class ThresholdStratifiedKFold(object):
def __init__(self, thresholds, *args, **kwargs):
if isinstance(thresholds, Iterable):
self.thresholds = list(thresholds)
else:
self.thresholds = [thresholds]
self.stratified = StratifiedKFold(*args, **kwargs)
def get_n_splits(self, *args, **kwargs):
return self.stratified.get_n_splits(*args, **kwargs)
def split(self, X, y):
y_thresh = np.zeros(y.shape)
for thresh in self.thresholds:
y_thresh += y >= thresh
for train, test in self.stratified.split(X, y_thresh):
yield train, test
def MLKFoldCrossValid(epoch):
seed = 7
np.random.seed(seed)
dataset = np.loadtxt("pima-indians-diabetes.csv", delimiter=",")
X = dataset[:, 0:8]
Y = dataset[:, 8]
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed)
cvscores = []
for train, test in kfold.split(X, Y):
layers = [Dense(12, input_dim=8, activation='relu', kernel_initializer='uniform'),\
Dense(8,activation='relu', kernel_initializer='uniform'),\
Dense(1,activation='sigmoid', kernel_initializer='uniform')]
model = Sequential(layers)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(X[train], Y[train], epochs=epoch, batch_size=10, verbose=0)
scores = model.evaluate(X[test], Y[test], verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1] * 100))
cvscores.append(scores[1] * 100)
print("%.2f%%(+/- %.2f%%)" % (np.mean(cvscores), np.std(cvscores)))
# Get input shape
aux = pd.read_csv(data[0])
inputShape = (parameters['dataLength'], len(aux.columns))
config = None
if os.path.exists(parameters['modelConfigPath']):
with open(parameters['modelConfigPath'], 'r') as configHandler:
config = json.load(configHandler)
i = 0
# ====================== Script that start training new models
with open(parameters['resultFilePath'], 'a+'
) as cvsFileHandler: # where the results for each fold are appended
dictWriter = None
for trainIndex, testIndex in kf.split(data, classes_for_stratified):
if config is not None and config['fold'] > i:
print("Pass fold {}".format(i))
i += 1
continue
if config is not None and config['epoch'] == parameters[
'trainingEpochs']:
print("Pass fold {}-".format(i))
i += 1
continue
print("======== Fold {} ========".format(i))
# If exists a valid config to resume a training
if config is not None and config['fold'] == i and config[
'epoch'] < parameters['trainingEpochs']:
epochs = parameters['trainingEpochs'] - config['epoch']
class_label = "organism_resistence"
for result_file in results_file_paths:
print("========== {} ==========".format(result_file))
results_df = pd.read_csv(result_file)
data = pd.read_csv('csvs/' + results_df.loc[0]['fname'])
if 'Unnamed: 0' in data.columns:
data = data.drop(columns=['Unnamed: 0'])
classes = data[class_label]
data = data.drop(columns=[class_label])
data = preprocess(data)
classes = preprocess_classes(classes)
kf = StratifiedKFold(n_splits=10, shuffle=True, random_state=15)
results = []
folds = 0
for train_index, test_index in kf.split(data, classes):
print("====== Fold {} =====".format(folds))
folds_classifiers = results_df[results_df['fold'] == folds]
data_train, data_test = data.iloc[train_index], data.iloc[test_index]
mean = data_train.mean()
std = data_train.std()
data_test = normalize(data_test, mean, std)
classes_test = classes[test_index]
for index, classifier_row in folds_classifiers.iterrows():
print("====== {} =====".format(classifier_row['classifier']))
classifier_fname = 'classifiers/{}_{}_fold{}.pkl'.format(
classifier_row['fname'].split('.')[0],
classifier_row['classifier'], classifier_row['fold'])
classifier = joblib.load(open(classifier_fname, 'rb'))
try:
predicted = classifier.predict(data_test)