Ошибка с удемом Глубокое изучение кода ANN

Question

* Я посещаю углубленный курс обучения по Удеми. Я написал код точно так же, как сказал инструктор. но возникает проблема после classifier.fit(X_train, y_train, batch_size = 10,epochs = 100) Ошибка выглядит следующим образом:

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values

# Encoding categorical data


from sklearn.preprocessing import OneHotEncoder, LabelEncoder

from sklearn.compose import ColumnTransformer

label_encoder_x_1 = LabelEncoder()
X[: , 2] = label_encoder_x_1.fit_transform(X[:,2])
transformer = ColumnTransformer(
    transformers=[
        ("OneHot",        # Just a name
         OneHotEncoder(), # The transformer class
         [1]              # The column(s) to be applied on.
         )
    ],
    remainder='passthrough' # donot apply anything to the remaining columns
)
X = transformer.fit_transform(X.tolist())
X = X.astype('float64')
X = X[:, 1:]

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#importing keras 
import keras
from keras.models import Sequential
from keras.layers import Dense
# Fitting classifier to the Training set
# Create your classifier here
classifier = Sequential()
classifier.add(Dense(output_dim = 6, init = 'uniform', activation = 'relu', input_dim = 11))
classifier.add(Dense(output_dim = 6, init = 'uniform', activation = 'relu'))
classifier.add(Dense(output_dim = 1, init = 'uniform', activation = 'sigmoid'))

classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

classifier.fit(X_train, y_train, batch_size = 10, epochs = 100) 
# Predicting the Test set results
y_pred = classifier.predict(X_test)

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

Файл "C: \ Anaconda3 \ envs \ py37 \ lib \ site-packages \ sklearn \ metrics_classification.py ", строка 268, в confusion_matrix y_type, y_true, y_pred = _check_targets (y_true, y_pred)

Файл" C: \ Anaconda3 \ envs \ py37 \ lib \ site-packages \ sklearn \ metrics_class .py ", строка 90, в _check_targets" и {1} target ".format (type_true, type_pred))

ValueError: метрики классификации не могут обрабатывать сочетание двоичных и непрерывных целей

Как это решить *

Answer 1

Проблема, кажется, со строкой, y_pred = classifier.predict(X_test). Согласно документации predict_classes используется для получения прогнозов класса, https://www.tensorflow.org/api_docs/python/tf/keras/Sequential#predict_classes. Predict возвращает непрерывные значения, которые не являются метками классов. Я внес небольшие изменения в ваш код,

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values

#print(X)
#print(y)



# Encoding categorical data


from sklearn.preprocessing import OneHotEncoder, LabelEncoder

from sklearn.compose import ColumnTransformer

label_encoder_x_1 = LabelEncoder()
X[: , 2] = label_encoder_x_1.fit_transform(X[:,2])
transformer = ColumnTransformer(
    transformers=[
        ("OneHot",        # Just a name
         OneHotEncoder(), # The transformer class
         [1]              # The column(s) to be applied on.
         )
    ],
    remainder='passthrough' # donot apply anything to the remaining columns
)
X = transformer.fit_transform(X.tolist())
X = X.astype('float64')
X = X[:, 1:]

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

#print(sum(y_train))
#print(sum(y_test))

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#importing keras 
import keras
from keras.models import Sequential
from keras.layers import Dense
# Fitting classifier to the Training set
# Create your classifier here
classifier = Sequential()
classifier.add(Dense(output_dim = 6, init = 'uniform', activation = 'relu', input_dim = 11))
classifier.add(Dense(output_dim = 6, init = 'uniform', activation = 'relu'))
classifier.add(Dense(output_dim = 1, init = 'uniform', activation = 'sigmoid'))

classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

classifier.fit(X_train, y_train, batch_size = 10, epochs = 10) 
# Predicting the Test set results
y_pred = classifier.predict_classes(X_test)
#print(classifier.predict(X_test))
#print(y_pred)


# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
#cm = confusion_matrix(y_test, y_pred)

print(confusion_matrix(y_test, y_pred, labels=[0, 1]))
print(classification_report(y_test, y_pred, target_names=['0', '1']))