Python 3.x “如何修复”；PermissionError:[WinError 5]访问被拒绝；在虚拟环境和Jupyter笔记本中由n_作业引起=-1

我在一个虚拟环境中工作，该虚拟环境的设置如下

此外，我正在使用Jupyter笔记本

在我的代码中，我使用sklearn.model\u selection.cross\u val\u score（…）。参数n_jobs=“1”或“-1”似乎导致了使用“1”时没有收到错误的问题。使用“-1”时，会出现以下错误：

其他信息/更新：

2020年2月3日

如果有人遇到这个问题，这里有一个更活跃的线程。这里有人提到了一个新的可能的解决方案，但不确定 但如果它解决了这里提到的问题。它与数据的传输方式有关 已阅读，但我怀疑这是否是解决方案

小更新，我还没有重新考虑这个问题，但我最近 不同程序遇到类似的运行时错误（不确定 如果是完全相同的运行时错误。也不确定是否正确 甚至将其称为运行时错误）。我意识到我的python 不知什么原因，它是32位的。在这一点上，我升级到64位 这解决了我的问题。我还没有在我发布的旧代码上尝试这个 在这里不确定，但我还需要检查python在我的计算机上是否为32位 其他机器

---

您可以在此处查看我的答案，以了解类似的问题：

---------------------------------------------------------------------------
_RemoteTraceback                          Traceback (most recent call last)
_RemoteTraceback: 
'''
Traceback (most recent call last):
  File "c:\users\chang\ml\lib\site-packages\sklearn\externals\joblib\externals\loky\process_executor.py", line 391, in _process_worker
    call_item = call_queue.get(block=True, timeout=timeout)
  File "C:\Users\chang\AppData\Local\Programs\Python\Python37-32\lib\multiprocessing\queues.py", line 99, in get
    if not self._rlock.acquire(block, timeout):
PermissionError: [WinError 5] Access is denied
'''

The above exception was the direct cause of the following exception:

BrokenProcessPool                         Traceback (most recent call last)
<ipython-input-10-56afe11b41fd> in <module>
     11     X_poly = poly.fit_transform(X)
     12 
---> 13     score = cross_val_score(lgr_clf, X_poly, y, cv=loo, scoring='accuracy', n_jobs=-1).mean()
     14     scores.append(score)
     15 

c:\users\chang\ml\lib\site-packages\sklearn\model_selection\_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, error_score)
    400                                 fit_params=fit_params,
    401                                 pre_dispatch=pre_dispatch,
--> 402                                 error_score=error_score)
    403     return cv_results['test_score']
    404 

c:\users\chang\ml\lib\site-packages\sklearn\model_selection\_validation.py in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
    238             return_times=True, return_estimator=return_estimator,
    239             error_score=error_score)
--> 240         for train, test in cv.split(X, y, groups))
    241 
    242     zipped_scores = list(zip(*scores))

c:\users\chang\ml\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
    928 
    929             with self._backend.retrieval_context():
--> 930                 self.retrieve()
    931             # Make sure that we get a last message telling us we are done
    932             elapsed_time = time.time() - self._start_time

c:\users\chang\ml\lib\site-packages\sklearn\externals\joblib\parallel.py in retrieve(self)
    831             try:
    832                 if getattr(self._backend, 'supports_timeout', False):
--> 833                     self._output.extend(job.get(timeout=self.timeout))
    834                 else:
    835                     self._output.extend(job.get())

c:\users\chang\ml\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in wrap_future_result(future, timeout)
    519         AsyncResults.get from multiprocessing."""
    520         try:
--> 521             return future.result(timeout=timeout)
    522         except LokyTimeoutError:
    523             raise TimeoutError()

~\AppData\Local\Programs\Python\Python37-32\lib\concurrent\futures\_base.py in result(self, timeout)
    430                 raise CancelledError()
    431             elif self._state == FINISHED:
--> 432                 return self.__get_result()
    433             else:
    434                 raise TimeoutError()

~\AppData\Local\Programs\Python\Python37-32\lib\concurrent\futures\_base.py in __get_result(self)
    382     def __get_result(self):
    383         if self._exception:
--> 384             raise self._exception
    385         else:
    386             return self._result

BrokenProcessPool: A task has failed to un-serialize. Please ensure that the arguments of the function are all picklable.
------------------------------------------------------------------------------

#!/usr/bin/env python
# coding: utf-8

# In[14]:


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

import sklearn.linear_model as skl_lm
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split, LeaveOneOut, KFold, cross_val_score
from sklearn.preprocessing import PolynomialFeatures


import matplotlib as mpl
import matplotlib.pyplot as plt

from sklearn.metrics import confusion_matrix, classification_report, precision_score
from sklearn import preprocessing
from sklearn import neighbors

import statsmodels.api as sm
import statsmodels.formula.api as smf

get_ipython().run_line_magic('matplotlib', 'inline')
plt.style.use('seaborn-white')


# In[15]:


df = pd.read_csv('Default.csv', index_col = 0)
df.info()


