def test_regression_model(spark_context, regression_model,
boston_housing_dataset):
batch_size = 64
epochs = 10
x_train, y_train, x_test, y_test = boston_housing_dataset
df = to_data_frame(spark_context, x_train, y_train)
test_df = to_data_frame(spark_context, x_test, y_test)
sgd = optimizers.SGD(lr=0.00001)
sgd_conf = optimizers.serialize(sgd)
estimator = ElephasEstimator()
estimator.set_keras_model_config(regression_model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("mae")
estimator.set_metrics(['mae'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
estimator.set_validation_split(0.01)
estimator.set_categorical_labels(False)
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(df)
prediction = fitted_pipeline.transform(test_df)
pnl = prediction.select("label", "prediction")
pnl.show(100)
prediction_and_observations = pnl.rdd.map(lambda row:
(row.label, row.prediction))
metrics = RegressionMetrics(prediction_and_observations)
print(metrics.r2)
def test_spark_ml_model(spark_context):
df = to_data_frame(spark_context, x_train, y_train, categorical=True)
test_df = to_data_frame(spark_context, x_test, y_test, categorical=True)
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
sgd_conf = optimizers.serialize(sgd)
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
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.rdd.map(lambda row: (row.label, row.prediction))
metrics = MulticlassMetrics(prediction_and_label)
print(metrics.precision())
print(metrics.recall())
def test_custom_objects(spark_context, boston_housing_dataset):
def custom_activation(x):
return 2 * relu(x)
model = Sequential()
model.add(Dense(64, input_shape=(13, )))
model.add(Dense(64, activation=custom_activation))
model.add(Dense(1, activation='linear'))
x_train, y_train, x_test, y_test = boston_housing_dataset
df = to_data_frame(spark_context, x_train, y_train)
test_df = to_data_frame(spark_context, x_test, y_test)
sgd = optimizers.SGD(lr=0.00001)
sgd_conf = optimizers.serialize(sgd)
estimator = ElephasEstimator()
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("mae")
estimator.set_metrics(['mae'])
estimator.set_epochs(10)
estimator.set_batch_size(32)
estimator.set_validation_split(0.01)
estimator.set_categorical_labels(False)
estimator.set_custom_objects({'custom_activation': custom_activation})
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(df)
prediction = fitted_pipeline.transform(test_df)
def test_functional_model(spark_context, classification_model_functional,
mnist_data):
batch_size = 64
epochs = 1
x_train, y_train, x_test, y_test = mnist_data
x_train = x_train[:1000]
y_train = y_train[:1000]
df = to_data_frame(spark_context, x_train, y_train, categorical=True)
test_df = to_data_frame(spark_context, x_test, y_test, categorical=True)
sgd = optimizers.SGD()
sgd_conf = optimizers.serialize(sgd)
estimator = ElephasEstimator()
estimator.set_keras_model_config(classification_model_functional.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
estimator.set_validation_split(0.1)
estimator.set_categorical_labels(True)
estimator.set_nb_classes(10)
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(df)
prediction = fitted_pipeline.transform(test_df)
pnl = prediction.select("label", "prediction")
pnl.show(100)
prediction_and_label = pnl.rdd.map(lambda row: (row.label, row.prediction))
metrics = MulticlassMetrics(prediction_and_label)
print(metrics.accuracy)
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 test_spark_ml_model_classification(spark_context, classification_model,
mnist_data):
batch_size = 64
nb_classes = 10
epochs = 1
x_train, y_train, x_test, y_test = mnist_data
x_train = x_train[:1000]
y_train = y_train[:1000]
df = to_data_frame(spark_context, x_train, y_train, categorical=True)
test_df = to_data_frame(spark_context, x_test, y_test, categorical=True)
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
sgd_conf = optimizers.serialize(sgd)
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(classification_model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
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)
# since prediction in a multiclass classification problem is a vector, we need to compute argmax
# the casting to a double is just necessary for using MulticlassMetrics
pnl = pnl.select(
'label',
argmax('prediction').astype(DoubleType()).alias('prediction'))
prediction_and_label = pnl.rdd.map(lambda row: (row.label, row.prediction))
metrics = MulticlassMetrics(prediction_and_label)
print(metrics.accuracy)
def test_batch_predict_classes_probability(spark_context, classification_model,
mnist_data):
batch_size = 64
nb_classes = 10
epochs = 1
x_train, y_train, x_test, y_test = mnist_data
x_train = x_train[:1000]
y_train = y_train[:1000]
df = to_data_frame(spark_context, x_train, y_train, categorical=True)
test_df = to_data_frame(spark_context, x_test, y_test, categorical=True)
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
sgd_conf = optimizers.serialize(sgd)
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(classification_model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
estimator.set_validation_split(0.1)
estimator.set_categorical_labels(True)
estimator.set_nb_classes(nb_classes)
# Fitting a model returns a Transformer
fitted_pipeline = estimator.fit(df)
results = fitted_pipeline.transform(test_df)
# Set inference batch size and do transform again on the same test_df
inference_batch_size = int(len(y_test) / 10)
fitted_pipeline.set_params(inference_batch_size=inference_batch_size)
fitted_pipeline.set_params(outputCol="prediction_via_batch_inference")
results_with_batch_prediction = fitted_pipeline.transform(results)
# we should have an array of 10 elements in the prediction column, since we have 10 classes
# and therefore 10 probabilities
results_np = results_with_batch_prediction.take(1)[0]
assert len(results_np.prediction) == 10
assert len(results_np.prediction_via_batch_inference) == 10
assert np.array_equal(results_np.prediction,
results_np.prediction_via_batch_inference)
def test_save_pipeline(spark_context, classification_model):
