From dda9065a88b604b1c2ccf8e163d5289cbe328d5e Mon Sep 17 00:00:00 2001 From: quandanrepo <45804868+quandanrepo@users.noreply.github.com> Date: Tue, 10 Oct 2023 11:45:50 +0100 Subject: [PATCH 1/5] Update README.md --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 5879c41..6a63c61 100644 --- a/README.md +++ b/README.md @@ -81,4 +81,8 @@ To test the Lambda function, use the following curl command: ```json curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/model_build_data/change_data/rdsap_full/test_data_with_id.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"' ``` + +```json +curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/model_build_data/change_data/rdsap_full/test_data_with_id.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"}' +``` This will send a POST request to the running Lambda function and pass in the required data as JSON. From d3b1bb4bb9bf03a1d5708e1c4f77642d4e33112a Mon Sep 17 00:00:00 2001 From: quandanrepo <45804868+quandanrepo@users.noreply.github.com> Date: Tue, 10 Oct 2023 11:49:37 +0100 Subject: [PATCH 2/5] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6a63c61..a37f5fb 100644 --- a/README.md +++ b/README.md @@ -83,6 +83,6 @@ curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d ``` ```json -curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/model_build_data/change_data/rdsap_full/test_data_with_id.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"}' +curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/sap_change_model/dataset.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"}' ``` This will send a POST request to the running Lambda function and pass in the required data as JSON. From 391cc6643591c4eeb1dd516d4d0465d0b9ea817a Mon Sep 17 00:00:00 2001 From: quandanrepo <45804868+quandanrepo@users.noreply.github.com> Date: Tue, 10 Oct 2023 11:53:52 +0100 Subject: [PATCH 3/5] Update README.md --- README.md | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/README.md b/README.md index a37f5fb..7f018ad 100644 --- a/README.md +++ b/README.md @@ -79,10 +79,7 @@ Sets the RUNTIME_ENVIRONMENT variable to dev. To test the Lambda function, use the following curl command: ```json -curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/model_build_data/change_data/rdsap_full/test_data_with_id.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"' +curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/sap_change_model/one_sample_test_dataset.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"}' ``` -```json -curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/sap_change_model/dataset.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"}' -``` This will send a POST request to the running Lambda function and pass in the required data as JSON. From 70b3008dc5f19214cecbbec377c53529cadd428d Mon Sep 17 00:00:00 2001 From: quandanrepo <45804868+quandanrepo@users.noreply.github.com> Date: Tue, 10 Oct 2023 11:56:56 +0100 Subject: [PATCH 4/5] Update README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 7f018ad..55cae8e 100644 --- a/README.md +++ b/README.md @@ -31,7 +31,7 @@ In order for this to be set up, some key environment variables needs to be inser secrets. Each different model and protected branch has its own set of secrets which allows for flexibility between different pipelines. -For example, for the branch sap_change-dev, the prefix=SAP_CHANGE_DEV, and the following secrets are: +For example, for the branch sap-dev, the prefix=SAP_DEV, and the following secrets are: - {prefix}_ECR_URI, which is the URI of the ECR repository to push to. For example, for the sap change model this is the lambda-sap-prediction-dev repository. @@ -58,7 +58,7 @@ First, navigate to the root directory of the repository. Open a terminal and exe 2. command to build the Docker image: ```bash -docker build -t sap_change -f deployment/Dockerfile.prediction.lambda . +docker build -t sap -f deployment/Dockerfile.prediction.lambda . ``` This will build a Docker image tagged as sap_change using the Dockerfile.prediction.lambda located @@ -68,7 +68,7 @@ in the deployment directory. Once the image is built, you can run it using the following command: ```bash -docker run -p 9000:8080 -v ~/.aws/credentials:/root/.aws/credentials:ro -e RUNTIME_ENVIRONMENT=dev sap_change +docker run -p 9000:8080 -v ~/.aws/credentials:/root/.aws/credentials:ro -e RUNTIME_ENVIRONMENT=dev -e PREDICTIONS_BUCKET=retrofit-sap-predictions-dev sap ``` This command does the following: From 57934d0ae37daf61d67534a2671eda318659ba45 Mon Sep 17 00:00:00 2001 From: Michael Duong Date: Tue, 10 Oct 2023 12:35:34 +0100 Subject: [PATCH 5/5] fixed buffer bug and add id --- deployment/handlers/prediction_app.py | 1 + .../ml-pipeline/src/pipeline/configs/settings.yaml | 1 + modules/ml-pipeline/src/pipeline/core/DataClient.py | 6 ++++++ .../ml-pipeline/src/pipeline/generate_predictions.py | 11 +++++++++-- 4 files changed, 17 insertions(+), 2 deletions(-) diff --git a/deployment/handlers/prediction_app.py b/deployment/handlers/prediction_app.py index 6f9d162..36a906c 100644 --- a/deployment/handlers/prediction_app.py +++ b/deployment/handlers/prediction_app.py @@ -107,6 +107,7 @@ def handler(event, context): predictions_column_name=generate_predictions_params[ "predictions_column_name" ], + identifier_column=generate_predictions_params["identifier_column"], ) return { diff --git a/modules/ml-pipeline/src/pipeline/configs/settings.yaml b/modules/ml-pipeline/src/pipeline/configs/settings.yaml index a84c095..ce7ed2c 100644 --- a/modules/ml-pipeline/src/pipeline/configs/settings.yaml +++ b/modules/ml-pipeline/src/pipeline/configs/settings.yaml @@ -43,6 +43,7 @@ default: test_data_filepath: ./data/prepared_data/test.parquet predictions_output_filepath: ./data/predictions/predictions.parquet predictions_column_name: predictions + identifier_column: id generate_metrics: dataclient_type: local diff --git a/modules/ml-pipeline/src/pipeline/core/DataClient.py b/modules/ml-pipeline/src/pipeline/core/DataClient.py index 28ffff7..53f4072 100644 --- a/modules/ml-pipeline/src/pipeline/core/DataClient.py +++ b/modules/ml-pipeline/src/pipeline/core/DataClient.py @@ -142,9 +142,15 @@ class AWSS3Client: buffer = BytesIO() obj.to_parquet(buffer, index=False) + # Reset the buffer position to the beginning + buffer.seek(0) + bucket, key = location.strip("s3://").split("/", 1) self.client.upload_fileobj(buffer, bucket, key) + # Close the buffer + buffer.close() + def _load_parquet(self, location: str, load_config: dict) -> pd.DataFrame: """ Load a parquet file diff --git a/modules/ml-pipeline/src/pipeline/generate_predictions.py b/modules/ml-pipeline/src/pipeline/generate_predictions.py index 85b3022..83ea103 100644 --- a/modules/ml-pipeline/src/pipeline/generate_predictions.py +++ b/modules/ml-pipeline/src/pipeline/generate_predictions.py @@ -14,6 +14,7 @@ def generate_predictions( test_data_filepath: str, predictions_output_filepath: str, predictions_column_name: str, + identifier_column: str = "id", ): """ For a given model, we generate prediction and evaluate this against the true target @@ -52,6 +53,12 @@ def generate_predictions( predictions_df = pd.DataFrame(predictions) predictions_df.columns = [predictions_column_name] - output_dataclient.save_data( - obj=predictions_df, location=predictions_output_filepath, save_config=None + output_df = ( + pd.concat([test_data[identifier_column], predictions_df], axis=1) + if identifier_column in test_data.columns + else predictions_df + ) + + output_dataclient.save_data( + obj=output_df, location=predictions_output_filepath, save_config=None )