def main():
gps_files = glob.glob('../data/prototype/**/gps_points.csv')
trip_files = glob.glob('../data/prototype/**/gps_trips.csv')
file_results = process_file(trip_file = trip_files[0], gps_file = gps_files[0])
seq_results = build_seq(input_df = file_results['df'], unique_trips = file_results['unique_trips'])
X = seq_results['x']
y = seq_results['y']
print('Bulding training data from files..')
for i in range(1, len(gps_files)):
file_results = process_file(trip_file = trip_files[i], gps_file = gps_files[i])
seq_results = build_seq(input_df = file_results['df'], unique_trips = file_results['unique_trips'])
X = np.vstack((X, seq_results['x']))
y = np.vstack((y, seq_results['y']))
x_train, x_val, y_train, y_val = train_test_split(X, y, random_state=1, train_size=0.8)
rdd = to_simple_rdd(sc, x_train, y_train)
model = build_model()
spark_model = SparkModel(model, frequency='epoch', mode='asynchronous')
spark_model.fit(rdd, epochs=5, batch_size=32, verbose=0, validation_split=0.1)
# model.fit(x_train, y_train, epochs=5, validation_data=(x_val, y_val))
y_pred = spark_model.predict(x_val)
acc = sum(np.argmax(y_pred, axis=1) == np.argmax(y_val, axis=1)) / y_pred.shape[0]
print("Validation Accuracy: {number:.{digits}f}%".format(number=(acc*100), digits=2))
def train_gate(self, datagen, weights_file):
model = self.gateModel
model.compile(loss='categorical_crossentropy',
optimizer=Adam(),
metrics=['accuracy'])
print(model.summary())
self.gateModel = SparkModel(model,
frequency='epoch',
mode='asynchronous')
score = self.gateModel.master_network.evaluate(self.x_test,
self.y_test,
verbose=2,
batch_size=50)
self.gateModel.fit(self.rdd, epochs=1, batch_size=50, verbose=1)
self.gateModel = self.gateModel.master_network
self.gateModel.save_weights(weights_file + '.hdf5')
file = '../lib/output.txt'
if os.path.exists(file):
append_write = 'a'
else:
append_write = 'w'
#score = self.gateModel.evaluate(self.x_test, self.y_test, verbose=2, batch_size=50)
print("------------------------------")
print("Score is:" + str(score[1]))
print("-------------------------------")
text_file = open(file, append_write)
text_file.write("Score: %s" % score[1])
text_file.close()
def predictMain(modelName,sc):
timeSteps= 30 # No of past values that has to be used for Training purpose
print "Going to Initialize the LSTM model"
SMARTparameters=getSMARTParameters()
print("The following are the SMART parameters:",SMARTparameters)
lstm = ls.cloudLSTM(timeSteps=timeSteps,parms=SMARTparameters) # Initializing the DiskPrediction Model(LSTM Model)
print "Initialized the Model"
lstmModel = lstm.get_LSTM_Model() # Obtaining the LSTM model for initializing SparkModel Class
trainSize= 0.2 # Fraction of input used for Training purpose
acc = 0.0 # Model accuracy
inputFilePath = os.environ.get('DATA_FILE_PATH') # Get the Input CSV filepath from environment
year=sys.argv[1] # get the year from the Command Line arguments
month=sys.argv[2] # get the month from the Command Line arguments
inputFilePath=inputFilePath+str(year)+"/"+str(year)+"-"+str(month)+"*.csv" # For E.g "/home/user/Desktop/Cloud/Test/2014/2014-11*.csv"
print("InputPath",inputFilePath)
rd.generate_DataFrame(inputFilePath,SMARTparameters)
inputCSVFilePath = os.environ.get('MODEL_CSV_FILEPATH')+str(modelName)+".csv" # For E.g "/hadoop/elephas/Output/ST4000DM000.csv"
modelFeatures = pd.read_csv(filepath_or_buffer=inputCSVFilePath,usecols=SMARTparameters)
modelLabel = pd.read_csv(filepath_or_buffer=inputCSVFilePath,usecols=['failure']) #"/hadoop/elephas/Output/ST4000DM000.csv"
# Removing Not A Number values from the Input Dataframe
modelFeatures = modelFeatures.fillna(0)
modelLabel = modelLabel.fillna(0)
# Obtaining 3D training and testing vectors
(feature_train, label_train), (feature_test, label_test) = lstm.train_test_split(modelFeatures,modelLabel,trainSize,timeSteps)
# Condition to check whether the failure cases exists in the data
if len(feature_train)==0:
print("DiskModel has no failure eleements. Training of the model cannot proceed!!")
return
# Initializing the Adam Optimizer for Elephas
adam = elephas_optimizers.Adam()
print "Adam Optimizer initialized"
#Converting Dataframe to Spark RDD
rddataset = to_simple_rdd(sc, feature_train, label_train)
print "Training data converted into Resilient Distributed Dataset"
#Initializing the SparkModel with Optimizer,Master-Worker Mode and Number of Workers
spark_model = SparkModel(sc,lstmModel,optimizer=adam ,frequency='epoch', mode='asynchronous', num_workers=2)
print "Spark Model Initialized"
#Initial training run of the model
spark_model.train(rddataset, nb_epoch=10, batch_size=200, verbose=1, validation_split=0)
# Saving the model
score = spark_model.evaluate(feature_test, label_test,show_accuracy=True)
while(score <= 0.5):
# Training the Input Data set
spark_model.train(rddataset, nb_epoch=10, batch_size=200, verbose=1, validation_split=0)
print "LSTM model training done !!"
score = spark_model.evaluate(feature_test, label_test,show_accuracy=True)
print "Saving weights!!"
outFilePath=os.environ.get('GATOR_SQUAD_HOME')
outFilePath=outFilePath+"Weights/"+str(year)+"/"+str(month)+"/"+str(modelName)+"_my_model_weights.h5"
spark_model.save_weights(outFilePath)
print "LSTM model testing commencing !!"
predicted1=spark_model.predict_classes(feature_test)
df_confusion = pd.crosstab(label_test.flatten(), predicted1.flatten(), rownames=['Actual'], colnames=['Predicted'], margins=True)
print df_confusion
def test_sequential_serialization(spark_context, classification_model):
classification_model.compile(optimizer="sgd",
loss="categorical_crossentropy",
metrics=["acc"])
spark_model = SparkModel(classification_model,
frequency='epoch',
mode='synchronous')
spark_model.save("elephas_sequential.h5")
def run_train(master_name, filename, outname):
import pyspark
conf = pyspark.SparkConf().setAppName("CRF").setMaster(master_name)
sc = pyspark.SparkContext(conf=conf)
tfile = sc.textFile(filename)
dataset = textFileToDataset(tfile)
indexer = Indexer()
indexer.prepareIndexer(dataset, min_count=0)
print('[Prepare Trainloader] {} samples'.format(dataset.count()))
trainset = indexer.convertToElephasFormat(dataset)
embedding_size = 128
print('[Char account] {}'.format(len(indexer.chars)))
crf_model = CRF(5, True, name='CRF')
cnn_model = Sequential([
Embedding(len(indexer.chars)+1, embedding_size),
Conv1D(128, 3, activation='relu', padding='same',\
kernel_constraint=maxnorm(1.0), name='conv1'),
Conv1D(128, 3, activation='relu', padding='same',\
kernel_constraint=maxnorm(1.0), name='conv2'),
Dense(5),
Lambda(lambda x:x)
#crf_model
])
'''
embed=Embedding(len(Indexer._chars)+1, embedding_size)(inph)
cnn=Conv1D(128, 3, activation='relu', padding='same')(embed)
cnn=Conv1D(128, 3, activation='relu', padding='same')(cnn)
tag_score=Dense(5)(cnn)
'''
crf_model.trans = cnn_model.layers[-1].add_weight(name='transM', \
shape=(crf_model.num_labels, crf_model.num_labels),\
initializer=glorot_normal())
cnn_model.compile(loss=crf_model.loss,
optimizer='adam',
metrics=[crf_model.accuracy])
cnn_model.summary()
# momentum = 0., decay=0. nesterov=False
optimizerE = elephas.optimizers.SGD(lr=0.0001,
momentum=0.9,
decay=0.7,
nesterov=True)
spark_model = SparkModel(sc, cnn_model, optimizer=optimizerE,\
frequency='epoch', mode='asynchronous', num_workers=2,\
) #custom_objects={'CRF': crf_model})
spark_model.train(trainset,
nb_epoch=2,
batch_size=200,
validation_split=0.3,
verbose=1)
model = spark_model.master_network
model.save(outname)
print('Train Finish')
def test_sync_mode(spark_context):
# Define basic parameters
batch_size = 64
nb_classes = 10
epochs = 10
# Load data
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype("float32")
x_test = x_test.astype("float32")
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# Convert class vectors to binary class matrices
y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Dense(128, input_dim=784))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))
sgd = SGD(lr=0.1)
model.compile(sgd, 'categorical_crossentropy', ['acc'])
# Build RDD from numpy features and labels
rdd = to_simple_rdd(spark_context, x_train, y_train)
# Initialize SparkModel from Keras model and Spark context
spark_model = SparkModel(model, mode='synchronous')
# Train Spark model
spark_model.fit(rdd,
epochs=epochs,
batch_size=batch_size,
verbose=2,
validation_split=0.1)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.master_network.evaluate(x_test, y_test, verbose=2)
assert score[1] >= 0.70
def set_model(self):
"""
Set the HAN model according to the given hyperparameters
"""
if self.hyperparameters['l2_regulizer'] is None:
kernel_regularizer = None
else:
kernel_regularizer = regularizers.l2(
self.hyperparameters['l2_regulizer'])
if self.hyperparameters['dropout_regulizer'] is None:
dropout_regularizer = 1
else:
dropout_regularizer = self.hyperparameters['dropout_regulizer']
word_input = Input(shape=(self.max_senten_len, ), dtype='float32')
word_sequences = self.get_embedding_layer()(word_input)
word_lstm = Bidirectional(self.hyperparameters['rnn'](
self.hyperparameters['rnn_units'],
return_sequences=True,
kernel_regularizer=kernel_regularizer))(word_sequences)
word_dense = TimeDistributed(
Dense(self.hyperparameters['dense_units'],
kernel_regularizer=kernel_regularizer))(word_lstm)
word_att = AttentionWithContext()(word_dense)
wordEncoder = Model(word_input, word_att)
sent_input = Input(shape=(self.max_senten_num, self.max_senten_len),
dtype='float32')
sent_encoder = TimeDistributed(wordEncoder)(sent_input)
sent_lstm = Bidirectional(self.hyperparameters['rnn'](
self.hyperparameters['rnn_units'],
return_sequences=True,
kernel_regularizer=kernel_regularizer))(sent_encoder)
sent_dense = TimeDistributed(
Dense(self.hyperparameters['dense_units'],
kernel_regularizer=kernel_regularizer))(sent_lstm)
sent_att = Dropout(dropout_regularizer)(
AttentionWithContext()(sent_dense))
preds = Dense(len(self.classes))(sent_att)
self.model = Model(sent_input, preds)
self.model.compile(loss=self.hyperparameters['loss'],
optimizer=self.hyperparameters['optimizer'],
metrics=self.hyperparameters['metrics'])
self.spark_model = SparkModel(self.model,
frequency='epoch',
mode='asynchronous')
def test_sequential_serialization():
# Create Spark context
pytest.mark.usefixtures("spark_context")
seq_model = Sequential()
seq_model.add(Dense(128, input_dim=784))
seq_model.add(Activation('relu'))
seq_model.add(Dropout(0.2))
seq_model.add(Dense(128))
seq_model.add(Activation('relu'))
seq_model.add(Dropout(0.2))
seq_model.add(Dense(10))
seq_model.add(Activation('softmax'))
seq_model.compile(
optimizer="sgd", loss="categorical_crossentropy", metrics=["acc"])
spark_model = SparkModel(seq_model, frequency='epoch', mode='synchronous')
spark_model.save("elephas_sequential.h5")
def test_model_serialization():
# This returns a tensor
inputs = Input(shape=(784,))
# a layer instance is callable on a tensor, and returns a tensor
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
# This creates a model that includes
# the Input layer and three Dense layers
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
spark_model = SparkModel(model, frequency='epoch', mode='synchronous')
spark_model.save("elephas_model.h5")
def make_model(data):
data.show()
data = data.dropna()
nb_classes = data.select("label").distinct().count()
input_dim = len(data.select("features").first()[0])
print(nb_classes, input_dim)
model = Sequential()
model.add(Embedding(input_dim=input_dim, output_dim=100))
#model.add(LSTM(64,return_sequences=False,dropout=0.1,recurrent_dropout=0.1))
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes, activation='softmax'))
#sgd = optimizers.SGD(lr=0.1)
#model.compile(sgd, 'categorical_crossentropy', ['acc'])
model.compile(loss='binary_crossentropy', optimizer='adam')
#model.compile(loss='categorical_crossentropy', optimizer='adam')
spark_model = SparkModel(model, frequency='epoch', mode='asynchronous')
adam = optimizers.Adam(lr=0.01)
opt_conf = optimizers.serialize(adam)
estimator = ElephasEstimator()
estimator.setFeaturesCol("features")
estimator.setLabelCol("label")
estimator.set_keras_model_config(model.to_yaml())
estimator.set_categorical_labels(True)
estimator.set_nb_classes(nb_classes)
estimator.set_num_workers(1)
estimator.set_epochs(20)
estimator.set_batch_size(128)
estimator.set_verbosity(1)
estimator.set_validation_split(0.15)
estimator.set_optimizer_config(opt_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
#estimator = ElephasEstimator(model, epochs=20, batch_size=32, frequency='batch', mode='asynchronous', nb_classes=1)
pipeline = Pipeline(stages=[estimator])
#fitted_model = estimator.fit(data)
#prediction = fitted_model.transform(data)
fitted_pipeline = pipeline.fit(data) # Fit model to data
prediction = fitted_pipeline.transform(data) # Evaluate on train data.
# prediction = fitted_pipeline.transform(test_df) # <-- The same code evaluates test data.
pnl = prediction.select("text", "prediction")
pnl.show(100)
prediction_and_label = pnl.map(lambda row: (row.text, row.prediction))
metrics = MulticlassMetrics(prediction_and_label)
print(metrics.precision())
pnl = prediction.select("label", "prediction").show()
pnl.show(100)
def train_elephas_model(x, y):
model = models.Sequential()
# Input Layer
sgd = optimizers.Adam(lr=0.01)
model.add(Dense(256, activation="relu", input_shape=(x.shape[1],)))
model.add(Dropout(0.05))
model.add(Dense(256, activation="relu", input_shape=(x.shape[1],)))
model.add(Dropout(0.05))
# output layer
model.add(Dense(1))
model.compile(optimizer=sgd, loss="mse", metrics=["mse"])
model.summary()
rdd = to_simple_rdd(sc, x, y)
spark_model = SparkModel(model, frequency='epoch', mode='asynchronous')
# spark_model.fit(rdd, epochs=10, batch_size=64, verbose=1, validation_split=0.2)
spark_model.fit(rdd, epochs=25, batch_size=64, verbose=1, validation_split=0.2)
return spark_model
def dist_training(n_iter):
sbcnn = SBCNN_Model(field_size, bands, frames, num_channels, num_labels)
sgd = SGD(lr=0.001, momentum=0.0, decay=0.0, nesterov=False)
sbcnn.compile(loss='categorical_crossentropy',
metrics=['accuracy'],
optimizer=sgd)
train_arr, train_labels_arr, test_arr, test_labels_arr = get_data()
rdd = to_simple_rdd(sc, train_arr, train_labels_arr)
spark_model = SparkModel(sbcnn, frequency='epoch', mode='asynchronous')
spark_model.fit(rdd,
epochs=n_iter,
batch_size=32,
verbose=0,
validation_split=0.1)
score = spark_model.master_network.evaluate(test_arr,
test_labels_arr,
verbose=2)
print('Test accuracy:', score[1])
def test_sequential_serialization():
# Define basic parameters
batch_size = 64
nb_classes = 10
epochs = 1
# Create Spark context
pytest.mark.usefixtures("spark_context")
# Load data
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype("float32")
x_test = x_test.astype("float32")
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# Convert class vectors to binary class matrices
y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)
seq_model = Sequential()
seq_model.add(Dense(128, input_dim=784))
seq_model.add(Activation('relu'))
seq_model.add(Dropout(0.2))
seq_model.add(Dense(128))
seq_model.add(Activation('relu'))
seq_model.add(Dropout(0.2))
seq_model.add(Dense(10))
seq_model.add(Activation('softmax'))
seq_model.compile(optimizer="sgd", loss="categorical_crossentropy", metrics=["acc"])
spark_model = SparkModel(seq_model, frequency='epoch', mode='synchronous')
spark_model.save("elephas_sequential.h5")
def test_training_classification(spark_context, mode, parameter_server_mode,
mnist_data, classification_model):
# Define basic parameters
batch_size = 64
epochs = 10
# Load data
x_train, y_train, x_test, y_test = mnist_data
x_train = x_train[:1000]
y_train = y_train[:1000]
sgd = SGD(lr=0.1)
classification_model.compile(sgd, 'categorical_crossentropy', ['acc'])
# Build RDD from numpy features and labels
rdd = to_simple_rdd(spark_context, x_train, y_train)
# Initialize SparkModel from keras model and Spark context
spark_model = SparkModel(classification_model,
frequency='epoch',
mode=mode,
parameter_server_mode=parameter_server_mode,
port=4000 + random.randint(0, 500))
# Train Spark model
spark_model.fit(rdd,
epochs=epochs,
batch_size=batch_size,
verbose=0,
validation_split=0.1)
# run inference on trained spark model
predictions = spark_model.predict(x_test)
# run evaluation on trained spark model
evals = spark_model.evaluate(x_test, y_test)
# assert we can supply rdd and get same prediction results when supplying numpy array
test_rdd = spark_context.parallelize(x_test)
assert [np.argmax(x) for x in predictions
] == [np.argmax(x) for x in spark_model.predict(test_rdd)]
# assert we get the same prediction result with calling predict on keras model directly
assert [np.argmax(x) for x in predictions] == [
np.argmax(x) for x in spark_model.master_network.predict(x_test)
]
# assert we get the same evaluation results when calling evaluate on keras model directly
assert isclose(evals[0],
spark_model.master_network.evaluate(x_test, y_test)[0],
abs_tol=0.01)
assert isclose(evals[1],
spark_model.master_network.evaluate(x_test, y_test)[1],
abs_tol=0.01)
def _build_model(self):
model = Sequential()
adam = elephas_optimizers.Adam()
layers = self._layers
model.add(Dense(layers[1], input_dim=layers[0], init='normal', activation='relu'))
for i in range(2, len(layers) - 1):
model.add(Dense(layers[i], activation='relu'))
model.add(Dense(layers[-1], activation='sigmoid'))
self._model = SparkModel(self._spark.sparkContext, model,
optimizer=adam,
frequency='epoch',
mode='asynchronous',
master_loss='mse',
num_workers=self._worker_num)
def test_training_regression(spark_context, mode, parameter_server_mode,
boston_housing_dataset, regression_model):
x_train, y_train, x_test, y_test = boston_housing_dataset
rdd = to_simple_rdd(spark_context, x_train, y_train)
# Define basic parameters
batch_size = 64
epochs = 10
sgd = SGD(lr=0.0000001)
regression_model.compile(sgd, 'mse', ['mae'])
spark_model = SparkModel(regression_model,
frequency='epoch',
mode=mode,
parameter_server_mode=parameter_server_mode,
port=4000 + random.randint(0, 500))
# Train Spark model
spark_model.fit(rdd,
epochs=epochs,
batch_size=batch_size,
verbose=0,
validation_split=0.1)
# run inference on trained spark model
predictions = spark_model.predict(x_test)
# run evaluation on trained spark model
evals = spark_model.evaluate(x_test, y_test)
# assert we can supply rdd and get same prediction results when supplying numpy array
test_rdd = spark_context.parallelize(x_test)
assert all(
np.isclose(x, y, 0.01)
for x, y in zip(predictions, spark_model.predict(test_rdd)))
# assert we get the same prediction result with calling predict on keras model directly
assert all(
np.isclose(x, y, 0.01) for x, y in zip(
predictions, spark_model.master_network.predict(x_test)))
