Repository: spark Updated Branches: refs/heads/branch-1.4 6d7cf5382 -> 2790bb035
[SPARK-7918] [MLLIB] MLlib Python doc parity check for evaluation and feature Check then make the MLlib Python evaluation and feature doc to be as complete as the Scala doc. Author: Yanbo Liang <yblia...@gmail.com> Closes #6461 from yanboliang/spark-7918 and squashes the following commits: 940e3f1 [Yanbo Liang] truncate too long line and remove extra sparse a80ae58 [Yanbo Liang] MLlib Python doc parity check for evaluation and feature (cherry picked from commit 1617363fbb9b22a2eb09e7bab98c8d05f9508761) Signed-off-by: Joseph K. Bradley <jos...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2790bb03 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2790bb03 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2790bb03 Branch: refs/heads/branch-1.4 Commit: 2790bb03546fd917b1f8d597ed6ad54e1dfdc65b Parents: 6d7cf53 Author: Yanbo Liang <yblia...@gmail.com> Authored: Sat May 30 16:24:07 2015 -0700 Committer: Joseph K. Bradley <jos...@databricks.com> Committed: Sat May 30 16:24:26 2015 -0700 ---------------------------------------------------------------------- python/pyspark/mllib/evaluation.py | 26 +++++++++-------- python/pyspark/mllib/feature.py | 49 +++++++++++++++------------------ 2 files changed, 36 insertions(+), 39 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/2790bb03/python/pyspark/mllib/evaluation.py ---------------------------------------------------------------------- diff --git a/python/pyspark/mllib/evaluation.py b/python/pyspark/mllib/evaluation.py index aab5e5f..c5cf3a4 100644 --- a/python/pyspark/mllib/evaluation.py +++ b/python/pyspark/mllib/evaluation.py @@ -27,6 +27,8 @@ class BinaryClassificationMetrics(JavaModelWrapper): """ Evaluator for binary classification. + :param scoreAndLabels: an RDD of (score, label) pairs + >>> scoreAndLabels = sc.parallelize([ ... (0.1, 0.0), (0.1, 1.0), (0.4, 0.0), (0.6, 0.0), (0.6, 1.0), (0.6, 1.0), (0.8, 1.0)], 2) >>> metrics = BinaryClassificationMetrics(scoreAndLabels) @@ -38,9 +40,6 @@ class BinaryClassificationMetrics(JavaModelWrapper): """ def __init__(self, scoreAndLabels): - """ - :param scoreAndLabels: an RDD of (score, label) pairs - """ sc = scoreAndLabels.ctx sql_ctx = SQLContext(sc) df = sql_ctx.createDataFrame(scoreAndLabels, schema=StructType([ @@ -76,6 +75,9 @@ class RegressionMetrics(JavaModelWrapper): """ Evaluator for regression. + :param predictionAndObservations: an RDD of (prediction, + observation) pairs. + >>> predictionAndObservations = sc.parallelize([ ... (2.5, 3.0), (0.0, -0.5), (2.0, 2.0), (8.0, 7.0)]) >>> metrics = RegressionMetrics(predictionAndObservations) @@ -92,9 +94,6 @@ class RegressionMetrics(JavaModelWrapper): """ def __init__(self, predictionAndObservations): - """ - :param predictionAndObservations: an RDD of (prediction, observation) pairs. - """ sc = predictionAndObservations.ctx sql_ctx = SQLContext(sc) df = sql_ctx.createDataFrame(predictionAndObservations, schema=StructType([ @@ -148,6 +147,8 @@ class MulticlassMetrics(JavaModelWrapper): """ Evaluator for multiclass classification. + :param predictionAndLabels an RDD of (prediction, label) pairs. + >>> predictionAndLabels = sc.parallelize([(0.0, 0.0), (0.0, 1.0), (0.0, 0.0), ... (1.0, 0.0), (1.0, 1.0), (1.0, 1.0), (1.0, 1.0), (2.0, 2.0), (2.0, 0.0)]) >>> metrics = MulticlassMetrics(predictionAndLabels) @@ -176,9 +177,6 @@ class MulticlassMetrics(JavaModelWrapper): """ def __init__(self, predictionAndLabels): - """ - :param predictionAndLabels an RDD of (prediction, label) pairs. - """ sc = predictionAndLabels.ctx sql_ctx = SQLContext(sc) df = sql_ctx.createDataFrame(predictionAndLabels, schema=StructType([ @@ -277,6 +275,9 @@ class RankingMetrics(JavaModelWrapper): """ Evaluator for ranking algorithms. + :param predictionAndLabels: an RDD of (predicted ranking, + ground truth set) pairs. + >>> predictionAndLabels = sc.parallelize([ ... ([1, 6, 2, 7, 8, 3, 9, 10, 4, 5], [1, 2, 3, 4, 5]), ... ([4, 1, 5, 6, 2, 7, 3, 8, 9, 10], [1, 2, 3]), @@ -298,9 +299,6 @@ class RankingMetrics(JavaModelWrapper): """ def __init__(self, predictionAndLabels): - """ - :param predictionAndLabels: an RDD of (predicted ranking, ground truth set) pairs. - """ sc = predictionAndLabels.ctx sql_ctx = SQLContext(sc) df = sql_ctx.createDataFrame(predictionAndLabels, @@ -347,6 +345,10 @@ class MultilabelMetrics(JavaModelWrapper): """ Evaluator for multilabel classification. + :param predictionAndLabels: an RDD of (predictions, labels) pairs, + both are non-null Arrays, each with + unique elements. + >>> predictionAndLabels = sc.parallelize([([0.0, 1.0], [0.0, 2.0]), ([0.0, 2.0], [0.0, 1.0]), ... ([], [0.0]), ([2.0], [2.0]), ([2.0, 0.0], [2.0, 0.0]), ... ([0.0, 1.0, 2.0], [0.0, 1.0]), ([1.0], [1.0, 2.0])]) http://git-wip-us.apache.org/repos/asf/spark/blob/2790bb03/python/pyspark/mllib/feature.py ---------------------------------------------------------------------- diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py index aac305d..da90554 100644 --- a/python/pyspark/mllib/feature.py +++ b/python/pyspark/mllib/feature.py @@ -68,6 +68,8 @@ class Normalizer(VectorTransformer): For `p` = float('inf'), max(abs(vector)) will be used as norm for normalization. + :param p: Normalization in L^p^ space, p = 2 by default. + >>> v = Vectors.dense(range(3)) >>> nor = Normalizer(1) >>> nor.transform(v) @@ -82,9 +84,6 @@ class Normalizer(VectorTransformer): DenseVector([0.0, 0.5, 1.0]) """ def __init__(self, p=2.0): - """ - :param p: Normalization in L^p^ space, p = 2 by default. - """ assert p >= 1.0, "p should be greater than 1.0" self.p = float(p) @@ -94,7 +93,7 @@ class Normalizer(VectorTransformer): :param vector: vector or RDD of vector to be normalized. :return: normalized vector. If the norm of the input is zero, it - will return the input vector. + will return the input vector. """ sc = SparkContext._active_spark_context assert sc is not None, "SparkContext should be initialized first" @@ -164,6 +163,13 @@ class StandardScaler(object): variance using column summary statistics on the samples in the training set. + :param withMean: False by default. Centers the data with mean + before scaling. It will build a dense output, so this + does not work on sparse input and will raise an + exception. + :param withStd: True by default. Scales the data to unit + standard deviation. + >>> vs = [Vectors.dense([-2.0, 2.3, 0]), Vectors.dense([3.8, 0.0, 1.9])] >>> dataset = sc.parallelize(vs) >>> standardizer = StandardScaler(True, True) @@ -174,14 +180,6 @@ class StandardScaler(object): DenseVector([0.7071, -0.7071, 0.7071]) """ def __init__(self, withMean=False, withStd=True): - """ - :param withMean: False by default. Centers the data with mean - before scaling. It will build a dense output, so this - does not work on sparse input and will raise an - exception. - :param withStd: True by default. Scales the data to unit - standard deviation. - """ if not (withMean or withStd): warnings.warn("Both withMean and withStd are false. The model does nothing.") self.withMean = withMean @@ -193,7 +191,7 @@ class StandardScaler(object): for later scaling. :param data: The data used to compute the mean and variance - to build the transformation model. + to build the transformation model. :return: a StandardScalarModel """ dataset = dataset.map(_convert_to_vector) @@ -223,6 +221,8 @@ class ChiSqSelector(object): Creates a ChiSquared feature selector. + :param numTopFeatures: number of features that selector will select. + >>> data = [ ... LabeledPoint(0.0, SparseVector(3, {0: 8.0, 1: 7.0})), ... LabeledPoint(1.0, SparseVector(3, {1: 9.0, 2: 6.0})), @@ -236,9 +236,6 @@ class ChiSqSelector(object): DenseVector([5.0]) """ def __init__(self, numTopFeatures): - """ - :param numTopFeatures: number of features that selector will select. - """ self.numTopFeatures = int(numTopFeatures) def fit(self, data): @@ -246,9 +243,9 @@ class ChiSqSelector(object): Returns a ChiSquared feature selector. :param data: an `RDD[LabeledPoint]` containing the labeled dataset - with categorical features. Real-valued features will be - treated as categorical for each distinct value. - Apply feature discretizer before using this function. + with categorical features. Real-valued features will be + treated as categorical for each distinct value. + Apply feature discretizer before using this function. """ jmodel = callMLlibFunc("fitChiSqSelector", self.numTopFeatures, data) return ChiSqSelectorModel(jmodel) @@ -263,15 +260,14 @@ class HashingTF(object): Note: the terms must be hashable (can not be dict/set/list...). + :param numFeatures: number of features (default: 2^20) + >>> htf = HashingTF(100) >>> doc = "a a b b c d".split(" ") >>> htf.transform(doc) SparseVector(100, {...}) """ def __init__(self, numFeatures=1 << 20): - """ - :param numFeatures: number of features (default: 2^20) - """ self.numFeatures = numFeatures def indexOf(self, term): @@ -311,7 +307,7 @@ class IDFModel(JavaVectorTransformer): Call transform directly on the RDD instead. :param x: an RDD of term frequency vectors or a term frequency - vector + vector :return: an RDD of TF-IDF vectors or a TF-IDF vector """ if isinstance(x, RDD): @@ -342,6 +338,9 @@ class IDF(object): `minDocFreq`). For terms that are not in at least `minDocFreq` documents, the IDF is found as 0, resulting in TF-IDFs of 0. + :param minDocFreq: minimum of documents in which a term + should appear for filtering + >>> n = 4 >>> freqs = [Vectors.sparse(n, (1, 3), (1.0, 2.0)), ... Vectors.dense([0.0, 1.0, 2.0, 3.0]), @@ -362,10 +361,6 @@ class IDF(object): SparseVector(4, {1: 0.0, 3: 0.5754}) """ def __init__(self, minDocFreq=0): - """ - :param minDocFreq: minimum of documents in which a term - should appear for filtering - """ self.minDocFreq = minDocFreq def fit(self, dataset): --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org