From d20559b157743981b9c09e286f2aaff8cbefab59 Mon Sep 17 00:00:00 2001 From: "Joseph K. Bradley" Date: Wed, 25 Feb 2015 16:13:17 -0800 Subject: [SPARK-5974] [SPARK-5980] [mllib] [python] [docs] Update ML guide with save/load, Python GBT * Add GradientBoostedTrees Python examples to ML guide * I ran these in the pyspark shell, and they worked. * Add save/load to examples in ML guide * Added note to python docs about predict,transform not working within RDD actions,transformations in some cases (See SPARK-5981) CC: mengxr Author: Joseph K. Bradley Closes #4750 from jkbradley/SPARK-5974 and squashes the following commits: c410e38 [Joseph K. Bradley] Added note to LabeledPoint about attributes bcae18b [Joseph K. Bradley] Added import of models for save/load examples in ml guide. Fixed line length for tree.py, feature.py (but not other ML Pyspark files yet). 6d81c3e [Joseph K. Bradley] completed python GBT examples 9903309 [Joseph K. Bradley] Added note to python docs about predict,transform not working within RDD actions,transformations in some cases c7dfad8 [Joseph K. Bradley] Added model save/load to ML guide. Added GBT examples to ML guide --- python/pyspark/mllib/feature.py | 67 ++++++++++++++++++++++++++--------------- 1 file changed, 42 insertions(+), 25 deletions(-) (limited to 'python/pyspark/mllib/feature.py') diff --git a/python/pyspark/mllib/feature.py b/python/pyspark/mllib/feature.py index 10df628806..0ffe092a07 100644 --- a/python/pyspark/mllib/feature.py +++ b/python/pyspark/mllib/feature.py @@ -58,7 +58,8 @@ class Normalizer(VectorTransformer): For any 1 <= `p` < float('inf'), normalizes samples using sum(abs(vector) :sup:`p`) :sup:`(1/p)` as norm. - For `p` = float('inf'), max(abs(vector)) will be used as norm for normalization. + For `p` = float('inf'), max(abs(vector)) will be used as norm for + normalization. >>> v = Vectors.dense(range(3)) >>> nor = Normalizer(1) @@ -120,9 +121,14 @@ class StandardScalerModel(JavaVectorTransformer): """ Applies standardization transformation on a vector. + Note: In Python, transform cannot currently be used within + an RDD transformation or action. + Call transform directly on the RDD instead. + :param vector: Vector or RDD of Vector to be standardized. - :return: Standardized vector. If the variance of a column is zero, - it will return default `0.0` for the column with zero variance. + :return: Standardized vector. If the variance of a column is + zero, it will return default `0.0` for the column with + zero variance. """ return JavaVectorTransformer.transform(self, vector) @@ -148,9 +154,10 @@ class StandardScaler(object): """ :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. + 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.") @@ -159,10 +166,11 @@ class StandardScaler(object): def fit(self, dataset): """ - Computes the mean and variance and stores as a model to be used for later scaling. + Computes the mean and variance and stores as a model to be used + for later scaling. - :param data: The data used to compute the mean and variance to build - the transformation model. + :param data: The data used to compute the mean and variance + to build the transformation model. :return: a StandardScalarModel """ dataset = dataset.map(_convert_to_vector) @@ -174,7 +182,8 @@ class HashingTF(object): """ .. note:: Experimental - Maps a sequence of terms to their term frequencies using the hashing trick. + Maps a sequence of terms to their term frequencies using the hashing + trick. Note: the terms must be hashable (can not be dict/set/list...). @@ -195,8 +204,9 @@ class HashingTF(object): def transform(self, document): """ - Transforms the input document (list of terms) to term frequency vectors, - or transform the RDD of document to RDD of term frequency vectors. + Transforms the input document (list of terms) to term frequency + vectors, or transform the RDD of document to RDD of term + frequency vectors. """ if isinstance(document, RDD): return document.map(self.transform) @@ -220,7 +230,12 @@ class IDFModel(JavaVectorTransformer): the terms which occur in fewer than `minDocFreq` documents will have an entry of 0. - :param x: an RDD of term frequency vectors or a term frequency vector + Note: In Python, transform cannot currently be used within + an RDD transformation or action. + Call transform directly on the RDD instead. + + :param x: an RDD of term frequency vectors or a term frequency + vector :return: an RDD of TF-IDF vectors or a TF-IDF vector """ if isinstance(x, RDD): @@ -241,9 +256,9 @@ class IDF(object): of documents that contain term `t`. This implementation supports filtering out terms which do not appear - in a minimum number of documents (controlled by the variable `minDocFreq`). - For terms that are not in at least `minDocFreq` documents, the IDF is - found as 0, resulting in TF-IDFs of 0. + in a minimum number of documents (controlled by the variable + `minDocFreq`). For terms that are not in at least `minDocFreq` + documents, the IDF is found as 0, resulting in TF-IDFs of 0. >>> n = 4 >>> freqs = [Vectors.sparse(n, (1, 3), (1.0, 2.0)), @@ -325,15 +340,16 @@ class Word2Vec(object): The vector representation can be used as features in natural language processing and machine learning algorithms. - We used skip-gram model in our implementation and hierarchical softmax - method to train the model. The variable names in the implementation - matches the original C implementation. + We used skip-gram model in our implementation and hierarchical + softmax method to train the model. The variable names in the + implementation matches the original C implementation. - For original C implementation, see https://code.google.com/p/word2vec/ + For original C implementation, + see https://code.google.com/p/word2vec/ For research papers, see Efficient Estimation of Word Representations in Vector Space - and - Distributed Representations of Words and Phrases and their Compositionality. + and Distributed Representations of Words and Phrases and their + Compositionality. >>> sentence = "a b " * 100 + "a c " * 10 >>> localDoc = [sentence, sentence] @@ -374,15 +390,16 @@ class Word2Vec(object): def setNumPartitions(self, numPartitions): """ - Sets number of partitions (default: 1). Use a small number for accuracy. + Sets number of partitions (default: 1). Use a small number for + accuracy. """ self.numPartitions = numPartitions return self def setNumIterations(self, numIterations): """ - Sets number of iterations (default: 1), which should be smaller than or equal to number of - partitions. + Sets number of iterations (default: 1), which should be smaller + than or equal to number of partitions. """ self.numIterations = numIterations return self -- cgit v1.2.3