]['factor'].values

为您提供一个 numpy 数组，该数组不能在后一个除法中传递。您需要决定如何处理这种情况，例如，选择第一个值：

base_factor = df[(df['variable'] == variable1) & 
                 (df['level'] == unity_value)]['factor'].values[0]

再一次，这也很危险，因为

df[(df['variable'] == variable1) & 
   (df['level'] == unity_value)]['factor']

可能会返回一个空序列，并且该函数将抛出异常。但是，如果您保证 unity_value 会出现在您的数据框中，那么应该没问题。