Ik heb andere berichten hierover gezien, maar iedereen van deze kan me helpen. Ik gebruik jupyter-notebook met Python 3.6.0 op een Windows x6-machine.
Ik heb een grote dataset, maar ik bewaar er slechts een deel van om mijn modellen uit te voeren:
Dit is een stukje code dat ik heb gebruikt:
df = loan_2.reindex(columns= ['term_clean','grade_clean', 'annual_inc', 'loan_amnt', 'int_rate','purpose_clean','installment','loan_status_clean'])
df.fillna(method= 'ffill').astype(int)
from sklearn.preprocessing import Imputer
from sklearn.preprocessing import StandardScaler
imp = Imputer(missing_values='NaN', strategy='median', axis=0)
array = df.values
y = df['loan_status_clean'].values
imp.fit(array)
array_imp = imp.transform(array)
y2= y.reshape(1,-1)
imp.fit(y2)
y_imp= imp.transform(y2)
X = array_imp[:,0:4]
Y = array_imp[:,4]
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = model_selection.train_test_split(X, Y, test_size=validation_size, random_state=seed)
seed = 7
scoring = 'accuracy'
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import BernoulliNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.ensemble import AdaBoostClassifier
from sklearn.neural_network import MLPClassifier
# Spot Check Algorithms
models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('BNB', BernoulliNB()))
models.append(('RF', RandomForestClassifier()))
models.append(('GBM', AdaBoostClassifier()))
models.append(('NN', MLPClassifier()))
models.append(('SVM', SVC()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
kfold = model_selection.KFold(n_splits=10, random_state=seed)
cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
results.append(cv_results)
names.append(name)
msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
print(msg)
Wanneer ik het laatste stuk code runt, komt deze fout op:
ValueError Traceback (most recent call last)
<ipython-input-262-1e6860ba615b> in <module>()
4 for name, model in models:
5 kfold = model_selection.KFold(n_splits=10, random_state=seed)
----> 6 cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
7 results.append(cv_results)
8 names.append(name)
C:\Users\dalila\Anaconda\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)
138 train, test, verbose, None,
139 fit_params)
--> 140 for train, test in cv_iter)
141 return np.array(scores)[:, 0]
142
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
756 # was dispatched. In particular this covers the edge
757 # case of Parallel used with an exhausted iterator.
--> 758 while self.dispatch_one_batch(iterator):
759 self._iterating = True
760 else:
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
606 return False
607 else:
--> 608 self._dispatch(tasks)
609 return True
610
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in _dispatch(self, batch)
569 dispatch_timestamp = time.time()
570 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571 job = self._backend.apply_async(batch, callback=cb)
572 self._jobs.append(job)
573
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in apply_async(self, func, callback)
107 def apply_async(self, func, callback=None):
108 """Schedule a func to be run"""
--> 109 result = ImmediateResult(func)
110 if callback:
111 callback(result)
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in __init__(self, batch)
324 # Don't delay the application, to avoid keeping the input
325 # arguments in memory
--> 326 self.results = batch()
327
328 def get(self):
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
236 estimator.fit(X_train, **fit_params)
237 else:
--> 238 estimator.fit(X_train, y_train, **fit_params)
239
240 except Exception as e:
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\linear_model\logistic.py in fit(self, X, y, sample_weight)
1172 X, y = check_X_y(X, y, accept_sparse='csr', dtype=np.float64,
1173 order="C")
-> 1174 check_classification_targets(y)
1175 self.classes_ = np.unique(y)
1176 n_samples, n_features = X.shape
C:\Users\dalila\Anaconda\lib\site-packages\sklearn\utils\multiclass.py in check_classification_targets(y)
170 if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
171 'multilabel-indicator', 'multilabel-sequences']:
--> 172 raise ValueError("Unknown label type: %r" % y_type)
173
174
ValueError: Unknown label type: 'continuous'
Korte aanname: Mijn gegevens zijn schoon van NAN en ontbrekende waarde in het algemeen.
Antwoord 1, Autoriteit 100%
De oplossing van uw probleem is dat u regressiemodel nodig hebt in plaats van classificatiemodel, dus:
in plaats van deze twee regels:
from sklearn.svm import SVC
..
..
models.append(('SVM', SVC()))
gebruik deze:
from sklearn.svm import SVR
..
..
models.append(('SVM', SVR()))
Antwoord 2, autoriteit 50%
Classifier verwacht in Y_train alleen gehele waarden (labels van klassen). Maar het wordt float en verhoogt deze fout.
Als je een regressie uitvoert, gebruik dan de regressors in plaats van classifiers.
Of als je een classificatie nodig hebt, check y_train. Mogelijk is dit deel van je code getransformeerd naar zwevend:
imp = Imputer(missing_values='NaN', strategy='median', axis=0)
array = df.values
imp.fit(array)
array_imp = imp.transform(array)
Y = array_imp[:,4]
probeer het te veranderen in
Y = array[:,4] # take it from not changed data
imp = Imputer(missing_values='NaN', strategy='median', axis=0)
array = df.values
imp.fit(array)
array_imp = imp.transform(array)