diff options
author | Davies Liu <davies@databricks.com> | 2014-11-10 22:26:16 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2014-11-10 22:26:25 -0800 |
commit | df8242c9b6307c085d4c1a7ec446b1701a7e7cde (patch) | |
tree | 4d144b6278dcf3a0d96cbd9929227ec6efb2c3ff /python/pyspark/mllib/classification.py | |
parent | 4eeaf3395a885b0a9ef79c31b720969155b0b7af (diff) | |
download | spark-df8242c9b6307c085d4c1a7ec446b1701a7e7cde.tar.gz spark-df8242c9b6307c085d4c1a7ec446b1701a7e7cde.tar.bz2 spark-df8242c9b6307c085d4c1a7ec446b1701a7e7cde.zip |
[SPARK-4324] [PySpark] [MLlib] support numpy.array for all MLlib API
This PR check all of the existing Python MLlib API to make sure that numpy.array is supported as Vector (also RDD of numpy.array).
It also improve some docstring and doctest.
cc mateiz mengxr
Author: Davies Liu <davies@databricks.com>
Closes #3189 from davies/numpy and squashes the following commits:
d5057c4 [Davies Liu] fix tests
6987611 [Davies Liu] support numpy.array for all MLlib API
(cherry picked from commit 65083e93ddd552b7d3e4eb09f87c091ef2ae83a2)
Signed-off-by: Xiangrui Meng <meng@databricks.com>
Diffstat (limited to 'python/pyspark/mllib/classification.py')
-rw-r--r-- | python/pyspark/mllib/classification.py | 13 |
1 files changed, 8 insertions, 5 deletions
diff --git a/python/pyspark/mllib/classification.py b/python/pyspark/mllib/classification.py index 297a2bf37d..5d90dddb5d 100644 --- a/python/pyspark/mllib/classification.py +++ b/python/pyspark/mllib/classification.py @@ -62,6 +62,7 @@ class LogisticRegressionModel(LinearModel): """ def predict(self, x): + x = _convert_to_vector(x) margin = self.weights.dot(x) + self._intercept if margin > 0: prob = 1 / (1 + exp(-margin)) @@ -79,7 +80,7 @@ class LogisticRegressionWithSGD(object): """ Train a logistic regression model on the given data. - :param data: The training data. + :param data: The training data, an RDD of LabeledPoint. :param iterations: The number of iterations (default: 100). :param step: The step parameter used in SGD (default: 1.0). @@ -136,6 +137,7 @@ class SVMModel(LinearModel): """ def predict(self, x): + x = _convert_to_vector(x) margin = self.weights.dot(x) + self.intercept return 1 if margin >= 0 else 0 @@ -148,7 +150,7 @@ class SVMWithSGD(object): """ Train a support vector machine on the given data. - :param data: The training data. + :param data: The training data, an RDD of LabeledPoint. :param iterations: The number of iterations (default: 100). :param step: The step parameter used in SGD (default: 1.0). @@ -233,11 +235,12 @@ class NaiveBayes(object): classification. By making every vector a 0-1 vector, it can also be used as Bernoulli NB (U{http://tinyurl.com/p7c96j6}). - :param data: RDD of NumPy vectors, one per element, where the first - coordinate is the label and the rest is the feature vector - (e.g. a count vector). + :param data: RDD of LabeledPoint. :param lambda_: The smoothing parameter """ + first = data.first() + if not isinstance(first, LabeledPoint): + raise ValueError("`data` should be an RDD of LabeledPoint") labels, pi, theta = callMLlibFunc("trainNaiveBayes", data, lambda_) return NaiveBayesModel(labels.toArray(), pi.toArray(), numpy.array(theta)) |