36 lines
973 B
Python
36 lines
973 B
Python
|
from keras.models import Sequential
|
||
|
|
from keras.layers import Dense
|
||
|
|
import numpy as np
|
||
|
|
from sklearn.metrics import f1_score
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
print('Hello')
|
||
|
|
dataset = np.loadtxt('data.csv', delimiter=',')
|
||
|
|
|
||
|
|
np.random.shuffle(dataset)
|
||
|
|
|
||
|
|
X = dataset[:,0:8]
|
||
|
|
y = dataset[:,8]
|
||
|
|
|
||
|
|
X_train = X[0:650]
|
||
|
|
y_train = y[0:650]
|
||
|
|
|
||
|
|
X_test = X[651:]
|
||
|
|
y_test = y[651:]
|
||
|
|
|
||
|
|
model = Sequential()
|
||
|
|
model.add(Dense(12, input_dim=8, activation='relu'))
|
||
|
|
model.add(Dense(8, activation='relu'))
|
||
|
|
model.add(Dense(1, activation='sigmoid'))
|
||
|
|
|
||
|
|
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
|
||
|
|
model.fit(X_train, y_train, epochs=15, batch_size=10)
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
_, accuracy = model.evaluate(X_test, y_test)
|
||
|
|
|
||
|
|
print('Accuracy: %.2f' % (accuracy*100))
|
||
|
|
predictions = (model.predict(X_test) > 0.5).astype(int)
|
||
|
|
fscore = f1_score(y_test, predictions, average='macro')
|
||
|
|
print('fscore: ', fscore)
|