我有一个 MLPRegressor，它非常适合我的数据集。这是我的代码的精简版本，删除了一些不必要的东西：
from sklearn.neural_network import MLPRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler, StandardScaler, RobustScaler
from sklearn import preprocessing
import pandas as pd
import numpy as np
from sklearn import tree
from sklearn.tree import export_graphviz
from datetime import datetime
def str_to_num(arr):
le = preprocessing.LabelEncoder()
new_arr = le.fit_transform(arr)
return new_arr
def compare_values(arr1, arr2):
thediff = 0
thediffs = []
for thing1, thing2 in zip(arr1, arr2):
thediff = abs(thing1 - thing2)
thediffs.append(thediff)
return thediffs
def minmaxscale(data):
scaler = MinMaxScaler()
df_scaled = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)
return df_scaled
data = pd.read_csv('reg.csv')
label = data['TOTAL']
data = data.drop('TOTAL', axis=1)
data = minmaxscale(data)
mlp = MLPRegressor(
activation = 'tanh',
alpha = 0.005,
learning_rate = 'invscaling',
learning_rate_init = 0.01,
max_iter = 200,
momentum = 0.9,
solver = 'lbfgs',
warm_start = True
)
X_train, X_test, y_train, y_test = train_test_split(data, label, test_size = 0.2)
mlp.fit(X_train, y_train)
preds = mlp.predict(X_test)
score = compare_values(y_test, preds)
print("Score: ", np.average(score))
而且效果很好！生产：Score: 7.246851606714535
但是，我想看看这个模型中的特征重要性。我知道这并不总是神经网络的重点，但这是一个商业理由，所以这是必要的。我通过LIME Paper发现了LIME，我想使用它。由于这是回归，我尝试在此处遵循示例
所以我添加了以下几行：
categorical_features = np.argwhere(np.array([len(set(data[:,x])) for x in range(data.shape[1])]) <= 10).flatten()
explainer = lime.lime_tabular.LimeTabularExplainer(
X_train,
feature_names=X_train.columns,
class_names=['TOTAL'],
verbose=True,
categorical_features = categorical_features,
mode='regression')
但现在得到错误：
Traceback (most recent call last):
File "c:\Users\jerry\Desktop\mlp2.py", line 65, in <module>
categorical_features = np.argwhere(np.array([len(set(data[:,x])) for x in range(data.shape[1])]) <= 10).flatten()
File "c:\Users\J39304\Desktop\mlp2.py", line 65, in <listcomp>
categorical_features = np.argwhere(np.array([len(set(data[:,x])) for x in range(data.shape[1])]) <= 10).flatten()
File "C:\Python35-32\lib\site-packages\pandas\core\frame.py", line 2927, in __getitem__
indexer = self.columns.get_loc(key)
File "C:\Python35-32\lib\site-packages\pandas\core\indexes\base.py", line 2657, in get_loc
return self._engine.get_loc(key)
File "pandas\_libs\index.pyx", line 108, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 110, in pandas._libs.index.IndexEngine.get_loc
TypeError: '(slice(None, None, None), 0)' is an invalid key
为什么我会收到此错误，我该怎么办？我不明白如何正确集成 LIME。