def test_config_features():
all_input_features = [
audio_feature("/tmp/destination_folder"),
bag_feature(),
binary_feature(),
category_feature(),
date_feature(),
h3_feature(),
image_feature("/tmp/destination_folder"),
number_feature(),
sequence_feature(),
set_feature(),
text_feature(),
timeseries_feature(),
vector_feature(),
]
all_output_features = [
binary_feature(),
category_feature(),
number_feature(),
sequence_feature(),
set_feature(),
text_feature(),
vector_feature(),
]
# validate config with all features
config = {
"input_features": all_input_features,
"output_features": all_output_features,
}
validate_config(config)
# make sure all defaults provided also registers as valid
config = merge_with_defaults(config)
validate_config(config)
# test various invalid output features
input_only_features = [
feature for feature in all_input_features
if feature["type"] not in output_type_registry.keys()
]
for input_feature in input_only_features:
config = {
"input_features": all_input_features,
"output_features": all_output_features + [input_feature],
}
dtype = input_feature["type"]
with pytest.raises(ValidationError,
match=rf"^'{dtype}' is not one of .*"):
validate_config(config)
def get_schema():
input_feature_types = sorted(list(input_type_registry.keys()))
output_feature_types = sorted(list(output_type_registry.keys()))
combiner_types = sorted(list(combiner_registry.keys()))
schema = {
"type": "object",
"properties": {
"input_features": {
"type": "array",
"items": {
"type":
"object",
"properties": {
"name": {
"type": "string"
},
"type": {
"type": "string",
"enum": input_feature_types
},
"column": {
"type": "string"
},
"encoder": {
"type": "string"
},
},
"allOf":
get_input_encoder_conds(input_feature_types) +
get_input_preproc_conds(input_feature_types),
"required": ["name", "type"],
},
},
"output_features": {
"type": "array",
"items": {
"type":
"object",
"properties": {
"name": {
"type": "string"
},
"type": {
"type": "string",
"enum": output_feature_types
},
"column": {
"type": "string"
},
"decoder": {
"type": "string"
},
},
"allOf":
get_output_decoder_conds(output_feature_types) +
get_output_preproc_conds(output_feature_types),
"required": ["name", "type"],
},
},
"combiner": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": combiner_types
},
},
"allOf": get_combiner_conds(combiner_types),
"required": ["type"],
},
"training": {},
"preprocessing": {},
"hyperopt": {},
},
"definitions": get_custom_definitions(),
"required": ["input_features", "output_features"],
}
return schema
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
from jsonschema import validate
from ludwig.combiners.combiners import combiner_registry
from ludwig.features.feature_registries import input_type_registry, output_type_registry
INPUT_FEATURE_TYPES = sorted(list(input_type_registry.keys()))
OUTPUT_FEATURE_TYPES = sorted(list(output_type_registry.keys()))
COMBINER_TYPES = sorted(list(combiner_registry.keys()))
def get_schema():
schema = {
'type': 'object',
'properties': {
'input_features': {
'type': 'array',
'items': {
'type': 'object',
'properties': {
'name': {
'type': 'string'
},