Python pyspark IDF用法及代码示例

>>> from pyspark.ml.linalg import DenseVector
>>> df = spark.createDataFrame([(DenseVector([1.0, 2.0]),),
...     (DenseVector([0.0, 1.0]),), (DenseVector([3.0, 0.2]),)], ["tf"])
>>> idf = IDF(minDocFreq=3)
>>> idf.setInputCol("tf")
IDF...
>>> idf.setOutputCol("idf")
IDF...
>>> model = idf.fit(df)
>>> model.setOutputCol("idf")
IDFModel...
>>> model.getMinDocFreq()
3
>>> model.idf
DenseVector([0.0, 0.0])
>>> model.docFreq
[0, 3]
>>> model.numDocs == df.count()
True
>>> model.transform(df).head().idf
DenseVector([0.0, 0.0])
>>> idf.setParams(outputCol="freqs").fit(df).transform(df).collect()[1].freqs
DenseVector([0.0, 0.0])
>>> params = {idf.minDocFreq: 1, idf.outputCol: "vector"}
>>> idf.fit(df, params).transform(df).head().vector
DenseVector([0.2877, 0.0])
>>> idfPath = temp_path + "/idf"
>>> idf.save(idfPath)
>>> loadedIdf = IDF.load(idfPath)
>>> loadedIdf.getMinDocFreq() == idf.getMinDocFreq()
True
>>> modelPath = temp_path + "/idf-model"
>>> model.save(modelPath)
>>> loadedModel = IDFModel.load(modelPath)
>>> loadedModel.transform(df).head().idf == model.transform(df).head().idf
True