pointblank 0.9.5__py3-none-any.whl → 0.9.6__py3-none-any.whl

pointblank/_constants.py

@@ -109,6 +109,7 @@ ROW_BASED_VALIDATION_TYPES = [
 ]
 
 IBIS_BACKENDS = [
+    "bigquery",
     "databricks",
     "duckdb",
     "memtable",
@@ -165,6 +166,7 @@ TABLE_TYPE_STYLES = {
     "parquet": {"background": "#3F9FF9", "text": "#FFFFFF", "label": "Parquet"},
     "memtable": {"background": "#2C3E50", "text": "#FFFFFF", "label": "Ibis memtable"},
     "mssql": {"background": "#E2E2E2", "text": "#222222", "label": "MSSQL"},
+    "bigquery": {"background": "#4285F4", "text": "#FFFFFF", "label": "BigQuery"},
     "pyspark": {"background": "#E66F21", "text": "#FFFFFF", "label": "Spark DataFrame"},
     "databricks": {"background": "#FF3621", "text": "#FFFFFF", "label": "Databricks"},
 }

pointblank/_utils.py

@@ -514,6 +514,8 @@ def _get_api_text() -> str:
         "Validate.get_data_extracts",
         "Validate.all_passed",
         "Validate.assert_passing",
+        "Validate.assert_below_threshold",
+        "Validate.above_threshold",
         "Validate.n",
         "Validate.n_passed",
         "Validate.n_failed",

pointblank/actions.py

@@ -216,7 +216,7 @@ def send_slack_notification(
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
             actions=pb.Actions(critical=notify_slack),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()
@@ -248,7 +248,7 @@ def send_slack_notification(
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
             final_actions=pb.FinalActions(notify_slack),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()
@@ -316,7 +316,7 @@ def send_slack_notification(
             actions=pb.Actions(default=notify_slack),
             final_actions=pb.FinalActions(notify_slack),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()

pointblank/column.py

@@ -1007,7 +1007,7 @@ def matches(pattern: str, case_sensitive: bool = False) -> Matches:
     `[rev_01, rev_02, profit_01, profit_02, age]`
 
     and you want to validate columns that have two digits at the end of the name, you can use
-    `columns=matches(r"\d{2}$")`. This will select the `rev_01`, `rev_02`, `profit_01`, and
+    `columns=matches(r"[0-9]{2}$")`. This will select the `rev_01`, `rev_02`, `profit_01`, and
     `profit_02` columns.
 
     There will be a validation step created for every resolved column. Note that if there aren't any
@@ -1061,7 +1061,7 @@ def matches(pattern: str, case_sensitive: bool = False) -> Matches:
     [`col()`](`pointblank.col`) function, like this:
 
     ```python
-    col(matches(r"^\d{5}") & ends_with("_id"))
+    col(matches(r"^[0-9]{5}") & ends_with("_id"))
     ```
 
     There are four operators that can be used to compose column selectors:
@@ -1107,7 +1107,7 @@ def matches(pattern: str, case_sensitive: bool = False) -> Matches:
 
     validation = (
         pb.Validate(data=tbl)
-        .col_vals_regex(columns=pb.matches("id|identifier"), pattern=r"ID\d{4}")
+        .col_vals_regex(columns=pb.matches("id|identifier"), pattern=r"ID[0-9]{4}")
         .interrogate()
     )
 
@@ -1115,7 +1115,7 @@ def matches(pattern: str, case_sensitive: bool = False) -> Matches:
     ```
 
     From the results of the validation table we get two validation steps, one for `id_old` and one
-    for `new_identifier`. The values in both columns all match the pattern `"ID\d{4}"`.
+    for `new_identifier`. The values in both columns all match the pattern `"ID[0-9]{4}"`.
 
