pointblank 0.9.2__py3-none-any.whl → 0.9.4__py3-none-any.whl

pointblank/_typing.py

@@ -1,26 +1,37 @@
 from __future__ import annotations
 
-from typing import TypeAlias
-
-## Absolute bounds, ie. plus or minus
-AbsoluteBounds: TypeAlias = tuple[int, int]
-
-## Relative bounds, ie. plus or minus some percent
-RelativeBounds: TypeAlias = tuple[float, float]
-
-## Tolerance afforded to some check
-Tolerance: TypeAlias = int | float | AbsoluteBounds | RelativeBounds
-
-## Types for data segmentation
-
-## Value(s) that can be used in a segment tuple
-SegmentValue: TypeAlias = str | list[str]
-
-## (column, value(s)) format for segments
-SegmentTuple: TypeAlias = tuple[str, SegmentValue]
-
-## Individual segment item (string or tuple)
-SegmentItem: TypeAlias = str | SegmentTuple
-
-## Full segment specification options
-SegmentSpec: TypeAlias = str | SegmentTuple | list[SegmentItem]
+import sys
+from typing import List, Tuple, Union
+
+# Check Python version for TypeAlias support
+if sys.version_info >= (3, 10):
+    from typing import TypeAlias
+
+    # Python 3.10+ style type aliases
+    AbsoluteBounds: TypeAlias = Tuple[int, int]
+    RelativeBounds: TypeAlias = Tuple[float, float]
+    Tolerance: TypeAlias = Union[int, float, AbsoluteBounds, RelativeBounds]
+    SegmentValue: TypeAlias = Union[str, List[str]]
+    SegmentTuple: TypeAlias = Tuple[str, SegmentValue]
+    SegmentItem: TypeAlias = Union[str, SegmentTuple]
+    SegmentSpec: TypeAlias = Union[str, SegmentTuple, List[SegmentItem]]
+else:
+    # Python 3.8 and 3.9 compatible type aliases
+    AbsoluteBounds = Tuple[int, int]
+    RelativeBounds = Tuple[float, float]
+    Tolerance = Union[int, float, AbsoluteBounds, RelativeBounds]
+    SegmentValue = Union[str, List[str]]
+    SegmentTuple = Tuple[str, SegmentValue]
+    SegmentItem = Union[str, SegmentTuple]
+    SegmentSpec = Union[str, SegmentTuple, List[SegmentItem]]
+
+# Add docstrings for better IDE support
+AbsoluteBounds.__doc__ = "Absolute bounds (i.e., plus or minus)"
+RelativeBounds.__doc__ = "Relative bounds (i.e., plus or minus some percent)"
+Tolerance.__doc__ = "Tolerance (i.e., the allowed deviation)"
+SegmentValue.__doc__ = "Value(s) that can be used in a segment tuple"
+SegmentTuple.__doc__ = "(column, value(s)) format for segments"
+SegmentItem.__doc__ = "Individual segment item (string or tuple)"
+SegmentSpec.__doc__ = (
+    "Full segment specification options (i.e., all options for segment specification)"
+)

pointblank/validate.py

@@ -385,7 +385,7 @@ def config(
 
 
 def load_dataset(
-    dataset: Literal["small_table", "game_revenue", "nycflights"] = "small_table",
+    dataset: Literal["small_table", "game_revenue", "nycflights", "global_sales"] = "small_table",
     tbl_type: Literal["polars", "pandas", "duckdb"] = "polars",
 ) -> FrameT | Any:
     """
@@ -401,7 +401,7 @@ def load_dataset(
     ----------
     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"`.
@@ -423,6 +423,8 @@ def load_dataset(
     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
     -------------------------
@@ -434,18 +436,18 @@ def load_dataset(
 
     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"`:
 
     ```{python}
     import pointblank as pb
 
-    small_table = pb.load_dataset()
+    small_table = pb.load_dataset(dataset="small_table", tbl_type="polars")
 
     pb.preview(small_table)
     ```
 
-    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.
 
@@ -473,10 +475,23 @@ def load_dataset(
     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.
     """
 
     # Raise an error if the dataset is from the list of provided datasets
-    if dataset not in ["small_table", "game_revenue", "nycflights"]:
+    if dataset not in ["small_table", "game_revenue", "nycflights", "global_sales"]:
         raise ValueError(
             f"The dataset name `{dataset}` is not valid. Choose one of the following:\n"
             "- `small_table`\n"
@@ -518,6 +533,7 @@ def load_dataset(
             "small_table": ["date_time", "date"],
             "game_revenue": ["session_start", "time", "start_day"],
             "nycflights": [],
+            "global_sales": ["timestamp"],
         }
 
         dataset = pd.read_csv(data_path, parse_dates=parse_date_columns[dataset])
@@ -8142,6 +8158,7 @@ class Validate:
             inclusive = validation.inclusive
             na_pass = validation.na_pass
             threshold = validation.thresholds
+            segment = validation.segments
 
             assertion_method = ASSERTION_TYPE_METHOD_MAP[assertion_type]
             assertion_category = METHOD_CATEGORY_MAP[assertion_method]
@@ -8149,7 +8166,14 @@ class Validate:
 
             # Process the `brief` text for the validation step by including template variables to
             # the user-supplied text
-            validation.brief = _process_brief(brief=validation.brief, step=validation.i, col=column)
+            validation.brief = _process_brief(
+                brief=validation.brief,
+                step=validation.i,
+                col=column,
+                values=value,
+                thresholds=threshold,
+                segment=segment,
+            )
 
