Python 随机森林回归器在 nan 值上出错，尽管已删除

Question

我有一个干净的数据集，nan 值为零，但我继续在回归量上遇到相同的错误。我的相框叫做 new_player_data

我试过

list(new_player_data.where(new_player_data.isna()).count() > 0)

哪个returns

[假，错误的，错误的，错误的，错误的，假]

大约两百次。我认为可能有一些浮动太大。我试过这个：

for i in new_player_data.columns[:]:
    if new_player_data[i].dtype == float:
        new_player_data[i] = round(new_player_data[i],2)

无论我得到什么：

regressor.fit(X_train, y_train)  
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-327-3a664017ddaa> in <module>
----> 1 regressor.fit(X_train, y_train)

/anaconda3/lib/python3.7/site-packages/sklearn/ensemble/forest.py in fit(self, X, y, sample_weight)
    248 
    249         # Validate or convert input data
--> 250         X = check_array(X, accept_sparse="csc", dtype=DTYPE)
    251         y = check_array(y, accept_sparse='csc', ensure_2d=False, dtype=None)
    252         if sample_weight is not None:

/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    571         if force_all_finite:
    572             _assert_all_finite(array,
--> 573                                allow_nan=force_all_finite == 'allow-nan')
    574 
    575     shape_repr = _shape_repr(array.shape)

/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py in _assert_all_finite(X, allow_nan)
     54                 not allow_nan and not np.isfinite(X).all()):
     55             type_err = 'infinity' if allow_nan else 'NaN, infinity'
---> 56             raise ValueError(msg_err.format(type_err, X.dtype))
     57 
     58 

ValueError: Input contains NaN, infinity or a value too large for dtype('float32').

关于我还可以在这里检查的内容有什么想法吗？一败涂地

Answer 1

归功于@gmds 得出的答案，原来是 inf 值，通过

找到

infs = np.where(np.isinf(new_player_data))
infs

out: (array([ 261, 1162, 1190, 1339, 1365, 1451, 1656, 1736, 1878, 1954, 2189,
    2299, 2741, 3137, 3162, 3799, 3821, 3881, 4305]),
 array([ 3, 43, 43,  3, 43, 43, 43, 43, 43, 43, 23, 43,  3, 43, 43, 43,  3,
    23, 43]))

然后我就这样换了

pd.options.mode.use_inf_as_na = True
infs = np.where(np.isinf(new_player_data))
infs
out: (array([], dtype=int64), array([], dtype=int64))

感谢 gmds 的定向帮助！

Python 随机森林回归器在 nan 值上出错，尽管已删除

Python Random Forest Regressor Erroring on nan values, despite removal

python

random-forest