python - 支持向量机中无法使用奇怪的错误 “ValueError: ' x'来为numpy.random.RandomState实例播种？

Question

贝娄，当我在应用程序中使用这段代码时，该代码抛出一个奇怪的错误，如下所示。此错误是由于SVC分类器(https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html)的“random_state”参数引起的。

from sklearn.svm import SVC
import pandas as pd
from sklearn.metrics import *
from sklearn.model_selection import train_test_split
def Fit_Model(TrainData, Algo):

    print Algo


    df = pd.read_csv(TrainData, sep='\t')
    clm_list = df.columns.tolist()
    X_train = df[clm_list[0:len(clm_list)-1]].values
    y_train = df[clm_list[len(clm_list)-1]].values
    X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, random_state=0)
    prob = Algo.fit(X_train, y_train).predict_proba(X_test)
    predicted = Algo.fit(X_train, y_train).predict(X_test)


def SVM_classification(TrainFile, probability=None, randomRtate=None ):


    pera = {"C":1.0, 
    "kernel":'rbf', 
    "degree":3, 
    "gamma":'scale', 
    "coef0":0.0, 
    "shrinking":True,
    "probability":probability, 
    "tol":0.001, 
    "cache_size":200, 
    "class_weight":None, 
    "verbose":False, 
    "max_iter":-1, 
    "decision_function_shape":'ovr',
    "random_state":randomRtate,

    }

    model = SVC(**pera )


    Fit_Model(TrainData=TrainFile,  Algo=model)



import argparse

parser = argparse.ArgumentParser()

parser.add_argument("-f", "--file_name",
                    required=True,
                    default=None,
                    help="Path to target CSV file")

parser.add_argument("-p", "--proba",
                    required=None,
                    default=False,
                    help="n_folds for Cross Validation")

parser.add_argument("-r", "--Rand",
                    required=None,
                    default=False,
                    help="n_folds for Cross Validation")


args = parser.parse_args()

SVM_classification( args.file_name, args.proba, args.Rand )

当我尝试运行脚本时:

$ python Stack.py -f Resampled.tsv -p True -r 9

错误:

SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape='ovr', degree=3, gamma='scale', kernel='rbf',
  max_iter=-1, probability='True', random_state='9', shrinking=True,
  tol=0.001, verbose=False)
Traceback (most recent call last):
  File "Stack.py", line 68, in <module>
    SVM_classification( args.file_name, args.proba, args.Rand )
  File "Stack.py", line 42, in SVM_classification
    Fit_Model(TrainData=TrainFile,  Algo=model)
  File "Stack.py", line 15, in Fit_Model
    prob = Algo.fit(X_train, y_train).predict_proba(X_test)
  File "/home/joshij/anaconda3/envs/Jay/lib/python2.7/site-packages/sklearn/svm/base.py", line 140, in fit
    rnd = check_random_state(self.random_state)
  File "/home/joshij/anaconda3/envs/Jay/lib/python2.7/site-packages/sklearn/utils/validation.py", line 818, in check_random_state
    ' instance' % seed)
ValueError: '9' cannot be used to seed a numpy.random.RandomState instance

但是，奇怪的是我正在传递一个整数，并且一次又一次地显示相同的错误，为了测试代码，我直接传递了“int(8)”，但错误仍然相同。

示例数据“test.tsv”:

col1    col2    col3    col4    class_label
3   4   5   3   0
2   3   3   4   0
2   3   3   5   0
2   3   3   4   0
2   3   2   4   0
2   3   3   3   1
1   2   3   2   1
1   5   6   9   1
1   2   2   2   1
1   2   2   2   1

请帮忙。

更新:

当我改变

"random_state":randomRtate,

如

"random_state":int(randomRtate),

现在不同的错误。

SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape='ovr', degree=3, gamma='scale', kernel='rbf',
  max_iter=-1, probability='True', random_state=9, shrinking=True,
  tol=0.001, verbose=False)
Traceback (most recent call last):
  File "Stack.py", line 69, in <module>
    SVM_classification( args.file_name, args.proba, args.Rand )
  File "Stack.py", line 43, in SVM_classification
    Fit_Model(TrainData=TrainFile,  Algo=model)
  File "Stack.py", line 15, in Fit_Model
    prob = Algo.fit(X_train, y_train).predict_proba(X_test)
  File "/home/joshij/anaconda3/envs/Jay/lib/python2.7/site-packages/sklearn/svm/base.py", line 212, in fit
    fit(X, y, sample_weight, solver_type, kernel, random_seed=seed)
  File "/home/joshij/anaconda3/envs/Jay/lib/python2.7/site-packages/sklearn/svm/base.py", line 271, in _dense_fit
    max_iter=self.max_iter, random_seed=random_seed)
  File "sklearn/svm/libsvm.pyx", line 64, in sklearn.svm.libsvm.fit
TypeError: an integer is required 

Answer 1

请检查所有参数类型。您已将class_weight设置为None，这可能会覆盖所有1的默认大小写。您还已将probability设置为字符串，其中需要 bool(boolean) 值。如果基础实现将bool强制转换为int，则可能会收到int类型错误。