Skip to content

[SPARK-20861][ML][PYTHON] Delegate looping over paramMaps to estimators #18077

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
MrBago wants to merge 1 commit into from
Closed

[SPARK-20861][ML][PYTHON] Delegate looping over paramMaps to estimators #18077

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions python/pyspark/ml/tuning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,14 +18,11 @@
import itertools
import numpy as np

from pyspark import SparkContext
from pyspark import since, keyword_only
from pyspark.ml import Estimator, Model
from pyspark.ml.param import Params, Param, TypeConverters
from pyspark.ml.param.shared import HasSeed
from pyspark.ml.wrapper import JavaParams
from pyspark.sql.functions import rand
from pyspark.ml.common import inherit_doc, _py2java

__all__ = ['ParamGridBuilder', 'CrossValidator', 'CrossValidatorModel', 'TrainValidationSplit',
'TrainValidationSplitModel']
Expand Down Expand Up @@ -232,8 +229,9 @@ def _fit(self, dataset):
condition = (df[randCol] >= validateLB) & (df[randCol] < validateUB)
validation = df.filter(condition)
train = df.filter(~condition)
models = est.fit(train, epm)
for j in range(numModels):
model = est.fit(train, epm[j])
model = models[j]
# TODO: duplicate evaluator to take extra params from input
metric = eva.evaluate(model.transform(validation, epm[j]))
metrics[j] += metric/nFolds
Expand Down Expand Up @@ -388,8 +386,9 @@ def _fit(self, dataset):
condition = (df[randCol] >= tRatio)
validation = df.filter(condition)
train = df.filter(~condition)
models = est.fit(train, epm)
for j in range(numModels):
model = est.fit(train, epm[j])
model = models[j]
metric = eva.evaluate(model.transform(validation, epm[j]))
metrics[j] += metric
if eva.isLargerBetter():
Expand Down