Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/11142#discussion_r53559446
--- Diff: examples/src/main/python/mllib/tf_idf_example.py ---
@@ -0,0 +1,53 @@
+#
+# 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.
+#
+
+from __future__ import print_function
+
+from pyspark.mllib.linalg import Vectors
+# $example on$
+from pyspark import SparkContext
+from pyspark.mllib.feature import HashingTF
+from pyspark.mllib.feature import IDF
+# $example off$
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="TFIDFExample") # SparkContext
+
+ # $example on$
+ # Load documents (one per line).
+ documents = sc.textFile("data/mllib/kmeans_data.txt").map(lambda line:
line.split(" "))
+
+ hashingTF = HashingTF()
+ tf = hashingTF.transform(documents)
+
+ # While applying HashingTF only needs a single pass to the data,
+ # applying IDF needs two passes:
+ # first to compute the IDF vector and second to scale the term
frequencies by IDF.
+ tf.cache()
+ idf = IDF().fit(tf)
+ tfidf = idf.transform(tf)
+
+ # spark.mllibâs IDF implementation provides an option for ignoring
terms
--- End diff --
The `'` of `spark.mllibâs` is not an English one.
---
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]
