output_nfs = data_normalization(nf_data.iloc[:, 1:28], 'PCA') #Normalization via StandardScaler
output_afs = data_normalization(af_data.iloc[:, 1:28], 'PCA')
output_nfs ['Fault'] = nf_data['Fault'].values
output_afs ['Fault'] = af_data['Fault'].values

output_nfs_rec_array = output_nfs.to_records (index = False)
output_afs_rec_array = output_afs.to_records (index = False)

final_data = np.concatenate ([output_nfs_rec_array, output_afs_rec_array])
np.random.shuffle(final_data)
y=final_data ['Fault'] #target
X=rf.drop_fields(final_data, ['Fault'], False).view (np.float64).reshape(len(final_data), len(final_data.dtype)-1) #Actual datapoints
y_new = [] #Combine all the faults into 3 separate categories: no faults (0), electrical (1), mechanical (2)
for i in range(len(y)):
    if y[i]==0:
        y_new.append(0)
    elif (y[i] == 188)|(y[i] ==176)|(y[i] == 315)|(y[i] == 485)|(y[i] == 286)|(y[i] ==707)|
         (y[i] == 959)|(y[i] ==958)|(y[i] ==817)|(y[i] == 187)|(y[i] == 489)|(y[i] == 632)|
         (y[i] == 102)|(y[i] ==648)|(y[i] ==687)|(y[i] == 935)|(y[i] == 332)|(y[i] == 846)|
         (y[i] == 944)|(y[i] == 254)|(y[i] == 181)|(y[i] == 317):
        y_new.append(1) #electrical
    elif (y[i]==604)|(y[i]==603)|(y[i]==958)|(y[i]==154)|(y[i]==162)|
         (y[i]==165)|(y[i]==512)|(y[i]==948)|(y[i]==151)|(y[i]==163)|(y[i]==296)|
         (y[i]==734)|(y[i]==844)|(y[i]==191)|(y[i]==560)|(y[i]==297)|(y[i]==504)|(y[i]==735):
        y_new.append(2) #mechanical
y = y_new
y=np.array(y,dtype=int)

from sklearn.model_selection import KFold
n_folds = 10
kfold = KFold(n_folds, True, 1)
scores, members = list(), list()


import keras_metrics as km
from keras.layers import Dropout
labels = ['no faults', 'electrical fault', 'mechanical fault']
def evaluate_model(X_train, y_train, X_test, y_test):
    trainy_enc=to_categorical(y_train)
    testy_enc=to_categorical(y_test)
    early_stopping_monitor = EarlyStopping(monitor='val_loss', patience=3)
    model = Sequential()
    n_cols = X_train.shape[1]
    model.add (Dense (35, activation = 'relu', input_shape = (n_cols,)))
    model.add(Dropout(0.5))
    model.add (Dense (10, activation = 'relu'))
    model.add(Dropout(0.5))
    model.add (Dense (3, activation = 'softmax'))
    model.compile (loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['acc'])
    model.fit (X_train, trainy_enc, batch_size=10, shuffle=True, epochs= 100,
               validation_data=(X_test,testy_enc), callbacks = [early_stopping_monitor], verbose = 1)
    # evaluate the model
    _, test_acc = model.evaluate(X_test, testy_enc, verbose=1)

    return model, test_acc

for train_iX, test_iX in kfold.split(X):
    X_train, y_train = X[train_iX], y[train_iX]
    X_test, y_test = X[test_iX], y[test_iX]
    #Class imbalance is too severe. No Fault prevails. Using smote to balance out electrical and mechanical faults
    from imblearn.over_sampling import SMOTE
    sm = SMOTE (random_state = 12)
    X_train,y_train = sm.fit_resample(X_train,y_train)
    X_train, y_train = utils.shuffle(X_train, y_train, random_state=42)
    X_train, X_test = feature_selection (X_train, X_test, None, 'PCA', None)
    model, test_acc = evaluate_model(X_train, y_train, X_test, y_test)
    scores.append(test_acc)
    members.append(model)

pca = PCA (0.95)
pca.fit(X_train)
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)