duckguard 2.3.0__py3-none-any.whl → 3.0.1__py3-none-any.whl

{duckguard-2.3.0.dist-info → duckguard-3.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckguard
-Version: 2.3.0
+Version: 3.0.1
 Summary: A Python-native data quality tool with AI superpowers, built on DuckDB for speed
 Project-URL: Homepage, https://github.com/XDataHubAI/duckguard
 Project-URL: Documentation, https://github.com/XDataHubAI/duckguard
@@ -50,6 +50,7 @@ Requires-Dist: pymongo>=4.0.0; extra == 'all'
 Requires-Dist: pymysql>=1.0.0; extra == 'all'
 Requires-Dist: pyodbc>=4.0.0; extra == 'all'
 Requires-Dist: redshift-connector>=2.0.0; extra == 'all'
+Requires-Dist: scipy>=1.11.0; extra == 'all'
 Requires-Dist: snowflake-connector-python>=3.0.0; extra == 'all'
 Requires-Dist: weasyprint>=60.0; extra == 'all'
 Provides-Extra: bigquery
@@ -70,9 +71,13 @@ Requires-Dist: databricks-sql-connector>=2.0.0; extra == 'databricks'
 Provides-Extra: dev
 Requires-Dist: black>=23.0.0; extra == 'dev'
 Requires-Dist: mypy>=1.0.0; extra == 'dev'
+Requires-Dist: numpy>=1.24.0; extra == 'dev'
+Requires-Dist: pandas>=2.0.0; extra == 'dev'
+Requires-Dist: psutil>=5.9.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
 Requires-Dist: pytest>=7.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Requires-Dist: scipy>=1.11.0; extra == 'dev'
 Provides-Extra: kafka
 Requires-Dist: kafka-python>=2.0.0; extra == 'kafka'
 Provides-Extra: llm
@@ -95,6 +100,8 @@ Provides-Extra: snowflake
 Requires-Dist: snowflake-connector-python>=3.0.0; extra == 'snowflake'
 Provides-Extra: sqlserver
 Requires-Dist: pyodbc>=4.0.0; extra == 'sqlserver'
+Provides-Extra: statistics
+Requires-Dist: scipy>=1.11.0; extra == 'statistics'
 Description-Content-Type: text/markdown
 
 <div align="center">
@@ -137,6 +144,118 @@ assert orders.status.isin(['pending', 'shipped', 'delivered'])
 
 ---
 
+## What's New in 3.0
+
+DuckGuard 3.0 introduces **23 new check types** and powerful validation capabilities that make complex data quality checks simple.
+
+### Conditional Expectations
+
+Apply validation rules only when certain conditions are met:
+
+```python
+# Validate state is not null only for US orders
+orders.state.not_null_when("country = 'USA'")
+
+# Check shipping_cost only for orders that were shipped
+orders.shipping_cost.greater_than_when(0, "status = 'shipped'")
+
+# Require tracking_number for expedited orders
+orders.tracking_number.not_null_when("shipping_type = 'expedited'")
+```
+
+### Multi-Column Expectations
+
+Validate relationships between columns with cross-column checks:
+
+```python
+# Ensure end_date comes after start_date
+orders.expect_column_pair_satisfy("end_date", "start_date", "end_date >= start_date")
+
+# Validate discount doesn't exceed original price
+orders.expect_column_pair_satisfy("discount", "price", "discount <= price")
+
+# Check that total matches sum of components
+orders.expect_column_pair_satisfy("total", "subtotal", "total = subtotal + tax")
+```
+
+### Query-Based Expectations
+
+Run custom SQL queries for unlimited flexibility:
+
+```python
+# Ensure no negative amounts
+orders.expect_query_to_return_no_rows("SELECT * FROM table WHERE amount < 0")
+
+# Validate business rules
+orders.expect_query_to_return_no_rows(
+    "SELECT * FROM table WHERE status = 'shipped' AND tracking_number IS NULL"
+)
+
+# Check referential integrity with custom logic
+orders.expect_query_result_equals(
+    "SELECT COUNT(*) FROM orders WHERE customer_id NOT IN (SELECT id FROM customers)",
+    0
+)
+```
+
+### Distributional Checks
+
+Test if data follows expected statistical distributions:
+
+```python
+# Test for normal distribution
+data.values.expect_distribution_normal()
+
+# Test for uniform distribution
+data.values.expect_distribution_uniform()
+
+# Chi-square goodness of fit test
+data.category.expect_distribution_chi_square(expected_freq={'A': 0.5, 'B': 0.3, 'C': 0.2})
+
+# Kolmogorov-Smirnov test for distribution matching
+current.amount.expect_distribution_ks_test(baseline.amount)
+```
+
+### Enhanced Profiling
+
+Four new profiling modules for deeper data insights:
+
+```python
+from duckguard.profiling import (
+    DistributionProfiler,   # Statistical distributions and shape analysis
+    CorrelationProfiler,    # Column relationships and dependencies
+    PatternProfiler,        # Detect common patterns in text data
+    TimeSeriesProfiler      # Temporal patterns and trends
+)
+
+# Analyze distributions
+dist_profile = DistributionProfiler().profile(orders)
+print(f"Amount distribution: {dist_profile['amount'].distribution_type}")  # 'normal', 'skewed', etc.