# In[16]:


##ESTIAMATE TEST ERROR. 3 SPLITS

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn import metrics

cols = ['student', 'balance', 'income']

X=df[cols]
y=df['default']

X=X.replace("Yes",1)
X=X.replace("No",0)

y=y.replace("Yes",1)
y=y.replace("No",0)

t_prop = 0.5
poly_order = np.arange(1,4) #degrees
r_state = np.arange(3) #number of splits


Z = np.zeros((poly_order.size,r_state.size))
X1, Y1 = np.meshgrid(poly_order, r_state, indexing='ij')


for (i,j),v in np.ndenumerate(Z):

    poly = PolynomialFeatures(int(X1[i,j]))

    X_poly = poly.fit_transform(X)

    X_train, X_test, y_train, y_test = train_test_split(X_poly, y, test_size=0.3,)# random_state=42)

    y_train_default = (y_train == 1)
    y_test_default = (y_test == 1)

    lgr_clf = LogisticRegression(solver = "lbfgs")
    lgr_clf.fit(X_train, y_train_default)

    y_train_pred = lgr_clf.predict(X_train)
    y_test_pred = lgr_clf.predict(X_test)

    Z[i,j]= metrics.accuracy_score(y_test, y_test_pred)

plt.plot(X1,Z)
plt.title('{} random splits of the data set'.format(max(r_state)+1))
plt.ylabel('Accuracy Score')
plt.ylim(.94,1)
plt.xlabel('Degree of Polynomial')
plt.xlim(1,3)


# In[17]:


##LOOCV
loo = LeaveOneOut()
loo.get_n_splits(df)
scores = list()

X = X[:2500]
y = y[:2500]

for i in poly_order:
    poly = PolynomialFeatures(i)
    X_poly = poly.fit_transform(X)

    score = cross_val_score(lgr_clf, X_poly, y, cv=loo, scoring='accuracy', n_jobs = -1).mean()
    scores.append(score)

# k-fold CV
folds = 3
elements = len(df.index)

X1, Y1 = np.meshgrid(poly_order, r_state, indexing='ij')
Z3 = np.zeros((poly_order.size,r_state.size))

for (i,j),v in np.ndenumerate(Z3):
      poly = PolynomialFeatures(X1[i,j])
      X_poly = poly.fit_transform(X)
      kf_10 = KFold(n_splits=folds, random_state=Y1[i,j])
      Z3[i,j] = cross_val_score(lgr_clf, X_poly, y, cv=kf_10, scoring='accuracy').mean()
fig, (ax1, ax2) = plt.subplots(1,2, figsize=(10,4))

# Note: cross_val_score() method return negative values for the scores.
# https://github.com/scikit-learn/scikit-learn/issues/2439

# Left plot
ax1.plot(poly_order, np.array(scores), '-o')
ax1.set_title('LOOCV')

# Right plot
ax2.plot(X1,Z3,'-o')
ax2.set_title('3-fold CV')

for ax in fig.axes:
    ax.set_ylabel('Mean Squared Error')
    ax.set_xlabel('Degree of Polynomial')
    ax.set_ylim(0.9,1)
    ax.set_xlim(0.5,3.5)
    #ax.set_xticks(range(1,5,2));


# In[18]:


##ESTIAMATE TEST ERROR. 4 SPLITS

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn import metrics

cols = ['student', 'balance', 'income']

X=df[cols]
y=df['default']

X=X.replace("Yes",1)
X=X.replace("No",0)

y=y.replace("Yes",1)
y=y.replace("No",0)

t_prop = 0.5
poly_order = np.arange(1,4) #degrees
r_state = np.arange(4) #number of splits


Z = np.zeros((poly_order.size,r_state.size))
X1, Y1 = np.meshgrid(poly_order, r_state, indexing='ij')


for (i,j),v in np.ndenumerate(Z):

    poly = PolynomialFeatures(int(X1[i,j]))

    X_poly = poly.fit_transform(X)

    X_train, X_test, y_train, y_test = train_test_split(X_poly, y, test_size=0.3,)# random_state=42)

    y_train_default = (y_train == 1)
    y_test_default = (y_test == 1)

    lgr_clf = LogisticRegression(solver = "lbfgs")
    lgr_clf.fit(X_train, y_train_default)

    y_train_pred = lgr_clf.predict(X_train)
    y_test_pred = lgr_clf.predict(X_test)

    Z[i,j]= metrics.accuracy_score(y_test, y_test_pred)

plt.plot(X1,Z)
plt.title('{} random splits of the data set'.format(max(r_state)+1))
plt.ylabel('Accuracy Score')
plt.ylim(.94,1)
plt.xlabel('Degree of Polynomial')
plt.xlim(1,3)


# In[19]:



##LOOCV
loo = LeaveOneOut()
loo.get_n_splits(df)
scores = list()

X = X[:2500]
y = y[:2500]

for i in poly_order:
    poly = PolynomialFeatures(i)
    X_poly = poly.fit_transform(X)

    score = cross_val_score(lgr_clf, X_poly, y, cv=loo, scoring='accuracy', n_jobs = -1).mean()
    scores.append(score)