# assert we get the same evaluation results when calling evaluate on keras model directly
assert isclose(evals[0],
spark_model.master_network.evaluate(x_test, y_test)[0],
abs_tol=0.01)
assert isclose(evals[1],
spark_model.master_network.evaluate(x_test, y_test)[1],
abs_tol=0.01)
def test_training_custom_activation(mode, spark_context):
def custom_activation(x):
return sigmoid(x) + 1
model = Sequential()
model.add(Dense(1, input_dim=1, activation=custom_activation))
model.add(Dense(1, activation='sigmoid'))
sgd = SGD(lr=0.1)
model.compile(sgd, 'binary_crossentropy', ['acc'])
x_train = np.random.rand(1000)
y_train = np.zeros(1000)
x_test = np.random.rand(100)
y_test = np.zeros(100)
y_train[:500] = 1
rdd = to_simple_rdd(spark_context, x_train, y_train)
spark_model = SparkModel(model, frequency='epoch', mode=mode,
custom_objects={'custom_activation': custom_activation})
spark_model.fit(rdd, epochs=1, batch_size=16, verbose=0, validation_split=0.1)
assert spark_model.predict(x_test)
assert spark_model.evaluate(x_test, y_test)
input_shape=(modelpara_dict['Column_num'], 1)))
model.add(MaxPooling1D(pool_size=4))
model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(modelpara_dict['Lable_num'], activation='softmax'))
print(model.summary())
sgd = SGD(lr=0.1)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
adagrad = elephas_optimizers.Adagrad()
spark_model = SparkModel(sc,
model,
optimizer=adagrad,
frequency='epoch',
mode='synchronous',
num_workers=3)
# Train Spark model
spark_model.train(train_data,
nb_epoch=1,
batch_size=32,
verbose=2,
validation_split=0.1)
spark_model.master_network.save('model/' + modelname + '/' + modelname +
'.h5')
# Evaluate Spark model by evaluating the underlying model
#score = spark_model.master_network.evaluate(x_test, y_test, verbose=2)
#print('Test accuracy:', score[1])
print("Creating Training and Test Data")
((x_train, y_train), (x_test, y_test)) = train_test_split(testinput.fillna(0), testoutput.fillna(0), test_size=0.3)
print("Training data : x")
print(type(x_train))
print(x_train)
print("Training data : y")
print(type(y_train))
print(y_train)
print("Test data : x")
print(type(x_test))
print(x_test)
print("Test data : y")
print(type(y_test))
print(y_test)
print("Converting training data to RDD")
rddataset = to_simple_rdd(sc, x_train, y_train)
print("Initializing SPark Model")
sgd = elephas_optimizers.SGD()
spark_model = SparkModel(sc, model, optimizer=sgd, frequency="epoch", mode="asynchronous", num_workers=2)
print("Commencing training")
spark_model.train(rddataset, nb_epoch=10, batch_size=200, verbose=1, validation_split=0)
# model.fit(x_train, y_train, nb_epoch=5, batch_size=32)
print("Training completed")
sc.stop()
#early_stopping = EarlyStopping(monitor='val_acc', patience=5)
#print 'Start training...'
#model.fit( X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=verbose, callbacks=[checkpointer],validation_split=validation_split, shuffle=shuffle,show_accuracy=show_accuracy)
# Create Spark Context
conf = SparkConf().setAppName(MODEL)
sc = SparkContext(conf=conf)
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, X_train, Y_train)
# Initialize SparkModel from Keras model and Spark Context
rmsprop = elephas_optimizers.RMSprop()
spark_model = SparkModel(sc,\
model,\
optimizer=rmsprop,\
frequency='epoch',\
mode='asynchronous',\
num_workers=3)
spark_model.train(rdd,\
nb_epoch=nb_epoch,\
batch_size=batch_size,\
verbose=2,\
validation_split=validation_split)
spark_model.get_network().save_weights(MODEL_FILE_NAME)
class HAN(object):
"""
HAN model is implemented here.
"""
def __init__(self,
text,
labels,
pretrained_embedded_vector_path,
max_features,
max_senten_len,
max_senten_num,
embedding_size,
num_categories=None,
validation_split=0.2,
verbose=0):
"""Initialize the HAN module
Keyword arguments:
text -- list of the articles for training.
labels -- labels corresponding the given `text`.
pretrained_embedded_vector_path -- path of any pretrained vector
max_features -- max features embeddeding matrix can have. To more checkout https://keras.io/layers/embeddings/
max_senten_len -- maximum sentence length. It is recommended not to use the maximum one but the one that covers 0.95 quatile of the data.
max_senten_num -- maximum number of sentences. It is recommended not to use the maximum one but the one that covers 0.95 quatile of the data.
embedding_size -- size of the embedding vector
num_categories -- total number of categories.
validation_split -- train-test split.
verbose -- how much you want to see.
"""
try:
self.verbose = verbose
self.max_features = max_features
self.max_senten_len = max_senten_len
self.max_senten_num = max_senten_num
self.embed_size = embedding_size
self.validation_split = validation_split
self.embedded_dir = pretrained_embedded_vector_path
self.text = pd.Series(text)
self.categories = pd.Series(labels)
self.classes = self.categories.unique().tolist()
# Initialize default hyperparameters
# You can change it using `set_hyperparameters` function
self.hyperparameters = {
'l2_regulizer': None,
'dropout_regulizer': None,
'rnn': LSTM,
'rnn_units': 150,
'dense_units': 200,
'activation': 'softmax',
'optimizer': 'adam',
'metrics': ['acc'],
'loss': 'categorical_crossentropy'
}
if num_categories is not None:
assert (num_categories == len(self.classes))
assert (self.text.shape[0] == self.categories.shape[0])
self.data, self.labels = self.preprocessing()
self.x_train, self.y_train, self.x_val, self.y_val = self.split_dataset(
)
self.embedding_index = self.add_glove_model()
self.set_model()
except AssertionError:
print('Input and label data must be of same size')
# Implement this after you have seen all the different kinds of errors
# try:
# conf = SparkConf().setAppName('HANMusicClassifier').setMaster('')
# self.sc = SparkContext(conf=conf)
# except Error:
conf = SparkConf().setAppName('HANMusicClassifier')
self.sc = SparkContext(conf=conf)
def set_hyperparameters(self, tweaked_instances):
"""Set hyperparameters of HAN model.
