def train():
global model
data_reset = request.get_json()
X = [data_reset['user_history'], data_reset['item_history']]
y = data_reset['rating_history']
nb_users, nb_items = data_reset['nb_users'], data_reset['nb_items']
model = EmbeddingModel(nb_users, nb_items, embedding_size=30)
model.fit(X, y, verbose=True)
return jsonify({'info': 'successful'})
def main():
obj_etl = ETLDataPipeline("data/train.csv", "data/test.csv")
train, test = obj_etl.read_data()
train = obj_etl.drop_cols([
'id', 'bin_0', 'bin_1', 'bin_2', 'bin_3', 'bin_4', 'nom_0', 'nom_1',
'nom_2', 'nom_3', 'nom_4', 'ord_0', 'ord_1', 'ord_2', 'ord_3', 'ord_4',
'ord_5', 'day', 'month'
])
train = obj_etl.convert_dtypes(
['nom_5', 'nom_6', 'nom_7', 'nom_8', 'nom_9'])
train = obj_etl.encoder(['nom_5', 'nom_6', 'nom_7', 'nom_8', 'nom_9'])
target = obj_etl.get_target('target')
X_train, X_valid, y_train, y_valid = obj_etl.get_train_test(train, target)
val1 = np.reshape(X_train['nom_5'].values, (-1, 1))
val2 = np.reshape(X_train['nom_6'].values, (-1, 1))
val3 = np.reshape(X_train['nom_7'].values, (-1, 1))
val4 = np.reshape(X_train['nom_8'].values, (-1, 1))
val5 = np.reshape(X_train['nom_9'].values, (-1, 1))
val6 = np.reshape(y_train.values, (-1, 1))
val11 = np.reshape(X_valid['nom_5'].values, (-1, 1))
val22 = np.reshape(X_valid['nom_6'].values, (-1, 1))
val33 = np.reshape(X_valid['nom_7'].values, (-1, 1))
val44 = np.reshape(X_valid['nom_8'].values, (-1, 1))
val55 = np.reshape(X_valid['nom_9'].values, (-1, 1))
val66 = np.reshape(y_valid.values, (-1, 1))
tf.random.set_seed(0)
# 100 is number of epochs, 32 is batch size
s = 100 * len(X_train) // 32
learning_rate = tf.keras.optimizers.schedules.ExponentialDecay(
0.01, s, 0.1)
opt = tf.keras.optimizers.Adam(learning_rate)
model = EmbeddingModel(
hidden_units=3,
output_units=1,
embeddings_initializer=tf.random.normal,
kernel_initializer=tf.keras.initializers.he_uniform(seed=0),
dropout_rate=0.4,
activation="sigmoid",
trainable=True)
model.compile(loss=tf.keras.losses.binary_crossentropy,
metrics=['accuracy'],
optimizer=opt)
baseline_history = model.fit(
(val1, val2, val3, val4, val5),
val6,
epochs=10,
batch_size=32,
validation_data=((val11, val22, val33, val44, val55), val66),
class_weight={
0: 0.5,
1: 0.5
})
def main():
# hyper parameter setting
emb_dim = 50
epochs = 2
model_path = 'model.h5'
negative_samples = 1
num_words = 10000
window_size = 1
# corpus
text = load_data(filepath = '../chap04/data/ja.text8')
# vocablary
vocab = build_vocablary(text, num_words)
# create dataset
x, y = create_dataset(text, vocab, num_words, window_size, negative_samples)
# construction of model
model = EmbeddingModel(num_words, emb_dim)
model = model.build()
model.compile(optimizer = 'adam', loss = 'binary_crossentropy')
# callback
callbacks = [
EarlyStopping(patience=1),
ModelCheckpoint(model_path, save_best_only=True)
]
# model
model.fit(x=x,y=y,
batch_size=128,
epochs=epochs,
validation_split=0.2,
callbacks=callbacks)
# prediction
model = load_model(model_path)
api = InferenceAPI(model, vocab)
pprint(api.most_similar(word='日本'))