Skip to content
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

Jump to bottom

[AIR] Remove unnecessary pandas from examples #26009

Merged
merged 2 commits into from
Jun 24, 2022
Merged

[AIR] Remove unnecessary pandas from examples #26009

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1931cf1
[AIR] Remove unnecessary pandas from examples
Yard1 Jun 22, 2022
2c8de93
Implement feedback from code review
Yard1 Jun 24, 2022
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
6 changes: 1 addition & 5 deletions doc/source/ray-air/doc_code/air_key_concepts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,11 +75,7 @@
batch_predictor = BatchPredictor.from_checkpoint(result.checkpoint, XGBoostPredictor)

# Bulk batch prediction.
predicted_labels = (
batch_predictor.predict(test_dataset)
.map_batches(lambda df: (df > 0.5).astype(int), batch_format="pandas")
.to_pandas(limit=float("inf"))
)
predicted_probabilities = batch_predictor.predict(test_dataset)

# Pipelined batch prediction: instead of processing the data in bulk, process it
# incrementally in windows of the given size.
Expand Down
24 changes: 11 additions & 13 deletions doc/source/ray-air/doc_code/preprocessors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,19 +88,17 @@
test_dataset = ray.data.from_items([{"x": x} for x in range(2, 32, 3)])

batch_predictor = BatchPredictor.from_checkpoint(checkpoint, XGBoostPredictor)
predicted_labels = batch_predictor.predict(test_dataset)
print(predicted_labels.to_pandas())
# predictions
# 0 0.098437
# 1 5.604667
# 2 11.405312
# 3 15.684700
# 4 23.990948
# 5 29.900211
# 6 34.599442
# 7 40.696899
# 8 45.681076
# 9 50.290031
predicted_probabilities = batch_predictor.predict(test_dataset)
predicted_probabilities.show()
# {'predictions': 0.09843720495700836}
# {'predictions': 5.604666709899902}
# {'predictions': 11.405311584472656}
# {'predictions': 15.684700012207031}
# {'predictions': 23.990947723388672}
# {'predictions': 29.900211334228516}
# {'predictions': 34.59944152832031}
# {'predictions': 40.6968994140625}
# {'predictions': 45.68107604980469}
# __predictor_end__


Expand Down
4 changes: 2 additions & 2 deletions doc/source/ray-air/doc_code/tf_starter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ def train_func(config: dict):

predictions = batch_predictor.predict(prediction_dataset, dtype=tf.float32)

pandas_predictions = predictions.to_pandas(float("inf"))
print("PREDICTIONS")
predictions.show()

print(f"PREDICTIONS\n{pandas_predictions}")
# __air_tf_batchpred_end__
16 changes: 5 additions & 11 deletions doc/source/ray-air/doc_code/xgboost_starter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,17 +59,11 @@

batch_predictor = BatchPredictor.from_checkpoint(result.checkpoint, XGBoostPredictor)

predicted_labels = (
batch_predictor.predict(test_dataset)
.map_batches(lambda df: (df > 0.5).astype(int), batch_format="pandas")
.to_pandas(limit=float("inf"))
)
print("PREDICTED LABELS")
print(f"{predicted_labels}")
predicted_probabilities = batch_predictor.predict(test_dataset)
print("PREDICTED PROBABILITIES")
predicted_probabilities.show()

shap_values = batch_predictor.predict(test_dataset, pred_contribs=True).to_pandas(
limit=float("inf")
)
shap_values = batch_predictor.predict(test_dataset, pred_contribs=True)
print("SHAP VALUES")
print(f"{shap_values}")
shap_values.show()
# __air_xgb_batchpred_end__
Loading