本文整理汇总了Python中pyspark.ml.Pipeline.save方法的典型用法代码示例。如果您正苦于以下问题:Python Pipeline.save方法的具体用法?Python Pipeline.save怎么用?Python Pipeline.save使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pyspark.ml.Pipeline
的用法示例。
在下文中一共展示了Pipeline.save方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_nested_pipeline_persistence
# 需要导入模块: from pyspark.ml import Pipeline [as 别名]
# 或者: from pyspark.ml.Pipeline import save [as 别名]
def test_nested_pipeline_persistence(self):
"""
Pipeline[HashingTF, Pipeline[PCA]]
"""
sqlContext = SQLContext(self.sc)
temp_path = tempfile.mkdtemp()
try:
df = sqlContext.createDataFrame([(["a", "b", "c"],), (["c", "d", "e"],)], ["words"])
tf = HashingTF(numFeatures=10, inputCol="words", outputCol="features")
pca = PCA(k=2, inputCol="features", outputCol="pca_features")
p0 = Pipeline(stages=[pca])
pl = Pipeline(stages=[tf, p0])
model = pl.fit(df)
pipeline_path = temp_path + "/pipeline"
pl.save(pipeline_path)
loaded_pipeline = Pipeline.load(pipeline_path)
self._compare_pipelines(pl, loaded_pipeline)
model_path = temp_path + "/pipeline-model"
model.save(model_path)
loaded_model = PipelineModel.load(model_path)
self._compare_pipelines(model, loaded_model)
finally:
try:
rmtree(temp_path)
except OSError:
pass
示例2: test_pipeline_persistence
# 需要导入模块: from pyspark.ml import Pipeline [as 别名]
# 或者: from pyspark.ml.Pipeline import save [as 别名]
def test_pipeline_persistence(self):
sqlContext = SQLContext(self.sc)
temp_path = tempfile.mkdtemp()
try:
df = sqlContext.createDataFrame([(["a", "b", "c"],), (["c", "d", "e"],)], ["words"])
tf = HashingTF(numFeatures=10, inputCol="words", outputCol="features")
pca = PCA(k=2, inputCol="features", outputCol="pca_features")
pl = Pipeline(stages=[tf, pca])
model = pl.fit(df)
pipeline_path = temp_path + "/pipeline"
pl.save(pipeline_path)
loaded_pipeline = Pipeline.load(pipeline_path)
self.assertEqual(loaded_pipeline.uid, pl.uid)
self.assertEqual(len(loaded_pipeline.getStages()), 2)
[loaded_tf, loaded_pca] = loaded_pipeline.getStages()
self.assertIsInstance(loaded_tf, HashingTF)
self.assertEqual(loaded_tf.uid, tf.uid)
param = loaded_tf.getParam("numFeatures")
self.assertEqual(loaded_tf.getOrDefault(param), tf.getOrDefault(param))
self.assertIsInstance(loaded_pca, PCA)
self.assertEqual(loaded_pca.uid, pca.uid)
self.assertEqual(loaded_pca.getK(), pca.getK())
model_path = temp_path + "/pipeline-model"
model.save(model_path)
loaded_model = PipelineModel.load(model_path)
[model_tf, model_pca] = model.stages
[loaded_model_tf, loaded_model_pca] = loaded_model.stages
self.assertEqual(model_tf.uid, loaded_model_tf.uid)
self.assertEqual(model_tf.getOrDefault(param), loaded_model_tf.getOrDefault(param))
self.assertEqual(model_pca.uid, loaded_model_pca.uid)
self.assertEqual(model_pca.pc, loaded_model_pca.pc)
self.assertEqual(model_pca.explainedVariance, loaded_model_pca.explainedVariance)
finally:
try:
rmtree(temp_path)
except OSError:
pass