Merge branches 'development' and 'master' of https://github.com/mlrun/functions

Author: yaronha

catalog.json

@@ -1 +1 @@
-{"aggregate": {"name": "aggregate", "description": "Rolling aggregation over Metrics and Lables according to specifications", "categories": ["preprocessing"], "versions": {"latest": "hub://aggregate"}}, "arc-to-parquet": {"name": "arc-to-parquet", "description": "retrieve remote archive, open and save as parquet", "categories": ["fileutils", "retrieve"], "versions": {"latest": "hub://arc_to_parquet"}}, "describe": {"name": "describe", "description": "describe and visualizes dataset stats", "categories": ["models", "visualization"], "versions": {"latest": "hub://describe"}}, "describe-dask": {"name": "describe-dask", "description": "describe and visualizes dataset stats", "categories": ["models", "visualization"], "versions": {"latest": "hub://describe_dask"}}, "gen-class-data": {"name": "gen-class-data", "description": "simulate classification data using scikit-learn", "categories": ["datagen", "filesutils"], "versions": {"latest": "hub://gen_class_data"}}, "load-dask": {"name": "load-dask", "description": "load dask cluster with data", "categories": ["fileutils", "distributed"], "versions": {"latest": "hub://load_dask"}}, "load-dataset": {"name": "load-dataset", "description": "load a toy dataset from scikit-learn", "categories": ["datagen", "filesutils"], "versions": {"latest": "hub://load_dataset"}}, "sklearn-server": {"name": "sklearn-server", "description": "generic sklearn model server", "categories": ["serving", "models"], "versions": {"latest": "hub://model_server"}}, "model-server-tester": {"name": "model-server-tester", "description": "test model servers", "categories": ["models", "testing"], "versions": {"latest": "hub://model_server_tester"}}, "open-archive": {"name": "open-archive", "description": "Open a file/object archive into a target directory", "categories": ["fileutils", "retrieve"], "versions": {"latest": "hub://open_archive"}}, "sklearn-classifier": {"name": "sklearn-classifier", "description": "train any classifier using scikit-learn's API", "categories": ["models", "classifier"], "versions": {"latest": "hub://sklearn_classifier"}}, "test-classifier": {"name": "test-classifier", "description": "test a classifier using held-out or new data", "categories": ["models", "testing"], "versions": {"latest": "hub://test_classifier"}}, "tf-images-server": {"name": "tf-images-server", "description": "", "categories": [], "versions": {"latest": "hub://tf-serving"}}}
+{"aggregate": {"description": "Rolling aggregation over Metrics and Lables according to specifications", "categories": ["preprocessing"], "versions": {"latest": "hub://aggregate"}}, "arc-to-parquet": {"description": "retrieve remote archive, open and save as parquet", "categories": ["fileutils", "retrieve"], "versions": {"latest": "hub://arc_to_parquet"}}, "describe": {"description": "describe and visualizes dataset stats", "categories": ["models", "visualization"], "versions": {"latest": "hub://describe"}}, "describe-dask": {"description": "describe and visualizes dataset stats", "categories": ["models", "visualization"], "versions": {"latest": "hub://describe_dask"}}, "gen-class-data": {"description": "simulate classification data using scikit-learn", "categories": ["datagen", "filesutils"], "versions": {"latest": "hub://gen_class_data"}}, "load-dask": {"description": "load dask cluster with data", "categories": ["fileutils", "distributed"], "versions": {"latest": "hub://load_dask"}}, "load-dataset": {"description": "load a toy dataset from scikit-learn", "categories": ["datagen", "filesutils"], "versions": {"latest": "hub://load_dataset"}}, "sklearn-server": {"description": "generic sklearn model server", "categories": ["serving", "models"], "versions": {"latest": "hub://model_server"}}, "model-server-tester": {"description": "test model servers", "categories": ["models", "testing"], "versions": {"latest": "hub://model_server_tester"}}, "open-archive": {"description": "Open a file/object archive into a target directory", "categories": ["fileutils", "retrieve"], "versions": {"latest": "hub://open_archive"}}, "sklearn-classifier": {"description": "train any classifier using scikit-learn's API", "categories": ["models", "classifier"], "versions": {"latest": "hub://sklearn_classifier"}}, "test-classifier": {"description": "test a classifier using held-out or new data", "categories": ["models", "testing"], "versions": {"latest": "hub://test_classifier"}}, "tf-images-server": {"description": "", "categories": [], "versions": {"latest": "hub://tf-serving"}}}

catalog.yaml

@@ -2,100 +2,87 @@ aggregate:
   categories:
   - preprocessing
   description: Rolling aggregation over Metrics and Lables according to specifications
-  name: aggregate
   versions:
     latest: hub://aggregate
 arc-to-parquet:
   categories:
   - fileutils
   - retrieve
   description: retrieve remote archive, open and save as parquet
-  name: arc-to-parquet
   versions:
     latest: hub://arc_to_parquet
 describe:
   categories:
   - models
   - visualization
   description: describe and visualizes dataset stats
-  name: describe
   versions:
     latest: hub://describe
 describe-dask:
   categories:
   - models
   - visualization
   description: describe and visualizes dataset stats
-  name: describe-dask
   versions:
     latest: hub://describe_dask
 gen-class-data:
   categories:
   - datagen
   - filesutils
   description: simulate classification data using scikit-learn
-  name: gen-class-data
   versions:
     latest: hub://gen_class_data
 load-dask:
   categories:
   - fileutils
   - distributed
   description: load dask cluster with data
-  name: load-dask
   versions:
     latest: hub://load_dask
 load-dataset:
   categories:
   - datagen
   - filesutils
   description: load a toy dataset from scikit-learn
-  name: load-dataset
   versions:
     latest: hub://load_dataset
 model-server-tester:
   categories:
   - models
   - testing
   description: test model servers
-  name: model-server-tester
   versions:
     latest: hub://model_server_tester
 open-archive:
   categories:
   - fileutils
   - retrieve
   description: Open a file/object archive into a target directory
-  name: open-archive
   versions:
     latest: hub://open_archive
 sklearn-classifier:
   categories:
   - models
   - classifier
   description: train any classifier using scikit-learn's API
-  name: sklearn-classifier
   versions:
     latest: hub://sklearn_classifier
 sklearn-server:
   categories:
   - serving
   - models
   description: generic sklearn model server
-  name: sklearn-server
   versions:
     latest: hub://model_server
 test-classifier:
   categories:
   - models
   - testing
   description: test a classifier using held-out or new data
-  name: test-classifier
   versions:
     latest: hub://test_classifier
 tf-images-server:
   categories: []
   description: ''
-  name: tf-images-server
   versions:
     latest: hub://tf-serving

create_catalog.py

@@ -11,12 +11,11 @@
     if os.path.isfile(specpath):
         fn = import_function(specpath)
 
-        entry = {'name': fn.metadata.name,
-                 'description': fn.spec.description,
+        entry = {'description': fn.spec.description,
                  'categories': fn.metadata.categories,
                  'versions': {'latest': f'hub://{funcdir}'}}
 
-        print(entry)
+        print(fn.metadata.name, entry)
         catalog[fn.metadata.name] = entry