pointblank 0.9.4__py3-none-any.whl → 0.9.5__py3-none-any.whl

pointblank/data/api-docs.txt

@@ -8837,7 +8837,7 @@ assistant(model: 'str', data: 'FrameT | Any | None' = None, tbl_name: 'str | Non
     Pandas DataFrame, the availability of Ibis is not needed.
     
 
-load_dataset(dataset: "Literal['small_table', 'game_revenue', 'nycflights']" = 'small_table', tbl_type: "Literal['polars', 'pandas', 'duckdb']" = 'polars') -> 'FrameT | Any'
+load_dataset(dataset: "Literal['small_table', 'game_revenue', 'nycflights', 'global_sales']" = 'small_table', tbl_type: "Literal['polars', 'pandas', 'duckdb']" = 'polars') -> 'FrameT | Any'
 
     Load a dataset hosted in the library as specified table type.
 
@@ -8851,7 +8851,7 @@ load_dataset(dataset: "Literal['small_table', 'game_revenue', 'nycflights']" = '
     ----------
     dataset
         The name of the dataset to load. Current options are `"small_table"`, `"game_revenue"`,
-        and `"nycflights"`.
+        `"nycflights"`, and `"global_sales"`.
     tbl_type
         The type of table to generate from the dataset. The named options are `"polars"`,
         `"pandas"`, and `"duckdb"`.
@@ -8873,6 +8873,8 @@ load_dataset(dataset: "Literal['small_table', 'game_revenue', 'nycflights']" = '
     they purchased, ads viewed, and the revenue generated.
     - `"nycflights"`: A dataset with 336,776 rows and 18 columns. This dataset provides information
     about flights departing from New York City airports (JFK, LGA, or EWR) in 2013.
+    - `"global_sales"`: A dataset with 50,000 rows and 20 columns. Provides information about
+    global sales of products across different regions and countries.
 
     Supported DataFrame Types
     -------------------------
@@ -8884,10 +8886,10 @@ load_dataset(dataset: "Literal['small_table', 'game_revenue', 'nycflights']" = '
 
     Examples
     --------
-    Load the `"small_table"` dataset as a Polars DataFrame by calling `load_dataset()` with its
-    defaults:
+    Load the `"small_table"` dataset as a Polars DataFrame by calling `load_dataset()` with
+    `dataset="small_table"` and `tbl_type="polars"`:
 
-    Note that the `"small_table"` dataset is a simple Polars DataFrame and using the
+    Note that the `"small_table"` dataset is a Polars DataFrame and using the
     [`preview()`](`pointblank.preview`) function will display the table in an HTML viewing
     environment.
 
@@ -8915,6 +8917,19 @@ load_dataset(dataset: "Literal['small_table', 'game_revenue', 'nycflights']" = '
     The `"nycflights"` dataset is a large dataset with 336,776 rows and 18 columns. This dataset is
     truly a real-world dataset and provides information about flights originating from New York City
     airports in 2013.
+
+    Finally, the `"global_sales"` dataset can be loaded as a Polars table by specifying the dataset
+    name. Since `tbl_type=` is set to `"polars"` by default, we don't need to specify it:
+
+    ```python
+    global_sales = pb.load_dataset(dataset="global_sales")
+
+    pb.preview(global_sales)
+    ```
+
+    The `"global_sales"` dataset is a large dataset with 50,000 rows and 20 columns. Each record
+    describes the sales of a particular product to a customer located in one of three global
+    regions: North America, Europe, or Asia.
     
 
 

pointblank/schema.py

@@ -728,7 +728,14 @@ class Schema:
                 return new_schema
 
     def __str__(self):
-        return "Pointblank Schema\n" + "\n".join([f"  {col[0]}: {col[1]}" for col in self.columns])
+        formatted_columns = []
+        for col in self.columns:
+            if len(col) == 1:  # Only column name provided (no data type)
+                formatted_columns.append(f"  {col[0]}: <ANY>")
+            else:  # Both column name and data type provided
+                formatted_columns.append(f"  {col[0]}: {col[1]}")
+
+        return "Pointblank Schema\n" + "\n".join(formatted_columns)
 
     def __repr__(self):
         return f"Schema(columns={self.columns})"

pointblank/validate.py

@@ -8031,7 +8031,7 @@ class Validate:
 
         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.
@@ -8772,6 +8772,10 @@ class Validate:
         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
@@ -8781,8 +8785,9 @@ class Validate:
         --------
         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
@@ -8803,12 +8808,16 @@ class Validate:
             .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()
         ```
         """
+        # Check if validation has been interrogated
+        if not hasattr(self, "time_start") or self.time_start is None:
+            # Auto-interrogate with default parameters
+            self.interrogate()
 
         if not self.all_passed():
             failed_steps = [
@@ -8821,6 +8830,167 @@ class Validate:
             )
             raise AssertionError(msg)
 
+    def assert_below_threshold(
+        self, level: str = "warning", i: int = None, message: str = 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
+        --------
+        ```{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 `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:
+
+        ```{python}
+        try:
+            validation.assert_below_threshold(level="warning")
+        except AssertionError as e:
+            print(f"Assertion failed: {e}")
+        ```
+
+        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
+        """
+        # Check if validation has been interrogated
+        if not hasattr(self, "time_start") or self.time_start is None:
+            # Auto-interrogate with default parameters
+            self.interrogate()
+
+        # 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)
+
+        # Find any steps that exceeded the threshold
+        failures = []
+        for step_num, exceeded in status.items():
+            if exceeded:
+                # Get the step's description
+                validation_step = self.validation_info[step_num - 1]
+                step_descriptor = (
+                    validation_step.autobrief
+                    if hasattr(validation_step, "autobrief") and validation_step.autobrief
+                    else f"Validation step {step_num}"
+                )
+                failures.append(f"Step {step_num}: {step_descriptor}")
+
+        # If any failures were found, raise an AssertionError
+        if failures:
+            if message:
+                msg = message
+            else:
+                msg = f"The following steps exceeded the {level} threshold level:\n" + "\n".join(
+                    failures
+                )
+            raise AssertionError(msg)
+
     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-0.9.4.dist-info → pointblank-0.9.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.9.4
+Version: 0.9.5
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License
@@ -103,7 +103,7 @@ _Data validation made beautiful and powerful_
 
 </div>
 
-<div align="right">
+<div align="center">
    <a href="translations/README.fr.md">Français</a> |
    <a href="translations/README.de.md">Deutsch</a> |
    <a href="translations/README.it.md">Italiano</a> |
@@ -112,7 +112,9 @@ _Data validation made beautiful and powerful_
    <a href="translations/README.nl.md">Nederlands</a> |
    <a href="translations/README.zh-CN.md">简体中文</a> |
    <a href="translations/README.ja.md">日本語</a> |
-   <a href="translations/README.ko.md">한국어</a>
+   <a href="translations/README.ko.md">한국어</a> |
+   <a href="translations/README.hi.md">हिन्दी</a> |
+   <a href="translations/README.ar.md">العربية</a>
 </div>
 
 ## What is Pointblank?

{pointblank-0.9.4.dist-info → pointblank-0.9.5.dist-info}/RECORD

@@ -12,11 +12,11 @@ pointblank/assistant.py,sha256=ZIQJKTy9rDwq_Wmr1FMp0J7Q3ekxSgF3_tK0p4PTEUM,14850
 pointblank/column.py,sha256=LumGbnterw5VM7-2-7Za3jdlug1VVS9a3TOH0Y1E5eg,76548
 pointblank/datascan.py,sha256=rRz0hR81uTgd1e9OfLdfsNYXRk8vcpE8PW8exu-GJoE,47697
 pointblank/draft.py,sha256=cusr4fBiNncCKIOU8UwvJcvkBeBuUnqH_UfYp9dtNss,15777
-pointblank/schema.py,sha256=gzUCmtccO2v15MH2bo9uHUYjkKEEne1okQucxcH39pc,44291
+pointblank/schema.py,sha256=nHkOXykPw7mTmVGjT67hjx13iKySZ5xsfVgPUQV0yCM,44588
 pointblank/tf.py,sha256=8o_8m4i01teulEe3-YYMotSNf3tImjBMInsvdjSAO5Q,8844
 pointblank/thresholds.py,sha256=cweex25DwBPrsvPW12pRoaTQnwFpUUwqTdHyFJXTnN0,25760
-pointblank/validate.py,sha256=9dIWFetyBm70f_Ps0UkroT1gO4b5qACGs8trhObKUHg,608551
-pointblank/data/api-docs.txt,sha256=jKjPSq6X_vU_RRSJAydnVc3C35WvTqNvu-lLKroVO4I,482044
+pointblank/validate.py,sha256=DfTChQcLyaJFNLdjkG3jQAsY7GtLvTHSbxkzKusG9I4,615287
+pointblank/data/api-docs.txt,sha256=Sk2ePat_ngz3tAizQVSo7uG_fInv638HFLmM6041osM,482808
 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-0.9.4.dist-info/licenses/LICENSE,sha256=apLF-HWPNU7pT5bmf5KmZpD5Cklpy2u-BN_0xBoRMLY,1081
-pointblank-0.9.4.dist-info/METADATA,sha256=TO7kSRz1e8_lhuqkF6st8ompJq-I0i5mevVfsCiHumU,14732
-pointblank-0.9.4.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-pointblank-0.9.4.dist-info/top_level.txt,sha256=-wHrS1SvV8-nhvc3w-PPYs1C1WtEc1pK-eGjubbCCKc,11
-pointblank-0.9.4.dist-info/RECORD,,
+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-0.9.4.dist-info → pointblank-0.9.5.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.3.1)
+Generator: setuptools (80.7.1)
 Root-Is-Purelib: true
 Tag: py3-none-any