+
+# Discover correlations
+corr_profile = CorrelationProfiler().profile(orders)
+print(f"Highly correlated pairs: {corr_profile.high_correlations}")
+
+# Find patterns in text columns
+pattern_profile = PatternProfiler().profile(orders)
+print(f"Email pattern: {pattern_profile['email'].common_pattern}")  # Regex pattern
+
+# Analyze time series
+ts_profile = TimeSeriesProfiler().profile(orders, date_column='order_date')
+print(f"Seasonality detected: {ts_profile.has_seasonality}")
+```
+
+### More Validation Power
+
+DuckGuard 3.0 adds 23 new check types including:
+- **Conditional validations**: `not_null_when()`, `between_when()`, `isin_when()`
+- **Multi-column checks**: `expect_column_pair_satisfy()`, `expect_column_sum_equals()`
+- **Query-based**: `expect_query_to_return_no_rows()`, `expect_query_result_equals()`
+- **Distribution tests**: `expect_distribution_normal()`, `expect_distribution_chi_square()`
+- **Advanced string**: `expect_column_values_to_match_strftime()`, `expect_column_values_to_be_json()`
+
+---
+
 ## Why DuckGuard?
 
 ### The Problem

{duckguard-2.3.0.dist-info → duckguard-3.0.1.dist-info}/RECORD

@@ -1,18 +1,23 @@
-duckguard/__init__.py,sha256=TUiy1yQKA20tv77qAFsFrk_yjWuzQD9csTKCtweQ_S4,3078
+duckguard/__init__.py,sha256=hi1-MykRG4918Yj_vkOcnqQOyGZXS7fmqvkKDQcW2kU,3078
 duckguard/errors.py,sha256=xhQPxCCeB3dCQspTbQf58h_DvwHP1vAb6vKI9fHYAJ0,11493
 duckguard/anomaly/__init__.py,sha256=mrTyL70cOR5S7_RNc9QLADdnBimIsbAoFTbKlWiIsbw,1353
 duckguard/anomaly/baselines.py,sha256=k28CjjqBa8IaZxnIgof-wjw_Xdb7NJZImC2OJJkGXQ8,8776
 duckguard/anomaly/detector.py,sha256=voA7WS2x2p5h5cnwH3C_2ly7HdYpXLwC4jDiPL2Xleo,12443
-duckguard/anomaly/methods.py,sha256=CtV2G-kowXGgz0HYvNoi2Ge7eyHUg2GwGa3oZvunS38,13475
-duckguard/anomaly/ml_methods.py,sha256=UyEr8q4K_wNq7pWgTsV23IoBI13aqm0hHIwIFjIxeas,23449
+duckguard/anomaly/methods.py,sha256=IRt7_1YWGaQHz2syfEd89lL6kAjOjheSk6ayLRUi58M,15237
+duckguard/anomaly/ml_methods.py,sha256=Ne8BOULj-bcPmf1_YAqJqnlXDlljfhsxvFbBIjWkJB8,28221
+duckguard/checks/__init__.py,sha256=aSxO02ZILHnfrGhfomQ5EN69t7NZ4yr61Etwtcv_zIw,847
+duckguard/checks/conditional.py,sha256=gYFZD_6M-IUs1MGMZeDYH-qC99dyMJ-u63r1SgcBVs8,26646