Keywords arguemnts:
tweaked_instances -- dictionary of all those keys you want to change
"""
for key, value in tweaked_instances.items():
if key in self.hyperparameters:
self.hyperparameters[key] = value
else:
raise KeyError(key + ' does not exist in hyperparameters')
self.set_model()
def show_hyperparameters(self):
"""To check the values of all the current hyperparameters
"""
print('Hyperparameter\tCorresponding Value')
for key, value in self.hyperparameters.items():
print(key, '\t\t', value)
def clean_string(self, string):
"""
Tokenization/string cleaning for dataset
Every dataset is lower cased except
"""
string = re.sub(r"\\", "", string)
string = re.sub(r"\'", "", string)
string = re.sub(r"\"", "", string)
return string.strip().lower()
def add_dataset(self, text, labels):
try:
self.text = pd.concat([self.text, pd.Series(text)])
self.categories = pd.concat([self.categories, pd.Series(labels)])
assert (len(self.classes) == self.categories.unique().tolist())
except AssertionError:
print("New class cannot be added in this manner")
def preprocessing(self):
"""Preprocessing of the text to make it more resonant for training
"""
paras = []
labels = []
texts = []
for idx in range(self.text.shape[0]):
text = self.clean_string(self.text[idx])
texts.append(text)
sentences = tokenize.sent_tokenize(text)
paras.append(sentences)
tokenizer = Tokenizer(num_words=self.max_features, oov_token=True)
tokenizer.fit_on_texts(texts)
data = np.zeros((len(texts), self.max_senten_num, self.max_senten_len),
dtype='int32')
for i, sentences in enumerate(paras):
for j, sent in enumerate(sentences):
if j < self.max_senten_num:
wordTokens = text_to_word_sequence(sent)
k = 0
for _, word in enumerate(wordTokens):
if k < self.max_senten_len and word in tokenizer.word_index and tokenizer.word_index[
word] < self.max_features:
data[i, j, k] = tokenizer.word_index[word]
k = k + 1
self.word_index = tokenizer.word_index
if self.verbose == 1:
print('Total %s unique tokens.' % len(self.word_index))
labels = pd.get_dummies(self.categories)
if self.verbose == 1:
print('Shape of data tensor:', data.shape)
print('Shape of labels tensor:', labels.shape)
assert (len(self.classes) == labels.shape[1])
assert (data.shape[0] == labels.shape[0])
return data, labels
def split_dataset(self):
indices = np.arange(self.data.shape[0])
np.random.shuffle(indices)
self.data = self.data[indices]
self.labels = self.labels.iloc[indices]
nb_validation_samples = int(self.validation_split * self.data.shape[0])
x_train = self.data[:-nb_validation_samples]
y_train = self.labels[:-nb_validation_samples]
x_val = self.data[-nb_validation_samples:]
y_val = self.labels[-nb_validation_samples:]
if self.verbose == 1:
print(
'Number of positive and negative reviews in traing and validation set'
)
print(y_train.columns.tolist())
print(y_train.sum(axis=0).tolist())
print(y_val.sum(axis=0).tolist())
return x_train, y_train, x_val, y_val
def get_model(self):
"""
Returns the HAN model so that it can be used as a part of pipeline
"""
return self.model
def add_glove_model(self):
"""
Read and save Pretrained Embedding model
"""
embeddings_index = {}
try:
f = open(self.embedded_dir)
for line in f:
values = line.split()
word = values[0]
coefs = np.asarray(values[1:], dtype='float32')
assert (coefs.shape[0] == self.embed_size)
embeddings_index[word] = coefs
f.close()
except OSError:
print('Embedded file does not found')
exit()
except AssertionError:
print(
"Embedding vector size does not match with given embedded size"
)
return embeddings_index
def get_embedding_matrix(self):
"""
Returns Embedding matrix
"""
embedding_matrix = np.random.random(
(len(self.word_index) + 1, self.embed_size))
absent_words = 0
for word, i in self.word_index.items():
embedding_vector = self.embedding_index.get(word)
if embedding_vector is not None:
# words not found in embedding index will be all-zeros.
embedding_matrix[i] = embedding_vector
else:
absent_words += 1
if self.verbose == 1:
print('Total absent words are', absent_words, 'which is',
"%0.2f" % (absent_words * 100 / len(self.word_index)),
'% of total words')
return embedding_matrix
def get_embedding_layer(self):
"""
Returns Embedding layer
"""
embedding_matrix = self.get_embedding_matrix()
return Embedding(len(self.word_index) + 1,
self.embed_size,
weights=[embedding_matrix],
input_length=self.max_senten_len,
trainable=False)
def set_model(self):
"""
Set the HAN model according to the given hyperparameters
"""
if self.hyperparameters['l2_regulizer'] is None:
kernel_regularizer = None
else:
kernel_regularizer = regularizers.l2(
self.hyperparameters['l2_regulizer'])
if self.hyperparameters['dropout_regulizer'] is None:
dropout_regularizer = 1
else:
dropout_regularizer = self.hyperparameters['dropout_regulizer']
word_input = Input(shape=(self.max_senten_len, ), dtype='float32')
word_sequences = self.get_embedding_layer()(word_input)
word_lstm = Bidirectional(self.hyperparameters['rnn'](
self.hyperparameters['rnn_units'],
return_sequences=True,
kernel_regularizer=kernel_regularizer))(word_sequences)
word_dense = TimeDistributed(
Dense(self.hyperparameters['dense_units'],
kernel_regularizer=kernel_regularizer))(word_lstm)
word_att = AttentionWithContext()(word_dense)
wordEncoder = Model(word_input, word_att)
sent_input = Input(shape=(self.max_senten_num, self.max_senten_len),
dtype='float32')
sent_encoder = TimeDistributed(wordEncoder)(sent_input)
sent_lstm = Bidirectional(self.hyperparameters['rnn'](
self.hyperparameters['rnn_units'],
return_sequences=True,
kernel_regularizer=kernel_regularizer))(sent_encoder)
sent_dense = TimeDistributed(
Dense(self.hyperparameters['dense_units'],
kernel_regularizer=kernel_regularizer))(sent_lstm)
sent_att = Dropout(dropout_regularizer)(
AttentionWithContext()(sent_dense))
preds = Dense(len(self.classes))(sent_att)
self.model = Model(sent_input, preds)
self.model.compile(loss=self.hyperparameters['loss'],
optimizer=self.hyperparameters['optimizer'],
metrics=self.hyperparameters['metrics'])
self.spark_model = SparkModel(self.model,
frequency='epoch',
mode='asynchronous')
# Currently cannot plot learning curve
def train_model(self,
rdd,
epochs,
batch_size,
verbose=1,
validation_split=0.1):
"""Training the model
rdd -- The actual data
epochs -- Total number of epochs
batch_size -- size of a batch
verbose -- Whether or not we want verbose feedback
validation_split -- What percentage of the data from the rdd is actually used as a validation set
"""
self.spark_model.fit(self,
rdd,
epochs=epochs,
batch_size=batch_size,
verbose=verbose,
validation_split=validation_split)
def predict(self, rdd):
self.spark_model.predict(rdd)
def plot_results(self):
"""
Plotting learning curve of last trained model.
