Python ml.Model方法代码示例

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def test_java_params(self):
        import pyspark.ml.feature
        import pyspark.ml.classification
        import pyspark.ml.clustering
        import pyspark.ml.evaluation
        import pyspark.ml.pipeline
        import pyspark.ml.recommendation
        import pyspark.ml.regression

        modules = [pyspark.ml.feature, pyspark.ml.classification, pyspark.ml.clustering,
                   pyspark.ml.evaluation, pyspark.ml.pipeline, pyspark.ml.recommendation,
                   pyspark.ml.regression]
        for module in modules:
            for name, cls in inspect.getmembers(module, inspect.isclass):
                if not name.endswith('Model') and not name.endswith('Params')\
                        and issubclass(cls, JavaParams) and not inspect.isabstract(cls):
                    # NOTE: disable check_params_exist until there is parity with Scala API
                    ParamTests.check_params(self, cls(), check_params_exist=False)

        # Additional classes that need explicit construction
        from pyspark.ml.feature import CountVectorizerModel, StringIndexerModel
        ParamTests.check_params(self, CountVectorizerModel.from_vocabulary(['a'], 'input'),
                                check_params_exist=False)
        ParamTests.check_params(self, StringIndexerModel.from_labels(['a', 'b'], 'input'),
                                check_params_exist=False) 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def _make_java_param_pair(self, param, value):
        """
        Makes a Java param pair.
        """
        sc = SparkContext._active_spark_context
        param = self._resolveParam(param)
        _java_obj = JavaParams._new_java_obj("org.apache.spark.ml.classification.OneVsRest",
                                             self.uid)
        java_param = _java_obj.getParam(param.name)
        if isinstance(value, JavaParams):
            # used in the case of an estimator having another estimator as a parameter
            # the reason why this is not in _py2java in common.py is that importing
            # Estimator and Model in common.py results in a circular import with inherit_doc
            java_value = value._to_java()
        else:
            java_value = _py2java(sc, value)
        return java_param.w(java_value) 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def test_idf(self):
        dataset = self.spark.createDataFrame([
            (DenseVector([1.0, 2.0]),),
            (DenseVector([0.0, 1.0]),),
            (DenseVector([3.0, 0.2]),)], ["tf"])
        idf0 = IDF(inputCol="tf")
        self.assertListEqual(idf0.params, [idf0.inputCol, idf0.minDocFreq, idf0.outputCol])
        idf0m = idf0.fit(dataset, {idf0.outputCol: "idf"})
        self.assertEqual(idf0m.uid, idf0.uid,
                         "Model should inherit the UID from its parent estimator.")
        output = idf0m.transform(dataset)
        self.assertIsNotNone(output.head().idf)
        # Test that parameters transferred to Python Model
        ParamTests.check_params(self, idf0m) 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def coefficients(self):
        """
        Model coefficients of Linear SVM Classifier.
        """
        return self._call_java("coefficients") 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def intercept(self):
        """
        Model intercept of Linear SVM Classifier.
        """
        return self._call_java("intercept") 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def coefficientMatrix(self):
        """
        Model coefficients.
        """
        return self._call_java("coefficientMatrix") 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def interceptVector(self):
        """
        Model intercept.
        """
        return self._call_java("interceptVector") 

# 需要导入模块: from pyspark import ml [as 别名]
# 或者: from pyspark.ml import Model [as 别名]
def _validate_model(spark_model):
    from pyspark.ml.util import MLReadable, MLWritable
    from pyspark.ml import Model as PySparkModel
    if not isinstance(spark_model, PySparkModel) \
            or not isinstance(spark_model, MLReadable) \
            or not isinstance(spark_model, MLWritable):
        raise MlflowException(
            "Cannot serialize this model. MLflow can only save descendants of pyspark.Model"
            "that implement MLWritable and MLReadable.",
            INVALID_PARAMETER_VALUE)