# k-fold CV
folds = 4
elements = len(df.index)

X1, Y1 = np.meshgrid(poly_order, r_state, indexing='ij')
Z4 = np.zeros((poly_order.size,r_state.size))

for (i,j),v in np.ndenumerate(Z4):
      poly = PolynomialFeatures(X1[i,j])
      X_poly = poly.fit_transform(X)
      kf_10 = KFold(n_splits=folds, random_state=Y1[i,j])
      Z4[i,j] = cross_val_score(lgr_clf, X_poly, y, cv=kf_10, scoring='accuracy').mean()


fig, (ax1, ax2) = plt.subplots(1,2, figsize=(10,4))

# Note: cross_val_score() method return negative values for the scores.
# https://github.com/scikit-learn/scikit-learn/issues/2439

# Left plot
ax1.plot(poly_order, np.array(scores), '-o')
ax1.set_title('LOOCV')

# Right plot
ax2.plot(X1,Z4,'-o')
ax2.set_title('4-fold CV')

for ax in fig.axes:
    ax.set_ylabel('Mean Squared Error')
    ax.set_xlabel('Degree of Polynomial')
    ax.set_ylim(0.9,1)
    ax.set_xlim(0.5,3.5)
    #ax.set_xticks(range(1,5,2));


# In[21]:


##ESTIAMATE TEST ERROR. 5 SPLITS

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn import metrics

cols = ['student', 'balance', 'income']

X=df[cols]
y=df['default']

X=X.replace("Yes",1)
X=X.replace("No",0)

y=y.replace("Yes",1)
y=y.replace("No",0)

t_prop = 0.5
poly_order = np.arange(1,4) #degrees
r_state = np.arange(5) #number of splits


Z = np.zeros((poly_order.size,r_state.size))
X1, Y1 = np.meshgrid(poly_order, r_state, indexing='ij')


for (i,j),v in np.ndenumerate(Z):

    poly = PolynomialFeatures(int(X1[i,j]))

    X_poly = poly.fit_transform(X)

    X_train, X_test, y_train, y_test = train_test_split(X_poly, y, test_size=0.3,)# random_state=42)

    y_train_default = (y_train == 1)
    y_test_default = (y_test == 1)

    lgr_clf = LogisticRegression(solver = "lbfgs")
    lgr_clf.fit(X_train, y_train_default)

    y_train_pred = lgr_clf.predict(X_train)
    y_test_pred = lgr_clf.predict(X_test)

    Z[i,j]= metrics.accuracy_score(y_test, y_test_pred)

plt.plot(X1,Z)
plt.title('{} random splits of the data set'.format(max(r_state)+1))
plt.ylabel('Accuracy Score')
plt.ylim(.94,1)
plt.xlabel('Degree of Polynomial')
plt.xlim(1,3)


# In[22]:


##LOOCV
loo = LeaveOneOut()
loo.get_n_splits(df)
scores = list()

X = X[:2500]
y = y[:2500]

for i in poly_order:
    poly = PolynomialFeatures(i)
    X_poly = poly.fit_transform(X)

    score = cross_val_score(lgr_clf, X_poly, y, cv=loo, scoring='accuracy', n_jobs = -1).mean()
    scores.append(score)

# k-fold CV
folds = 5
elements = len(df.index)

X1, Y1 = np.meshgrid(poly_order, r_state, indexing='ij')
Z5 = np.zeros((poly_order.size,r_state.size))

for (i,j),v in np.ndenumerate(Z5):
      poly = PolynomialFeatures(X1[i,j])
      X_poly = poly.fit_transform(X)
      kf_10 = KFold(n_splits=folds, random_state=Y1[i,j])
      Z5[i,j] = cross_val_score(lgr_clf, X_poly, y, cv=kf_10, scoring='accuracy').mean()


fig, (ax1, ax2) = plt.subplots(1,2, figsize=(10,4))

# Note: cross_val_score() method return negative values for the scores.
# https://github.com/scikit-learn/scikit-learn/issues/2439

# Left plot
ax1.plot(poly_order, np.array(scores), '-o')
ax1.set_title('LOOCV')

# Right plot
ax2.plot(X1,Z5,'-o')
ax2.set_title('5-fold CV')

for ax in fig.axes:
    ax.set_ylabel('Mean Squared Error')
    ax.set_xlabel('Degree of Polynomial')
    ax.set_ylim(0.9,1)
    ax.set_xlim(0.5,3.5)
    #ax.set_xticks(range(1,5,2));


# In[23]:


#Analysis

#When Comparing the LOOCV to the random split, it can be seen that the 
#LOOCV is closest to a linear model with polynomial degree one.
#This is also a true statement when compared to the K-fold CV.
#In addition the number of folds does not cause a huge deviation
#compared to LOOCV. This proves the statement in class that having
#a large or small number of folds does not necessarily make the model better


# In[ ]: