pointblank 0.12.1__py3-none-any.whl → 0.12.2__py3-none-any.whl

pointblank/data/api-docs.txt

@@ -9798,7 +9798,7 @@ validation workflows. The `yaml_interrogate()` function can be used to run a val
 YAML strings or files. The `validate_yaml()` function checks if the YAML configuration
 passes its own validity checks.
 
-yaml_interrogate(yaml: 'Union[str, Path]') -> 'Validate'
+yaml_interrogate(yaml: 'Union[str, Path]', set_tbl: 'Union[FrameT, Any, None]' = None) -> 'Validate'
 Execute a YAML-based validation workflow.
 
     This is the main entry point for YAML-based validation workflows. It takes YAML configuration
@@ -9813,13 +9813,20 @@ Execute a YAML-based validation workflow.
     yaml
         YAML configuration as string or file path. Can be: (1) a YAML string containing the
         validation configuration, or (2) a Path object or string path to a YAML file.
+    set_tbl
+        An optional table to override the table specified in the YAML configuration. This allows you
+        to apply a YAML-defined validation workflow to a different table than what's specified in
+        the configuration. If provided, this table will replace the table defined in the YAML's
+        `tbl` field before executing the validation workflow. This can be any supported table type
+        including DataFrame objects, Ibis table objects, CSV file paths, Parquet file paths, GitHub
+        URLs, or database connection strings.
 
     Returns
     -------
     Validate
-        An instance of the `Validate` class that has been configured based on the YAML input.
-        This object contains the results of the validation steps defined in the YAML configuration.
-        It includes metadata like table name, label, language, and thresholds if specified.
+        An instance of the `Validate` class that has been configured based on the YAML input. This
+        object contains the results of the validation steps defined in the YAML configuration. It
+        includes metadata like table name, label, language, and thresholds if specified.
 
     Raises
     ------
@@ -9918,6 +9925,44 @@ Execute a YAML-based validation workflow.
     This approach is particularly useful for storing validation configurations as part of your data
     pipeline or version control system, allowing you to maintain validation rules alongside your
     code.
+
+    ### Using `set_tbl=` to Override the Table
+
+    The `set_tbl=` parameter allows you to override the table specified in the YAML configuration.
+    This is useful when you have a template validation workflow but want to apply it to different
+    tables:
+
+    ```python
+    import polars as pl
+
+    # Create a test table with similar structure to small_table
+    test_table = pl.DataFrame({
+        "date": ["2023-01-01", "2023-01-02", "2023-01-03"],
+        "a": [1, 2, 3],
+        "b": ["1-abc-123", "2-def-456", "3-ghi-789"],
+        "d": [150, 200, 250]
+    })
+
+    # Use the same YAML config but apply it to our test table
+    yaml_config = '''
+    tbl: small_table  # This will be overridden
+    tbl_name: Test Table  # This name will be used
+    steps:
+    - col_exists:
+        columns: [date, a, b, d]
+    - col_vals_gt:
+        columns: [d]
+        value: 100
+    '''
+
+    # Execute with table override
+    result = pb.yaml_interrogate(yaml_config, set_tbl=test_table)
+    print(f"Validation applied to: {result.tbl_name}")
+    result
+    ```
+
+    This feature makes YAML configurations more reusable and flexible, allowing you to define
+    validation logic once and apply it to multiple similar tables.
     
 
 validate_yaml(yaml: 'Union[str, Path]') -> 'None'

pointblank/validate.py

@@ -3758,6 +3758,141 @@ class Validate:
 
         self.validation_info = []
 