             # Generate the autobrief description for the validation step; it's important to perform
             # that here since text components like the column and the value(s) have been resolved
@@ -11629,7 +11653,14 @@ def _string_date_dttm_conversion(value: any) -> any:
     return value
 
 
-def _process_brief(brief: str | None, step: int, col: str | list[str] | None) -> str:
+def _process_brief(
+    brief: str | None,
+    step: int,
+    col: str | list[str] | None,
+    values: any | None,
+    thresholds: any | None,
+    segment: any | None,
+) -> str:
     # If there is no brief, return `None`
     if brief is None:
         return None
@@ -11649,6 +11680,34 @@ def _process_brief(brief: str | None, step: int, col: str | list[str] | None) ->
         brief = brief.replace("{col}", col)
         brief = brief.replace("{column}", col)
 
+    if values is not None:
+        # If the value is a list, then join the values into a comma-separated string
+        if isinstance(values, list):
+            values = ", ".join([str(v) for v in values])
+
+        brief = brief.replace("{value}", str(values))
+
+    if thresholds is not None:
+        # Get the string representation of thresholds in the form of:
+        # "W: 0.20 / C: 0.40 / E: 1.00"
+
+        warning_val = thresholds._get_threshold_value(level="warning")
+        error_val = thresholds._get_threshold_value(level="error")
+        critical_val = thresholds._get_threshold_value(level="critical")
+
+        thresholds_fmt = f"W: {warning_val} / E: {error_val} / C: {critical_val}"
+
+        brief = brief.replace("{thresholds}", thresholds_fmt)
+
+    if segment is not None:
+        # The segment is always a tuple of the form ("{column}", "{value}")
+
+        segment_fmt = f"{segment[0]} / {segment[1]}"
+
+        brief = brief.replace("{segment}", segment_fmt)
+        brief = brief.replace("{segment_column}", segment[0])
+        brief = brief.replace("{segment_value}", segment[1])
+
     return brief
 
 

{pointblank-0.9.2.dist-info → pointblank-0.9.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.9.2
+Version: 0.9.4
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License

{pointblank-0.9.2.dist-info → pointblank-0.9.4.dist-info}/RECORD

@@ -3,7 +3,7 @@ pointblank/_constants.py,sha256=D4HF0NrNAd-mdb88gZ6VatkRYfVX-9gC6C7TOQjjAw4,8112
 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=ConITAbsFxU8CkNXY7l0Lua9hGofeDDJAWw-lGAIVgI,764
+pointblank/_typing.py,sha256=aItbCbzhbzqjK3lCbL27ltRyXoAH1c3-U6xQdRzg-lU,1594
 pointblank/_utils.py,sha256=CsuUYXNzox-Nc5CjQNhyy2XnmnvYJVJrS5cZxklzIFo,24745
 pointblank/_utils_check_args.py,sha256=rFEc1nbCN8ftsQQWVjCNWmQ2QmUDxkfgmoJclrZeTLs,5489
 pointblank/_utils_html.py,sha256=sTcmnBljkPjRZF1hbpoHl4HmnXOazsA91gC9iWVIrRk,2848
@@ -15,17 +15,19 @@ pointblank/draft.py,sha256=cusr4fBiNncCKIOU8UwvJcvkBeBuUnqH_UfYp9dtNss,15777
 pointblank/schema.py,sha256=gzUCmtccO2v15MH2bo9uHUYjkKEEne1okQucxcH39pc,44291
 pointblank/tf.py,sha256=8o_8m4i01teulEe3-YYMotSNf3tImjBMInsvdjSAO5Q,8844
 pointblank/thresholds.py,sha256=cweex25DwBPrsvPW12pRoaTQnwFpUUwqTdHyFJXTnN0,25760
-pointblank/validate.py,sha256=0LWCuex5DeNcoRoq0BppcKn1J-WaqCc3TYyQGWB-a2E,606287
+pointblank/validate.py,sha256=9dIWFetyBm70f_Ps0UkroT1gO4b5qACGs8trhObKUHg,608551
 pointblank/data/api-docs.txt,sha256=jKjPSq6X_vU_RRSJAydnVc3C35WvTqNvu-lLKroVO4I,482044
 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
+pointblank/data/global_sales.zip,sha256=JeUnR1apKQ35PPwEcvTKCEIEiYeYQtoGmYjmzbz99DM,2138604
 pointblank/data/nycflights-duckdb.zip,sha256=GQrHO9tp7d9cNGFNSbA9EKF19MLf6t2wZE0U9-hIKow,5293077
 pointblank/data/nycflights.zip,sha256=yVjbUaKUz2LydSdF9cABuir0VReHBBgV7shiNWSd0mU,7828965
 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-0.9.2.dist-info/licenses/LICENSE,sha256=apLF-HWPNU7pT5bmf5KmZpD5Cklpy2u-BN_0xBoRMLY,1081
-pointblank-0.9.2.dist-info/METADATA,sha256=iUvV_QGj9ekzd3ddoPvT-HubBptqM7EIClXJ7HBs8-M,14732
-pointblank-0.9.2.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-pointblank-0.9.2.dist-info/top_level.txt,sha256=-wHrS1SvV8-nhvc3w-PPYs1C1WtEc1pK-eGjubbCCKc,11
-pointblank-0.9.2.dist-info/RECORD,,
+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,,