Question

我创建了一个数据框：

import numpy as np
import pandas as pd
from sklearn.neighbors import KNeighborsRegressor    
data = pd.DataFrame(np.random.randint(0,10,(10,5)), columns=list('abcde'))
data.c[:5] = 0
data.c[5:] = 1
data.a = np.arange(5).tolist()+np.arange(5).tolist()
data=data.set_index(list('ac'))
data = data.unstack('c')

然后定义度量函数：

myfunc = lambda a, b: ((a - b)**2).sum(axis=1, level=[0]).apply(np.sqrt).sum(axis=1).values

我想要的是在列上按级别0对数据帧求和，并应用sqrt，最后求和所有列。它适用于这样的自定义代码：

b = data.iloc[-1]
myfunc(data,b)
#output:array([ 18.09035957,  12.62123278,  20.45561243,  14.29386508,   0.        ])

但在myfunc中使用KNeighborsRegressor作为指标，会引发错误。这是KNeighborsRegressor的平均类不能适合数据帧吗？任何人都可以帮助我，谢谢？

knn = KNeighborsRegressor(n_neighbors=3, metric=myfunc)
knn.fit(a, np.arange(5))
knn.predict(b)
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-23-33f10a670994> in <module>()
      1 knn = KNeighborsRegressor(n_neighbors=3, metric=myfunc)
      2 knn.fit(a, np.arange(5))
----> 3 knn.predict(b)

C:\Anaconda3\lib\site-packages\sklearn\neighbors\regression.py in predict(self, X)
    142         X = check_array(X, accept_sparse='csr')
    143 
--> 144         neigh_dist, neigh_ind = self.kneighbors(X)
    145 
    146         weights = _get_weights(neigh_dist, self.weights)

C:\Anaconda3\lib\site-packages\sklearn\neighbors\base.py in kneighbors(self, X, n_neighbors, return_distance)
    355                 dist = pairwise_distances(
    356                     X, self._fit_X, self.effective_metric_, n_jobs=n_jobs,
--> 357                     **self.effective_metric_params_)
    358 
    359             neigh_ind = argpartition(dist, n_neighbors - 1, axis=1)

C:\Anaconda3\lib\site-packages\sklearn\metrics\pairwise.py in pairwise_distances(X, Y, metric, n_jobs, **kwds)
   1238         func = partial(distance.cdist, metric=metric, **kwds)
   1239 
-> 1240     return _parallel_pairwise(X, Y, func, n_jobs, **kwds)
   1241 
   1242 

C:\Anaconda3\lib\site-packages\sklearn\metrics\pairwise.py in _parallel_pairwise(X, Y, func, n_jobs, **kwds)
   1081     if n_jobs == 1:
   1082         # Special case to avoid picklability checks in delayed
-> 1083         return func(X, Y, **kwds)
   1084 
   1085     # TODO: in some cases, backend='threading' may be appropriate

C:\Anaconda3\lib\site-packages\sklearn\metrics\pairwise.py in _pairwise_callable(X, Y, metric, **kwds)
   1119         iterator = itertools.product(range(X.shape[0]), range(Y.shape[0]))
   1120         for i, j in iterator:
-> 1121             out[i, j] = metric(X[i], Y[j], **kwds)
   1122 
   1123     return out

<ipython-input-17-7f81015a2d21> in <lambda>(a, b)
----> 1 myfunc = lambda a, b: ((a - b)**2).sum(axis=1, level=[0]).apply(np.sqrt).sum(axis=1).values

TypeError: _sum() got an unexpected keyword argument 'level'

KNeighborsRegressor适合数据帧

0 个答案: