Project import generated by Copybara. (#73)

GitOrigin-RevId: 6af23f3594aae1b0f36177bfe8c706ef07c9350c

Co-authored-by: Snowflake Authors <[email protected]>

.github/workflows/jira_close.yml

@@ -0,0 +1,38 @@
+---
+name: Jira closure
+
+on:
+  issues:
+    types:
+      - closed
+      - deleted
+
+jobs:
+  close-issue:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+        with:
+          repository: snowflakedb/gh-actions
+          ref: jira_v1
+          token: ${{ secrets.SNOWFLAKE_GITHUB_TOKEN }}  # stored in GitHub secrets
+          path: .
+      - name: Jira login
+        uses: atlassian/gajira-login@master
+        env:
+          JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
+          JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
+          JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
+      - name: Extract issue from title
+        id: extract
+        env:
+          TITLE: ${{ github.event.issue.title }}
+        run: |
+          jira=$(echo -n $TITLE | awk '{print $1}' | sed -e 's/://')
+          echo ::set-output name=jira::$jira
+      - name: Close issue
+        uses: ./jira/gajira-close
+        if: startsWith(steps.extract.outputs.jira, 'SNOW-')
+        with:
+          issue: ${{ steps.extract.outputs.jira }}

.github/workflows/jira_comment.yml

@@ -0,0 +1,33 @@
+---
+name: Jira comment
+
+on:
+  issue_comment:
+    types:
+      - created
+
+jobs:
+  comment-issue:
+    if: ${{ !github.event.issue.pull_request }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Jira login
+        uses: atlassian/gajira-login@master
+        env:
+          JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
+          JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
+          JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
+      - name: Extract issue from title
+        id: extract
+        env:
+          TITLE: ${{ github.event.issue.title }}
+        run: |
+          jira=$(echo -n $TITLE | awk '{print $1}' | sed -e 's/://')
+          echo ::set-output name=jira::$jira
+      - name: Comment on issue
+        uses: atlassian/gajira-comment@master
+        if: startsWith(steps.extract.outputs.jira, 'SNOW-')
+        with:
+          issue: ${{ steps.extract.outputs.jira }}
+          comment: "${{ github.event.comment.user.login }} commented:\n\n${{ github.event.comment.body }}\n\n${{ github.event.comment.html_url\
+            \ }}"

.github/workflows/jira_issue.yml

@@ -0,0 +1,54 @@
+---
+name: Jira creation
+
+on:
+  issues:
+    types:
+      - opened
+  issue_comment:
+    types:
+      - created
+
+jobs:
+  create-issue:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+    if: (github.event_name == 'issues' && github.event.pull_request.user.login != 'whitesource-for-github-com[bot]')
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+        with:
+          repository: snowflakedb/gh-actions
+          ref: jira_v1
+          token: ${{ secrets.SNOWFLAKE_GITHUB_TOKEN }}  # stored in GitHub secrets
+          path: .
+
+      - name: Login
+        uses: atlassian/[email protected]
+        env:
+          JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
+          JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
+          JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
+
+      - name: Create JIRA Ticket
+        id: create
+        uses: atlassian/[email protected]
+        with:
+          project: SNOW
+          issuetype: Bug
+          summary: ${{ github.event.issue.title }}
+          description: |
+            ${{ github.event.issue.body }} \\ \\ _Created from GitHub Action_ for ${{ github.event.issue.html_url }}
+          # Assign triage-ml-platform-dl and set "Data Platform: ML Engineering" component.
+          fields: '{"customfield_11401":{"id":"14538"}, "assignee":{"id":"639020ab3c26ca7fa0d6eb3f"},"components":[{"id":"16520"}]}'
+
+      - name: Update GitHub Issue
+        uses: ./jira/gajira-issue-update
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          issue_number: '{{ event.issue.id }}'
+          owner: '{{ event.repository.owner.login }}'
+          name: '{{ event.repository.name }}'
+          jira: ${{ steps.create.outputs.issue }}

CHANGELOG.md

@@ -1,5 +1,20 @@
 # Release History
 
+## 1.1.1
+
+### Bug Fixes
+
+- Model Registry: The `predict` target method on registered models is now compatible with unsupervised estimators.
+- Model Development: Fix confusion_matrix incorrect results when the row number cannot be divided by the batch size.
+
+### Behavior Changes
+
+### New Features
+
+- Introduced passthrough_col param in Modeling API. This new param is helpful in scenarios
+  requiring automatic input_cols inference, but need to avoid using specific
+  columns, like index columns, during training or inference.
+
 ## 1.1.0
 
 ### Bug Fixes

codegen/sklearn_wrapper_generator.py

@@ -21,8 +21,8 @@
 input_cols: Optional[Union[str, List[str]]]
     A string or list of strings representing column names that contain features.
     If this parameter is not specified, all columns in the input DataFrame except
-    the columns specified by label_cols and sample_weight_col parameters are
-    considered input columns.
+    the columns specified by label_cols, sample_weight_col, and passthrough_cols
+    parameters are considered input columns.
 
 label_cols: Optional[Union[str, List[str]]]
     A string or list of strings representing column names that contain labels.
@@ -44,6 +44,13 @@
     A string representing the column name containing the sample weights.
     This argument is only required when working with weighted datasets.
 
