Skip to content

Fix Spark file and cache warnings #137

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

Merged
merged 3 commits into from
Jun 5, 2019
Merged

Fix Spark file and cache warnings #137

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fa9b653
don't re-upload impls
1vn Jun 5, 2019
4d52796
remove second cache calll
1vn Jun 5, 2019
a2f3c43
rename sample_df -> transformed_df
1vn Jun 5, 2019
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
1 change: 1 addition & 0 deletions pkg/workloads/lib/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@ def __init__(self, **kwargs):
self._aggregator_impls = {}
self._model_impls = {}
self._metadatas = {}
self.spark_uploaded_impls = {}

# This affects Tensorflow S3 access
os.environ["AWS_REGION"] = self.cortex_config.get("region", "")
Expand Down
14 changes: 7 additions & 7 deletions pkg/workloads/spark_job/spark_job.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,8 +236,8 @@ def validate_transformers(spark, ctx, cols_to_transform, raw_df):
TEST_DF_SIZE = 100

logger.info("Sanity checking transformers against the first {} samples".format(TEST_DF_SIZE))
sample_df = raw_df.limit(TEST_DF_SIZE).cache()
test_df = raw_df.limit(TEST_DF_SIZE).cache()
transformed_df = raw_df.limit(TEST_DF_SIZE).cache()
test_df = raw_df.limit(TEST_DF_SIZE)

resource_list = sorted([ctx.tf_id_map[f] for f in cols_to_transform], key=lambda r: r["name"])
for transformed_column in resource_list:
Expand All @@ -257,17 +257,17 @@ def validate_transformers(spark, ctx, cols_to_transform, raw_df):
logger.info("Transforming {} to {}".format(", ".join(input_cols), tf_name))

spark_util.validate_transformer(tf_name, test_df, ctx, spark)
sample_df = spark_util.transform_column(
transformed_column["name"], sample_df, ctx, spark
transformed_df = spark_util.transform_column(
transformed_column["name"], transformed_df, ctx, spark
)

sample_df.select(tf_name).collect() # run the transformer
show_df(sample_df.select(*input_cols, tf_name), ctx, n=3, sort=False)
transformed_df.select(tf_name).collect() # run the transformer
show_df(transformed_df.select(*input_cols, tf_name), ctx, n=3, sort=False)

for alias in transformed_column["aliases"][1:]:
logger.info("Transforming {} to {}".format(", ".join(input_cols), alias))

display_transform_df = sample_df.withColumn(alias, F.col(tf_name)).select(
display_transform_df = transformed_df.withColumn(alias, F.col(tf_name)).select(
*input_cols, alias
)
show_df(display_transform_df, ctx, n=3, sort=False)
Expand Down
13 changes: 10 additions & 3 deletions pkg/workloads/spark_job/spark_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -501,7 +501,11 @@ def extract_inputs(column_name, ctx):

def execute_transform_spark(column_name, df, ctx, spark):
trans_impl, trans_impl_path = ctx.get_transformer_impl(column_name)
spark.sparkContext.addPyFile(trans_impl_path) # Executor pods need this because of the UDF

if trans_impl_path not in ctx.spark_uploaded_impls:
spark.sparkContext.addPyFile(trans_impl_path) # Executor pods need this because of the UDF
ctx.spark_uploaded_impls[trans_impl_path] = True

columns_input_config, impl_args = extract_inputs(column_name, ctx)
try:
return trans_impl.transform_spark(df, columns_input_config, impl_args, column_name)
Expand All @@ -513,8 +517,11 @@ def execute_transform_python(column_name, df, ctx, spark, validate=False):
trans_impl, trans_impl_path = ctx.get_transformer_impl(column_name)
columns_input_config, impl_args = extract_inputs(column_name, ctx)

spark.sparkContext.addPyFile(trans_impl_path) # Executor pods need this because of the UDF
# not a dictionary because it is possible that one column may map to multiple input names
if trans_impl_path not in ctx.spark_uploaded_impls:
spark.sparkContext.addPyFile(trans_impl_path) # Executor pods need this because of the UDF
# not a dictionary because it is possible that one column may map to multiple input names
ctx.spark_uploaded_impls[trans_impl_path] = True

required_columns_sorted, columns_input_config_indexed = column_names_to_index(
columns_input_config
)
Expand Down