pointblank 0.8.7__tar.gz → 0.9.1__tar.gz

{pointblank-0.8.7 → pointblank-0.9.1}/.github/workflows/ci-tests.yaml

@@ -29,7 +29,7 @@ jobs:
           pip install -e '.[dev]'
       - name: Install test dependencies
         run: |
-          pip install pytest pytest-cov pytest-snapshot pandas polars ibis-framework[duckdb,mysql,postgres,sqlite]>=9.5.0 chatlas requests shiny
+          pip install pytest pytest-rerunfailures pytest-randomly pytest-xdist pytest-cov pytest-snapshot pandas polars ibis-framework[duckdb,mysql,postgres,sqlite]>=9.5.0 chatlas requests shiny
       - name: pytest unit tests
         run: |
           make test

{pointblank-0.8.7 → pointblank-0.9.1}/Makefile

@@ -1,13 +1,18 @@
 .PHONY: check
 
+.PHONY: test
 test:
-	pytest --cov=pointblank --cov-report=xml
+	@pytest \
+		--cov=pointblank \
+		--cov-report=term-missing \
+		--randomly-seed 123 \
+		-n auto \
+		--reruns 3 \
+		--reruns-delay 1
 
 test-update:
 	pytest --snapshot-update
 
-test-coverage:
-	pytest --cov=pointblank --cov-report=term-missing
 
 lint: ## Run ruff formatter and linter
 	@uv run ruff format

{pointblank-0.8.7 → pointblank-0.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pointblank
-Version: 0.8.7
+Version: 0.9.1
 Summary: Find out if your data is what you think it is.
 Author-email: Richard Iannone <riannone@me.com>
 License: MIT License
@@ -89,6 +89,7 @@ _Data validation made beautiful and powerful_
 [![Python Versions](https://img.shields.io/pypi/pyversions/pointblank.svg)](https://pypi.python.org/pypi/pointblank)
 [![PyPI](https://img.shields.io/pypi/v/pointblank)](https://pypi.org/project/pointblank/#history)
 [![PyPI Downloads](https://img.shields.io/pypi/dm/pointblank)](https://pypistats.org/packages/pointblank)
+[![Conda Version](https://img.shields.io/conda/vn/conda-forge/pointblank.svg)](https://anaconda.org/conda-forge/pointblank)
 [![License](https://img.shields.io/github/license/posit-dev/pointblank)](https://img.shields.io/github/license/posit-dev/pointblank)
 
 [![CI Build](https://github.com/posit-dev/pointblank/actions/workflows/ci-tests.yaml/badge.svg)](https://github.com/posit-dev/pointblank/actions/workflows/ci-tests.yaml)
@@ -108,7 +109,10 @@ _Data validation made beautiful and powerful_
    <a href="translations/README.it.md">Italiano</a> |
    <a href="translations/README.es.md">Español</a> |
    <a href="translations/README.pt-BR.md">Português</a> |
-   <a href="translations/README.zh-CN.md">简体中文</a>
+   <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>
 </div>
 
 ## What is Pointblank?

{pointblank-0.8.7 → pointblank-0.9.1}/README.md

@@ -7,6 +7,7 @@ _Data validation made beautiful and powerful_
 [![Python Versions](https://img.shields.io/pypi/pyversions/pointblank.svg)](https://pypi.python.org/pypi/pointblank)
 [![PyPI](https://img.shields.io/pypi/v/pointblank)](https://pypi.org/project/pointblank/#history)
 [![PyPI Downloads](https://img.shields.io/pypi/dm/pointblank)](https://pypistats.org/packages/pointblank)
+[![Conda Version](https://img.shields.io/conda/vn/conda-forge/pointblank.svg)](https://anaconda.org/conda-forge/pointblank)
 [![License](https://img.shields.io/github/license/posit-dev/pointblank)](https://img.shields.io/github/license/posit-dev/pointblank)
 
 [![CI Build](https://github.com/posit-dev/pointblank/actions/workflows/ci-tests.yaml/badge.svg)](https://github.com/posit-dev/pointblank/actions/workflows/ci-tests.yaml)
@@ -26,7 +27,10 @@ _Data validation made beautiful and powerful_
    <a href="translations/README.it.md">Italiano</a> |
    <a href="translations/README.es.md">Español</a> |
    <a href="translations/README.pt-BR.md">Português</a> |
-   <a href="translations/README.zh-CN.md">简体中文</a>
+   <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>
 </div>
 
 ## What is Pointblank?

{pointblank-0.8.7 → pointblank-0.9.1}/docs/_quarto.yml

@@ -61,10 +61,12 @@ website:
           contents:
             - user-guide/types.qmd
             - user-guide/columns.qmd
-            - user-guide/across.qmd
             - user-guide/preprocessing.qmd
+            - user-guide/segmentation.qmd
+            - user-guide/briefs.qmd
         - section: "Post Interrogation"
           contents:
+            - user-guide/step-reports.qmd
             - user-guide/extracts.qmd
             - user-guide/sundering.qmd
         - section: "Data Inspection"
@@ -126,6 +128,7 @@ quartodoc:
         - name: Validate.col_vals_expr
         - name: Validate.col_exists
         - name: Validate.rows_distinct
+        - name: Validate.rows_complete
         - name: Validate.col_schema_match
         - name: Validate.row_count_match
         - name: Validate.col_count_match

{pointblank-0.8.7 → pointblank-0.9.1}/docs/demos/02-advanced/index.qmd

@@ -15,7 +15,6 @@ A validation with a comprehensive set of rules.
 
 import pointblank as pb
 import polars as pl
-import narwhals as nw
 
 validation = (
     pb.Validate(
@@ -52,7 +51,6 @@ validation
 ```python
 import pointblank as pb
 import polars as pl
-import narwhals as nw
 
 validation = (
     pb.Validate(

{pointblank-0.8.7 → pointblank-0.9.1}/docs/styles.css

@@ -17,6 +17,17 @@ p a {
     text-underline-offset: 4px;
 }
 
+li a {
+    color: black;
+    text-underline-offset: 4px;
+}
+
+dt {
+    height: 32px;
+    overflow-x: scroll;
+    margin-left: -4px;
+}
+
 .table td {
     padding-left: 0px;
 }

{pointblank-0.8.7 → pointblank-0.9.1}/docs/user-guide/actions.qmd

@@ -107,9 +107,18 @@ validation_2 = (
         thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
         actions=pb.Actions(critical=action_str),
     )
-    .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
-    .col_vals_gt(columns="item_revenue", value=0.10)
-    .col_vals_ge(columns="session_duration", value=15)
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.10
+    )
+    .col_vals_ge(
+        columns="session_duration",
+        value=15
+    )
     .interrogate()
 )
 
@@ -139,8 +148,14 @@ validation_3 = (
         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_gt(columns="item_revenue", value=0.05)
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.05
+    )
     .col_vals_gt(
         columns="session_duration",
         value=15,
@@ -191,8 +206,14 @@ validation = (
         actions=pb.Actions(default=print_problem),
         brief=True,
     )
-    .col_vals_regex(columns="player_id", pattern=r"[A-Z]{12}\d{3}")
-    .col_vals_gt(columns="item_revenue", value=0.05)
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.05
+    )
     .col_vals_gt(
         columns="session_duration",
         value=15,
@@ -222,3 +243,196 @@ The metadata dictionary contains the following fields for a given validation ste
 - `level_num`: The severity level as a numeric value (`30`, `40`, or `50`).
 - `autobrief`: A localized and brief statement of the expectation for the step.
 - `failure_text`: Localized text that explains how the validation step failed.
+
+## Final Actions with `FinalActions`
+
+When you need to execute actions after all validation steps are complete, Pointblank provides the
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html) class. Unlike
+[`Actions`](https://posit-dev.github.io/pointblank/reference/Actions.html) which triggers on a
+per-step basis during the validation process,
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html) executes after
+the entire validation is complete, giving you a way to respond to the overall validation results.
+
+Here's how to use
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html):
+
+```{python}
+import pointblank as pb
+
+def send_alert():
+    summary = pb.get_validation_summary()
+    if summary["highest_severity"] == "critical":
+        print(f"ALERT: Critical validation failures found in `{summary['tbl_name']}`")
+
+validation_with_final = (
+    pb.Validate(
+        data=pb.load_dataset(dataset="game_revenue", tbl_type="duckdb"),
+        tbl_name="game_revenue",
+        thresholds=pb.Thresholds(warning=0.05, error=0.10, critical=0.15),
+        final_actions=pb.FinalActions(
+            "Validation complete.",  # a string message
+            send_alert               # a callable function
+        )
+    )
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.10
+    )
+    .interrogate()
+)
+
+validation_with_final
+```
+
+In this example:
+
+- We define the function `send_alert()` that checks the validation summary for critical failures
+- We provide a simple string message `"Validation complete."` that will print to the console
+- Both actions will execute in order after all validation steps have completed
+
+Because the 'critical' threshold was exceeded in Step 2, we see the printed alert of `send_alert()`
+after the simple string message.
+
+### Creating Final Actions
+
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html) accepts any
+number of actions as positional arguments. Each argument can be:
+
+1. **String**: A message to be displayed in the console
+2. **Callable**: A function to be called with no arguments
+3. **List of Strings/Callables**: Multiple actions to execute in sequence
+
+All actions will be executed in the order they are provided after all validation steps have
+completed.
+
+### Using `get_validation_summary()` in Final Actions
+
+When creating a callable function to use with
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html), you can access
+information about the overall validation results using the
+[`get_validation_summary()`](https://posit-dev.github.io/pointblank/reference/get_validation_summary.html)
+function. This gives you a dictionary with comprehensive information about the validation:
+
+```python
+def comprehensive_report():
+    summary = pb.get_validation_summary()
+    print(f"Validation Report for {summary['tbl_name']}:")
+    print(f"- Steps: {summary['n_steps']}")
+    print(f"- Passing steps: {summary['n_passing_steps']}")
+    print(f"- Failing steps: {summary['n_failing_steps']}")
+
+    # Take additional actions based on results
+    if summary["n_failing_steps"] > 0:
+        # Create and execute a Slack notification
+        notify = pb.send_slack_notification(
+            webhook_url="https://hooks.slack.com/services/your/webhook/url",
+            summary_msg="""
+            🚨 *Validation Failure Alert*
+            • Table: {tbl_name}
+            • Failed Steps: {n_failing_steps} of {n_steps}
+            • Highest Severity: {highest_severity}
+            • Time: {time}
+            """,
+        )
+        notify()  # Execute the notification function
+
+
+validation = (
+    pb.Validate(
+        data=pb.load_dataset(dataset="game_revenue", tbl_type="duckdb"),
+        tbl_name="game_revenue",
+        final_actions=pb.FinalActions(comprehensive_report),
+    )
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.05
+    )
+    .interrogate()
+)
+
+validation
+```
+
+```{python}
+# | echo: false
+
+validation = (
+    pb.Validate(
+        data=pb.load_dataset(dataset="game_revenue", tbl_type="duckdb"),
+        tbl_name="game_revenue",
+    )
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.05
+    )
+    .interrogate()
+)
+
+validation
+```
+
+Here we used the [`send_slack_notification()`](https://posit-dev.github.io/pointblank/reference/send_slack_notification.html)
+function, which is available in Pointblank as a pre-built action. It can be used by itself in
+`final_actions=` but here it's integrated into the user's `comprehensive_report()` function.
+
+### Combining the Two Types of Actions
+
+You can use both [`Actions`](https://posit-dev.github.io/pointblank/reference/Actions.html) and
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html) together for
+comprehensive validation control:
+
+```{python}
+def log_step_failure():
+    m = pb.get_action_metadata()
+    print(f"Step {m['step']} failed with {m['level']}")
+
+
+def generate_summary():
+    summary = pb.get_validation_summary()
+    # Sum up total failed test units across all steps
+    total_failed = sum(summary["dict_n_failed"].values())
+    # Sum up total test units across all steps
+    total_units = sum(summary["dict_n"].values())
+    print(f"Validation complete: {total_failed} failures out of {total_units} tests")
+
+
+validation_combined = (
+    pb.Validate(
+        data=pb.load_dataset(dataset="game_revenue", tbl_type="duckdb"),
+        thresholds=pb.Thresholds(warning=0.05, error=0.10),
+        actions=pb.Actions(default=log_step_failure),
+        final_actions=pb.FinalActions(generate_summary),
+    )
+    .col_vals_regex(
+        columns="player_id",
+        pattern=r"[A-Z]{12}\d{3}"
+    )
+    .col_vals_gt(
+        columns="item_revenue",
+        value=0.05
+    )
+    .interrogate()
+)
+```
+
+This approach allows you to:
+
+1. Log individual step failures during the validation process using
+[`Actions`](https://posit-dev.github.io/pointblank/reference/Actions.html)
+2. Generate a comprehensive report after all validation steps are complete using
+[`FinalActions`](https://posit-dev.github.io/pointblank/reference/FinalActions.html)
+
+Using both action types gives you fine-grained control over when and how notifications and other
+actions are triggered in your validation workflow.