kumoai 2.12.0.dev202511111731__cp311-cp311-macosx_11_0_arm64.whl → 2.13.0.dev202512091732__cp311-cp311-macosx_11_0_arm64.whl

{kumoai-2.12.0.dev202511111731.dist-info → kumoai-2.13.0.dev202512091732.dist-info}/RECORD

@@ -1,33 +1,48 @@
 kumoai/_logging.py,sha256=U2_5ROdyk92P4xO4H2WJV8EC7dr6YxmmnM-b7QX9M7I,886
 kumoai/mixin.py,sha256=MP413xzuCqWhxAPUHmloLA3j4ZyF1tEtfi516b_hOXQ,812
-kumoai/_version.py,sha256=EmBJ4U0JvENPiq7lq8M80mpSdMDFEwNkBsjWDdzaLT4,39
-kumoai/__init__.py,sha256=LU1zmKYc0KV5hy2VGKUuXgSvbJwj2rSRQ_R_bpHyl1o,10708
+kumoai/_version.py,sha256=bUx8YEaVu-Ejr0CkVpysUTjmuNl9FBowBo1W0BvlWVo,39
+kumoai/__init__.py,sha256=Nn9YH_x9kAeEFn8RWbP95slZow0qFnakPZZ1WADe1hY,10843
 kumoai/formatting.py,sha256=jA_rLDCGKZI8WWCha-vtuLenVKTZvli99Tqpurz1H84,953
 kumoai/futures.py,sha256=oJFIfdCM_3nWIqQteBKYMY4fPhoYlYWE_JA2o6tx-ng,3737
 kumoai/kumolib.cpython-311-darwin.so,sha256=AmB_Fysmud1y7Gm5CuBQ5lWDuSzpxVDV_iTA2cjH1s8,232544
 kumoai/jobs.py,sha256=NrdLEFNo7oeCYSy-kj2nAvCFrz9BZ_xrhkqHFHk5ksY,2496
 kumoai/exceptions.py,sha256=b-_sdbAKOg50uaJZ65GmBLdTo4HANdjl8_R0sJpwaN0,833
 kumoai/databricks.py,sha256=e6E4lOFvZHXFwh4CO1kXU1zzDU3AapLQYMxjiHPC-HQ,476
-kumoai/spcs.py,sha256=N4ddeoHAc4I3bKrDitsb91lUx5VKvCyPyMT3zWiuCcY,4275
+kumoai/spcs.py,sha256=N31d7rLa-bgYh8e2J4YzX1ScxGLqiVXrqJnCl1y4Mts,4139
 kumoai/_singleton.py,sha256=UTwrbDkoZSGB8ZelorvprPDDv9uZkUi1q_SrmsyngpQ,836
 kumoai/experimental/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kumoai/experimental/rfm/local_graph_sampler.py,sha256=o60_sdMa_fr60DrdmCIaE6lKQAD2msp1t-GGubFNt-o,6738
-kumoai/experimental/rfm/local_graph.py,sha256=2iJDlsGVzqCe1bD_puXWlhwGkn7YnQyJ4p4C-fwCZNE,30076
-kumoai/experimental/rfm/local_pquery_driver.py,sha256=aO7Jfwx9gxGKYvpqxZx1LLWdI1MhuZQOPtAITxoOQO0,26162
-kumoai/experimental/rfm/__init__.py,sha256=ornmi2x947jkQLptMn7ZLvTf2Sw-RMcVW73AnjVsWAo,1709
-kumoai/experimental/rfm/utils.py,sha256=3IiBvT_aLBkkcJh3H11_50yt_XlEzHR0cm9Kprrtl8k,11123
-kumoai/experimental/rfm/local_table.py,sha256=r8xZ33Mjs6JD8ud6h23tZ99Dag2DvZ4h6tWjmGrKQg4,19605
-kumoai/experimental/rfm/rfm.py,sha256=V2NxxhrYi_MqLi_xcZsOYsdciT7V44iS5Fc9Ewq9eiM,48101
-kumoai/experimental/rfm/local_graph_store.py,sha256=8BqonuaMftAAsjgZpB369i5AeNd1PkisMbbEqc0cKBo,13847
+kumoai/experimental/rfm/local_graph_sampler.py,sha256=32ZCNirPyCqCD8IccaXmRt0EJk1p54mWXpJ33NotAqE,7883
+kumoai/experimental/rfm/local_pquery_driver.py,sha256=dhOS1L9aboya86EL4AFYc8bQkimbOchSLfe_jn2qGh4,26158
