Skip to content

Commit

Permalink
Fix diabetes example memory limit (#137)
Browse files Browse the repository at this point in the history
Signed-off-by: Ketan Umare <[email protected]>
  • Loading branch information
wild-endeavor authored and kumare3 committed Mar 23, 2021
1 parent 8390a42 commit 07495e9
Show file tree
Hide file tree
Showing 6 changed files with 23 additions and 13 deletions.
10 changes: 5 additions & 5 deletions cookbook/case_studies/pima_diabetes/diabetes.py
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
import joblib
import pandas as pd
from dataclasses_json import dataclass_json
from flytekit import task, workflow
from flytekit import Resources, task, workflow
from flytekit.types.file import FlyteFile
from flytekit.types.schema import FlyteSchema
from sklearn.metrics import accuracy_score
Expand Down Expand Up @@ -63,7 +63,7 @@
# columns and converts it to a typed schema.
# An example CSV file is available at
# `https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv<https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv>`
@task(cache_version="1.0", cache=True, memory_limit="200Mi")
@task(cache_version="1.0", cache=True, limits=Resources(mem="200Mi"))
def split_traintest_dataset(
dataset: FlyteFile[typing.TypeVar("csv")], seed: int, test_split_ratio: float
) -> (
Expand Down Expand Up @@ -121,7 +121,7 @@ class XGBoostModelHyperparams(object):
)


@task(cache_version="1.0", cache=True, memory_limit="200Mi")
@task(cache_version="1.0", cache=True, limits=Resources(mem="200Mi"))
def fit(
x: FlyteSchema[FEATURE_COLUMNS],
y: FlyteSchema[CLASSES_COLUMNS],
Expand Down Expand Up @@ -151,7 +151,7 @@ def fit(
return (fname,)


@task(cache_version="1.0", cache=True, memory_limit="200Mi")
@task(cache_version="1.0", cache=True, limits=Resources(mem="200Mi"))
def predict(
x: FlyteSchema[FEATURE_COLUMNS], model_ser: FlyteFile[MODELSER_JOBLIB],
) -> FlyteSchema[CLASSES_COLUMNS]:
Expand All @@ -170,7 +170,7 @@ def predict(
return y_pred_df


@task(cache_version="1.0", cache=True, memory_limit="200Mi")
@task(cache_version="1.0", cache=True, limits=Resources(mem="200Mi"))
def score(
predictions: FlyteSchema[CLASSES_COLUMNS], y: FlyteSchema[CLASSES_COLUMNS]
) -> float:
Expand Down
4 changes: 3 additions & 1 deletion cookbook/core/intermediate/map_task.py
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,9 @@
"""

import typing
from flytekit import task, workflow, map_task, TaskMetadata

from flytekit import TaskMetadata, map_task, task, workflow


# %%
# Note that this is the single task that we'll use in our map task. It can only accept one input and produce one output
Expand Down
8 changes: 6 additions & 2 deletions cookbook/docs/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,14 +6,14 @@

# -- Path setup --------------------------------------------------------------

import re
import logging

# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
#
import os
import re
import sys

from sphinx_gallery.sorting import ExplicitOrder, FileNameSortKey
Expand Down Expand Up @@ -157,7 +157,11 @@ def __call__(self, filename):
"nav_links": [
{"href": "https://flyte.readthedocs.io/", "internal": False, "title": "Flyte"},
{"href": "index", "internal": True, "title": "Tutorials"},
{"href": "https://flytekit.readthedocs.io/en/latest/", "internal": False, "title": "Flytekit Python Reference"},
{
"href": "https://flytekit.readthedocs.io/en/latest/",
"internal": False,
"title": "Flytekit Python Reference",
},
],
}

Expand Down
2 changes: 1 addition & 1 deletion cookbook/plugins/k8s_spark/dataframe_passing.py
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ def create_spark_df() -> my_schema:
"""
sess = flytekit.current_context().spark_session
return sess.createDataFrame(
[("Alice", 5), ("Bob", 10), ("Charlie", 15), ], my_schema.column_names(),
[("Alice", 5), ("Bob", 10), ("Charlie", 15),], my_schema.column_names(),
)


Expand Down
8 changes: 6 additions & 2 deletions cookbook/plugins/papermilltasks/simple.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,9 @@
# The example task is shown below
nb = NotebookTask(
name="simple-nb",
notebook_path=os.path.join(pathlib.Path(__file__).parent.absolute(), "nb-simple.ipynb"),
notebook_path=os.path.join(
pathlib.Path(__file__).parent.absolute(), "nb-simple.ipynb"
),
inputs=kwtypes(v=float),
outputs=kwtypes(square=float),
)
Expand All @@ -47,13 +49,15 @@
def square_root_task(f: float) -> float:
return math.sqrt(f)


#%%
# You can now treat the notebook task as a regular task
@workflow
def nb_to_python_wf(f: float) -> float:
out = nb(v=f)
return square_root_task(f=out.square)


#%%
# You can execute the task locally as well
if __name__ == "__main__":
Expand All @@ -64,4 +68,4 @@ def nb_to_python_wf(f: float) -> float:
# ^^^^^^^^^^^^^^^^^^
# On executing you should see 3 outputs instead of the expected one. This is because this task generates 2 implicit outputs.
# One of them is the executed notebook (captured) and a rendered (HTML) of the executed notebook. In this case they are called
# ``nb-simple-out.ipynb`` and ``nb-simple-out.html`` respectively
# ``nb-simple-out.ipynb`` and ``nb-simple-out.html`` respectively
4 changes: 2 additions & 2 deletions cookbook/plugins/pod/pod.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,11 +29,11 @@
from flytekitplugins.pod import Pod
from kubernetes.client.models import (
V1Container,
V1EmptyDirVolumeSource,
V1PodSpec,
V1VolumeMount,
V1ResourceRequirements,
V1Volume,
V1EmptyDirVolumeSource,
V1VolumeMount,
)

_SHARED_DATA_PATH = "/data/message.txt"
Expand Down

0 comments on commit 07495e9

Please sign in to comment.