+    def set_tbl(
+        self,
+        tbl: FrameT | Any,
+        tbl_name: str | None = None,
+        label: str | None = None,
+    ) -> Validate:
+        """
+        Set or replace the table associated with the Validate object.
+
+        This method allows you to replace the table associated with a Validate object with a
+        different (but presumably similar) table. This is useful when you want to apply the same
+        validation plan to multiple tables or when you have a validation workflow defined but want
+        to swap in a different data source.
+
+        Parameters
+        ----------
+        tbl
+            The table to replace the existing table with. This can be any supported table type
+            including DataFrame objects, Ibis table objects, CSV file paths, Parquet file paths,
+            GitHub URLs, or database connection strings. The same table type constraints apply as in
+            the `Validate` constructor.
+        tbl_name
+            An optional name to assign to the new input table object. If no value is provided, the
+            existing table name will be retained.
+        label
+            An optional label for the validation plan. If no value is provided, the existing label
+            will be retained.
+
+        Returns
+        -------
+        Validate
+            A new `Validate` object with the replacement table.
+
+        When to Use
+        -----------
+        The `set_tbl()` method is particularly useful in scenarios where you have:
+
+        - multiple similar tables that need the same validation checks
+        - a template validation workflow that should be applied to different data sources
+        - YAML-defined validations where you want to override the table specified in the YAML
+
+        The `set_tbl()` method creates a copy of the validation object with the new table, so the
+        original validation object remains unchanged. This allows you to reuse validation plans
+        across multiple tables without interference.
+
+        Examples
+        --------
+        ```{python}
+        #| echo: false
+        #| output: false
+        import pointblank as pb
+        pb.config(report_incl_header=False, report_incl_footer=False, preview_incl_header=False)
+        ```
+        We will first create two similar tables for our future validation plans.
+
+        ```{python}
+        import pointblank as pb
+        import polars as pl
+
+        # Create two similar tables
+        table_1 = pl.DataFrame({
+            "x": [1, 2, 3, 4, 5],
+            "y": [5, 4, 3, 2, 1],
+            "z": ["a", "b", "c", "d", "e"]
+        })
+
+        table_2 = pl.DataFrame({
+            "x": [2, 4, 6, 8, 10],
+            "y": [10, 8, 6, 4, 2],
+            "z": ["f", "g", "h", "i", "j"]
+        })
+        ```
+
+        Create a validation plan with the first table.
+
+        ```{python}
+        validation_table_1 = (
+            pb.Validate(
+                data=table_1,
+                tbl_name="Table 1",
+                label="Validation applied to the first table"
+            )
+            .col_vals_gt(columns="x", value=0)
+            .col_vals_lt(columns="y", value=10)
+        )
+        ```
+
+        Now apply the same validation plan to the second table.
+
+        ```{python}
+        validation_table_2 = (
+            validation_table_1
+            .set_tbl(
+                tbl=table_2,
+                tbl_name="Table 2",
+                label="Validation applied to the second table"
+            )
+        )
+        ```
+
+        Here is the interrogation of the first table:
+
+        ```{python}
+        validation_table_1.interrogate()
+        ```
+
+        And the second table:
+
+        ```{python}
+        validation_table_2.interrogate()
+        ```
+        """
+        from copy import deepcopy
+
+        # Create a deep copy of the current Validate object
+        new_validate = deepcopy(self)
+
+        # Process the new table through the centralized data processing pipeline
+        new_validate.data = _process_data(tbl)
+
+        # Update table name if provided, otherwise keep existing
+        if tbl_name is not None:
+            new_validate.tbl_name = tbl_name
+
+        # Update label if provided, otherwise keep existing
+        if label is not None:
+            new_validate.label = label
+
+        # Reset interrogation state since we have a new table, but preserve validation steps
+        new_validate.time_start = None
+        new_validate.time_end = None
+        # Note: We keep validation_info as it contains the defined validation steps
+
+        return new_validate
+
     def _repr_html_(self) -> str:
         return self.get_tabular_report()._repr_html_()  # pragma: no cover
 

pointblank/yaml.py

@@ -4,6 +4,7 @@ from pathlib import Path
 from typing import Any, Union
 
 import yaml
+from narwhals.typing import FrameT
 
 from pointblank._utils import _is_lib_present
 from pointblank.thresholds import Actions
@@ -749,7 +750,7 @@ class YAMLValidator:
         return validation
 
 
-def yaml_interrogate(yaml: Union[str, Path]) -> Validate:
+def yaml_interrogate(yaml: Union[str, Path], set_tbl: Union[FrameT, Any, None] = None) -> Validate:
     """Execute a YAML-based validation workflow.
 