     We can also use the `matches()` function in combination with other column selectors (within
     [`col()`](`pointblank.col`)) to create more complex column selection criteria (i.e., to select

pointblank/data/api-docs.txt

@@ -107,6 +107,11 @@ Validate(data: 'FrameT | Any', tbl_name: 'str | None' = None, label: 'str | None
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -580,7 +585,7 @@ Actions(warning: 'str | Callable | list[str | Callable] | None' = None, error: '
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
             actions=pb.Actions(critical="Major data quality issue found in step {step}."),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()
@@ -610,7 +615,7 @@ Actions(warning: 'str | Callable | list[str | Callable] | None' = None, error: '
             data=pb.load_dataset(dataset="game_revenue", tbl_type="duckdb"),
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(
             columns="session_duration",
@@ -6231,7 +6236,7 @@ matches(pattern: 'str', case_sensitive: 'bool' = False) -> 'Matches'
     `[rev_01, rev_02, profit_01, profit_02, age]`
 
     and you want to validate columns that have two digits at the end of the name, you can use
-    `columns=matches(r"\d{2}$")`. This will select the `rev_01`, `rev_02`, `profit_01`, and
+    `columns=matches(r"[0-9]{2}$")`. This will select the `rev_01`, `rev_02`, `profit_01`, and
     `profit_02` columns.
 
     There will be a validation step created for every resolved column. Note that if there aren't any
@@ -6285,7 +6290,7 @@ matches(pattern: 'str', case_sensitive: 'bool' = False) -> 'Matches'
     [`col()`](`pointblank.col`) function, like this:
 
     ```python
-    col(matches(r"^\d{5}") & ends_with("_id"))
+    col(matches(r"^[0-9]{5}") & ends_with("_id"))
     ```
 
     There are four operators that can be used to compose column selectors:
@@ -6324,7 +6329,7 @@ matches(pattern: 'str', case_sensitive: 'bool' = False) -> 'Matches'
 
     validation = (
         pb.Validate(data=tbl)
-        .col_vals_regex(columns=pb.matches("id|identifier"), pattern=r"ID\d{4}")
+        .col_vals_regex(columns=pb.matches("id|identifier"), pattern=r"ID[0-9]{4}")
         .interrogate()
     )
 
@@ -6332,7 +6337,7 @@ matches(pattern: 'str', case_sensitive: 'bool' = False) -> 'Matches'
     ```
 
     From the results of the validation table we get two validation steps, one for `id_old` and one
-    for `new_identifier`. The values in both columns all match the pattern `"ID\d{4}"`.
+    for `new_identifier`. The values in both columns all match the pattern `"ID[0-9]{4}"`.
 
     We can also use the `matches()` function in combination with other column selectors (within
     [`col()`](`pointblank.col`)) to create more complex column selection criteria (i.e., to select
@@ -6875,7 +6880,7 @@ interrogate(self, collect_extracts: 'bool' = True, collect_tbl_checked: 'bool' =
 
         After interrogation is complete, the `Validate` object will have gathered information, and
         we can use methods like [`n_passed()`](`pointblank.Validate.n_passed`),
-        [`f_failed()`](`pointblank.Validate.f_failed`)`, etc., to understand how the table performed
+        [`f_failed()`](`pointblank.Validate.f_failed`), etc., to understand how the table performed
         against the validation plan. A visual representation of the validation results can be viewed
         by printing the `Validate` object; this will display the validation table in an HTML viewing
         environment.
@@ -7578,6 +7583,10 @@ assert_passing(self) -> 'None'
         assertion made is printed in the `AssertionError` message if a failure occurs, ensuring
         some details are preserved.
 
+        If the validation has not yet been interrogated, this method will automatically call
+        [`interrogate()`](`pointblank.Validate.interrogate`) with default parameters before checking
+        for passing tests.
+
         Raises
         -------
         AssertionError
@@ -7587,8 +7596,9 @@ assert_passing(self) -> 'None'
         --------
         In the example below, we'll use a simple Polars DataFrame with three columns (`a`, `b`, and
         `c`). There will be three validation steps, and the second step will have a failing test
-        unit (the value `10` isn't less than `9`). After interrogation, the `assert_passing()`
-        method is used to assert that all validation steps passed perfectly.
+        unit (the value `10` isn't less than `9`). The `assert_passing()` method is used to assert
+        that all validation steps passed perfectly, automatically performing the interrogation if
+        needed.
 
