[SPARK-14615][ML] Use the new ML Vector and Matrix in the ML pipeline based algorithms

## What changes were proposed in this pull request?

Once SPARK-14487 and SPARK-14549 are merged, we will migrate to use the new vector and matrix type in the new ml pipeline based apis.

## How was this patch tested?

Unit tests

Author: DB Tsai <dbt@netflix.com>
Author: Liang-Chi Hsieh <simonh@tw.ibm.com>
Author: Xiangrui Meng <meng@databricks.com>

Closes #12627 from dbtsai/SPARK-14615-NewML.

1 files changed, 7 insertions, 7 deletions

diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py
index 5c11aa71b4..a1c3f72984 100644
--- a/python/pyspark/ml/classification.py
+++ b/python/pyspark/ml/classification.py
@@ -53,7 +53,7 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti
     Currently, this class only supports binary classification.
 
     >>> from pyspark.sql import Row
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> df = sc.parallelize([
     ...     Row(label=1.0, weight=2.0, features=Vectors.dense(1.0)),
     ...     Row(label=0.0, weight=2.0, features=Vectors.sparse(1, [], []))]).toDF()
@@ -496,7 +496,7 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
     It supports both binary and multiclass labels, as well as both continuous and categorical
     features.
 
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> from pyspark.ml.feature import StringIndexer
     >>> df = sqlContext.createDataFrame([
     ...     (1.0, Vectors.dense(1.0)),
@@ -625,7 +625,7 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
 
     >>> import numpy
     >>> from numpy import allclose
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> from pyspark.ml.feature import StringIndexer
     >>> df = sqlContext.createDataFrame([
     ...     (1.0, Vectors.dense(1.0)),
@@ -752,7 +752,7 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
     `SPARK-4240 <https://issues.apache.org/jira/browse/SPARK-4240>`_
 
     >>> from numpy import allclose
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> from pyspark.ml.feature import StringIndexer
     >>> df = sqlContext.createDataFrame([
     ...     (1.0, Vectors.dense(1.0)),
@@ -884,7 +884,7 @@ class NaiveBayes(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol, H
     The input feature values must be nonnegative.
 
     >>> from pyspark.sql import Row
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> df = sqlContext.createDataFrame([
     ...     Row(label=0.0, features=Vectors.dense([0.0, 0.0])),
     ...     Row(label=0.0, features=Vectors.dense([0.0, 1.0])),
@@ -1028,7 +1028,7 @@ class MultilayerPerceptronClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol,
     Number of inputs has to be equal to the size of feature vectors.
     Number of outputs has to be equal to the total number of labels.
 
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> df = sqlContext.createDataFrame([
     ...     (0.0, Vectors.dense([0.0, 0.0])),
     ...     (1.0, Vectors.dense([0.0, 1.0])),
@@ -1193,7 +1193,7 @@ class OneVsRest(Estimator, OneVsRestParams, MLReadable, MLWritable):
     is picked to label the example.
 
     >>> from pyspark.sql import Row
-    >>> from pyspark.mllib.linalg import Vectors
+    >>> from pyspark.ml.linalg import Vectors
     >>> df = sc.parallelize([
     ...     Row(label=0.0, features=Vectors.dense(1.0, 0.8)),
     ...     Row(label=1.0, features=Vectors.sparse(2, [], [])),