+kumoai/experimental/rfm/graph.py,sha256=76hlQyaEYqBYNIF3jslIqRRuAPNtXvc1kR6InwyHH-M,39751
+kumoai/experimental/rfm/__init__.py,sha256=slliYcrh80xPtQQ_nnsp3ny9IbmHCyirmdZUfKTdME4,6064
+kumoai/experimental/rfm/sagemaker.py,sha256=_hTrFg4qfXe7uzwqSEG_wze-IFkwn7qde9OpUodCpbc,4982
+kumoai/experimental/rfm/rfm.py,sha256=BSgxeM0xW2mt74jq4Ah4hl85RxT6337NoDQP7f7iXvY,47699
 kumoai/experimental/rfm/authenticate.py,sha256=FiuHMvP7V3zBZUlHMDMbNLhc-UgDZgz4hjVSTuQ7DRw,18888
+kumoai/experimental/rfm/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kumoai/experimental/rfm/backend/sqlite/__init__.py,sha256=jYmZDNAVsojuPO1Q5idFmG5N0aCB8BDyrpAoS31n9bc,844
+kumoai/experimental/rfm/backend/sqlite/table.py,sha256=kcYpWaZKFez2Tru6Sdz-Ywk8jP8VpLnjmCIQQtRFGnU,3800
+kumoai/experimental/rfm/backend/local/__init__.py,sha256=2s9sSA-E-8pfkkzCH4XPuaSxSznEURMfMgwEIfYYPsg,1014
+kumoai/experimental/rfm/backend/local/table.py,sha256=Ahob9HidpU6z_M41rK5FATa3d7CL2UzZl8pGVyrzLNc,3565
+kumoai/experimental/rfm/backend/local/graph_store.py,sha256=RpfJldemOG-4RzGSIS9EcytHbvC4gYm-Ps3a-4qfptk,13297
+kumoai/experimental/rfm/backend/local/sampler.py,sha256=xJf53jD8kJCQa6gZTmxp9AXsOXwPoQ7G7dAefXGX16E,8459
+kumoai/experimental/rfm/backend/snow/__init__.py,sha256=B-tG-p8WA-mBuwvK1f0S2gdRPEGwApdxlnyeVSnY2xg,927
+kumoai/experimental/rfm/backend/snow/table.py,sha256=sHagXhW7RifzOiB4yjxV_9FtR0KUFVIw1mYwZe4bpMg,4255
 kumoai/experimental/rfm/pquery/__init__.py,sha256=X0O3EIq5SMfBEE-ii5Cq6iDhR3s3XMXB52Cx5htoePw,152
-kumoai/experimental/rfm/pquery/pandas_executor.py,sha256=kiBJq7uVGbasG7TiqsubEl6ey3UYzZiM4bwxILqp_54,18487
+kumoai/experimental/rfm/pquery/pandas_executor.py,sha256=wYI9a3smClR2pQGwsYRdmpOm0PlUsbtyW9wpAVpCEe4,18492
 kumoai/experimental/rfm/pquery/executor.py,sha256=f7-pJhL0BgFU9E4o4gQpQyArOvyrZtwxFmks34-QOAE,2741
 kumoai/experimental/rfm/infer/multicategorical.py,sha256=0-cLpDnGryhr76QhZNO-klKokJ6MUSfxXcGdQ61oykY,1102
 kumoai/experimental/rfm/infer/categorical.py,sha256=VwNaKwKbRYkTxEJ1R6gziffC8dGsEThcDEfbi-KqW5c,853
+kumoai/experimental/rfm/infer/time_col.py,sha256=7R5Itl8RRBOr61qLpRTanIqrUVZFZcAXzDA9lCw4nx4,1820
+kumoai/experimental/rfm/infer/pkey.py,sha256=ubNqW1LIjLKiXbjXELAY3g6n2f3u2Eis_uC2DEiXFiU,4393
 kumoai/experimental/rfm/infer/id.py,sha256=ZIO0DWIoiEoS_8MVc5lkqBfkTWWQ0yGCgjkwLdaYa_Q,908
-kumoai/experimental/rfm/infer/__init__.py,sha256=xQ8_SuejIzXyn2J7bIKX3pXumFtRuEfBtE5oEDUDJjI,293
+kumoai/experimental/rfm/infer/dtype.py,sha256=ZZ6ztqJnTR1CaC2z5Uhf0o0rSdNThnss5tem5JNQkck,2607