         ```python
         #| error: True
@@ -7609,13 +7619,221 @@ assert_passing(self) -> 'None'
             .col_vals_gt(columns="a", value=0)
             .col_vals_lt(columns="b", value=9) # this assertion is false
             .col_vals_in_set(columns="c", set=["a", "b"])
-            .interrogate()
         )
 
+        # No need to call [`interrogate()`](`pointblank.Validate.interrogate`) explicitly
         validation.assert_passing()
         ```
         
 
+assert_below_threshold(self, level: 'str' = 'warning', i: 'int | None' = None, message: 'str | None' = None) -> 'None'
+
+        Raise an `AssertionError` if validation steps exceed a specified threshold level.
+
+        The `assert_below_threshold()` method checks whether validation steps' failure rates are
+        below a given threshold level (`"warning"`, `"error"`, or `"critical"`). This is
+        particularly useful in automated testing environments where you want to ensure your data
+        quality meets minimum standards before proceeding.
+
+        If any validation step exceeds the specified threshold level, an `AssertionError` will be
+        raised with details about which steps failed. If the validation has not yet been
+        interrogated, this method will automatically call
+        [`interrogate()`](`pointblank.Validate.interrogate`) with default parameters.
+
+        Parameters
+        ----------
+        level
+            The threshold level to check against, which could be any of `"warning"` (the default),
+            `"error"`, or `"critical"`. An `AssertionError` will be raised if any validation step
+            exceeds this level.
+        i
+            Specific validation step number(s) to check. Can be provided as a single integer or a
+            list of integers. If `None` (the default), all steps are checked.
+        message
+            Custom error message to use if assertion fails. If `None`, a default message will be
+            generated that lists the specific steps that exceeded the threshold.
+
+        Returns
+        -------
+        None
+
+        Raises
+        ------
+        AssertionError
+            If any specified validation step exceeds the given threshold level.
+        ValueError
+            If an invalid threshold level is provided.
+
+        Examples
+        --------
+        Below are some examples of how to use the `assert_below_threshold()` method. First, we'll
+        create a simple Polars DataFrame with two columns (`a` and `b`).
+
+        ```python
+        import polars as pl
+
+        tbl = pl.DataFrame({
+            "a": [7, 4, 9, 7, 12],
+            "b": [9, 8, 10, 5, 10]
+        })
+        ```
+
+        Then a validation plan will be created with thresholds (`warning=0.1`, `error=0.2`,
+        `critical=0.3`). After interrogating, we display the validation report table:
+
+        ```python
+        import pointblank as pb
+
+        validation = (
+            pb.Validate(data=tbl, thresholds=(0.1, 0.2, 0.3))
+            .col_vals_gt(columns="a", value=5)   # 1 failing test unit
+            .col_vals_lt(columns="b", value=10)  # 2 failing test units
+            .interrogate()
+        )
+
+        validation
+        ```
+
+        Using `assert_below_threshold(level="warning")` will raise an `AssertionError` if any step
+        exceeds the 'warning' threshold:
+
+        Check a specific step against the 'critical' threshold using the `i=` parameter:
+
+        ```python
+        validation.assert_below_threshold(level="critical", i=1)  # Won't raise an error
+        ```
+
+        As the first step is below the 'critical' threshold (it exceeds the 'warning' and 'error'
+        thresholds), no error is raised and nothing is printed.
+
+        We can also provide a custom error message with the `message=` parameter. Let's try that
+        here:
+
+        ```python
+        try:
+            validation.assert_below_threshold(
+                level="error",
+                message="Data quality too low for processing!"
+            )
+        except AssertionError as e:
+            print(f"Custom error: {e}")
+        ```
+
+        See Also
+        --------
+        - [`warning()`](`pointblank.Validate.warning`): get the 'warning' status for each validation
+        step
+        - [`error()`](`pointblank.Validate.error`): get the 'error' status for each validation step
+        - [`critical()`](`pointblank.Validate.critical`): get the 'critical' status for each
+        validation step
+        - [`assert_passing()`](`pointblank.Validate.assert_passing`): assert all validations pass
+        completely
+        
+
