kumoai 2.13.0.dev202511261731__cp310-cp310-win_amd64.whl → 2.13.0.dev202512021731__cp310-cp310-win_amd64.whl

kumoai/experimental/rfm/utils.py

@@ -1,127 +1,8 @@
 import re
 import warnings
-from typing import Any, Dict, Optional
+from typing import Optional
 
-import numpy as np
 import pandas as pd
-import pyarrow as pa
-from kumoapi.typing import Dtype, Stype
-
-from kumoai.experimental.rfm.infer import (
-    contains_categorical,
-    contains_id,
-    contains_multicategorical,
-    contains_timestamp,
-)
-
-# Mapping from pandas/numpy dtypes to Kumo Dtypes
-PANDAS_TO_DTYPE: Dict[Any, Dtype] = {
-    np.dtype('bool'): Dtype.bool,
-    pd.BooleanDtype(): Dtype.bool,
-    pa.bool_(): Dtype.bool,
-    np.dtype('byte'): Dtype.int,
-    pd.UInt8Dtype(): Dtype.int,
-    np.dtype('int16'): Dtype.int,
-    pd.Int16Dtype(): Dtype.int,
-    np.dtype('int32'): Dtype.int,
-    pd.Int32Dtype(): Dtype.int,
-    np.dtype('int64'): Dtype.int,
-    pd.Int64Dtype(): Dtype.int,
-    np.dtype('float32'): Dtype.float,
-    pd.Float32Dtype(): Dtype.float,
-    np.dtype('float64'): Dtype.float,
-    pd.Float64Dtype(): Dtype.float,
-    np.dtype('object'): Dtype.string,
-    pd.StringDtype(storage='python'): Dtype.string,
-    pd.StringDtype(storage='pyarrow'): Dtype.string,
-    pa.string(): Dtype.string,
-    pa.binary(): Dtype.binary,
-    np.dtype('datetime64[ns]'): Dtype.date,
-    np.dtype('timedelta64[ns]'): Dtype.timedelta,
-    pa.list_(pa.float32()): Dtype.floatlist,
-    pa.list_(pa.int64()): Dtype.intlist,
-    pa.list_(pa.string()): Dtype.stringlist,
-}
-
-
-def to_dtype(ser: pd.Series) -> Dtype:
-    """Extracts the :class:`Dtype` from a :class:`pandas.Series`.
-
-    Args:
-        ser: A :class:`pandas.Series` to analyze.
-
-    Returns:
-        The data type.
-    """
-    if pd.api.types.is_datetime64_any_dtype(ser.dtype):
-        return Dtype.date
-
-    if isinstance(ser.dtype, pd.CategoricalDtype):
-        return Dtype.string
-
-    if pd.api.types.is_object_dtype(ser.dtype):
-        index = ser.iloc[:1000].first_valid_index()
-        if index is not None and pd.api.types.is_list_like(ser[index]):
-            pos = ser.index.get_loc(index)
-            assert isinstance(pos, int)
-            ser = ser.iloc[pos:pos + 1000].dropna()
-
-            if not ser.map(pd.api.types.is_list_like).all():
-                raise ValueError("Data contains a mix of list-like and "
-                                 "non-list-like values")
-
-            ser = ser[ser.map(lambda x: not isinstance(x, list) or len(x) > 0)]
-
-            dtypes = ser.apply(lambda x: PANDAS_TO_DTYPE.get(
-                np.array(x).dtype, Dtype.string)).unique().tolist()
-
-            invalid_dtypes = set(dtypes) - {
-                Dtype.string,
-                Dtype.int,
-                Dtype.float,
-            }
-            if len(invalid_dtypes) > 0:
-                raise ValueError(f"Data contains unsupported list data types: "
-                                 f"{list(invalid_dtypes)}")
-
-            if Dtype.string in dtypes:
-                return Dtype.stringlist
-
-            if dtypes == [Dtype.int]:
-                return Dtype.intlist
-
-            return Dtype.floatlist
-
-    if ser.dtype not in PANDAS_TO_DTYPE:
-        raise ValueError(f"Unsupported data type '{ser.dtype}'")
-
-    return PANDAS_TO_DTYPE[ser.dtype]
-
-
-def infer_stype(ser: pd.Series, column_name: str, dtype: Dtype) -> Stype:
-    r"""Infers the semantic type of a column.
-
-    Args:
-        ser: A :class:`pandas.Series` to analyze.
-        column_name: The name of the column (used for pattern matching).
-        dtype: The data type.
-
-    Returns:
-        The semantic type.
-    """
-    if contains_id(ser, column_name, dtype):
-        return Stype.ID
-
-    if contains_timestamp(ser, column_name, dtype):
-        return Stype.timestamp
-
-    if contains_multicategorical(ser, column_name, dtype):
-        return Stype.multicategorical
-
-    if contains_categorical(ser, column_name, dtype):
-        return Stype.categorical
-
-    return dtype.default_stype
 
 
 def detect_primary_key(

kumoai/testing/decorators.py

@@ -25,7 +25,7 @@ def onlyFullTest(func: Callable) -> Callable:
 def has_package(package: str) -> bool:
     r"""Returns ``True`` in case ``package`` is installed."""
     req = Requirement(package)
-    if importlib.util.find_spec(req.name) is None:
+    if importlib.util.find_spec(req.name) is None:  # type: ignore
         return False
 
     try:

{kumoai-2.13.0.dev202511261731.dist-info → kumoai-2.13.0.dev202512021731.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kumoai
-Version: 2.13.0.dev202511261731
+Version: 2.13.0.dev202512021731
 Summary: AI on the Modern Data Stack
 Author-email: "Kumo.AI" <hello@kumo.ai>
 License-Expression: MIT
@@ -23,13 +23,11 @@ Requires-Dist: requests>=2.28.2
 Requires-Dist: urllib3
 Requires-Dist: plotly
 Requires-Dist: typing_extensions>=4.5.0
-Requires-Dist: kumo-api==0.46.0
+Requires-Dist: kumo-api==0.48.0
 Requires-Dist: tqdm>=4.66.0
 Requires-Dist: aiohttp>=3.10.0
 Requires-Dist: pydantic>=1.10.21
 Requires-Dist: rich>=9.0.0
-Requires-Dist: mypy-boto3-sagemaker-runtime
-Requires-Dist: boto3
 Provides-Extra: doc
 Requires-Dist: sphinx; extra == "doc"
 Requires-Dist: sphinx-book-theme; extra == "doc"
@@ -40,13 +38,15 @@ Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-mock; extra == "test"
 Requires-Dist: requests-mock; extra == "test"
-Provides-Extra: test-sagemaker
-Requires-Dist: sagemaker; extra == "test-sagemaker"
-Requires-Dist: pandas==2.1.4; extra == "test-sagemaker"
-Requires-Dist: pyarrow==12.0.1; extra == "test-sagemaker"
+Provides-Extra: sqlite
+Requires-Dist: adbc_driver_sqlite; extra == "sqlite"
+Provides-Extra: snowflake
+Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Provides-Extra: sagemaker
 Requires-Dist: boto3<2.0,>=1.30.0; extra == "sagemaker"
 Requires-Dist: mypy-boto3-sagemaker-runtime<2.0,>=1.34.0; extra == "sagemaker"
+Provides-Extra: test-sagemaker
+Requires-Dist: sagemaker<3.0; extra == "test-sagemaker"
 Dynamic: license-file
 Dynamic: requires-dist
 

{kumoai-2.13.0.dev202511261731.dist-info → kumoai-2.13.0.dev202512021731.dist-info}/RECORD

@@ -1,13 +1,13 @@
 kumoai/__init__.py,sha256=qu-qohU2cQlManX1aZIlzA3ivKl52m-cSQBPSW8urUU,10837
 kumoai/_logging.py,sha256=qL4JbMQwKXri2f-SEJoFB8TY5ALG12S-nobGTNWxW-A,915
 kumoai/_singleton.py,sha256=i2BHWKpccNh5SJGDyU0IXsnYzJAYr8Xb0wz4c6LRbpo,861
-kumoai/_version.py,sha256=P7PbPaqmt6kLq-80AyouMRr_ZBx8A7_nPBBPEXW44ag,39
+kumoai/_version.py,sha256=J8ZxoMuLZm4ZbBIvjU8zNKn-zWD-Pu5i4RPV-vurJZU,39
 kumoai/databricks.py,sha256=ahwJz6DWLXMkndT0XwEDBxF-hoqhidFR8wBUQ4TLZ68,490
 kumoai/exceptions.py,sha256=7TMs0SC8xrU009_Pgd4QXtSF9lxJq8MtRbeX9pcQUy4,859
 kumoai/formatting.py,sha256=o3uCnLwXPhe1KI5WV9sBgRrcU7ed4rgu_pf89GL9Nc0,983
 kumoai/futures.py,sha256=J8rtZMEYFzdn5xF_x-LAiKJz3KGL6PT02f6rq_2bOJk,3836
 kumoai/jobs.py,sha256=dCi7BAdfm2tCnonYlGU4WJokJWbh3RzFfaOX2EYCIHU,2576
-kumoai/kumolib.cp310-win_amd64.pyd,sha256=lfpQDN2Fu1tGqTxas5A9Jv3fLm-WdA_oSkhQfo6-pvg,194048
+kumoai/kumolib.cp310-win_amd64.pyd,sha256=diW7mZyXCDEBISV6p-9XYxIXiwyZA3p5m-DxL6if4i4,194048
 kumoai/mixin.py,sha256=IaiB8SAI0VqOoMVzzIaUlqMt53-QPUK6OB0HikG-V9E,840
 kumoai/spcs.py,sha256=KWfENrwSLruprlD-QPh63uU0N6npiNrwkeKfBk3EUyQ,4260
 kumoai/artifact_export/__init__.py,sha256=UXAQI5q92ChBzWAk8o3J6pElzYHudAzFZssQXd4o7i8,247
@@ -50,23 +50,32 @@ kumoai/connector/glue_connector.py,sha256=kqT2q53Da7PeeaZrvLVzFXC186E7glh5eGitKL
 kumoai/connector/s3_connector.py,sha256=AUzENbQ20bYXh3XOXEOsWRKlaGGkm3YrW9JfBLm-LqY,10433
 kumoai/connector/snowflake_connector.py,sha256=tQzIWxC4oDGqxFt0212w5eoIPT4QBP2nuF9SdKRNwNI,9274
 kumoai/connector/source_table.py,sha256=fnqwIKY6qYo4G0EsRzchb6FgZ-dQyU6aRaD9UAxsml0,18010
-kumoai/connector/utils.py,sha256=SlkjPJS_wqfwFzIaQOHZtENQnbOz5sgLbvvvPDXE1ww,65786
+kumoai/connector/utils.py,sha256=5K9BMdWiIP3hhdkUc6Xt1e0xv5YyziXtZ4PnBqq0Ehw,66490
 kumoai/encoder/__init__.py,sha256=8FeP6mUyCeXxr1b8kUIi5dxe5vEXQRft9tPoaV1CBqg,186
 kumoai/experimental/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kumoai/experimental/rfm/__init__.py,sha256=gpjpeN8PT3ZESi6kUaeyZqYnoJnysRVXDaY9hrycJA4,7020
+kumoai/experimental/rfm/__init__.py,sha256=EFZz6IvvskmeO85Vig6p1m_6jdimS_BkeREOndHuRsc,6247
 kumoai/experimental/rfm/authenticate.py,sha256=G89_4TMeUpr5fG_0VTzMF5sdNhaciitA1oc2loTlTmo,19321
-kumoai/experimental/rfm/local_graph.py,sha256=nZ9hDfyWg1dHFLoTEKoLt0ZJPvf9MUA1MNyfTRzJThg,30886
+kumoai/experimental/rfm/graph.py,sha256=agUNrKA6gkH7Aqetn7f0Y4r1a8QJ9G3uA52WA1hKBpM,34476
 kumoai/experimental/rfm/local_graph_sampler.py,sha256=3JNpktW__nwxVKZxP4cQBgsIin7J_LNXYS7YlV36xbU,6854
-kumoai/experimental/rfm/local_graph_store.py,sha256=eUuIMFcdIRqN1kRxnqOdJpKEt-S_oyupAyHr7YuQoSU,14206
+kumoai/experimental/rfm/local_graph_store.py,sha256=PoUwyMpoJhE5VjtgWYU3pV8__TcZ8oAv-zES5cIB3RQ,14251
 kumoai/experimental/rfm/local_pquery_driver.py,sha256=Yd_yHIrvuDj16IC1pvsqiQvZS41vvOOCRMiuDGtN6Fk,26851
-kumoai/experimental/rfm/local_table.py,sha256=5H08657TIyH7n_QnpFKr2g4BtVqdXTymmrfhSGaDmkU,20150
-kumoai/experimental/rfm/rfm.py,sha256=MarISSPKuv6nIaGG69zFAwIagF6EA37xcSRClZrQMFc,49470
-kumoai/experimental/rfm/sagemaker.py,sha256=eebpZtASqiIGF2FpY53bbWLj6p-u5hkK4RLgBNAvEzg,4953
-kumoai/experimental/rfm/utils.py,sha256=dLx2wdyTWg7vZI_7R-I0z_lA-2aV5M8h9n3bnnLyylI,11467
-kumoai/experimental/rfm/infer/__init__.py,sha256=fPsdDr4D3hgC8snW0j3pAVpCyR-xrauuogMnTOMrfok,304
+kumoai/experimental/rfm/rfm.py,sha256=mS6LPNgl_kVHeLjmJoAW-hQhBZFKtEH4acGnjbFgee0,49445
+kumoai/experimental/rfm/sagemaker.py,sha256=sEJSyfEFBA3-7wKinBEzSooKHEn0BgPjrgRnPhYo79g,5120
+kumoai/experimental/rfm/utils.py,sha256=TN7HT_dy26Vhvd8YE90vB0hGZpTFsRMmpSZ3LcQoEIc,7626
+kumoai/experimental/rfm/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kumoai/experimental/rfm/backend/local/__init__.py,sha256=usMh0fuDxKK-aOVT1sU30BQWFS0eSkfUrhUVILisQQI,934
+kumoai/experimental/rfm/backend/local/table.py,sha256=oFf5cYu35Hcr950lvOGYjyXCmX6ICaoOBhzghCtVS1Q,8508
+kumoai/experimental/rfm/backend/snow/__init__.py,sha256=kn784OzM8tTnOnoieflOuWZZlab586v8yVVjyL9aXlc,898
+kumoai/experimental/rfm/backend/sqlite/__init__.py,sha256=xw5NNLrWSvUvRkD49X_9hZYjas5EuP1XDANPy0EEjOg,874
+kumoai/experimental/rfm/backend/sqlite/table.py,sha256=A-37etb2jNUV-I2tz_-7nvoHq-qdn1K7mYjsro85A1Y,5132
+kumoai/experimental/rfm/base/__init__.py,sha256=XQ_jx-dFWg95KWqHORThl9UIOcbfl-JzRy47SRwjqmc,101
+kumoai/experimental/rfm/base/column.py,sha256=OE-PRQ8HO4uTq0e3_3eHJFfhp5nzw79zd-43g3iMh4g,2385
+kumoai/experimental/rfm/base/table.py,sha256=HAYFqvbmJ5rLicNE3j-ykxyXFvAnK_E6xmJ18HJir-Y,17534
+kumoai/experimental/rfm/infer/__init__.py,sha256=PF654hCdPSf3tFAxNegDA9aOJLBG4IT1eIjRzI0Rvwo,356
 kumoai/experimental/rfm/infer/categorical.py,sha256=bqmfrE5ZCBTcb35lA4SyAkCu3MgttAn29VBJYMBNhVg,893
 kumoai/experimental/rfm/infer/id.py,sha256=xaJBETLZa8ttzZCsDwFSwfyCi3VYsLc_kDWT_t_6Ih4,954
 kumoai/experimental/rfm/infer/multicategorical.py,sha256=D-1KwYRkOSkBrOJr4Xa3eTCoAF9O9hPGa7Vg67V5_HU,1150
+kumoai/experimental/rfm/infer/stype.py,sha256=a5w_3WwQTctnAkFw0J9_EjFvOeLAEtnrtDbImqLeCXA,946
 kumoai/experimental/rfm/infer/timestamp.py,sha256=L2VxjtYTSyUBYAo4M-L08xSQlPpqnHMAVF5_vxjh3Y0,1135
 kumoai/experimental/rfm/pquery/__init__.py,sha256=RkTn0I74uXOUuOiBpa6S-_QEYctMutkUnBEfF9ztQzI,159
 kumoai/experimental/rfm/pquery/executor.py,sha256=S8wwXbAkH-YSnmEVYB8d6wyJF4JJ003mH_0zFTvOp_I,2843
@@ -80,7 +89,7 @@ kumoai/pquery/prediction_table.py,sha256=hWG4L_ze4PLgUoxCXNKk8_nkYxVXELQs8_X8KGO
 kumoai/pquery/predictive_query.py,sha256=GWhQpQxf6apyyu-bvE3z63mX6NLd8lKbyu_jzj7rNms,25608
 kumoai/pquery/training_table.py,sha256=L1QjaVlY4SAPD8OUmTaH6YjZzBbPOnS9mnAT69znWv0,16233
 kumoai/testing/__init__.py,sha256=XBQ_Sa3WnOYlpXZ3gUn8w6nVfZt-nfPhytfIBeiPt4w,178
-kumoai/testing/decorators.py,sha256=yznguzsdkL0UaZtBbnO6oaUrXisJvziaiO3dmN41UXE,1648
+kumoai/testing/decorators.py,sha256=p79ZCQqPY_MHWy0_l7-xQ6wUIqFTn4AbrGWTHLvpbQY,1664
 kumoai/trainer/__init__.py,sha256=uCFXy9bw_byn_wYd3M-BTZCHTVvv4XXr8qRlh-QOvag,981
 kumoai/trainer/baseline_trainer.py,sha256=oXweh8j1sar6KhQfr3A7gmQxcDq7SG0Bx3jIenbtyC4,4117
 kumoai/trainer/config.py,sha256=7_Jv1w1mqaokCQwQdJkqCSgVpmh8GqE3fL1Ky_vvttI,100
@@ -92,8 +101,8 @@ kumoai/utils/__init__.py,sha256=wAKgmwtMIGuiauW9D_GGKH95K-24Kgwmld27mm4nsro,278
 kumoai/utils/datasets.py,sha256=UyAII-oAn7x3ombuvpbSQ41aVF9SYKBjQthTD-vcT2A,3011
 kumoai/utils/forecasting.py,sha256=ZgKeUCbWLOot0giAkoigwU5du8LkrwAicFOi5hVn6wg,7624
 kumoai/utils/progress_logger.py,sha256=MZsWgHd4UZQKCXiJZgQeW-Emi_BmzlCKPLPXOL_HqBo,5239
-kumoai-2.13.0.dev202511261731.dist-info/licenses/LICENSE,sha256=ZUilBDp--4vbhsEr6f_Upw9rnIx09zQ3K9fXQ0rfd6w,1111
-kumoai-2.13.0.dev202511261731.dist-info/METADATA,sha256=KEPt_QdWVLyZhYMj3PNjwvb1gm6fXI9_FvWyMOvMrtw,2544
-kumoai-2.13.0.dev202511261731.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
-kumoai-2.13.0.dev202511261731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
-kumoai-2.13.0.dev202511261731.dist-info/RECORD,,
+kumoai-2.13.0.dev202512021731.dist-info/licenses/LICENSE,sha256=ZUilBDp--4vbhsEr6f_Upw9rnIx09zQ3K9fXQ0rfd6w,1111
+kumoai-2.13.0.dev202512021731.dist-info/METADATA,sha256=BYNYYVarUHxSCq5IctkyMu_VHIeu12aQ-AX34ZC9X3c,2535
+kumoai-2.13.0.dev202512021731.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
+kumoai-2.13.0.dev202512021731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
+kumoai-2.13.0.dev202512021731.dist-info/RECORD,,