"""
# summarize history for accuracy
plt.subplot(211)
plt.plot(self.history.history['acc'])
plt.plot(self.history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
# summarize history for loss
plt.subplot(212)
plt.plot(self.history.history['val_loss'])
plt.plot(self.history.history['loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
time.sleep(10)
plt.close()
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adadelta')
## spark
conf = SparkConf().setAppName(APP_NAME).setMaster(MASTER_IP)
sc = SparkContext(conf=conf)
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, X_train, Y_train)
# Initialize SparkModel from Keras model and Spark context
spark_model = SparkModel(sc,model)
# Train Spark model
spark_model.train(rdd, nb_epoch=nb_epoch, batch_size=batch_size, verbose=0, validation_split=0.1, num_workers=24)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.get_network().evaluate(X_test, Y_test, show_accuracy=True, verbose=2)
print('Test accuracy:', score[1])
# score = model.evaluate(x_test, y_test, verbose=0)
#
# print('Test score:', score[0])
# print('Test accuracy:', score[1])
# Create Spark context
conf = SparkConf().setAppName('Mnist_Spark_MLP')
# .setMaster('local[8]')
sc = SparkContext(conf=conf)
# Build RDD from numpy features and labels
# lp_rdd = to_labeled_point(sc, x_train, y_train, categorical=True)
rdd = to_simple_rdd(sc, x_train, y_train)
# Train Spark model
spark_model = SparkModel(model, frequency='epoch', mode='asynchronous')
spark_model.fit(rdd,
epochs=epochs,
batch_size=batch_size,
verbose=2,
validation_split=0.1)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.master_network.evaluate(x_test, y_test, verbose=2)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model_file = 'save/mlp.h5'
import os
if not os.path.exists("save/"):
model = Sequential()
model.add(Dense(18, input_dim=26))
model.add(Activation('sigmoid'))
model.add(Dense(6))
model.add(Activation('sigmoid'))
model.add(Dense(1))
model.add(Activation('sigmoid'))
spark = SparkSession.builder.appName('ElephasTest').getOrCreate()
rdd = to_simple_rdd(spark.sparkContext, train, y_train)
sgd = SGD(lr=0.1)
adagrad = elephas_optimizers.Adagrad()
spark_model = SparkModel(spark.sparkContext,
model,
optimizer=adagrad,
frequency='epoch',
mode='asynchronous',
master_loss='mse',
num_workers=2, master_optimizer=sgd)
# Train Spark model
spark_model.train(rdd, nb_epoch=nb_epoch, batch_size=batch_size, verbose=2, validation_split=0.1)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.master_network.evaluate(test.values, y_test, verbose=2)
print('Test accuracy:', score[1])
print spark_model.predict(test.values)
print y_test
.getOrCreate())
sc = spark.sparkContext
"""### Training Model"""
from elephas.spark_model import SparkModel
from elephas.utils.rdd_utils import to_simple_rdd
# Compile the model.
model_9.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
# Build RDD from features and labels.
rdd = to_simple_rdd(sc, x_train, y_train)
# Initialize SparkModel from Keras model and Spark context.
spark_model = SparkModel(model_9,
frequency='epoch',
mode='asynchronous',
num_workers=3)
# Train the Spark model.
spark_model.fit(rdd, epochs=10, batch_size=32, verbose=1, validation_split=0.1)
score = spark_model.master_network.evaluate(x_test, y_test, verbose=1)
print('Test accuracy:', score)
"""### Predcit and evaluate Model"""
"""### Save Model"""
import json
#lets assume 'model' is main model
model_json = model_9.to_json()
with open("model_in_json.json", "w") as json_file:
json.dump(model_json, json_file)
model = Sequential()
model.add(Dense(784, 128))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(128, 128))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(128, 10))
model.add(Activation('softmax'))
# Compile model
rms = RMSprop()
model.compile(loss='categorical_crossentropy', optimizer=rms)
# Create Spark context
conf = SparkConf().setAppName('Mnist_Spark_MLP').setMaster('local[8]')
sc = SparkContext(conf=conf)
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, X_train, Y_train)
# Initialize SparkModel from Keras model and Spark context
spark_model = SparkModel(sc,model)
# Train Spark model
spark_model.train(rdd, nb_epoch=nb_epoch, batch_size=batch_size, verbose=0, validation_split=0.1, num_workers=8)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.get_network().evaluate(X_test, Y_test, show_accuracy=True, verbose=2)
print('Test accuracy:', score[1])
import tensorflow as tf
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print("length = ( ", len(x_train), ", ", len(y_train), " )")
print("shape of the dataset = ", tf.shape(y_train))
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype("float32")
x_test = x_test.astype("float32")
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
nb_classes = 10
# Convert class vectors to binary class matrices
y_train = to_categorical(y_train, nb_classes)
y_test = to_categorical(y_test, nb_classes)
rdd = to_simple_rdd(sc, x_train, y_train)
print("rdd = ", rdd)
from elephas.spark_model import SparkModel
spark_model = SparkModel(model,
frequency='epoch',
mode='asynchronous',
num_workers=2)
spark_model.fit(rdd, epochs=10, batch_size=32, verbose=0, validation_split=0.1)
score = spark_model.evaluate(x_test, y_test, verbose=2)
print('Test accuracy:', score)
print("Test size: %d" % test_data.count())
# create model object
model = Sequential()
model.add(LSTM(128, activation="sigmoid", input_shape=(1, input_dim)))
model.add(Dropout(0.2))
model.add(Dense(1))
metrics = ['MeanSquaredError', 'MeanAbsoluteError']
model.compile(loss='mean_squared_error', optimizer='adam', metrics=metrics)
print(model.summary())
rdd = train_data.rdd.map(lambda x:
(x[0].toArray().reshape(1, len(x[0])), x[1]))
spark_model = SparkModel(model,
frequency='epoch',
mode='synchronous',
metrics=metrics)
start = time()
spark_model.fit(rdd,
epochs=1,
batch_size=64,
verbose=0,
validation_split=0.1)
fit_dt = time() - start
print(f"Fit took: {fit_dt}")
x_test = test_data.toPandas()['features']
x_test = np.asarray(test_data.rdd.map(lambda x: x[0].toArray()).collect())
x_test = x_test.reshape((x_test.shape[0], 1, x_test.shape[1]))
y_test = test_data.toPandas()["Weighted_Price"].to_numpy()
y_test = y_test.reshape((len(y_test), 1, 1))
class SparseGate(ModelFrame):
def __init__(self, x_train, y_train, x_test, y_test, inputs,
spark_context):
ModelFrame.__init__(self, x_train, y_train, x_test, y_test,
spark_context)
self.gateModel = None
self.inputs = inputs
def gating_network(self):
c1 = Conv2D(32, (3, 3),
padding='same',
kernel_regularizer=regularizers.l2(weight_decay),
input_shape=self.x_train.shape[1:],
name='gate1')(self.inputs)
c2 = Activation('elu', name='gate2')(c1)
c3 = BatchNormalization(name='gate3')(c2)
c4 = Conv2D(32, (3, 3),
padding='same',
kernel_regularizer=regularizers.l2(weight_decay),
name='gate4')(c3)
c5 = Activation('elu', name='gate5')(c4)
c6 = BatchNormalization(name='gate6')(c5)
c7 = MaxPooling2D(pool_size=(2, 2), name='gate7')(c6)
c8 = Dropout(0.2, name='gate26')(c7)
c9 = Conv2D(32 * 2, (3, 3),
name='gate8',
padding='same',
kernel_regularizer=regularizers.l2(weight_decay))(c8)
c10 = Activation('elu', name='gate9')(c9)
c11 = BatchNormalization(name='gate25')(c10)
c12 = Conv2D(32 * 2, (3, 3),
name='gate10',
padding='same',
kernel_regularizer=regularizers.l2(weight_decay))(c11)