+duckguard/checks/distributional.py,sha256=Cy3YlWnSPA5QZdNT_lYuTMRLrwvU1yJGk--RGzOQ5N4,18302
+duckguard/checks/multicolumn.py,sha256=cZhvW1S9qniQACz11tPtIWsBmcBVmz0kKpEDMnZ9ub0,23623
+duckguard/checks/query_based.py,sha256=T0shCxdPOQo70KUjV_5OUZTfOm6W2PJDWUUrQzD53-0,22045
 duckguard/cli/__init__.py,sha256=s5MNXEu_MbRqyV-jeUgCIDlHRQA97a9knM_anJooTl0,87
 duckguard/cli/main.py,sha256=sMq5RfM0-OeXTG_jgTRGyvfw-c4iwojNGUEW8AYQ3fA,46001
 duckguard/connectors/__init__.py,sha256=BMbVyyBPI9_GAFcwkQivf2xMvHwVOHvBMuT5qZ558jc,2232
 duckguard/connectors/base.py,sha256=XzGY6_pUwDJIVNhTfgNMkcGNOBs3xxjbnQ_NeMoz4eM,1864
 duckguard/connectors/bigquery.py,sha256=b-EHAF90dbyCh387qNirkRGY0sEsPAmvy-hNCbY7ilQ,5327
 duckguard/connectors/databricks.py,sha256=vsm5wWGb6V_J1yMdXyREjy9ElR84S0aLk0NgOAbd1J4,6550
-duckguard/connectors/factory.py,sha256=brO5ypD9nriHqWNN4x9KItq3mTtjcy5nM6eu5luS9RU,9156
-duckguard/connectors/files.py,sha256=QU5lFWf9NUv0lX_txx_CLfTzhcF7tAZtCGZOCrzX-tk,3841
+duckguard/connectors/factory.py,sha256=KA5uoN-2LPEJxNXDXpv2sKuyxTcNm2svmg9zSilgF_M,10246
+duckguard/connectors/files.py,sha256=V584kLHGLbZ3nCe2LbBdkTLcMc54VY-dSvHXKm_ffx8,4026
 duckguard/connectors/kafka.py,sha256=Oo_axyJck6gHrwLFpnGcUVKEfKqxqz-AEdlVkNBYVVE,10709
 duckguard/connectors/mongodb.py,sha256=3RI3-hiTHXQIk5cg9ZM5q2UDn5HU2wDnq-f8xj-Yc2A,7271
 duckguard/connectors/mysql.py,sha256=EW-VrZiNgOGFVnVccTR-jVrn3S6KHK6GA-Yj3kmmU5w,3875
@@ -29,10 +34,10 @@ duckguard/contracts/loader.py,sha256=iTmg9xjSAlYsBpQeTAJ1-ABQnuXs-qpMh3DH4rfN6qs
 duckguard/contracts/schema.py,sha256=pLoR4QIXs68Q93DOZqqTmPnPecCeZ4iy9lDXZMNuVmI,7032
 duckguard/contracts/validator.py,sha256=X972Ns-8UWBL8D4nCCQlNOHJas0Mc4ES8URbKqd0WLw,16432
 duckguard/core/__init__.py,sha256=pHndzrdehB0GFtlSQ46uvw8XgUQj55dVZQP1ZK-aDso,356
-duckguard/core/column.py,sha256=ux3B2HyrgXLkz0tCY4EmR7JVRoedzCfURhzCfuO-tU8,35346
-duckguard/core/dataset.py,sha256=SBwrXLtZyf-bkT1o42OU6tURWP7TOL4uBZ0BBMR3wD8,33287
+duckguard/core/column.py,sha256=88m3WipKNdNslXNWAk4ofTf0kmNlDDAyhjDUa-Q6UGg,48326
+duckguard/core/dataset.py,sha256=kQY2ALTsid5x1NWOM5Wse60mOrLdUj8lKUs1cLK7cCo,44364
 duckguard/core/engine.py,sha256=ld_NHsWyBkVynmWyvbyQcHdXHhpIoSaRDyqAAtVx8J0,7897
-duckguard/core/result.py,sha256=BwmP0gNPAKVYHdyque1rDkbAhEvwFaA3PwhxaI7cY14,15178
+duckguard/core/result.py,sha256=kQ_tzDkxjJTGK_k1P6crprrrYIszokhSxQMGlP1laAw,15316
 duckguard/core/scoring.py,sha256=42CVgxmmfo3Yb3m3Xl8qWnDgR7ndSZd8vXRwy9XSThI,16826
 duckguard/freshness/__init__.py,sha256=8XR7JxH9tz61En5DTMSDHrjhroPzvwCTVzBbBiRFexs,854
 duckguard/freshness/monitor.py,sha256=O_b4fh6unyZ2DXioX6O7KP9VpenGdLTpb9OdNb79dX8,14695
@@ -44,11 +49,15 @@ duckguard/integrations/__init__.py,sha256=SuqOzfdaejlMCti372FHD_R6bVaPaUmfEPG9IM
 duckguard/integrations/airflow.py,sha256=pxC14Kgwou_2xWPvTfx8YWO-xg_vgFeAlGDhgGfXRyM,13195
 duckguard/integrations/dbt.py,sha256=Dw1meY-UhylDFhUZ2s47FnJGMp_gszHvadGn_hqYkSM,14101
 duckguard/notifications/__init__.py,sha256=qEfUvt7d_WXlbsGlLB-FaNF4ksLtAyO8JXi1JCdo89w,1541
-duckguard/notifications/email.py,sha256=jwgxec8r6NUNqrxz3v5B4A3UL0-ZdxnJZhXQXWgMWH4,17168
+duckguard/notifications/email.py,sha256=6qmHXufExnczyXEpa1dt6A6dli0kgRHZV_DhEkfMsj4,17677
 duckguard/notifications/formatter.py,sha256=Z2vGMpLdqPWYaYTaVtVjYnIbNU8Haer-7efohZ5IZxM,3991
-duckguard/notifications/notifiers.py,sha256=e-UBvoskFSzIwlCFTxIFdkI-z54zZeEeSQkvOvgV6JI,11703
+duckguard/notifications/notifiers.py,sha256=nViWe2rms8C9t05WMbc2mwJrryS7V8N2OBSJ3u0PQGE,13023
 duckguard/profiler/__init__.py,sha256=a16GYeeFDZzwCemTsTuzO3Ih4M7_hOPb9hS8yt-nHzU,169
 duckguard/profiler/auto_profile.py,sha256=KbAkty-HrpNbTribi2uD17Fcsb-UiV5eG4zZsbyBOL4,12267
+duckguard/profiler/distribution_analyzer.py,sha256=I_jnDUtEG260yu7zEBU-2vHRIeYpAzuF-HKX99i8MGU,12644
+duckguard/profiler/outlier_detector.py,sha256=5c28HEWC4UobBVYsVnNRzJJvm1uz6BKXNfmZfJDlQ2A,15928
+duckguard/profiler/pattern_matcher.py,sha256=ue1x57fcQBivW9w3WjaAB-KDamjguK1D2H0r1cnpnPk,9387
+duckguard/profiler/quality_scorer.py,sha256=R7cfzPTxL6tMSb-cuNgCygquz92tXmB6BMEPmVZKmD0,13896
 duckguard/pytest_plugin/__init__.py,sha256=GuhFPvINnpoVSxhvCX9b5dymzdhsn2KZhXU6okk4xQU,168
 duckguard/pytest_plugin/plugin.py,sha256=SA1dvkZ0MYyNyRXzuqelreEo2zK0XTsNZeYwUYd3Gy0,4949
 duckguard/reporting/__init__.py,sha256=R7Fm--yEiuOb_II-Qo7MGXYyCNhsGnVsMVuAzZT6rIM,199
@@ -58,10 +67,10 @@ duckguard/reports/__init__.py,sha256=JGGZ2IJFVOutcQaZ8kpjDDKJru9e5EsVi91au2VFKsk
