diff options
Diffstat (limited to 'examples/src/main/python/ml/simple_text_classification_pipeline.py')
-rw-r--r-- | examples/src/main/python/ml/simple_text_classification_pipeline.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/src/main/python/ml/simple_text_classification_pipeline.py b/examples/src/main/python/ml/simple_text_classification_pipeline.py index 886f43c0b0..b528b59be9 100644 --- a/examples/src/main/python/ml/simple_text_classification_pipeline.py +++ b/examples/src/main/python/ml/simple_text_classification_pipeline.py @@ -48,7 +48,7 @@ if __name__ == "__main__": # Configure an ML pipeline, which consists of tree stages: tokenizer, hashingTF, and lr. tokenizer = Tokenizer(inputCol="text", outputCol="words") - hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features") + hashingTF = HashingTF(numFeatures=1000, inputCol=tokenizer.getOutputCol(), outputCol="features") lr = LogisticRegression(maxIter=10, regParam=0.001) pipeline = Pipeline(stages=[tokenizer, hashingTF, lr]) |