+passthrough_cols: Optional[Union[str, List[str]]]
+    A string or a list of strings indicating column names to be excluded from any
+    operations (such as train, transform, or inference). These specified column(s)
+    will remain untouched throughout the process. This option is helpful in scenarios
+    requiring automatic input_cols inference, but need to avoid using specific
+    columns, like index columns, during training or inference.
+
 drop_input_cols: Optional[bool], default=False
     If set, the response of predict(), transform() methods will not contain input columns.
 """
@@ -743,7 +750,7 @@ def _populate_function_names_and_signatures(self) -> None:
                     signature_lines.append(v.name)
                 sklearn_init_args_dict_list.append(f"'{v.name}':({v.name}, None, True)")
 
-        for arg in ["input_cols", "output_cols", "label_cols"]:
+        for arg in ["input_cols", "output_cols", "label_cols", "passthrough_cols"]:
             signature_lines.append(f"{arg}: Optional[Union[str, Iterable[str]]] = None")
             init_member_args.append(f"self.set_{arg}({arg})")
 

codegen/sklearn_wrapper_template.py_template

@@ -83,24 +83,6 @@ class {transform.original_class_name}(BaseTransformer):
         """
         return str(uuid4()).replace("-", "_").upper()
 
-    def _infer_input_output_cols(self, dataset: Union[DataFrame, pd.DataFrame]) -> None:
-        """
-        Infer `self.input_cols` and `self.output_cols` if they are not explicitly set.
-
-        Args:
-            dataset: Input dataset.
-        """
-        if not self.input_cols:
-            cols = [
-                c for c in dataset.columns 
-                if c not in self.get_label_cols() and c != self.sample_weight_col
-            ]
-            self.set_input_cols(input_cols=cols)
-
-        if not self.output_cols:
-            cols = [identifier.concat_names(ids=['OUTPUT_', c]) for c in self.label_cols]
-            self.set_output_cols(output_cols=cols)
-
     def set_input_cols(self, input_cols: Optional[Union[str, Iterable[str]]]) -> "{transform.original_class_name}":
         """
         Input columns setter.
@@ -737,12 +719,22 @@ class {transform.original_class_name}(BaseTransformer):
                 self._model_signature_dict["predict"] = ModelSignature(inputs,
                                                                        ([] if self._drop_input_cols else inputs)
                                                                        + outputs)
+            # For mixture models that use the density mixin, `predict` returns the argmax of the log prob.
+            # For outlier models, returns -1 for outliers and 1 for inliers.
+            # Clusterer returns int64 cluster labels. 
+            elif self._sklearn_object._estimator_type in ["DensityEstimator", "clusterer", "outlier_detector"]:
+                outputs = [FeatureSpec(dtype=DataType.INT64, name=c) for c in self.output_cols]
+                self._model_signature_dict["predict"] = ModelSignature(inputs,
+                                                                       ([] if self._drop_input_cols else inputs)
+                                                                       + outputs)
+
             # For regressor, the type of predict is float64
             elif self._sklearn_object._estimator_type == 'regressor':
                 outputs = [FeatureSpec(dtype=DataType.DOUBLE, name=c) for c in self.output_cols]
                 self._model_signature_dict["predict"] = ModelSignature(inputs,
                                                                        ([] if self._drop_input_cols else inputs)
                                                                        + outputs)
+
         for prob_func in PROB_FUNCTIONS:
             if hasattr(self, prob_func):
                 output_cols_prefix: str = f"{{prob_func}}_"

codegen/transformer_autogen_test_template.py_template

@@ -127,6 +127,8 @@ class {transform.test_class_name}(TestCase):
         inference_methods = ["transform", "predict"]
         for m in inference_methods:
             if callable(getattr(sklearn_reg, m, None)):
+                if m == 'predict':
+                    self.assertTrue(m in reg.model_signatures)
 
                 if inference_with_udf:
                     output_df = getattr(reg, m)(input_df)