     This is the main entry point for YAML-based validation workflows. It takes YAML configuration
@@ -764,13 +765,20 @@ def yaml_interrogate(yaml: Union[str, Path]) -> Validate:
     yaml
         YAML configuration as string or file path. Can be: (1) a YAML string containing the
         validation configuration, or (2) a Path object or string path to a YAML file.
+    set_tbl
+        An optional table to override the table specified in the YAML configuration. This allows you
+        to apply a YAML-defined validation workflow to a different table than what's specified in
+        the configuration. If provided, this table will replace the table defined in the YAML's
+        `tbl` field before executing the validation workflow. This can be any supported table type
+        including DataFrame objects, Ibis table objects, CSV file paths, Parquet file paths, GitHub
+        URLs, or database connection strings.
 
     Returns
     -------
     Validate
-        An instance of the `Validate` class that has been configured based on the YAML input.
-        This object contains the results of the validation steps defined in the YAML configuration.
-        It includes metadata like table name, label, language, and thresholds if specified.
+        An instance of the `Validate` class that has been configured based on the YAML input. This
+        object contains the results of the validation steps defined in the YAML configuration. It
+        includes metadata like table name, label, language, and thresholds if specified.
 
     Raises
     ------
@@ -875,10 +883,59 @@ def yaml_interrogate(yaml: Union[str, Path]) -> Validate:
     This approach is particularly useful for storing validation configurations as part of your data
     pipeline or version control system, allowing you to maintain validation rules alongside your
     code.
+
+    ### Using `set_tbl=` to Override the Table
+
+    The `set_tbl=` parameter allows you to override the table specified in the YAML configuration.
+    This is useful when you have a template validation workflow but want to apply it to different
+    tables:
+
+    ```{python}
+    import polars as pl
+
+    # Create a test table with similar structure to small_table
+    test_table = pl.DataFrame({
+        "date": ["2023-01-01", "2023-01-02", "2023-01-03"],
+        "a": [1, 2, 3],
+        "b": ["1-abc-123", "2-def-456", "3-ghi-789"],
+        "d": [150, 200, 250]
+    })
+
+    # Use the same YAML config but apply it to our test table
+    yaml_config = '''
+    tbl: small_table  # This will be overridden
+    tbl_name: Test Table  # This name will be used
+    steps:
+    - col_exists:
+        columns: [date, a, b, d]
+    - col_vals_gt:
+        columns: [d]
+        value: 100
+    '''
+
+    # Execute with table override
+    result = pb.yaml_interrogate(yaml_config, set_tbl=test_table)
+    print(f"Validation applied to: {result.tbl_name}")
+    result
+    ```
+
+    This feature makes YAML configurations more reusable and flexible, allowing you to define
+    validation logic once and apply it to multiple similar tables.
     """
     validator = YAMLValidator()
     config = validator.load_config(yaml)
-    return validator.execute_workflow(config)
+
+    # If `set_tbl=` is provided, we need to build the validation workflow and then use `set_tbl()`
+    if set_tbl is not None:
+        # First build the validation object without interrogation
+        validation = validator.build_validation(config)
+        # Then replace the table using set_tbl method
+        validation = validation.set_tbl(tbl=set_tbl)
+        # Finally interrogate with the new table
+        return validation.interrogate()
+    else:
+        # Standard execution without table override (includes interrogation)
+        return validator.execute_workflow(config)
 
 
 def load_yaml_config(file_path: Union[str, Path]) -> dict:

{pointblank-0.12.1.dist-info → pointblank-0.12.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.12.1
+Version: 0.12.2
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License

