Making predictions using Keras. I keep getting error message - keras

Question

Sorry if the query is primitive.
I have some code trying to classify integers if they are prime numbers or not. I have trained model using Keras. I am trying make predictions using:
predict( x, batch_size=None, verbose=0, steps=None)
I keep getting the following error message:
----> predict(x=5000003, batch_size=None, verbose=0, steps=None)
NameError: name 'predict' is not defined
When I used the the following command :"model.predict(x=5000003, batch_size=None, verbose=0, steps=None)" I got this error message "AttributeError: 'KerasClassifier' object has no attribute 'model'"
Code:
import numpy
from numpy import array
import pandas
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import StratifiedKFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import GridSearchCV
seed = 7
numpy.random.seed(seed)
def isPrime(number):
if number == 1:
return 0
elif number == 2:
return 1
elif number % 2 == 0:
return 0
for d in range(3, int(number**(0.5)+1), 2):
if number % d == 0:
return 0
else:
return 1
p=[]
N=[]
for i in range (1,10000):
p=[i,isPrime(i)]
N=N+[p]
a=array (N)
X=a[:10000,0]
Y=a[:10000,1]
def create_model(optimizer='rmsprop', init='glorot_uniform'):
# create model
model = Sequential()
model.add(Dense(2, input_dim=1, kernel_initializer=init, activation='selu'))
model.add(Dense(1, kernel_initializer=init, activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])
return model
# create model
model = KerasClassifier(build_fn=create_model, epochs=1000, batch_size=100, init='glorot_uniform', verbose=0)
kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=seed)
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
predict(x=5000003, batch_size=None, verbose=0, steps=None)

Answer 1

predict is a function of the model object, so you would use it as:
model = KerasClassifier(build_fn=create_model, epochs=1000, batch_size=100, init='glorot_uniform', verbose=0)
kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=seed)
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
# Call on model
model.predict(x=5000003, batch_size=None, verbose=0, steps=None)
Here is the source code to investigate what it does behind the scenes.