+above_threshold(self, level: 'str' = 'warning', i: 'int | None' = None) -> 'bool'
+
+        Check if any validation steps exceed a specified threshold level.
+
+        The `above_threshold()` method checks whether validation steps exceed a given threshold
+        level. This provides a non-exception-based alternative to
+        [`assert_below_threshold()`](`pointblank.Validate.assert_below_threshold`) for conditional
+        workflow control based on validation results.
+
+        This method is useful in scenarios where you want to check if any validation steps failed
+        beyond a certain threshold without raising an exception, allowing for more flexible
+        programmatic responses to validation issues.
+
+        Parameters
+        ----------
+        level
+            The threshold level to check against. Valid options are: `"warning"` (the least severe
+            threshold level), `"error"` (the middle severity threshold level), and `"critical"` (the
+            most severe threshold level). The default is `"warning"`.
+        i
+            Specific validation step number(s) to check. If a single integer, checks only that step.
+            If a list of integers, checks all specified steps. If `None` (the default), checks all
+            validation steps. Step numbers are 1-based (first step is `1`, not `0`).
+
+        Returns
+        -------
+        bool
+            `True` if any of the specified validation steps exceed the given threshold level,
+            `False` otherwise.
+
+        Raises
+        ------
+        ValueError
+            If an invalid threshold level is provided.
+
+        Examples
+        --------
+        Below are some examples of how to use the `above_threshold()` method. First, we'll create a
+        simple Polars DataFrame with a single column (`values`).
+
+        Then a validation plan will be created with thresholds (`warning=0.1`, `error=0.2`,
+        `critical=0.3`). After interrogating, we display the validation report table:
+
+        ```python
+        import pointblank as pb
+
+        validation = (
+            pb.Validate(data=tbl, thresholds=(0.1, 0.2, 0.3))
+            .col_vals_gt(columns="values", value=0)
+            .col_vals_lt(columns="values", value=10)
+            .col_vals_between(columns="values", left=0, right=5)
+            .interrogate()
+        )
+
+        validation
+        ```
+
+        Let's check if any steps exceed the 'warning' threshold with the `above_threshold()` method.
+        A message will be printed if that's the case:
+
+        ```python
+        if validation.above_threshold(level="warning"):
+            print("Some steps have exceeded the warning threshold")
+        ```
+
+        Check if only steps 2 and 3 exceed the 'error' threshold through use of the `i=` argument:
+
+        ```python
+        if validation.above_threshold(level="error", i=[2, 3]):
+            print("Steps 2 and/or 3 have exceeded the error threshold")
+        ```
+
+        You can use this in a workflow to conditionally trigger processes. Here's a snippet of how
+        you might use this in a function:
+
+        ```python
+        def process_data(validation_obj):
+            # Only continue processing if validation passes critical thresholds
+            if not validation_obj.above_threshold(level="critical"):
+                # Continue with processing
+                print("Data meets critical quality thresholds, proceeding...")
+                return True
+            else:
+                # Log failure and stop processing
+                print("Data fails critical quality checks, aborting...")
+                return False
+        ```
+
+        Note that this is just a suggestion for how to implement conditional workflow processes. You
+        should adapt this pattern to your specific requirements, which might include  different
+        threshold levels, custom logging mechanisms, or integration with your organization's data
+        pipelines and notification systems.
+
+        See Also
+        --------
+        - [`assert_below_threshold()`](`pointblank.Validate.assert_below_threshold`): a similar
+        method that raises an exception if thresholds are exceeded
+        - [`warning()`](`pointblank.Validate.warning`): get the 'warning' status for each validation
+        step
+        - [`error()`](`pointblank.Validate.error`): get the 'error' status for each validation step
+        - [`critical()`](`pointblank.Validate.critical`): get the 'critical' status for each
+        validation step
+        
+
 n(self, i: 'int | list[int] | None' = None, scalar: 'bool' = False) -> 'dict[int, int] | int'
 
