Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/5596#discussion_r28745663
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
---
@@ -0,0 +1,238 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.feature
+
+import org.apache.spark.annotation.AlphaComponent
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.ml.param.{HasInputCol, ParamMap, Params, _}
+import org.apache.spark.mllib.feature
+import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
+import org.apache.spark.sql.{DataFrame, Row}
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types._
+import org.apache.spark.util.Utils
+
+/**
+ * Params for [[Word2Vec]] and [[Word2VecModel]].
+ */
+private[feature] trait Word2VecParams extends Params
+ with HasInputCol with HasMaxIter with HasLearningRate {
+
+ /**
+ * The dimension of the code that you want to transform from words.
+ */
+ val vectorSize = new IntParam(
+ this, "vectorSize", "the dimension of codes after transforming from
words", Some(100))
+
+ /** @group getParam */
+ def getVectorSize: Int = get(vectorSize)
+
+ /**
+ * Number of partitions for sentences of words.
+ */
+ val numPartitions = new IntParam(
+ this, "numPartitions", "number of partitions for sentences of words",
Some(1))
+
+ /** @group getParam */
+ def getNumPartitions: Int = get(numPartitions)
+
+ /**
+ * A random seed to random an initial vector.
+ */
+ val seed = new LongParam(
+ this, "seed", "a random seed to random an initial vector",
Some(Utils.random.nextLong()))
+
+ /** @group getParam */
+ def getSeed: Long = get(seed)
+
+ /**
+ * The minimum count of words that can be kept in training set.
--- End diff --
Sure, I'll refine it in the next commit. Thx
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
