def test_NNEstimator_multi_input(self):
zx1 = ZLayer.Input(shape=(1, ))
zx2 = ZLayer.Input(shape=(1, ))
zz = ZLayer.merge([zx1, zx2], mode="concat")
zy = ZLayer.Dense(2)(zz)
zmodel = ZModel([zx1, zx2], zy)
criterion = MSECriterion()
df = self.get_estimator_df()
estimator = NNEstimator(zmodel, criterion, [[1], [1]]).setMaxEpoch(5) \
.setBatchSize(4)
nnmodel = estimator.fit(df)
nnmodel.transform(df).collect()
def test_NNEstimator_works_with_VectorAssembler_multi_input(self):
if self.sc.version.startswith("2"):
from pyspark.ml.linalg import Vectors
from pyspark.ml.feature import VectorAssembler
from pyspark.sql import SparkSession
spark = SparkSession \
.builder \
.getOrCreate()
df = spark.createDataFrame(
[(1, 35, 109.0, Vectors.dense([2.0, 5.0, 0.5, 0.5]), 1.0),
(2, 58, 2998.0, Vectors.dense([4.0, 10.0, 0.5, 0.5]), 2.0),
(3, 18, 123.0, Vectors.dense([3.0, 15.0, 0.5, 0.5]), 1.0)],
["user", "age", "income", "history", "label"])
assembler = VectorAssembler(
inputCols=["user", "age", "income", "history"],
outputCol="features")
df = assembler.transform(df)
x1 = ZLayer.Input(shape=(1, ))
x2 = ZLayer.Input(shape=(2, ))
x3 = ZLayer.Input(shape=(
2,
2,
))
user_embedding = ZLayer.Embedding(5, 10)(x1)
flatten = ZLayer.Flatten()(user_embedding)
dense1 = ZLayer.Dense(2)(x2)
gru = ZLayer.LSTM(4, input_shape=(2, 2))(x3)
merged = ZLayer.merge([flatten, dense1, gru], mode="concat")
zy = ZLayer.Dense(2)(merged)
zmodel = ZModel([x1, x2, x3], zy)
criterion = ClassNLLCriterion()
classifier = NNClassifier(zmodel, criterion, [[1], [2], [2, 2]]) \
.setOptimMethod(Adam()) \
.setLearningRate(0.1) \
.setBatchSize(2) \
.setMaxEpoch(10)
nnClassifierModel = classifier.fit(df)
print(nnClassifierModel.getBatchSize())
res = nnClassifierModel.transform(df).collect()
def test_nnEstimator_multiInput(self):
zx1 = ZLayer.Input(shape=(1, ))
zx2 = ZLayer.Input(shape=(1, ))
zz = ZLayer.merge([zx1, zx2], mode="concat")
zy = ZLayer.Dense(2)(zz)
zmodel = ZModel([zx1, zx2], zy)
criterion = MSECriterion()
df, _ = self.get_estimator_df()
estimator = Estimator.from_bigdl(model=zmodel,
loss=criterion,
feature_preprocessing=[[1], [1]])
estimator.fit(df, epochs=5, batch_size=4)
pred = estimator.predict(df)
pred_data = pred.collect()
assert type(pred).__name__ == 'DataFrame'
def test_merge_method_sum(self):
zx1 = ZLayer.Input(shape=(8, ))
zx2 = ZLayer.Input(shape=(6, ))
zy1 = ZLayer.Dense(10)(zx1)
zy2 = ZLayer.Dense(10)(zx2)
zz = ZLayer.merge([zy1, zy2], mode="sum")
zmodel = ZModel([zx1, zx2], zz, name="graph1")
kx1 = KLayer.Input(shape=(8, ))
kx2 = KLayer.Input(shape=(6, ))
ky1 = KLayer.Dense(10)(kx1)
ky2 = KLayer.Dense(10)(kx2)
kz = kmerge([ky1, ky2], mode="sum")
kmodel = KModel([kx1, kx2], kz)
input_data = [np.random.random([2, 8]), np.random.random([2, 6])]
self.compare_layer(kmodel, zmodel, input_data, self.convert_two_dense)
def test_nnEstimator_multiInput_cols(self):
from pyspark.ml.linalg import Vectors
from pyspark.sql import SparkSession
spark = SparkSession \
.builder \
.getOrCreate()
df = spark.createDataFrame(
[(1, 35, 109.0, Vectors.dense([2.0, 5.0, 0.5, 0.5]), 1.0),
(2, 58, 2998.0, Vectors.dense([4.0, 10.0, 0.5, 0.5]), 2.0),
(3, 18, 123.0, Vectors.dense([3.0, 15.0, 0.5, 0.5]), 1.0),
(4, 18, 123.0, Vectors.dense([3.0, 15.0, 0.5, 0.5]), 1.0)],
["user", "age", "income", "history", "label"])
x1 = ZLayer.Input(shape=(1, ))
x2 = ZLayer.Input(shape=(2, ))
x3 = ZLayer.Input(shape=(
2,
2,
))
user_embedding = ZLayer.Embedding(5, 10)(x1)
flatten = ZLayer.Flatten()(user_embedding)