         Provides a dictionary of the number of test units for each validation step.
@@ -8504,6 +8722,11 @@ preview(data: 'FrameT | Any', columns_subset: 'str | list[str] | Column | None'
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -8672,6 +8895,11 @@ missing_vals_tbl(data: 'FrameT | Any') -> 'GT'
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -8971,6 +9199,11 @@ get_column_count(data: 'FrameT | Any') -> 'int'
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -9028,6 +9261,11 @@ get_row_count(data: 'FrameT | Any') -> 'int'
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -9467,7 +9705,7 @@ send_slack_notification(webhook_url: 'str | None' = None, step_msg: 'str | None'
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
             actions=pb.Actions(critical=notify_slack),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()
@@ -9499,7 +9737,7 @@ send_slack_notification(webhook_url: 'str | None' = None, step_msg: 'str | None'
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
             final_actions=pb.FinalActions(notify_slack),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()
@@ -9567,7 +9805,7 @@ send_slack_notification(webhook_url: 'str | None' = None, step_msg: 'str | None'
             actions=pb.Actions(default=notify_slack),
             final_actions=pb.FinalActions(notify_slack),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()

pointblank/thresholds.py

@@ -404,7 +404,7 @@ class Actions:
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
             actions=pb.Actions(critical="Major data quality issue found in step {step}."),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(columns="session_duration", value=15)
         .interrogate()
@@ -434,7 +434,7 @@ class Actions:
             data=pb.load_dataset(dataset="game_revenue", tbl_type="duckdb"),
             thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
         )
-        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
+        .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}[0-9]{3}")
         .col_vals_gt(columns="item_revenue", value=0.05)
         .col_vals_gt(
             columns="session_duration",

pointblank/validate.py

@@ -636,6 +636,11 @@ def preview(
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -1134,6 +1139,11 @@ def missing_vals_tbl(data: FrameT | Any) -> GT:
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -1663,6 +1673,11 @@ def get_column_count(data: FrameT | Any) -> int:
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -1741,6 +1756,11 @@ def get_row_count(data: FrameT | Any) -> int:
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -2007,6 +2027,11 @@ class Validate:
     - MySQL table (`"mysql"`)*
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
+    - Microsoft SQL Server table (`"mssql"`)*
+    - Snowflake table (`"snowflake"`)*
+    - Databricks table (`"databricks"`)*
+    - PySpark table (`"pyspark"`)*
+    - BigQuery table (`"bigquery"`)*
     - Parquet table (`"parquet"`)*
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
@@ -8831,7 +8856,7 @@ class Validate:
             raise AssertionError(msg)
 
     def assert_below_threshold(
-        self, level: str = "warning", i: int = None, message: str = None
+        self, level: str = "warning", i: int | None = None, message: str | None = None
     ) -> None:
         """
         Raise an `AssertionError` if validation steps exceed a specified threshold level.
@@ -8940,12 +8965,12 @@ class Validate:
 
         See Also
         --------
-        - [`warning()`](`pointblank.Validate.warning`): Get the 'warning' status for each validation
+        - [`warning()`](`pointblank.Validate.warning`): get the 'warning' status for each validation
         step
-        - [`error()`](`pointblank.Validate.error`): Get the 'error' status for each validation step
-        - [`critical()`](`pointblank.Validate.critical`): Get the 'critical' status for each
+        - [`error()`](`pointblank.Validate.error`): get the 'error' status for each validation step
+        - [`critical()`](`pointblank.Validate.critical`): get the 'critical' status for each
         validation step
-        - [`assert_passing()`](`pointblank.Validate.assert_passing`): Assert all validations pass
+        - [`assert_passing()`](`pointblank.Validate.assert_passing`): assert all validations pass
         completely
         """
         # Check if validation has been interrogated
@@ -8991,6 +9016,145 @@ class Validate:
                 )
             raise AssertionError(msg)
 
