Python pyspark CountVectorizer用法及代码示例

>>> df = spark.createDataFrame(
...    [(0, ["a", "b", "c"]), (1, ["a", "b", "b", "c", "a"])],
...    ["label", "raw"])
>>> cv = CountVectorizer()
>>> cv.setInputCol("raw")
CountVectorizer...
>>> cv.setOutputCol("vectors")
CountVectorizer...
>>> model = cv.fit(df)
>>> model.setInputCol("raw")
CountVectorizerModel...
>>> model.transform(df).show(truncate=False)
+-----+---------------+-------------------------+
|label|raw            |vectors                  |
+-----+---------------+-------------------------+
|0    |[a, b, c]      |(3,[0,1,2],[1.0,1.0,1.0])|
|1    |[a, b, b, c, a]|(3,[0,1,2],[2.0,2.0,1.0])|
+-----+---------------+-------------------------+
...
>>> sorted(model.vocabulary) == ['a', 'b', 'c']
True
>>> countVectorizerPath = temp_path + "/count-vectorizer"
>>> cv.save(countVectorizerPath)
>>> loadedCv = CountVectorizer.load(countVectorizerPath)
>>> loadedCv.getMinDF() == cv.getMinDF()
True
>>> loadedCv.getMinTF() == cv.getMinTF()
True
>>> loadedCv.getVocabSize() == cv.getVocabSize()
True
>>> modelPath = temp_path + "/count-vectorizer-model"
>>> model.save(modelPath)
>>> loadedModel = CountVectorizerModel.load(modelPath)
>>> loadedModel.vocabulary == model.vocabulary
True
>>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
True
>>> fromVocabModel = CountVectorizerModel.from_vocabulary(["a", "b", "c"],
...     inputCol="raw", outputCol="vectors")
>>> fromVocabModel.transform(df).show(truncate=False)
+-----+---------------+-------------------------+
|label|raw            |vectors                  |
+-----+---------------+-------------------------+
|0    |[a, b, c]      |(3,[0,1,2],[1.0,1.0,1.0])|
|1    |[a, b, b, c, a]|(3,[0,1,2],[2.0,2.0,1.0])|
+-----+---------------+-------------------------+
...