use vector assember in spark linear regression
vectorAssembler = VectorAssembler(inputCols = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT'], outputCol = 'features') transformed_df = vectorAssembler.transform(df) transformed_df.show()