+    def above_threshold(self, level: str = "warning", i: int | None = None) -> bool:
+        """
+        Check if any validation steps exceed a specified threshold level.
+
+        The `above_threshold()` method checks whether validation steps exceed a given threshold
+        level. This provides a non-exception-based alternative to
+        [`assert_below_threshold()`](`pointblank.Validate.assert_below_threshold`) for conditional
+        workflow control based on validation results.
+
+        This method is useful in scenarios where you want to check if any validation steps failed
+        beyond a certain threshold without raising an exception, allowing for more flexible
+        programmatic responses to validation issues.
+
+        Parameters
+        ----------
+        level
+            The threshold level to check against. Valid options are: `"warning"` (the least severe
+            threshold level), `"error"` (the middle severity threshold level), and `"critical"` (the
+            most severe threshold level). The default is `"warning"`.
+        i
+            Specific validation step number(s) to check. If a single integer, checks only that step.
+            If a list of integers, checks all specified steps. If `None` (the default), checks all
+            validation steps. Step numbers are 1-based (first step is `1`, not `0`).
+
+        Returns
+        -------
+        bool
+            `True` if any of the specified validation steps exceed the given threshold level,
+            `False` otherwise.
+
+        Raises
+        ------
+        ValueError
+            If an invalid threshold level is provided.
+
+        Examples
+        --------
+        ```{python}
+        #| echo: false
+        #| output: false
+        import pointblank as pb
+        pb.config(report_incl_header=False, report_incl_footer=False, preview_incl_header=False)
+        ```
+        Below are some examples of how to use the `above_threshold()` method. First, we'll create a
+        simple Polars DataFrame with a single column (`values`).
+
+        ```{python}
+        import polars as pl
+
+        tbl = pl.DataFrame({
+            "values": [1, 2, 3, 4, 5, 0, -1]
+        })
+        ```
+
+        Then a validation plan will be created with thresholds (`warning=0.1`, `error=0.2`,
+        `critical=0.3`). After interrogating, we display the validation report table:
+
+        ```{python}
+        import pointblank as pb
+
+        validation = (
+            pb.Validate(data=tbl, thresholds=(0.1, 0.2, 0.3))
+            .col_vals_gt(columns="values", value=0)
+            .col_vals_lt(columns="values", value=10)
+            .col_vals_between(columns="values", left=0, right=5)
+            .interrogate()
+        )
+
+        validation
+        ```
+
+        Let's check if any steps exceed the 'warning' threshold with the `above_threshold()` method.
+        A message will be printed if that's the case:
+
+        ```{python}
+        if validation.above_threshold(level="warning"):
+            print("Some steps have exceeded the warning threshold")
+        ```
+
+        Check if only steps 2 and 3 exceed the 'error' threshold through use of the `i=` argument:
+
+        ```{python}
+        if validation.above_threshold(level="error", i=[2, 3]):
+            print("Steps 2 and/or 3 have exceeded the error threshold")
+        ```
+
+        You can use this in a workflow to conditionally trigger processes. Here's a snippet of how
+        you might use this in a function:
+
+        ```python
+        def process_data(validation_obj):
+            # Only continue processing if validation passes critical thresholds
+            if not validation_obj.above_threshold(level="critical"):
+                # Continue with processing
+                print("Data meets critical quality thresholds, proceeding...")
+                return True
+            else:
+                # Log failure and stop processing
+                print("Data fails critical quality checks, aborting...")
+                return False
+        ```
+
+        Note that this is just a suggestion for how to implement conditional workflow processes. You
+        should adapt this pattern to your specific requirements, which might include  different
+        threshold levels, custom logging mechanisms, or integration with your organization's data
+        pipelines and notification systems.
+
+        See Also
+        --------
+        - [`assert_below_threshold()`](`pointblank.Validate.assert_below_threshold`): a similar
+        method that raises an exception if thresholds are exceeded
+        - [`warning()`](`pointblank.Validate.warning`): get the 'warning' status for each validation
+        step
+        - [`error()`](`pointblank.Validate.error`): get the 'error' status for each validation step
+        - [`critical()`](`pointblank.Validate.critical`): get the 'critical' status for each
+        validation step
+        """
+        # Ensure validation has been run
+        if not hasattr(self, "time_start") or self.time_start is None:
+            return False
+
+        # Validate the level parameter
+        level = level.lower()
+        if level not in ["warning", "error", "critical"]:
+            raise ValueError(
+                f"Invalid threshold level: {level}. Must be one of 'warning', 'error', or 'critical'."
+            )
+
+        # Get the threshold status using the appropriate method
+        if level == "warning":
+            status = self.warning(i=i)
+        elif level == "error":
+            status = self.error(i=i)
+        elif level == "critical":
+            status = self.critical(i=i)
+
+        # Return True if any steps exceeded the threshold
+        return any(status.values())
+
     def n(self, i: int | list[int] | None = None, scalar: bool = False) -> dict[int, int] | int:
         """
         Provides a dictionary of the number of test units for each validation step.

{pointblank-0.9.5.dist-info → pointblank-0.9.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.9.5
+Version: 0.9.6
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License
@@ -55,6 +55,8 @@ Requires-Dist: chatlas>=0.3.0; extra == "generate"
 Requires-Dist: anthropic[bedrock]>=0.45.2; extra == "generate"
 Requires-Dist: openai>=1.63.0; extra == "generate"
 Requires-Dist: shiny>=1.3.0; extra == "generate"
+Provides-Extra: bigquery
+Requires-Dist: ibis-framework[bigquery]>=9.5.0; extra == "bigquery"
 Provides-Extra: databricks
 Requires-Dist: ibis-framework[databricks]>=9.5.0; extra == "databricks"
 Provides-Extra: duckdb

{pointblank-0.9.5.dist-info → pointblank-0.9.6.dist-info}/RECORD

@@ -1,22 +1,22 @@
 pointblank/__init__.py,sha256=uHrX-ARZOhvWogXXqKV65RO2DXdYLZNCD1oNcm8hE6o,1585
-pointblank/_constants.py,sha256=D4HF0NrNAd-mdb88gZ6VatkRYfVX-9gC6C7TOQjjAw4,81128
+pointblank/_constants.py,sha256=YeQVYpSkdQ8v7D8ZJnG-M75zqAH3yJuDzzjwWC2I-d8,81227
 pointblank/_constants_docs.py,sha256=JBmtt16zTYQ-zaM4ElLExtKs-dKlnN553Ys2ML1Y1C8,2099
 pointblank/_constants_translations.py,sha256=HXcCYmKoMjoaFv-Ym4UWv3AsIVXik2zDyAy7xvTvv0Y,186710
 pointblank/_interrogation.py,sha256=U4GQ8Ik5rP75BYBkmunBvHKwf3XvLPHcUx18JwiBQZI,89422
 pointblank/_typing.py,sha256=aItbCbzhbzqjK3lCbL27ltRyXoAH1c3-U6xQdRzg-lU,1594
-pointblank/_utils.py,sha256=CsuUYXNzox-Nc5CjQNhyy2XnmnvYJVJrS5cZxklzIFo,24745
+pointblank/_utils.py,sha256=BoIwMEZYBwPEe5xGku1vSmkgAeGgnA4_bQ4MDeYFGrc,24824
 pointblank/_utils_check_args.py,sha256=rFEc1nbCN8ftsQQWVjCNWmQ2QmUDxkfgmoJclrZeTLs,5489
 pointblank/_utils_html.py,sha256=sTcmnBljkPjRZF1hbpoHl4HmnXOazsA91gC9iWVIrRk,2848
-pointblank/actions.py,sha256=ilk__kbQiS4ieJp-4dM7SDGuobQihUxLyS5ahgiP7qE,18272
+pointblank/actions.py,sha256=D6o9B2_ES9PNQg9HZwREacrrt-3A5bhdrBkL1UXz__s,18281
 pointblank/assistant.py,sha256=ZIQJKTy9rDwq_Wmr1FMp0J7Q3ekxSgF3_tK0p4PTEUM,14850
-pointblank/column.py,sha256=LumGbnterw5VM7-2-7Za3jdlug1VVS9a3TOH0Y1E5eg,76548
