gistfile1.txt

import tensorflow as tf
import numpy as np
import keras
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
from keras import backend as K
from keras.utils import to_categorical
# https://datascience.stackexchange.com/questions/45165/how-to-get-accuracy-f1-precision-and-recall-for-a-keras-model
def recall_m(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
    recall = true_positives / (possible_positives + K.epsilon())
    return recall

def precision_m(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())
    return precision

def f1_m(y_true, y_pred):
    precision = precision_m(y_true, y_pred)
    recall = recall_m(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall+K.epsilon()))


def create_model():
    model = tf.keras.models.Sequential([
    keras.layers.Dense(600, activation='relu', input_shape = (512,)),
    keras.layers.Dropout(0.2),
    keras.layers.Dense(300, activation='relu'),
    keras.layers.Dropout(0.2),
    keras.layers.Dense(2, activation='softmax')
    ])

    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=[f1_m,precision_m, recall_m])
    return model


def get_data_from_csv():
    my_data = np.genfromtxt('spam.csv', delimiter=',')
    X = my_data[:, :512]
    X = X.astype('float32')
    Y = my_data[:, -1].astype('int')
    Y = to_categorical(Y)
    print(type(X), X.dtype, type(Y), Y.dtype)
    print(X.shape, Y.shape)
    return train_test_split(X, Y, test_size=0.25)
model = create_model()
X_train, X_test, y_train, y_test = get_data_from_csv()
model.fit(X_train, y_train, epochs=20, batch_size=100)
np.save('X_train.npy',X_train,allow_pickle=False)
np.save('X_test.npy',X_test,allow_pickle=False)
np.save('y_train.npy',y_train,allow_pickle=False)
np.save('y_test.npy',y_test,allow_pickle=False)


_,f1_score, precision, recall  = model.evaluate(X_test, y_test)
print('Accuracy: %.2f' % (f1_score * 100))
model.save('test-spam.hdf5')