from numpy import loadtxt
import numpy as np
from scikeras.wrappers import KerasClassifier
from keras.models import Sequential
from keras.layers import Dense
from sklearn.metrics import accuracy_score
from sklearn.utils import shuffle
from sklearn.pipeline import make_pipeline

def model_nn():

    model = Sequential()
    model.add(Dense(12, input_shape=(8,), activation='relu'))
    model.add(Dense(8, activation='relu'))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['binary_crossentropy'])
    return model

# load the dataset
dataset = loadtxt('pima-indians-diabetes.csv', delimiter=',')
modelscikeras = KerasClassifier(model_nn, epochs=30, batch_size=16, verbose=False)

n_split = 10
X, y = dataset[:, 0:8],  dataset[:, 8].astype(int)
num_runs = 30
all_scores = []
kf = KFold(n_splits=n_split, shuffle=True)
for train_index, eval_index in kf.split(X, y):
    x_test, x_train = X[eval_index, :], X[train_index, :]  # shuffle
    y_test, y_train = y[eval_index], y[train_index]
    scores = []
    score = 0
    for nrun in range(num_runs):
        modelscikeras.fit(x_, y_)
        y_pred = modelscikeras.predict(x_test)
        score += np.mean(accuracy_score(y_test, y_pred))
    score /= num_runs
    all_scores.append(score)
print(np.mean(all_scores))

from numpy import loadtxt
import numpy as np
from scikeras.wrappers import KerasClassifier
from keras.models import Sequential
from keras.layers import Dense
from sklearn.metrics import accuracy_score
from sklearn.utils import shuffle
from sklearn.pipeline import make_pipeline

def model_nn():

    model = Sequential()
    model.add(Dense(12, input_shape=(8,), activation='relu'))
    model.add(Dense(8, activation='relu'))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['binary_crossentropy'])
    return model

# load the dataset
dataset = loadtxt('pima-indians-diabetes.csv', delimiter=',')
model_nn = model_nn()

n_split = 10
X, y = dataset[:, 0:8],  dataset[:, 8].astype(int)
num_runs = 30
all_scores = []
kf = KFold(n_splits=n_split, shuffle=True)
for train_index, eval_index in kf.split(X, y):
    x_test, x_train = X[eval_index, :], X[train_index, :]  # shuffle
    y_test, y_train = y[eval_index], y[train_index]
    scores = []
    score = 0
    for nrun in range(num_runs):
        x_, y_ = shuffle(x_train, y_train)
        model_nn.fit(x_, y_, epochs=30, batch_size=16, verbose=False)
        y_pred = (model_nn.predict(x_test) > 0.5).astype(int)
        score += np.mean(accuracy_score(y_test, y_pred))
    score /= num_runs
    all_scores.append(score)
print(np.mean(all_scores))