How to save Linear Regression Model in PySpark 1.4.2?

Question

I am trying to save the model in PySpark 1.4.2. but getting below error

model.save(sc, modelpath)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: 'LinearRegressionModel' object has no attribute 'save'

Can you let me know where I am going wrong? Cannot figure out even in the Apache Spark 1.4.1 example

Below is my code,

>>> from pyspark.mllib.linalg import Vectors
>>> df = sqlContext.createDataFrame([
...     (1.0, Vectors.dense(1.0)),
...     (0.0, Vectors.sparse(1, [], []))], ["label", "features"])
>>> lr = LinearRegression(maxIter=5, regParam=0.0)
>>> model = lr.fit(df)
>>> model.transform(test0).head().prediction
-1.0
>>> model.weights
DenseVector([1.0])
>>> model.intercept
0.0
>>> model.save("path")
>>>model.save(sc, modelpath) --tried both got same error
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: 'LinearRegressionModel' object has no attribute 'save'
>>> modl = LinearRegression.load(path)

Last 2 lines are not working.

[Link1] (https://stackoverflow.com/questions/33027767/save-ml-model-for-future-usage#33038798) [Link2] (https://stackoverflow.com/questions/33027767/save-ml-model-for-future-usage#33038798) — Morse, Mar 12 '18 at 20:10
you cannot see your saved model also? For loading, load through LinearRegressionModel and not LinearRegression. — mayank agrawal, Mar 13 '18 at 10:31
@mayankagrawal when i am saving the model i am getting below error model.save(sc, modelpath) Traceback (most recent call last): File "", line 1, in AttributeError: 'LinearRegressionModel' object has no attribute 'save' — user3422413, Mar 13 '18 at 17:16
**save** is not implemented in that version . Please check other questions I have linked — Morse, Mar 14 '18 at 20:47
@Prateek thanks , yes save is not implemented in that version — user3422413, Mar 30 '18 at 02:12

How to save Linear Regression Model in PySpark 1.4.2?

0 Answers0