diff --git a/README.md b/README.md index 5879c41..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: @@ -79,6 +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\"}"}' ``` + This will send a POST request to the running Lambda function and pass in the required data as JSON. diff --git a/modules/ml-pipeline/src/pipeline/4_generate_metrics.py b/modules/ml-pipeline/src/pipeline/4_generate_metrics.py index 7b115a2..1f97d87 100644 --- a/modules/ml-pipeline/src/pipeline/4_generate_metrics.py +++ b/modules/ml-pipeline/src/pipeline/4_generate_metrics.py @@ -4,9 +4,7 @@ After the model is built, we can evaluate its performance """ import os -import yaml import pandas as pd -from pathlib import Path from core.interface.InterfaceModels import MLModel from core.interface.InterfaceMetrics import MLMetrics from core.interface.InterfaceDataClient import DataClient diff --git a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml index fdeb8c5..d296e6a 100644 --- a/modules/ml-pipeline/src/pipeline/configs/build_model.yaml +++ b/modules/ml-pipeline/src/pipeline/configs/build_model.yaml @@ -13,6 +13,6 @@ default: output_filepath: ./data/model/allmodels/ problem_type: regression eval_metric: mean_squared_error #mean_absolute_error - time_limit: 1000 + time_limit: 4000 presets: medium_quality excluded_model_types: ['KNN', 'RF'] diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock index 46211fa..13851cf 100644 --- a/modules/ml-pipeline/src/pipeline/dvc.lock +++ b/modules/ml-pipeline/src/pipeline/dvc.lock @@ -29,8 +29,8 @@ stages: outs: - path: data/prepared_data/ hash: md5 - md5: 71e63a792f7723e2aea0709efde1a92b.dir - size: 31751660 + md5: e0be70d5025e40dd0d655d9949f72130.dir + size: 31800776 nfiles: 2 build_model: cmd: python 2_build_model.py @@ -41,8 +41,8 @@ stages: size: 5359 - path: data/prepared_data hash: md5 - md5: 71e63a792f7723e2aea0709efde1a92b.dir - size: 31751660 + md5: e0be70d5025e40dd0d655d9949f72130.dir + size: 31800776 nfiles: 2 params: configs/build_model.yaml: @@ -58,7 +58,7 @@ stages: output_filepath: ./data/model/allmodels/ problem_type: regression eval_metric: mean_squared_error - time_limit: 1000 + time_limit: 4000 presets: medium_quality excluded_model_types: - KNN @@ -66,13 +66,13 @@ stages: outs: - path: data/model/ hash: md5 - md5: 0ffc51be7c8381c9e4106309e3e05ca3.dir - size: 345904743 + md5: 14ca33cde5e86770135f768abaf84978.dir + size: 422447808 nfiles: 27 - path: metrics/fit_metrics.json hash: md5 - md5: 3d4ff3a3ca3c327e2c1e9aa1338c18ce - size: 220 + md5: 41bfb8d2da8f06d1864d73ce125cc6aa + size: 221 generate_predictions: cmd: python 3_generate_predictions.py deps: @@ -82,13 +82,13 @@ stages: size: 3028 - path: data/model hash: md5 - md5: 0ffc51be7c8381c9e4106309e3e05ca3.dir - size: 345904743 + md5: 14ca33cde5e86770135f768abaf84978.dir + size: 422447808 nfiles: 27 - path: data/prepared_data hash: md5 - md5: 71e63a792f7723e2aea0709efde1a92b.dir - size: 31751660 + md5: e0be70d5025e40dd0d655d9949f72130.dir + size: 31800776 nfiles: 2 params: configs/settings.yaml: @@ -100,8 +100,8 @@ stages: outs: - path: data/predictions/ hash: md5 - md5: 00ff804016290d56e1490e59c098b060.dir - size: 351811 + md5: 40d0c7a7fd4a15add0615e322cf341a0.dir + size: 352151 nfiles: 1 generate_metrics: cmd: python 4_generate_metrics.py @@ -112,13 +112,13 @@ stages: size: 4487 - path: data/predictions hash: md5 - md5: 00ff804016290d56e1490e59c098b060.dir - size: 351811 + md5: 40d0c7a7fd4a15add0615e322cf341a0.dir + size: 352151 nfiles: 1 - path: data/prepared_data hash: md5 - md5: 71e63a792f7723e2aea0709efde1a92b.dir - size: 31751660 + md5: e0be70d5025e40dd0d655d9949f72130.dir + size: 31800776 nfiles: 2 params: configs/settings.yaml: @@ -128,8 +128,8 @@ stages: outs: - path: metrics/metrics.json hash: md5 - md5: 63ef63e4fabe929b914a0059ceeddabc - size: 221 + md5: 4e023650240e78d6ad761f1db7aac922 + size: 220 startup_cleanup: cmd: python 0_startup_cleanup.py deps: