sdv 1.38.2.dev0__tar.gz → 1.38.3.dev0__tar.gz

{sdv-1.38.2.dev0/sdv.egg-info → sdv-1.38.3.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdv
-Version: 1.38.2.dev0
+Version: 1.38.3.dev0
 Summary: Generate synthetic data for single table, multi table and sequential data
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License-Expression: BUSL-1.1
@@ -48,8 +48,7 @@ Requires-Dist: deepecho>=0.7.0; python_version < "3.14"
 Requires-Dist: deepecho>=0.8.0; python_version >= "3.14"
 Requires-Dist: rdt>=1.18.2; python_version < "3.14"
 Requires-Dist: rdt>=1.20.0; python_version >= "3.14"
-Requires-Dist: sdmetrics>=0.28.1
-Requires-Dist: plotly<7.0.0
+Requires-Dist: sdmetrics>=0.30.0
 Requires-Dist: platformdirs>=4.0
 Requires-Dist: pyyaml>=6.0.1
 Provides-Extra: excel

{sdv-1.38.2.dev0 → sdv-1.38.3.dev0}/pyproject.toml

@@ -46,8 +46,7 @@ dependencies = [
     "deepecho>=0.8.0;python_version>='3.14'",
     "rdt>=1.18.2;python_version<'3.14'",
     "rdt>=1.20.0;python_version>='3.14'",
-    "sdmetrics>=0.28.1",
-    "plotly<7.0.0",
+    "sdmetrics>=0.30.0",
     'platformdirs>=4.0',
     'pyyaml>=6.0.1',
 ]
@@ -150,7 +149,7 @@ namespaces = false
 version = {attr = 'sdv.__version__'}
 
 [tool.bumpversion]
-current_version = "1.38.2.dev0"
+current_version = "1.38.3.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

{sdv-1.38.2.dev0 → sdv-1.38.3.dev0}/sdv/__init__.py

@@ -6,7 +6,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.38.2.dev0'
+__version__ = '1.38.3.dev0'
 
 
 import sys

sdv-1.38.3.dev0/sdv/datasets/_utils.py

@@ -0,0 +1,116 @@
+import warnings
+
+from pandas.core.dtypes.common import is_object_dtype
+
+
+class InvalidDataWarning(Warning):
+    pass
+
+
+def _process_adventure_works(data):
+    data = data.copy()
+    data['CountryRegion'].loc[data['CountryRegion']['Name'] == 'Namibia', 'CountryRegionCode'] = (
+        'NA'
+    )
+    integer_comma_columns = {
+        'PurchaseOrderDetail': [
+            'ReceivedQty',
+            'RejectedQty',
+            'StockedQty',
+        ],
+        'BillOfMaterials': ['PerAssemblyQty'],
+        'TransactionHistoryArchive': [],
+    }
+    float_comma_columns = {
+        'Product': ['StandardCost', 'ListPrice', 'Weight'],
+        'ProductListPriceHistory': ['ListPrice'],
+        'ProductCostHistory': ['StandardCost'],
+        'ProductVendor': ['StandardPrice', 'LastReceiptCost'],
+        'SalesOrderDetail': ['UnitPrice', 'UnitPriceDiscount', 'LineTotal'],
+        'SalesOrderHeader': ['SubTotal', 'TaxAmt', 'Freight', 'TotalDue'],
+        'PurchaseOrderDetail': [
+            'UnitPrice',
+            'LineTotal',
+        ],
+        'PurchaseOrderHeader': ['SubTotal', 'TaxAmt', 'Freight', 'TotalDue'],
+        'TransactionHistory': ['ActualCost'],
+        'TransactionHistoryArchive': ['ActualCost'],
+        'SalesTaxRate': ['TaxRate'],
+        'EmployeePayHistory': ['Rate'],
+        'ShipMethod': ['ShipBase', 'ShipRate'],
+        'Location': ['CostRate', 'Availability'],
+        'WorkOrderRouting': ['ActualResourceHrs', 'PlannedCost', 'ActualCost'],
+        'SalesPersonQuotaHistory': ['SalesQuota'],
+        'SalesPerson': [
+            'SalesQuota',
+            'Bonus',
+            'CommissionPct',
+            'SalesYTD',
+            'SalesLastYear',
+        ],
+        'SalesTerritory': ['SalesYTD', 'SalesLastYear', 'CostYTD', 'CostLastYear'],
+        'CurrencyRate': ['AverageRate', 'EndOfDayRate'],
+        'SpecialOffer': ['DiscountPct'],
+    }
+    for table_name, columns in float_comma_columns.items():
+        for column_name in columns:
+            col = data[table_name][column_name]
+            if is_object_dtype(col.dtype):
+                data[table_name][column_name] = col.str.replace(',', '.').astype(float)
+
+    for table_name, columns in integer_comma_columns.items():
+        for column_name in columns:
+            col = data[table_name][column_name]
+            if is_object_dtype(col.dtype):
+                data[table_name][column_name] = (
+                    col.str.replace(',', '.').astype(float).astype('int64')
+                )
+    EMAIL_NAME_FIXES = {
+        'fran?ois': 'francois',
+        'jos?': 'jose',
+        'j?sus': 'jesus',
+        'mar?a': 'maria',
+        'c?sar': 'cesar',
+        'andr?s': 'andres',
+        'ram?n': 'ramon',
+        'bego?a': 'begona',
+        'desir?e': 'desiree',
+        'ren?e': 'renee',
+        'al?cia': 'alicia',
+        'ni?ia': 'ninia',
+    }
+    for table_name in ('EmailAddress', 'ProductReview'):
+        emails = data[table_name]['EmailAddress']
+        for broken, fixed in EMAIL_NAME_FIXES.items():
+            emails = emails.str.replace(broken, fixed, regex=False)
+        data[table_name]['EmailAddress'] = emails
+
+    PHONE_COLUMNS = {
+        'PersonPhone': ['PhoneNumber'],
+    }
+
+    for table_name, columns in PHONE_COLUMNS.items():
+        for column_name in columns:
+            col = data[table_name][column_name].astype('string')
+            needs_prefix = col.notna() & ~col.str.startswith('+')
+            data[table_name][column_name] = col.where(~needs_prefix, '+1 ' + col)
+
+    return data
+
+
+def process_adventure_works(data, metadata):
+    try:
+        metadata.validate_data(data)
+        return data, metadata
+    except Exception:
+        try:
+            processed_data = _process_adventure_works(data)
+            metadata.validate_data(processed_data)
+            return processed_data, metadata
+        except Exception:
+            warning_msg = (
+                'This downloaded data and metadata are not compatible with each other. They '
+                'cannot be modeled using SDV without some modifications.'
+            )
+            warnings.warn(warning_msg, InvalidDataWarning)
+            return data, metadata

{sdv-1.38.2.dev0 → sdv-1.38.3.dev0}/sdv/datasets/demo.py

@@ -18,6 +18,7 @@ import yaml
 from botocore import UNSIGNED
 from botocore.client import Config
 
+from sdv.datasets._utils import process_adventure_works
 from sdv.errors import DemoResourceNotFoundError, DemoResourceNotFoundWarning
 from sdv.metadata.metadata import Metadata
 
@@ -506,6 +507,8 @@ def download_demo(
         data = data.popitem()[1]
 
     metadata = _get_metadata(metadata_bytes, dataset_name, output_folder_name)
+    if dataset_name == 'adventure-works':
+        data, metadata = process_adventure_works(data, metadata)
     return data, metadata
 
 

{sdv-1.38.2.dev0 → sdv-1.38.3.dev0/sdv.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdv
-Version: 1.38.2.dev0
+Version: 1.38.3.dev0
 Summary: Generate synthetic data for single table, multi table and sequential data
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License-Expression: BUSL-1.1
@@ -48,8 +48,7 @@ Requires-Dist: deepecho>=0.7.0; python_version < "3.14"
 Requires-Dist: deepecho>=0.8.0; python_version >= "3.14"
 Requires-Dist: rdt>=1.18.2; python_version < "3.14"
 Requires-Dist: rdt>=1.20.0; python_version >= "3.14"
-Requires-Dist: sdmetrics>=0.28.1
-Requires-Dist: plotly<7.0.0
+Requires-Dist: sdmetrics>=0.30.0
 Requires-Dist: platformdirs>=4.0
 Requires-Dist: pyyaml>=6.0.1
 Provides-Extra: excel

{sdv-1.38.2.dev0 → sdv-1.38.3.dev0}/sdv.egg-info/SOURCES.txt

@@ -32,6 +32,7 @@ sdv/data_processing/errors.py
 sdv/data_processing/numerical_formatter.py
 sdv/data_processing/utils.py
 sdv/datasets/__init__.py
+sdv/datasets/_utils.py
 sdv/datasets/demo.py
 sdv/datasets/local.py
 sdv/evaluation/__init__.py

{sdv-1.38.2.dev0 → sdv-1.38.3.dev0}/sdv.egg-info/requires.txt

@@ -2,8 +2,7 @@ boto3<2.0.0,>=1.28
 botocore<2.0.0,>=1.31
 graphviz>=0.13.2
 tqdm>=4.29
-sdmetrics>=0.28.1
-plotly<7.0.0
+sdmetrics>=0.30.0
 platformdirs>=4.0
 pyyaml>=6.0.1