+kumoai/experimental/rfm/infer/__init__.py,sha256=krdMFN8iKZlSFOl-M5MW1KuSviQV3H1E18jj2uB8g6Q,469
 kumoai/experimental/rfm/infer/timestamp.py,sha256=vM9--7eStzaGG13Y-oLYlpNJyhL6f9dp17HDXwtl_DM,1094
+kumoai/experimental/rfm/base/__init__.py,sha256=V2B2TA064nppZ3o6uWAH7EFeKSz-hZKB7_YqV1jJfOI,303
+kumoai/experimental/rfm/base/table.py,sha256=yaY7Auvq2KblXOid3-a_Pw6RgnPK5Y1zGAY2xi1D2gg,19843
+kumoai/experimental/rfm/base/sampler.py,sha256=2FIUIN2fD0RCz-qx1NCuEpt3YRx7nxcQds5lEao4mq4,13433
+kumoai/experimental/rfm/base/source.py,sha256=8_waFQVsctryHkm9BwmFZ9-vw5cXAXfjk7KDmcl_kic,272
+kumoai/experimental/rfm/base/column.py,sha256=izCJmufJcd1RSi-ptFMfrue-JYag38MJxizka7ya0-A,2319
 kumoai/encoder/__init__.py,sha256=VPGs4miBC_WfwWeOXeHhFomOUocERFavhKf5fqITcds,182
 kumoai/graph/graph.py,sha256=iyp4klPIMn2ttuEqMJvsrxKb_tmz_DTnvziIhCegduM,38291
 kumoai/graph/__init__.py,sha256=n8X4X8luox4hPBHTRC9R-3JzvYYMoR8n7lF1H4w4Hzc,228
@@ -57,7 +72,7 @@ kumoai/codegen/handlers/utils.py,sha256=58b2GCgaTBUp2aId7BLMXMV0ENrusbNbfw7mlyXA
 kumoai/codegen/handlers/connector.py,sha256=afGf_GreyQ9y6qF3QTgSiM416qtUcP298SatNqUFhvQ,3828
 kumoai/codegen/handlers/table.py,sha256=POHpA-GFYFGTSuerGmtigYablk-Wq1L3EBvsOI-iFMQ,3956
 kumoai/testing/__init__.py,sha256=goHIIo3JE7uHV7njo4_aTd89mVVR74BEAZ2uyBaOR0w,170
-kumoai/testing/decorators.py,sha256=RiFrJcP-ym-mB1BYSGC26bBiryxoR9-GwL1G4EHc2sc,1591
+kumoai/testing/decorators.py,sha256=83tMifuPTpUqX7zHxMttkj1TDdB62EBtAP-Fjj72Zdo,1607
 kumoai/connector/glue_connector.py,sha256=HivT0QYQ8-XeB4QLgWvghiqXuq7jyBK9G2R1py_NnE4,4697
 kumoai/connector/databricks_connector.py,sha256=YQy203XHZGzNJ8bPUjUOnrVt2KlpgMdVuTHpc6sVCcs,7574
 kumoai/connector/snowflake_connector.py,sha256=K0s-H9tW3rve8g2x1PbyxvzSpkROfGQZz-Qa4PoT4UE,9022
@@ -65,7 +80,7 @@ kumoai/connector/bigquery_connector.py,sha256=IkyRqvF8Cg96kApUuuz86eYnl-BqBmDX1f
 kumoai/connector/source_table.py,sha256=QLT8bEYaxeMwy-b168url0VfnkTrs5K6VKLbxTI4hEY,17539
 kumoai/connector/__init__.py,sha256=9g6oNJ0qHWFlL5enTSoK4_SSH_5hP74xUDZx-9SggC4,842
 kumoai/connector/file_upload_connector.py,sha256=swp03HgChOvmNPJetuujBSAqADe7NRmS_T0F3o9it4w,7008
-kumoai/connector/utils.py,sha256=PUjunLpfqMZsrPDo2EmnyJRBl_mt-E6ugv2kNkf5Rn8,64011
+kumoai/connector/utils.py,sha256=wlqQxMmPvnFNoCcczGkKYjSu05h8OhWh4fhTzQm_2bQ,64694
 kumoai/connector/s3_connector.py,sha256=3kbv-h7DwD8O260Q0h1GPm5wwQpLt-Tb3d_CBSaie44,10155
 kumoai/connector/base.py,sha256=cujXSZF3zAfuxNuEw54DSL1T7XCuR4t0shSMDuPUagQ,5291
 kumoai/pquery/__init__.py,sha256=uTXr7t1eXcVfM-ETaM_1ImfEqhrmaj8BjiIvy1YZTL8,533
@@ -73,7 +88,7 @@ kumoai/pquery/predictive_query.py,sha256=oUqwdOWLLkPM-G4PhpUk_6mwSJGBtaD3t37Wp5O
 kumoai/pquery/prediction_table.py,sha256=QPDH22X1UB0NIufY7qGuV2XW7brG3Pv--FbjNezzM2g,10776
 kumoai/pquery/training_table.py,sha256=elmPDZx11kPiC_dkOhJcBUGtHKgL32GCBvZ9k6U0pMg,15809
 kumoai/client/pquery.py,sha256=R2hc-M8vPoyIDH0ywLwFVxCznVAqpZz3w2HszjdNW-o,6891
-kumoai/client/client.py,sha256=S1OfGDwTzoyf40fhg111xGQGNfEP-OnoXqFV6X9iMEc,8580
+kumoai/client/client.py,sha256=Jda8V9yiu3LbhxlcgRWPeYi7eF6jzCKcq8-B_vEd1ik,8514
 kumoai/client/graph.py,sha256=zvLEDExLT_RVbUMHqVl0m6tO6s2gXmYSoWmPF6YMlnA,3831
 kumoai/client/online.py,sha256=pkBBh_DEC3GAnPcNw6bopNRlGe7EUbIFe7_seQqZRaw,2720
 kumoai/client/source_table.py,sha256=VCsCcM7KYcnjGP7HLTb-AOSEGEVsJTWjk8bMg1JdgPU,2101
@@ -91,8 +106,8 @@ kumoai/trainer/baseline_trainer.py,sha256=LlfViNOmswNv4c6zJJLsyv0pC2mM2WKMGYx06o
 kumoai/trainer/__init__.py,sha256=zUdFl-f-sBWmm2x8R-rdVzPBeU2FaMzUY5mkcgoTa1k,939
 kumoai/trainer/online_serving.py,sha256=9cddb5paeZaCgbUeceQdAOxysCtV5XP-KcsgFz_XR5w,9566
 kumoai/trainer/trainer.py,sha256=hBXO7gwpo3t59zKFTeIkK65B8QRmWCwO33sbDuEAPlY,20133
-kumoai-2.12.0.dev202511111731.dist-info/RECORD,,
-kumoai-2.12.0.dev202511111731.dist-info/WHEEL,sha256=sunMa2yiYbrNLGeMVDqEA0ayyJbHlex7SCn1TZrEq60,136
-kumoai-2.12.0.dev202511111731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
-kumoai-2.12.0.dev202511111731.dist-info/METADATA,sha256=sNoIEIZxJx58O-0mQyfBmpsnrkAzg3ZVQhucsvlDX64,2052
-kumoai-2.12.0.dev202511111731.dist-info/licenses/LICENSE,sha256=TbWlyqRmhq9PEzCaTI0H0nWLQCCOywQM8wYH8MbjfLo,1102
+kumoai-2.13.0.dev202512091732.dist-info/RECORD,,
+kumoai-2.13.0.dev202512091732.dist-info/WHEEL,sha256=sunMa2yiYbrNLGeMVDqEA0ayyJbHlex7SCn1TZrEq60,136
+kumoai-2.13.0.dev202512091732.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
+kumoai-2.13.0.dev202512091732.dist-info/METADATA,sha256=vJw5NmUoOgDLJFHGcXgjPq6lYJXtSn8wvhyOKnCsaVU,2510
+kumoai-2.13.0.dev202512091732.dist-info/licenses/LICENSE,sha256=TbWlyqRmhq9PEzCaTI0H0nWLQCCOywQM8wYH8MbjfLo,1102

kumoai/experimental/rfm/utils.py

@@ -1,344 +0,0 @@
-import re
-import warnings
-from typing import Any, Dict, 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(
-    table_name: str,
-    df: pd.DataFrame,
-    candidates: list[str],
-) -> Optional[str]:
-    r"""Auto-detect potential primary key column.
