diff options
| author | Yanbo Liang <ybliang8@gmail.com> | 2015-07-23 18:53:07 -0700 |
|---|---|---|
| committer | Joseph K. Bradley <joseph@databricks.com> | 2015-07-23 18:53:07 -0700 |
| commit | 52de3acca4ce8c36fd4c9ce162473a091701bbc7 (patch) | |
| tree | 8029f2ff75e519e05c2a1894e1b6752578f0ca2d /python | |
| parent | 8a94eb23d53e291441e3144a1b800fe054457040 (diff) | |
| download | spark-52de3acca4ce8c36fd4c9ce162473a091701bbc7.tar.gz spark-52de3acca4ce8c36fd4c9ce162473a091701bbc7.tar.bz2 spark-52de3acca4ce8c36fd4c9ce162473a091701bbc7.zip | |
[SPARK-9122] [MLLIB] [PySpark] spark.mllib regression support batch predict
spark.mllib support batch predict for LinearRegressionModel, RidgeRegressionModel and LassoModel.
Author: Yanbo Liang <ybliang8@gmail.com>
Closes #7614 from yanboliang/spark-9122 and squashes the following commits:
4e610c0 [Yanbo Liang] spark.mllib regression support batch predict
Diffstat (limited to 'python')
| -rw-r--r-- | python/pyspark/mllib/regression.py | 12 |
1 files changed, 10 insertions, 2 deletions
diff --git a/python/pyspark/mllib/regression.py b/python/pyspark/mllib/regression.py index 8e90adee5f..5b7afc15dd 100644 --- a/python/pyspark/mllib/regression.py +++ b/python/pyspark/mllib/regression.py @@ -97,9 +97,11 @@ class LinearRegressionModelBase(LinearModel): def predict(self, x): """ - Predict the value of the dependent variable given a vector x - containing values for the independent variables. + Predict the value of the dependent variable given a vector or + an RDD of vectors containing values for the independent variables. """ + if isinstance(x, RDD): + return x.map(self.predict) x = _convert_to_vector(x) return self.weights.dot(x) + self.intercept @@ -124,6 +126,8 @@ class LinearRegressionModel(LinearRegressionModelBase): True >>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5 True + >>> abs(lrm.predict(sc.parallelize([[1.0]])).collect()[0] - 1) < 0.5 + True >>> import os, tempfile >>> path = tempfile.mkdtemp() >>> lrm.save(sc, path) @@ -267,6 +271,8 @@ class LassoModel(LinearRegressionModelBase): True >>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5 True + >>> abs(lrm.predict(sc.parallelize([[1.0]])).collect()[0] - 1) < 0.5 + True >>> import os, tempfile >>> path = tempfile.mkdtemp() >>> lrm.save(sc, path) @@ -382,6 +388,8 @@ class RidgeRegressionModel(LinearRegressionModelBase): True >>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5 True + >>> abs(lrm.predict(sc.parallelize([[1.0]])).collect()[0] - 1) < 0.5 + True >>> import os, tempfile >>> path = tempfile.mkdtemp() >>> lrm.save(sc, path) |