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
sgd_conf = optimizers.serialize(sgd)
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(classification_model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_epochs(10)
estimator.set_batch_size(10)
estimator.set_validation_split(0.1)
estimator.set_categorical_labels(True)
estimator.set_nb_classes(10)
# Fitting a model returns a Transformer
pipeline = Pipeline(stages=[estimator])
pipeline.save('tmp')
def test_set_cols_deprecated(spark_context, regression_model,
boston_housing_dataset):
with pytest.deprecated_call():
batch_size = 64
epochs = 10
x_train, y_train, x_test, y_test = boston_housing_dataset
df = to_data_frame(spark_context, x_train, y_train)
df = df.withColumnRenamed('features', 'scaled_features')
df = df.withColumnRenamed('label', 'ground_truth')
test_df = to_data_frame(spark_context, x_test, y_test)
test_df = test_df.withColumnRenamed('features', 'scaled_features')
test_df = test_df.withColumnRenamed('label', 'ground_truth')
sgd = optimizers.SGD(lr=0.00001)
sgd_conf = optimizers.serialize(sgd)
estimator = ElephasEstimator()
estimator.set_keras_model_config(regression_model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.setFeaturesCol('scaled_features')
estimator.setOutputCol('output')
estimator.setLabelCol('ground_truth')
estimator.set_mode("synchronous")
estimator.set_loss("mae")
estimator.set_metrics(['mae'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
estimator.set_validation_split(0.01)
estimator.set_categorical_labels(False)
pipeline = Pipeline(stages=[estimator])
fitted_pipeline = pipeline.fit(df)
prediction = fitted_pipeline.transform(test_df)
pnl = prediction.select("ground_truth", "output")
pnl.show(100)
prediction_and_observations = pnl.rdd.map(
lambda row: (row['ground_truth'], row['output']))
metrics = RegressionMetrics(prediction_and_observations)
print(metrics.r2)
def test_predict_classes_probability(spark_context, classification_model,
mnist_data):
batch_size = 64
nb_classes = 10
epochs = 1
x_train, y_train, x_test, y_test = mnist_data
x_train = x_train[:1000]
y_train = y_train[:1000]
df = to_data_frame(spark_context, x_train, y_train, categorical=True)
test_df = to_data_frame(spark_context, x_test, y_test, categorical=True)
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
sgd_conf = optimizers.serialize(sgd)
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(classification_model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_predict_classes(False)
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
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)
results = fitted_pipeline.transform(test_df)
# we should have an array of 10 elements in the prediction column, since we have 10 classes
# and therefore 10 probabilities
assert len(results.take(1)[0].prediction) == 10
from elephas.ml_model import ElephasEstimator
from elephas import optimizers as elephas_optimizers
# Define elephas optimizer (which tells the model how to aggregate updates on the Spark master)
adadelta = elephas_optimizers.Adadelta()
# Initialize SparkML Estimator and set all relevant properties
estimator = ElephasEstimator()
estimator.setFeaturesCol("scaled_features") # These two come directly from pyspark,
estimator.setLabelCol("index_category") # hence the camel case. Sorry :)
estimator.set_keras_model_config(model.to_yaml()) # Provide serialized Keras model
estimator.set_optimizer_config(adadelta.get_config()) # Provide serialized Elephas optimizer
estimator.set_categorical_labels(True)
estimator.set_nb_classes(nb_classes)
estimator.set_num_workers(1) # We just use one worker here. Feel free to adapt it.
estimator.set_nb_epoch(20)
estimator.set_batch_size(128)
estimator.set_verbosity(1)
estimator.set_validation_split(0.15)
from pyspark.ml import Pipeline
pipeline = Pipeline(stages=[string_indexer, scaler, estimator])
optimizer_conf = optimizers.Adam(lr=0.01)
opt_conf = optimizers.serialize(optimizer_conf)
# 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(opt_conf)
estimator.set_mode("synchronous")
estimator.set_loss("binary_crossentropy")
estimator.set_metrics(['acc'])
# Create Deep Learning Pipeline
dl_pipeline = Pipeline(stages=[estimator])
def dl_pipeline_fit_score_results(dl_pipeline=dl_pipeline,
train_data=train_data,
test_data=test_data,
label='label_index'):
fit_dl_pipeline = dl_pipeline.fit(train_data)
pred_train = fit_dl_pipeline.transform(train_data)
pred_test = fit_dl_pipeline.transform(test_data)
model.add(Activation("relu"))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation("softmax"))
model.compile(loss="categorical_crossentropy", optimizer="adam")
# Initialize Elephas Spark ML Estimator
adadelta = elephas_optimizers.Adadelta()
estimator = ElephasEstimator()
estimator.setFeaturesCol("scaled_features")
estimator.setLabelCol("index_category")
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(adadelta.get_config())
estimator.set_nb_epoch(10)
estimator.set_batch_size(128)
estimator.set_num_workers(1)
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
# Create Spark context
conf = SparkConf().setAppName('Mnist_Spark_MLP').setMaster('local[8]')
sc = SparkContext(conf=conf)
# 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)
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
sgd_conf = optimizers.serialize(sgd)
# Initialize Spark ML Estimator
estimator = ElephasEstimator()
estimator.set_keras_model_config(model.to_yaml())
estimator.set_optimizer_config(sgd_conf)
estimator.set_mode("synchronous")
estimator.set_loss("categorical_crossentropy")
estimator.set_metrics(['acc'])
estimator.set_epochs(epochs)
estimator.set_batch_size(batch_size)
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)
# Create Spark context
conf = SparkConf().setAppName('Mnist_Spark_MLP').setMaster('local[8]')
sc = SparkContext(conf=conf)
# 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")
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
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
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
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