-
-    Args:
-        table_name: The table name.
-        df: The pandas DataFrame to analyze
-        candidates: A list of potential candidates.
-
-    Returns:
-        The name of the detected primary key, or ``None`` if not found.
-    """
-    # A list of (potentially modified) table names that are eligible to match
-    # with a primary key, i.e.:
-    # - UserInfo -> User
-    # - snakecase <-> camelcase
-    # - camelcase <-> snakecase
-    # - plural <-> singular (users -> user, eligibilities -> eligibility)
-    # - verb -> noun (qualifying -> qualify)
-    _table_names = {table_name}
-    if table_name.lower().endswith('_info'):
-        _table_names.add(table_name[:-5])
-    elif table_name.lower().endswith('info'):
-        _table_names.add(table_name[:-4])
-
-    table_names = set()
-    for _table_name in _table_names:
-        table_names.add(_table_name.lower())
-        snakecase = re.sub(r'(.)([A-Z][a-z]+)', r'\1_\2', _table_name)
-        snakecase = re.sub(r'([a-z0-9])([A-Z])', r'\1_\2', snakecase)
-        table_names.add(snakecase.lower())
-        camelcase = _table_name.replace('_', '')
-        table_names.add(camelcase.lower())
-        if _table_name.lower().endswith('s'):
-            table_names.add(_table_name.lower()[:-1])
-            table_names.add(snakecase.lower()[:-1])
-            table_names.add(camelcase.lower()[:-1])
-        else:
-            table_names.add(_table_name.lower() + 's')
-            table_names.add(snakecase.lower() + 's')
-            table_names.add(camelcase.lower() + 's')
-        if _table_name.lower().endswith('ies'):
-            table_names.add(_table_name.lower()[:-3] + 'y')
-            table_names.add(snakecase.lower()[:-3] + 'y')
-            table_names.add(camelcase.lower()[:-3] + 'y')
-        elif _table_name.lower().endswith('y'):
-            table_names.add(_table_name.lower()[:-1] + 'ies')
-            table_names.add(snakecase.lower()[:-1] + 'ies')
-            table_names.add(camelcase.lower()[:-1] + 'ies')
-        if _table_name.lower().endswith('ing'):
-            table_names.add(_table_name.lower()[:-3])
-            table_names.add(snakecase.lower()[:-3])
-            table_names.add(camelcase.lower()[:-3])
-
-    scores: list[tuple[str, int]] = []
-    for col_name in candidates:
-        col_name_lower = col_name.lower()
-
-        score = 0
-
-        if col_name_lower == 'id':
-            score += 4
-
-        for table_name_lower in table_names:
-
-            if col_name_lower == table_name_lower:
-                score += 4  # USER -> USER
-                break
-
-            for suffix in ['id', 'hash', 'key', 'code', 'uuid']:
-                if not col_name_lower.endswith(suffix):
-                    continue
-
-                if col_name_lower == f'{table_name_lower}_{suffix}':
-                    score += 5  # USER -> USER_ID
-                    break
-
-                if col_name_lower == f'{table_name_lower}{suffix}':
-                    score += 5  # User -> UserId
-                    break
-
-                if col_name_lower.endswith(f'{table_name_lower}_{suffix}'):
-                    score += 2
-
-                if col_name_lower.endswith(f'{table_name_lower}{suffix}'):
-                    score += 2
-
-            # `rel-bench` hard-coding :(
-            if table_name == 'studies' and col_name == 'nct_id':
-                score += 1
-
-        ser = df[col_name].iloc[:1_000_000]
-        score += 3 * (ser.nunique() / len(ser))
-
-        scores.append((col_name, score))
-
-    scores = [x for x in scores if x[-1] >= 4]
-    scores.sort(key=lambda x: x[-1], reverse=True)
-
-    if len(scores) == 0:
-        return None
-
-    if len(scores) == 1:
-        return scores[0][0]
-
-    # In case of multiple candidates, only return one if its score is unique:
-    if scores[0][1] != scores[1][1]:
-        return scores[0][0]
-
-    max_score = max(scores, key=lambda x: x[1])
-    candidates = [col_name for col_name, score in scores if score == max_score]
-    warnings.warn(f"Found multiple potential primary keys in table "
-                  f"'{table_name}': {candidates}. Please specify the primary "
-                  f"key for this table manually.")
-
-    return None
-
-
-def detect_time_column(
-    df: pd.DataFrame,
-    candidates: list[str],
-) -> Optional[str]:
-    r"""Auto-detect potential time column.
-
-    Args:
-        df: The pandas DataFrame to analyze
-        candidates: A list of potential candidates.
-
-    Returns:
-        The name of the detected time column, or ``None`` if not found.
-    """
-    candidates = [  # Exclude all candidates with `*last*` in column names:
-        col_name for col_name in candidates
-        if not re.search(r'(^|_)last(_|$)', col_name, re.IGNORECASE)
-    ]
-
-    if len(candidates) == 0:
-        return None
-
-    if len(candidates) == 1:
-        return candidates[0]
-
-    # If there exists a dedicated `create*` column, use it as time column:
-    create_candidates = [
-        candidate for candidate in candidates
-        if candidate.lower().startswith('create')
-    ]
-    if len(create_candidates) == 1:
-        return create_candidates[0]
-    if len(create_candidates) > 1:
-        candidates = create_candidates
-
-    # Find the most optimal time column. Usually, it is the one pointing to
-    # the oldest timestamps:
-    with warnings.catch_warnings():
-        warnings.filterwarnings('ignore', message='Could not infer format')
-        min_timestamp_dict = {
-            key: pd.to_datetime(df[key].iloc[:10_000], 'coerce')
-            for key in candidates
-        }
-    min_timestamp_dict = {
-        key: value.min().tz_localize(None)
-        for key, value in min_timestamp_dict.items()
-    }
-    min_timestamp_dict = {
-        key: value
-        for key, value in min_timestamp_dict.items() if not pd.isna(value)
-    }
-
-    if len(min_timestamp_dict) == 0:
-        return None
-
-    return min(min_timestamp_dict, key=min_timestamp_dict.get)  # type: ignore
-
-
-PUNCTUATION = re.compile(r"[\'\"\.,\(\)\!\?\;\:]")
-MULTISPACE = re.compile(r"\s+")
-
-
-def normalize_text(
-    ser: pd.Series,
-    max_words: Optional[int] = 50,
-) -> pd.Series:
-    r"""Normalizes text into a list of lower-case words.
-
-    Args:
-        ser: The :class:`pandas.Series` to normalize.
-        max_words: The maximum number of words to return.
-            This will auto-shrink any large text column to avoid blowing up
-            context size.
-    """
-    if len(ser) == 0 or pd.api.types.is_list_like(ser.iloc[0]):
-        return ser
-
-    def normalize_fn(line: str) -> list[str]:
-        line = PUNCTUATION.sub(" ", line)
-        line = re.sub(r"<br\s*/?>", " ", line)  # Handle <br /> or <br>
-        line = MULTISPACE.sub(" ", line)
-        words = line.split()
-        if max_words is not None:
-            words = words[:max_words]
-        return words
-
-    ser = ser.fillna('').astype(str)
-
-    if max_words is not None:
-        # We estimate the number of words as 5 characters + 1 space in an
-        # English text on average. We need this pre-filter here, as word
-        # splitting on a giant text can be very expensive:
-        ser = ser.str[:6 * max_words]
-
-    ser = ser.str.lower()
-    ser = ser.map(normalize_fn)
-
-    return ser