 duckguard/reports/html_reporter.py,sha256=_8jzHg6WzC4xqXgqzHzYQTjE4vXbQGP-p1FUKmYAtuU,20670
 duckguard/reports/pdf_reporter.py,sha256=u6zuV24y9YCBlpDwDObHTSrVE9W9beTIqj-UQyvA8jQ,3094
 duckguard/rules/__init__.py,sha256=XYVasAnu8ErJ-Cvsqeh1mX5zxqd1wk-sM4OzuBJn72Y,813
-duckguard/rules/executor.py,sha256=0MKi4mA0Ig873J7JDKpE_O2OJsBFSx6w2jgcGQWl_8w,20720
+duckguard/rules/executor.py,sha256=AL32_0CwLZCg4oP64jIV1a6gL94WT0pjMnYurA3BWx0,43410
 duckguard/rules/generator.py,sha256=h8NWcRsqBqj4xEddavFRlnWZfCi3eoXsqWyIJmxPGeo,11184
 duckguard/rules/loader.py,sha256=gzFihSX6w3lpldEXVUn0Ysh9MAOEXh3ABNqJrVlGEng,14622
-duckguard/rules/schema.py,sha256=_YHgZSau89SuECHWdwHtUmO65HZrNFZkaIz7l3cqhEI,10755
+duckguard/rules/schema.py,sha256=EcmJfib-wSDDNwBphXN75Jn84BzgEvbVCQmIOdgr4DE,12693
 duckguard/schema_history/__init__.py,sha256=q7Kofw5PxbJlXTLzXNZyhvpsrYDKJl1OScWVwEGYIkY,949
 duckguard/schema_history/analyzer.py,sha256=NRDQCjhPstmp6zD7Co0D4D6jVSJ9SB-iAmv4GUQdvJc,14396
 duckguard/schema_history/tracker.py,sha256=ZuMYX8knruiodXd22KoGaT7MgQBElDjekNz73aSwkqI,8468
@@ -70,8 +79,8 @@ duckguard/semantic/analyzer.py,sha256=2be1oofe-owBhTg-Dy88-wihaoTQ7DPxf1NuA1sgfR
 duckguard/semantic/detector.py,sha256=MPdb2Rv9VGQBko7nmPk4-Kjga_XVjPZdHCr29gdET0M,15665
 duckguard/semantic/validators.py,sha256=8Zu3vwPwh79U09zGf4_PpcwV85_hbNCwRHcxTIQ7G_I,10945
 duckguard/validators/__init__.py,sha256=g717IM5xlVLCTg1nLRRccLAFHCsbRO-IgjzG4H6K32A,268
-duckguard-2.3.0.dist-info/METADATA,sha256=2CdxNqC8jwvv_cZAk1cMyWkJJiObUOKckPcB0D-74bw,27779
-duckguard-2.3.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-duckguard-2.3.0.dist-info/entry_points.txt,sha256=teP6JdXUvY20E9P44TW_Z24xuQtXMgnCyOuWtd_KIYU,108
-duckguard-2.3.0.dist-info/licenses/LICENSE,sha256=1Li9P3fainL-epQ9kEHZWKDScWtp4inPd6AkhUTJStk,3841
-duckguard-2.3.0.dist-info/RECORD,,
+duckguard-3.0.1.dist-info/METADATA,sha256=9jLfixYYUu4coNP0hadedJL2pacYkyjqD6vBtwQj6Og,31770
+duckguard-3.0.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+duckguard-3.0.1.dist-info/entry_points.txt,sha256=teP6JdXUvY20E9P44TW_Z24xuQtXMgnCyOuWtd_KIYU,108
+duckguard-3.0.1.dist-info/licenses/LICENSE,sha256=1Li9P3fainL-epQ9kEHZWKDScWtp4inPd6AkhUTJStk,3841
+duckguard-3.0.1.dist-info/RECORD,,