/spark_ml_pipeline
Created Jan 27, 2019
| indexer = [StringIndexer(inputCol=column_name, outputCol=column_name+"Index", handleInvalid="keep") for column_name in column_to_index] | |
| assembler = VectorAssembler(inputCols=["PclassIndex","SexIndex","Age","Fare","WithFamily","EmbarkedIndex"], outputCol="features") | |
| labelindexer = StringIndexer(inputCol="Survived", outputCol="label") | |
| sql_transformer = SQLTransformer(statement="SELECT features, label FROM __THIS__") | |
| indexer.extend([assembler, labelindexer, sql_transformer]) | |
| lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8) | |
| indexer.append(lr) | |
| pipeline = Pipeline(stages=indexer) | |
| model = pipeline.fit(trainingData) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment