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)
# Build RDD from numpy features and labels
df = to_data_frame(sc, x_train, y_train, categorical=True)
test_df = to_data_frame(sc, x_test, y_test, categorical=True)
# Define elephas optimizer
adadelta = elephas_optimizers.Adadelta()
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(adadelta.get_config())
estimator.set_nb_epoch(nb_epoch)
estimator.set_batch_size(batch_size)
estimator.set_num_workers(1)
estimator.set_verbosity(0)
estimator.set_validation_split(0.1)
estimator.set_categorical_labels(True)
estimator.set_nb_classes(nb_classes)
# Fitting a model returns a Transformer
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(df)
# Evaluate Spark model by evaluating the underlying model
prediction = fitted_pipeline.transform(test_df)
pnl = prediction.select("label", "prediction")
pnl.show(100)
prediction_and_label = pnl.map(lambda row: (row.label, row.prediction))
metrics = MulticlassMetrics(prediction_and_label)
model.compile(loss='binary_crossentropy', optimizer='sgd')
# Model Summary
model.summary()
# Initialize SparkML Estimator and Get Settings
estimator = ElephasEstimator()
estimator.setFeaturesCol("features")
estimator.setLabelCol("label_index")
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(25)
estimator.set_batch_size(64)
estimator.set_verbosity(1)
estimator.set_validation_split(0.10)
estimator.set_optimizer_config(sgd)
estimator.set_mode("synchronous")
estimator.set_loss("binary_crossentropy")
estimator.set_metrics(['acc'])
# Create Deep Learning Pipeline
dl_pipeline = Pipeline(stages=[estimator])
print(dl_pipeline)
def dl_pipeline_fit_score_results(dl_pipeline=dl_pipeline,
train_data=train_data,
test_data=test_data,
label='label_index'):
model.compile(loss='categorical_crossentropy', optimizer='adam')
# Initialize Elephas Spark ML Estimator
adagrad = elephas_optimizers.Adagrad()
estimator = ElephasEstimator()
estimator.setFeaturesCol("scaled_features")
estimator.setLabelCol("index_category")
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(adagrad.get_config())
estimator.set_nb_epoch(10)
estimator.set_batch_size(128)
estimator.set_num_workers(4)
estimator.set_verbosity(0)
estimator.set_validation_split(0.15)
estimator.set_categorical_labels(True)
estimator.set_nb_classes(nb_classes)
# Fitting a model returns a Transformer
pipeline = Pipeline(stages=[string_indexer, scaler, estimator])
fitted_pipeline = pipeline.fit(train_df)
from pyspark.mllib.evaluation import MulticlassMetrics
# Evaluate Spark model
prediction = fitted_pipeline.transform(train_df)
pnl = prediction.select("index_category", "prediction")
pnl.show(100)
# Build RDD from numpy features and labels
df = to_data_frame(sc, x_train, y_train, categorical=True)
test_df = to_data_frame(sc, x_test, y_test, categorical=True)
# Define elephas optimizer
adagrad = elephas_optimizers.Adagrad()
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(adagrad.get_config())
estimator.set_nb_epoch(nb_epoch)
estimator.set_batch_size(batch_size)
estimator.set_num_workers(4)
estimator.set_verbosity(2)
estimator.set_validation_split(0.1)
estimator.set_categorical_labels(True)
estimator.set_nb_classes(nb_classes)
estimator.set_frequency('batch')
# Fitting a model returns a Transformer
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(df)
# Evaluate Spark model by evaluating the underlying model
prediction = fitted_pipeline.transform(test_df)
pnl = prediction.select("label", "prediction")
pnl.show(100)
opt_conf = optimizers.serialize(adam)
# Initialize SparkML Estimator and set all relevant properties
estimator = ElephasEstimator()
estimator.setFeaturesCol(
"features") # These two come directly from pyspark,
estimator.setLabelCol("target") # hence the camel case. Sorry :)
estimator.set_keras_model_config(
model.to_yaml()) # Provide serialized Keras model
estimator.set_categorical_labels(True)
estimator.set_nb_classes(num_classes)
estimator.set_num_workers(
10) # We just use one worker here. Feel free to adapt it.
estimator.set_epochs(2) # was max-epochs
estimator.set_batch_size(batch_size) # was 128
estimator.set_verbosity(2) # was 1
estimator.set_validation_split(0.15)
estimator.set_optimizer_config(opt_conf)
estimator.set_mode("synchronous") # Was synchronous
estimator.set_loss(mywloss) # was("categorical_crossentropy")
estimator.set_metrics(['accuracy'])
buildModelElapsed = time.time() - start
buildModelElapseCpu = time.clock() - startCpu
start = time.time()
startCpu = time.clock()
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(train_df)