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 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 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_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
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())
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)
optimizer='rmsprop',
metrics=['accuracy'])
# 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("features") # These two come directly from pyspark,
estimator.setLabelCol("label") # 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(2)
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)
fitted_model = estimator.fit(train_df)
prediction = fitted_model.transform(test_df)
pnl = prediction.select("label", "prediction")
pnl.show(100)
#from pyspark.ml import Pipeline
#pipeline = Pipeline(stages=[estimator])
