spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Yunni <...@git.apache.org>
Subject [GitHub] spark pull request #16715: [Spark-18080][ML][PYTHON] Python API & Examples f...
Date Tue, 28 Feb 2017 02:07:48 GMT
Github user Yunni commented on a diff in the pull request:

    https://github.com/apache/spark/pull/16715#discussion_r103361528
  
    --- Diff: python/pyspark/ml/feature.py ---
    @@ -120,6 +122,196 @@ def getThreshold(self):
             return self.getOrDefault(self.threshold)
     
     
    +class LSHParams(Params):
    +    """
    +    Mixin for Locality Sensitive Hashing (LSH) algorithm parameters.
    +    """
    +
    +    numHashTables = Param(Params._dummy(), "numHashTables", "number of hash tables, where
" +
    +                          "increasing number of hash tables lowers the false negative
rate, " +
    +                          "and decreasing it improves the running performance.",
    +                          typeConverter=TypeConverters.toInt)
    +
    +    def __init__(self):
    +        super(LSHParams, self).__init__()
    +
    +    def setNumHashTables(self, value):
    +        """
    +        Sets the value of :py:attr:`numHashTables`.
    +        """
    +        return self._set(numHashTables=value)
    +
    +    def getNumHashTables(self):
    +        """
    +        Gets the value of numHashTables or its default value.
    +        """
    +        return self.getOrDefault(self.numHashTables)
    +
    +
    +class LSHModel(JavaModel):
    +    """
    +    Mixin for Locality Sensitive Hashing (LSH) models.
    +    """
    +
    +    def approxNearestNeighbors(self, dataset, key, numNearestNeighbors, distCol="distCol"):
    +        """
    +        Given a large dataset and an item, approximately find at most k items which have
the
    +        closest distance to the item. If the :py:attr:`outputCol` is missing, the method
will
    +        transform the data; if the :py:attr:`outputCol` exists, it will use that. This
allows
    +        caching of the transformed data when necessary.
    +
    +        .. note:: This method is experimental and will likely change behavior in the
next release.
    +
    +        :param dataset: The dataset to search for nearest neighbors of the key.
    +        :param key: Feature vector representing the item to search for.
    +        :param numNearestNeighbors: The maximum number of nearest neighbors.
    +        :param distCol: Output column for storing the distance between each result row
and the key.
    +                        Use "distCol" as default value if it's not specified.
    +        :return: A dataset containing at most k items closest to the key. A column "distCol"
is
    +                 added to show the distance between each row and the key.
    +        """
    +        return self._call_java("approxNearestNeighbors", dataset, key, numNearestNeighbors,
    +                               distCol)
    +
    +    def approxSimilarityJoin(self, datasetA, datasetB, threshold, distCol="distCol"):
    +        """
    +        Join two datasets to approximately find all pairs of rows whose distance are
smaller than
    +        the threshold. If the :py:attr:`outputCol` is missing, the method will transform
the data;
    +        if the :py:attr:`outputCol` exists, it will use that. This allows caching of
the
    +        transformed data when necessary.
    +
    +        :param datasetA: One of the datasets to join.
    +        :param datasetB: Another dataset to join.
    +        :param threshold: The threshold for the distance of row pairs.
    +        :param distCol: Output column for storing the distance between each pair of rows.
Use
    +                        "distCol" as default value if it's not specified.
    +        :return: A joined dataset containing pairs of rows. The original rows are in
columns
    +                 "datasetA" and "datasetB", and a column "distCol" is added to show the
distance
    +                 between each pair.
    +        """
    +        return self._call_java("approxSimilarityJoin", datasetA, datasetB, threshold,
distCol)
    +
    +
    +@inherit_doc
    +class BucketedRandomProjectionLSH(JavaEstimator, LSHParams, HasInputCol, HasOutputCol,
HasSeed,
    +                                  JavaMLReadable, JavaMLWritable):
    +    """
    +    .. note:: Experimental
    +
    +    LSH class for Euclidean distance metrics.
    +    The input is dense or sparse vectors, each of which represents a point in the Euclidean
    +    distance space. The output will be vectors of configurable dimension. Hash values
in the same
    +    dimension are calculated by the same hash function.
    +
    +    .. seealso:: `Stable Distributions \
    +    <https://en.wikipedia.org/wiki/Locality-sensitive_hashing#Stable_distributions>`_
    +    .. seealso:: `Hashing for Similarity Search: A Survey <https://arxiv.org/abs/1408.2927>`_
    +
    +    >>> from pyspark.ml.linalg import Vectors
    +    >>> from pyspark.sql.functions import col
    +    >>> data = [(0, Vectors.dense([-1.0, -1.0 ]),),
    +    ...         (1, Vectors.dense([-1.0, 1.0 ]),),
    +    ...         (2, Vectors.dense([1.0, -1.0 ]),),
    +    ...         (3, Vectors.dense([1.0, 1.0]),)]
    +    >>> df = spark.createDataFrame(data, ["id", "features"])
    +    >>> brp = BucketedRandomProjectionLSH(inputCol="features", outputCol="hashes",
    +    ...                                   seed=12345, bucketLength=1.0)
    +    >>> model = brp.fit(df)
    +    >>> model.transform(df).head()
    +    Row(id=0, features=DenseVector([-1.0, -1.0]), hashes=[DenseVector([-1.0])])
    +    >>> data2 = [(4, Vectors.dense([2.0, 2.0 ]),),
    +    ...          (5, Vectors.dense([2.0, 3.0 ]),),
    +    ...          (6, Vectors.dense([3.0, 2.0 ]),),
    +    ...          (7, Vectors.dense([3.0, 3.0]),)]
    +    >>> df2 = spark.createDataFrame(data2, ["id", "features"])
    +    >>> model.approxNearestNeighbors(df2, Vectors.dense([1.0, 2.0]), 1).collect()
    +    [Row(id=4, features=DenseVector([2.0, 2.0]), hashes=[DenseVector([1.0])], distCol=1.0)]
    +    >>> model.approxSimilarityJoin(df, df2, 3.0, distCol="EuclideanDistance").select(
    +    ...     col("datasetA.id").alias("idA"),
    +    ...     col("datasetB.id").alias("idB"),
    +    ...     col("EuclideanDistance")).show()
    +    +---+---+-----------------+
    +    |idA|idB|EuclideanDistance|
    +    +---+---+-----------------+
    +    |  3|  6| 2.23606797749979|
    +    +---+---+-----------------+
    +    ...
    +    >>> brpPath = temp_path + "/brp"
    +    >>> brp.save(brpPath)
    +    >>> brp2 = BucketedRandomProjectionLSH.load(brpPath)
    +    >>> brp2.getBucketLength() == brp.getBucketLength()
    +    True
    +    >>> modelPath = temp_path + "/brp-model"
    +    >>> model.save(modelPath)
    +    >>> model2 = BucketedRandomProjectionLSHModel.load(modelPath)
    +    >>> model.transform(df).head().hashes == model2.transform(df).head().hashes
    +    True
    +
    +    .. versionadded:: 2.2.0
    +    """
    +
    +    bucketLength = Param(Params._dummy(), "bucketLength", "the length of each hash bucket,
" +
    +                         "a larger bucket lowers the false negative rate.",
    +                         typeConverter=TypeConverters.toFloat)
    +
    +    @keyword_only
    +    def __init__(self, inputCol=None, outputCol=None, seed=None, numHashTables=1,
    +                 bucketLength=None):
    +        """
    +        __init__(self, inputCol=None, outputCol=None, seed=None, numHashTables=1,
    --- End diff --
    
    Sure. Will do.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message