|
1256 | 1256 | "traits": {
|
1257 | 1257 | "smithy.api#documentation": "<p>Indicates the status of the <code>CreateInferenceScheduler</code> operation. </p>"
|
1258 | 1258 | }
|
| 1259 | + }, |
| 1260 | + "ModelQuality": { |
| 1261 | + "target": "com.amazonaws.lookoutequipment#ModelQuality", |
| 1262 | + "traits": { |
| 1263 | + "smithy.api#documentation": "<p>Provides a quality assessment for a model that uses labels. \n If Lookout for Equipment determines that the\n model quality is poor based on training metrics, the value is\n <code>POOR_QUALITY_DETECTED</code>. Otherwise, the value is\n <code>QUALITY_THRESHOLD_MET</code>. </p>\n <p>If the model is unlabeled, the model quality can't\n be assessed and the value of <code>ModelQuality</code> is\n <code>CANNOT_DETERMINE_QUALITY</code>. In this situation, you can get a model quality\n assessment by adding labels to the input dataset and retraining the model.</p>\n <p>For information about using labels with your models, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/understanding-labeling.html\">Understanding labeling</a>.</p>\n <p>For information about improving the quality of a model, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/best-practices.html\">Best practices with\n Amazon Lookout for Equipment</a>.</p>" |
| 1264 | + } |
1259 | 1265 | }
|
1260 | 1266 | },
|
1261 | 1267 | "traits": {
|
|
3265 | 3271 | "traits": {
|
3266 | 3272 | "smithy.api#documentation": "<p>Configuration information for the model's pointwise model diagnostics.</p>"
|
3267 | 3273 | }
|
| 3274 | + }, |
| 3275 | + "ModelQuality": { |
| 3276 | + "target": "com.amazonaws.lookoutequipment#ModelQuality", |
| 3277 | + "traits": { |
| 3278 | + "smithy.api#documentation": "<p>Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the\n model quality is poor based on training metrics, the value is\n <code>POOR_QUALITY_DETECTED</code>. Otherwise, the value is\n <code>QUALITY_THRESHOLD_MET</code>.</p>\n <p>If the model is unlabeled, the model quality can't\n be assessed and the value of <code>ModelQuality</code> is\n <code>CANNOT_DETERMINE_QUALITY</code>. In this situation, you can get a model quality\n assessment by adding labels to the input dataset and retraining the model.</p>\n <p>For information about using labels with your models, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/understanding-labeling.html\">Understanding labeling</a>.</p>\n <p>For information about improving the quality of a model, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/best-practices.html\">Best practices with\n Amazon Lookout for Equipment</a>.</p>" |
| 3279 | + } |
3268 | 3280 | }
|
3269 | 3281 | },
|
3270 | 3282 | "traits": {
|
|
3522 | 3534 | "traits": {
|
3523 | 3535 | "smithy.api#documentation": "<p>The Amazon S3 output prefix for where Lookout for Equipment saves the pointwise model diagnostics for the model version.</p>"
|
3524 | 3536 | }
|
| 3537 | + }, |
| 3538 | + "ModelQuality": { |
| 3539 | + "target": "com.amazonaws.lookoutequipment#ModelQuality", |
| 3540 | + "traits": { |
| 3541 | + "smithy.api#documentation": "<p>Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the\n model quality is poor based on training metrics, the value is\n <code>POOR_QUALITY_DETECTED</code>. Otherwise, the value is\n <code>QUALITY_THRESHOLD_MET</code>.</p>\n <p>If the model is unlabeled, the model quality can't\n be assessed and the value of <code>ModelQuality</code> is\n <code>CANNOT_DETERMINE_QUALITY</code>. In this situation, you can get a model quality\n assessment by adding labels to the input dataset and retraining the model.</p>\n <p>For information about using labels with your models, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/understanding-labeling.html\">Understanding labeling</a>.</p>\n <p>For information about improving the quality of a model, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/best-practices.html\">Best practices with\n Amazon Lookout for Equipment</a>.</p>" |