dense1 = ZLayer.Dense(2)(x2)
gru = ZLayer.LSTM(4, input_shape=(2, 2))(x3)
merged = ZLayer.merge([flatten, dense1, gru], mode="concat")
zy = ZLayer.Dense(2)(merged)
zmodel = ZModel([x1, x2, x3], zy)
criterion = ClassNLLCriterion()
est = Estimator.from_bigdl(model=zmodel,
loss=criterion,
optimizer=Adam(learningrate=0.1),
feature_preprocessing=[[1], [2], [2, 2]])
est.fit(df,
epochs=1,
batch_size=4,
feature_cols=["user", "age", "income", "history"])
res = est.predict(df,
feature_cols=["user", "age", "income", "history"])
res_c = res.collect()
assert type(res).__name__ == 'DataFrame'
def test_xshards_spark_estimator_multi_inputs(self):
resource_path = os.path.join(
os.path.split(__file__)[0], "../../resources")
def transform(df):
result = {
"x": [
np.expand_dims(df['user'].to_numpy(), axis=1),
np.expand_dims(df['item'].to_numpy(), axis=1)
],
"y":
df['label'].to_numpy()
}
return result
file_path = os.path.join(resource_path, "orca/learn/ncf2.csv")
data_shard = read_csv(file_path)
data_shard = data_shard.transform_shard(transform)
zx1 = ZLayer.Input(shape=(1, ))
zx2 = ZLayer.Input(shape=(1, ))
zz = ZLayer.merge([zx1, zx2], mode="concat")
zy = ZLayer.Dense(2)(zz)
model = ZModel([zx1, zx2], zy)
optim_method = SGD(learningrate=0.01)
with tempfile.TemporaryDirectory() as temp_dir_name:
estimator = Estimator.from_bigdl(model=model,
optimizer=optim_method,
loss=ClassNLLCriterion(),
metrics=[Accuracy()],
model_dir=temp_dir_name)
estimator.set_constant_gradient_clipping(0.1, 1.2)
r1 = estimator.predict(data=data_shard)
r_c = r1.collect()
estimator.set_tensorboard(log_dir=temp_dir_name, app_name="test")
estimator.fit(data=data_shard,
epochs=5,
batch_size=8,
validation_data=data_shard,
checkpoint_trigger=EveryEpoch())
summary = estimator.get_train_summary(tag="Loss")
temp_path = os.path.join(temp_dir_name, "save_model")
estimator.save(temp_path)
eval_result = estimator.evaluate(data=data_shard, batch_size=8)
def test_merge_method_model_concat(self):
zx1 = ZLayer.Input(shape=(4, ))
zx2 = ZLayer.Input(shape=(5, ))
zy1 = ZLayer.Dense(6, activation="sigmoid")(zx1)
zbranch1 = ZModel(zx1, zy1)(zx1)
zbranch2 = ZLayer.Dense(8)(zx2)
zz = ZLayer.merge([zbranch1, zbranch2], mode="concat")
zmodel = ZModel([zx1, zx2], zz)
kx1 = KLayer.Input(shape=(4, ))
kx2 = KLayer.Input(shape=(5, ))
ky1 = KLayer.Dense(6, activation="sigmoid")(kx1)
kbranch1 = KModel(kx1, ky1)(kx1)
kbranch2 = KLayer.Dense(8)(kx2)
kz = KLayer.merge([kbranch1, kbranch2], mode="concat")
kmodel = KModel([kx1, kx2], kz)
input_data = [np.random.random([2, 4]), np.random.random([2, 5])]
self.compare_layer(kmodel, zmodel, input_data, self.convert_two_dense)
def test_merge_method_seq_concat(self):
zx1 = ZLayer.Input(shape=(10, ))
zx2 = ZLayer.Input(shape=(10, ))
zy1 = ZLayer.Dense(12, activation="sigmoid")(zx1)
zbranch1_node = ZModel(zx1, zy1)(zx1)
zbranch2 = ZSequential()
zbranch2.add(ZLayer.Dense(12, input_dim=10))
zbranch2_node = zbranch2(zx2)
zz = ZLayer.merge([zbranch1_node, zbranch2_node], mode="concat")
zmodel = ZModel([zx1, zx2], zz)
kx1 = KLayer.Input(shape=(10, ))
kx2 = KLayer.Input(shape=(10, ))
ky1 = KLayer.Dense(12, activation="sigmoid")(kx1)
kbranch1_node = KModel(kx1, ky1)(kx1)
kbranch2 = KSequential()
kbranch2.add(KLayer.Dense(12, input_dim=10))
kbranch2_node = kbranch2(kx2)
kz = KLayer.merge([kbranch1_node, kbranch2_node], mode="concat")
kmodel = KModel([kx1, kx2], kz)
input_data = [np.random.random([2, 10]), np.random.random([2, 10])]
self.compare_layer(kmodel, zmodel, input_data, self.convert_two_dense)