{pointblank-0.12.1.dist-info → pointblank-0.12.2.dist-info}/RECORD

@@ -21,9 +21,9 @@ pointblank/schema.py,sha256=vwGF8UKy2riRSQzcwatcI6L0t_6ccdbOayrKonvyodE,45777
 pointblank/segments.py,sha256=RXp3lPr3FboVseadNqLgIeoMBh_mykrQSFp1WtV41Yg,5570
 pointblank/tf.py,sha256=8o_8m4i01teulEe3-YYMotSNf3tImjBMInsvdjSAO5Q,8844
 pointblank/thresholds.py,sha256=mybeLzTVdmN04NLKoV-jiSBXsWknwHO0Gox0ttVN_MU,25766
-pointblank/validate.py,sha256=KvnC0UnvVW2mkoWkp1fDIXotuBl7MJeU6_ggp_0yDoo,693082
-pointblank/yaml.py,sha256=4DrkOJwCQ3CaXQ7ESNIW72pp-dL1ctlX6ONU30Vh1Fs,57901
-pointblank/data/api-docs.txt,sha256=0wXk__xYwgKeS24ZjbaTPFeJ3ZO7AIyMQoFClCcvPTc,529897
+pointblank/validate.py,sha256=9-lzWSvNVo2JDcXVAiMINPbyg1Xgy0SMmwW8IfKstJs,697641
+pointblank/yaml.py,sha256=v3uCrs4Hzt-9cAmGxiFJIU8A9XiRQsN7U3OBFa6_hUs,60287
+pointblank/data/api-docs.txt,sha256=w2nIkIL_fJpXlPR9clogqcgdiv-uHvdSDI8gjkP_mCQ,531711
 pointblank/data/game_revenue-duckdb.zip,sha256=tKIVx48OGLYGsQPS3h5AjA2Nyq_rfEpLCjBiFUWhagU,35880
 pointblank/data/game_revenue.zip,sha256=7c9EvHLyi93CHUd4p3dM4CZ-GucFCtXKSPxgLojL32U,33749
 pointblank/data/global_sales-duckdb.zip,sha256=2ok_cvJ1ZuSkXnw0R6_OkKYRTWhJ-jJEMq2VYsv5fqY,1336390
@@ -33,9 +33,9 @@ pointblank/data/nycflights.zip,sha256=yVjbUaKUz2LydSdF9cABuir0VReHBBgV7shiNWSd0m
 pointblank/data/polars-api-docs.txt,sha256=KGcS-BOtUs9zgpkWfXD-GFdFh4O_zjdkpX7msHjztLg,198045
 pointblank/data/small_table-duckdb.zip,sha256=BhTaZ2CRS4-9Z1uVhOU6HggvW3XCar7etMznfENIcOc,2028
 pointblank/data/small_table.zip,sha256=lmFb90Nb-v5X559Ikjg31YLAXuRyMkD9yLRElkXPMzQ,472
-pointblank-0.12.1.dist-info/licenses/LICENSE,sha256=apLF-HWPNU7pT5bmf5KmZpD5Cklpy2u-BN_0xBoRMLY,1081
-pointblank-0.12.1.dist-info/METADATA,sha256=1fJY92u1AiJdYggJLaUf0TKbovh3ytcihIdh4PcBEQ8,19242
-pointblank-0.12.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pointblank-0.12.1.dist-info/entry_points.txt,sha256=GqqqOTOH8uZe22wLcvYjzpizqk_j4MNcUo2YM14ryCw,42
-pointblank-0.12.1.dist-info/top_level.txt,sha256=-wHrS1SvV8-nhvc3w-PPYs1C1WtEc1pK-eGjubbCCKc,11
-pointblank-0.12.1.dist-info/RECORD,,
+pointblank-0.12.2.dist-info/licenses/LICENSE,sha256=apLF-HWPNU7pT5bmf5KmZpD5Cklpy2u-BN_0xBoRMLY,1081
+pointblank-0.12.2.dist-info/METADATA,sha256=yF9JixS22t9DR-S8mXMv3uyXmkACVb1LQMoHck2bMYs,19242
+pointblank-0.12.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pointblank-0.12.2.dist-info/entry_points.txt,sha256=GqqqOTOH8uZe22wLcvYjzpizqk_j4MNcUo2YM14ryCw,42
+pointblank-0.12.2.dist-info/top_level.txt,sha256=-wHrS1SvV8-nhvc3w-PPYs1C1WtEc1pK-eGjubbCCKc,11
+pointblank-0.12.2.dist-info/RECORD,,