c13 = Activation('elu', name='gate11')(c12)
c14 = BatchNormalization(name='gate12')(c13)
c15 = MaxPooling2D(pool_size=(2, 2), name='gate13')(c14)
c16 = Dropout(0.3, name='gate14')(c15)
c25 = Flatten(name='gate23')(c16)
c26 = Dense(5, name='gate24', activation='elu')(c25)
model = Model(inputs=self.inputs, outputs=c26)
return model
def create_gate_model(self, expert_models):
gate_network = self.gating_network()
merged = Lambda(lambda x: K.tf.transpose(
sum(
K.tf.transpose(x[i]) * x[0][:, i - 1] for i in range(
1, len(x)))))([gate_network.layers[-1].output] +
[m.layers[-1].output for m in expert_models])
b = Activation('softmax', name='gatex')(merged)
model = Model(inputs=self.inputs, outputs=b)
model.compile(loss='categorical_crossentropy',
optimizer=Adam(),
metrics=['accuracy'])
return model
def train_gate(self, datagen, weights_file):
model = self.gateModel
model.compile(loss='categorical_crossentropy',
optimizer=Adam(),
metrics=['accuracy'])
print(model.summary())
self.gateModel = SparkModel(model,
frequency='epoch',
mode='asynchronous')
score = self.gateModel.master_network.evaluate(self.x_test,
self.y_test,
verbose=2,
batch_size=50)
self.gateModel.fit(self.rdd, epochs=1, batch_size=50, verbose=1)
self.gateModel = self.gateModel.master_network
self.gateModel.save_weights(weights_file + '.hdf5')
file = '../lib/output.txt'
if os.path.exists(file):
append_write = 'a'
else:
append_write = 'w'
#score = self.gateModel.evaluate(self.x_test, self.y_test, verbose=2, batch_size=50)
print("------------------------------")
print("Score is:" + str(score[1]))
print("-------------------------------")
text_file = open(file, append_write)
text_file.write("Score: %s" % score[1])
text_file.close()
def load_gate_weights(self,
model_old,
weights_file='../lib/weights/moe_full.hdf5'):
model_old.load_weights(weights_file)
for l in self.gateModel.layers:
for b in model_old.layers:
if (l.name == b.name):
l.set_weights(b.get_weights())
print("loaded gate layer " + str(l.name))
early_stop = EarlyStopping(monitor='val_loss', patience=4, verbose=1)
model = Sequential()
model.add(Dense(32, input_shape=(239, ), activation='tanh'))
model.add(Dense(1))
opt = Adam(lr=0.001)
model.compile(loss='mean_squared_error', optimizer=opt)
model.summary()
from elephas.utils.rdd_utils import to_simple_rdd
rdd = train_data.rdd
from elephas.spark_model import SparkModel
from elephas.optimizers import Adam
spark_model = SparkModel(model,
frequency='epoch',
mode='synchronous',
num_workers=4,
elephas_optimizer=Adam())
spark_model.fit(rdd,
epochs=20,
batch_size=500,
verbose=1,
validation_split=0.1)
spark_model.fit()
from elephas.mllib.adapter import to_vector, from_vector
from pyspark import SparkContext, SparkConf
# Create Spark context
conf = SparkConf().setAppName('LSTM_Spark_MLP')
sc = SparkContext(conf=conf)
def deal_x(x):
x = np.array(x)
x_data = x[1:]
x_data = np.expand_dims(x_data, axis=2)
return x_data
test_data = sc.textFile("output/data/z2.csv").map(
lambda ln: deal_x([float(x) for x in ln.split(',')]))
model = load_model('model.h5')
adagrad = elephas_optimizers.Adagrad()
spark_model = SparkModel(sc,
model,
optimizer=adagrad,
frequency='epoch',
mode='synchronous',
num_workers=3)
# Test Spark model
spark_model.predict_classes(test_data, "output/data/prediction")
sc = SparkContext(conf=conf)
sc.setLogLevel("ERROR")
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, x_train, y_train)
# Epoch Before Check Point
num_epoch_in_one_step = 10
batch_size = 100
# Accuracy records
stat_lines = []
adagrad = elephas_optimizers.Adagrad()
for i in range(0, 200):
# Train Spark model
# Initialize SparkModel from Keras model and Spark context
spark_model = SparkModel(sc,
model,
mode='asynchronous',
frequency='epoch',
num_workers=1,
optimizer=adagrad)
spark_model.train(rdd,
nb_epoch=num_epoch_in_one_step,
batch_size=batch_size,
verbose=0,
validation_split=0.1)
score1 = model.evaluate(x_train, y_train, verbose=0)
score2 = model.evaluate(x_test, y_test, verbose=0)
print('#############################')
print('Finished epochs', (i + 1) * num_epoch_in_one_step)
print('Train accuracy:', score1[1])
print('Test accuracy:', score2[1])
print('#############################')
stat_lines.append(
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))
sgd = SGD(lr=0.1)
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, x_train, y_train)
# Initialize SparkModel from Keras model and Spark context
adagrad = elephas_optimizers.Adagrad()
spark_model = SparkModel(sc,
model,
optimizer=adagrad,
frequency='epoch',
mode='asynchronous',
num_workers=2,
master_optimizer=sgd)
# Train Spark model
spark_model.train(rdd,
nb_epoch=nb_epoch,
batch_size=batch_size,
verbose=2,
validation_split=0.1)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.master_network.evaluate(x_test, y_test, verbose=2)
print('Test accuracy:', score[1])
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))
# Compile model
sgd = SGD(lr=0.1)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, x_train, y_train)
# Initialize SparkModel from Keras model and Spark context
adagrad = elephas_optimizers.Adagrad()
spark_model = SparkModel(sc,
model,
optimizer=adagrad,
frequency='epoch',
mode='asynchronous',
num_workers=2)
# Train Spark model
spark_model.train(rdd,
nb_epoch=nb_epoch,
batch_size=batch_size,
verbose=2,
validation_split=0.1)
# Evaluate Spark model by evaluating the underlying model
score = spark_model.master_network.evaluate(x_test,
y_test,
show_accuracy=True,
verbose=2)
class KerasNeuralNetworkSpark(object):
def __init__(self, layers, spark, batch_size=64, epoch=10, num_workers=2, predictionCol='prediction',
labelCol='target', featuresCol='feature'):
self._batch_size = batch_size
self._epoch = epoch
self._model = None
self._spark = spark
self._labels = labelCol
self._features = featuresCol
self._prediction = predictionCol
self._layers = layers
self._worker_num = num_workers
self._build_model()
def _build_model(self):
model = Sequential()
adam = elephas_optimizers.Adam()
layers = self._layers
model.add(Dense(layers[1], input_dim=layers[0], init='normal', activation='relu'))
for i in range(2, len(layers) - 1):
model.add(Dense(layers[i], activation='relu'))
model.add(Dense(layers[-1], activation='sigmoid'))
self._model = SparkModel(self._spark.sparkContext, model,
optimizer=adam,
frequency='epoch',
mode='asynchronous',
master_loss='mse',
num_workers=self._worker_num)
def fit(self, df):
if hasattr(self._model, 'server'):
self._model.server.terminate()
pdf = df.toPandas()
rdd = to_simple_rdd(self._spark.sparkContext, pdf[self._features], pdf[self._labels])
self._model.train(rdd, self._epoch, self._batch_size, 0, 0.1)
def transform(self, df):
pdf = df.toPandas()
# df.write.save('test_df.parquet')
pnparray = pdf[self._features].values
container = np.zeros((pnparray.shape[0], len(pnparray[0])))
for i in range(pnparray.shape[0]):
container[i, :] = pnparray[i][:]
result = self._model.predict(container)
pdf[self._prediction] = result
# import pickle
# with open('ann_result.p', 'w') as f:
# pickle.dump(result, f)
# result_df = pd.DataFrame(pdf
new_df = self._spark.createDataFrame(pdf)
# df.join(new_df)
return new_df
def stop_server(self):
if hasattr(self._model, 'server') and hasattr(self._model.server, 'terminate'):
self._model.server.terminate()