+pointblank/column.py,sha256=_FJjpjv760D1p6YGgqbwmKYktouG7AJ2A9uIMYQBTYA,76560
 pointblank/datascan.py,sha256=rRz0hR81uTgd1e9OfLdfsNYXRk8vcpE8PW8exu-GJoE,47697
 pointblank/draft.py,sha256=cusr4fBiNncCKIOU8UwvJcvkBeBuUnqH_UfYp9dtNss,15777
 pointblank/schema.py,sha256=nHkOXykPw7mTmVGjT67hjx13iKySZ5xsfVgPUQV0yCM,44588
 pointblank/tf.py,sha256=8o_8m4i01teulEe3-YYMotSNf3tImjBMInsvdjSAO5Q,8844
-pointblank/thresholds.py,sha256=cweex25DwBPrsvPW12pRoaTQnwFpUUwqTdHyFJXTnN0,25760
-pointblank/validate.py,sha256=DfTChQcLyaJFNLdjkG3jQAsY7GtLvTHSbxkzKusG9I4,615287
-pointblank/data/api-docs.txt,sha256=Sk2ePat_ngz3tAizQVSo7uG_fInv638HFLmM6041osM,482808
+pointblank/thresholds.py,sha256=mybeLzTVdmN04NLKoV-jiSBXsWknwHO0Gox0ttVN_MU,25766
+pointblank/validate.py,sha256=dM5U41me38atNDt1Llzv08gdUcnYyvWoHycQPpctidg,621961
+pointblank/data/api-docs.txt,sha256=6cdUIYdVy2XfGRLNNxtcGTaxu2WX4EXEeICayOvJCTs,492756
 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
@@ -26,8 +26,8 @@ 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-0.9.5.dist-info/licenses/LICENSE,sha256=apLF-HWPNU7pT5bmf5KmZpD5Cklpy2u-BN_0xBoRMLY,1081
-pointblank-0.9.5.dist-info/METADATA,sha256=8SHBgMHqrX9T2cMOfa_cQMDw60NbCmMB1xLgrwWk5vw,14857
-pointblank-0.9.5.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-pointblank-0.9.5.dist-info/top_level.txt,sha256=-wHrS1SvV8-nhvc3w-PPYs1C1WtEc1pK-eGjubbCCKc,11
-pointblank-0.9.5.dist-info/RECORD,,
+pointblank-0.9.6.dist-info/licenses/LICENSE,sha256=apLF-HWPNU7pT5bmf5KmZpD5Cklpy2u-BN_0xBoRMLY,1081
+pointblank-0.9.6.dist-info/METADATA,sha256=_BocxWcU0_AXIiMGBPcxsd9VwrD8uGXjXpjE16hUhVw,14950
+pointblank-0.9.6.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+pointblank-0.9.6.dist-info/top_level.txt,sha256=-wHrS1SvV8-nhvc3w-PPYs1C1WtEc1pK-eGjubbCCKc,11
+pointblank-0.9.6.dist-info/RECORD,,

{pointblank-0.9.5.dist-info → pointblank-0.9.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.7.1)
+Generator: setuptools (80.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any