| 3542 | + } |
3525 | 3543 | }
|
3526 | 3544 | },
|
3527 | 3545 | "traits": {
|
|
6173 | 6191 | }
|
6174 | 6192 | }
|
6175 | 6193 | },
|
| 6194 | + "com.amazonaws.lookoutequipment#ModelQuality": { |
| 6195 | + "type": "enum", |
| 6196 | + "members": { |
| 6197 | + "QUALITY_THRESHOLD_MET": { |
| 6198 | + "target": "smithy.api#Unit", |
| 6199 | + "traits": { |
| 6200 | + "smithy.api#enumValue": "QUALITY_THRESHOLD_MET" |
| 6201 | + } |
| 6202 | + }, |
| 6203 | + "CANNOT_DETERMINE_QUALITY": { |
| 6204 | + "target": "smithy.api#Unit", |
| 6205 | + "traits": { |
| 6206 | + "smithy.api#enumValue": "CANNOT_DETERMINE_QUALITY" |
| 6207 | + } |
| 6208 | + }, |
| 6209 | + "POOR_QUALITY_DETECTED": { |
| 6210 | + "target": "smithy.api#Unit", |
| 6211 | + "traits": { |
| 6212 | + "smithy.api#enumValue": "POOR_QUALITY_DETECTED" |
| 6213 | + } |
| 6214 | + } |
| 6215 | + } |
| 6216 | + }, |
6176 | 6217 | "com.amazonaws.lookoutequipment#ModelStatus": {
|
6177 | 6218 | "type": "enum",
|
6178 | 6219 | "members": {
|
|
6291 | 6332 | },
|
6292 | 6333 | "ModelDiagnosticsOutputConfiguration": {
|
6293 | 6334 | "target": "com.amazonaws.lookoutequipment#ModelDiagnosticsOutputConfiguration"
|
| 6335 | + }, |
| 6336 | + "ModelQuality": { |
| 6337 | + "target": "com.amazonaws.lookoutequipment#ModelQuality", |
| 6338 | + "traits": { |
| 6339 | + "smithy.api#documentation": "<p>Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the\n model quality is poor based on training metrics, the value is\n <code>POOR_QUALITY_DETECTED</code>. Otherwise, the value is\n <code>QUALITY_THRESHOLD_MET</code>.</p>\n <p>If the model is unlabeled, the model quality can't\n be assessed and the value of <code>ModelQuality</code> is\n <code>CANNOT_DETERMINE_QUALITY</code>. In this situation, you can get a model quality\n assessment by adding labels to the input dataset and retraining the model.</p>\n <p>For information about using labels with your models, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/understanding-labeling.html\">Understanding labeling</a>.</p>\n <p>For information about improving the quality of a model, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/best-practices.html\">Best practices with\n Amazon Lookout for Equipment</a>.</p>" |
| 6340 | + } |
6294 | 6341 | }
|
6295 | 6342 | },
|
6296 | 6343 | "traits": {
|
|
6423 | 6470 | "traits": {
|
6424 | 6471 | "smithy.api#documentation": "<p>Indicates how this model version was generated.</p>"
|
6425 | 6472 | }
|
| 6473 | + }, |
| 6474 | + "ModelQuality": { |
| 6475 | + "target": "com.amazonaws.lookoutequipment#ModelQuality", |
| 6476 | + "traits": { |
| 6477 | + "smithy.api#documentation": "<p>Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the\n model quality is poor based on training metrics, the value is\n <code>POOR_QUALITY_DETECTED</code>. Otherwise, the value is\n <code>QUALITY_THRESHOLD_MET</code>. </p>\n <p>If the model is unlabeled, the model quality can't\n be assessed and the value of <code>ModelQuality</code> is\n <code>CANNOT_DETERMINE_QUALITY</code>. In this situation, you can get a model quality\n assessment by adding labels to the input dataset and retraining the model.</p>\n <p>For information about improving the quality of a model, see <a href=\"https://docs.aws.amazon.com/lookout-for-equipment/latest/ug/best-practices.html\">Best practices with\n Amazon Lookout for Equipment</a>.</p>" |
| 6478 | + } |
6426 | 6479 | }
|
6427 | 6480 | },
|
6428 | 6481 | "traits": {
|
|
0 commit comments