# output signal. Here's the activation function is given be ReLU.
model.add(Activation('relu'))
model.add(Dropout(0.5)) # dropout is then applied
# finally the 128 outputs of the previous FC layer are fully connected to num_classes of neurons, which
# is activated by a softmax function
model.add( Dense(nb_classes, W_regularizer=l2(0.01) ))
model.add( Activation('softmax') )
# write the neural network model representation to a png image
#grapher.plot(model, 'nn_mnist.png')
model.compile(loss='categorical_crossentropy', optimizer='adadelta')
# model.compile(loss='categorical_crossentropy', optimizer='sgd' or 'adam or 'adadelta')
## spark
conf = SparkConf().setAppName(APP_NAME) #.setMaster(MASTER_IP)
sc = SparkContext(conf=conf)
# Build RDD from numpy features and labels
rdd = to_simple_rdd(sc, X_train, Y_train)
# Initialize SparkModel from Keras model and Spark context
spark_model = SparkModel(sc,model)
# Train Spark model
spark_model.train(rdd, nb_epoch=nb_epoch, batch_size=batch_size, verbose=1, validation_split=0.15) # num_workers might not work in early spark version
# Evaluate Spark model by evaluating the underlying model
score = spark_model.get_network().evaluate(X_test, Y_test, show_accuracy=True, verbose=2)
print('Test accuracy:', score[1])
print('Test data : x')
print(type(x_test))
print(x_test)
print('Test data : y')
print(type(y_test))
print(y_test)
print('Converting training data to RDD')
rddataset = to_simple_rdd(sc, x_train, y_train)
print('Initializing SPark Model')
sgd = elephas_optimizers.SGD()
spark_model = SparkModel(sc,
model,
optimizer=sgd,
frequency='epoch',
mode='asynchronous',
num_workers=2)
print('Commencing training')
spark_model.train(rddataset,
nb_epoch=10,
batch_size=200,
verbose=1,
validation_split=0)
#model.fit(x_train, y_train, nb_epoch=5, batch_size=32)
print('Training completed')
sc.stop()
# Define elephas optimizer (which tells the model how to aggregate updates on the Spark master)
adadelta = elephas_optimizers.Adadelta()
from elephas.utils.rdd_utils import to_labeled_point
from elephas.utils.rdd_utils import to_simple_rdd
lp_rdd = to_simple_rdd(sc, features_train, labels_train)
#print(lp_rdd.take(5))
from elephas.spark_model import SparkModel
from elephas import optimizers as elephas_optimizers
adagrad = elephas_optimizers.Adagrad()
spark_model = SparkModel(sc,
model,
optimizer=adagrad,
frequency='epoch',
mode='asynchronous',
num_workers=8)
spark_model.train(lp_rdd,
nb_epoch=20,
batch_size=32,
verbose=0,
validation_split=0.1)
print(spark_model)
prediction = spark_model.predict_classes(features_test)
print(prediction)
truth = [l[1] for l in labels_test]
from sklearn.metrics import confusion_matrix
model_config.input_split_index = encoder_train_input.shape[1]
training_generator = WMTSequence(encoder_train_input, decoder_train_input, decoder_train_target, model_config)
for raw_train_input, decoder_train_target in training_generator:
encoder_train_input, decoder_train_input = raw_train_input
train_input = np.hstack((encoder_train_input, decoder_train_input))
train_rdd = to_simple_rdd(sc, train_input, decoder_train_target)
if args.ensemble:
model = DistributedEnsembleSeq2Seq(model_config)
else:
model = DistributedSeq2Seq(model_config)
spark_model = SparkModel(model.model,
frequency='epoch',
mode='synchronous',
batch_size=args.batch_size,
custom_objects={'EncoderSlice': EncoderSlice, 'DecoderSlice': DecoderSlice})
spark_model.fit(train_rdd,
batch_size=model_config.batch_size,
epochs=model_config.epochs,
validation_split=0.0,
verbose=1)
model.evaluate(encoder_test_input, raw_test_target)
else:
training_generator = WMTSequence(encoder_train_input, decoder_train_input, decoder_train_target, model_config)
validation_generator = WMTSequence(encoder_dev_input, decoder_dev_input, decoder_dev_target, model_config)
model.compile(loss='categorical_crossentropy', optimizer=SGD())
model.summary()
# Create a Resilient Distributed Dataset (RDD) from training data
# TODO: get data
# TODO: is it possible to separate traininng data into multiple batches?
rdd = to_simple_rdd(sc, X_train, Y_train)
# Create the Elephas model instance
spark_model = SparkModel(sc,
model,
optimizer = elephas_optimizers.Adagrad(),
frequency = 'epoch',
mode = 'asynchronous',
num_workers = WORKERS
)
# Train model
spark_model.train(rdd,
nb_epoch = EPOCHS,
batch_size = BATCH_SIZE,
verbose = False,
validation_split = VAL_SPLIT,
num_workers = WORKERS
)