user_embedding = Embedding(n_users,
n_latent_factors,
embeddings_regularizer=regularizers.l2(0.00001),
name='user_embedding')(user_input)
"""- 벡터화(Flatten)"""
# Item latent vector
movie_vec = Flatten()(movie_embedding)
# User latent vector
user_vec = Flatten()(user_embedding)
"""- 모델링(Modeling)"""
r_hat = dot([movie_vec, user_vec], axes=-1)
model = Model([user_input, movie_input], r_hat)
model.compile(optimizer='adam',
loss='mean_squared_error',
metrics=['accuracy'])
"""- 모델 훈련(Train Model)"""
# Commented out IPython magic to ensure Python compatibility.
hist = model.fit([train_df.userId, train_df.movieId],
train_df.rating,
validation_split=0.1,
batch_size=128,
epochs=50,
verbose=1)
print(hist.history.keys())
print('train loss: ', hist.history['loss'][-1])
print('train acc: ', hist.history['accuracy'][-1])
print('val acc: ', hist.history['val_loss'][-1])
print('val acc: ', hist.history['val_accuracy'][-1])
from sklearn.linear_model import SGDClassifier
clf = SGDClassifier(loss="hinge", penalty="l2", max_iter=50)
clf.fit(X_train, y_train)
clf.score(X_test, y_test)
# In[ ]:
from keras.models import Sequential
from keras import layers
input_dim = X_train.shape[1] # Number of features
model = Sequential()
model.add(layers.Dense(10, input_dim=input_dim, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.summary()
history = model.fit(X_train,
y_train,
epochs=100,
verbose=False,
validation_data=(X_test, y_test),
batch_size=10)
loss, accuracy = model.evaluate(X_train, y_train, verbose=False)
print("Training Accuracy: {:.4f}".format(accuracy))
loss, accuracy = model.evaluate(X_test, y_test, verbose=False)
print("Testing Accuracy: {:.4f}".format(accuracy))
# In[ ]:
model = tf.keras.models.Sequential([
tf.keras.layers.Input(shape=(5)),
tf.keras.layers.Dense(12800, activation="relu"),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(1600, activation="relu"),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(80, activation="relu"),
tf.keras.layers.Dense(4)
])
model.compile(optimizer="adam",
loss="mse",
metrics=['mae', 'mse'])
model.fit(x_train, y_train, epochs=50)
mse, mae, mse = model.evaluate(x_test, y_test, verbose=2)
print('\nTest mean absolute error:', mae)
model.add(BatchNormalization(axis=-1))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
#
model.add(Flatten())
#
## Fully connected layer
model.add(Dense(512))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(6))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
model.fit(X_train,label_train, steps_per_epoch=1,
validation_data=(x_val,y_val), validation_steps=1, epochs=5, verbose=2)
model.predict_generator(test_batch,verbose=2)
train_batch.filenames
