kumoai 2.13.0.dev202511261731__cp313-cp313-macosx_11_0_arm64.whl → 2.13.0.dev202512061731__cp313-cp313-macosx_11_0_arm64.whl

kumoai/experimental/rfm/infer/dtype.py

@@ -0,0 +1,79 @@
+from typing import Dict
+
+import numpy as np
+import pandas as pd
+import pyarrow as pa
+from kumoapi.typing import Dtype
+
+PANDAS_TO_DTYPE: Dict[str, Dtype] = {
+    'bool': Dtype.bool,
+    'boolean': Dtype.bool,
+    'int8': Dtype.int,
+    'int16': Dtype.int,
+    'int32': Dtype.int,
+    'int64': Dtype.int,
+    'float16': Dtype.float,
+    'float32': Dtype.float,
+    'float64': Dtype.float,
+    'object': Dtype.string,
+    'string': Dtype.string,
+    'string[python]': Dtype.string,
+    'string[pyarrow]': Dtype.string,
+    'binary': Dtype.binary,
+}
+
+
+def infer_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 pd.api.types.is_timedelta64_dtype(ser.dtype):
+        return Dtype.timedelta
+    if isinstance(ser.dtype, pd.CategoricalDtype):
+        return Dtype.string
+
+    if (pd.api.types.is_object_dtype(ser.dtype)
+            and not isinstance(ser.dtype, pd.ArrowDtype)):
+        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()
+            arr = pa.array(ser.tolist())
+            ser = pd.Series(arr, dtype=pd.ArrowDtype(arr.type))
+
+    if isinstance(ser.dtype, pd.ArrowDtype):
+        if pa.types.is_list(ser.dtype.pyarrow_dtype):
+            elem_dtype = ser.dtype.pyarrow_dtype.value_type
+            if pa.types.is_integer(elem_dtype):
+                return Dtype.intlist
+            if pa.types.is_floating(elem_dtype):
+                return Dtype.floatlist
+            if pa.types.is_decimal(elem_dtype):
+                return Dtype.floatlist
+            if pa.types.is_string(elem_dtype):
+                return Dtype.stringlist
+            if pa.types.is_null(elem_dtype):
+                return Dtype.floatlist
+
+    if isinstance(ser.dtype, np.dtype):
+        dtype_str = str(ser.dtype).lower()
+    elif isinstance(ser.dtype, pd.api.extensions.ExtensionDtype):
+        dtype_str = ser.dtype.name.lower()
+        dtype_str = dtype_str.split('[')[0]  # Remove backend metadata
+    elif isinstance(ser.dtype, pa.DataType):
+        dtype_str = str(ser.dtype).lower()
+    else:
+        dtype_str = 'object'
+
+    if dtype_str not in PANDAS_TO_DTYPE:
+        raise ValueError(f"Unsupported data type '{ser.dtype}'")
+
+    return PANDAS_TO_DTYPE[dtype_str]

kumoai/experimental/rfm/infer/pkey.py

@@ -0,0 +1,126 @@
+import re
+import warnings
+from typing import Optional
+
+import pandas as pd
+
+
+def infer_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

kumoai/experimental/rfm/infer/time_col.py

@@ -0,0 +1,62 @@
+import re
+import warnings
+from typing import Optional
+
+import pandas as pd
+
+
+def infer_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

kumoai/experimental/rfm/local_graph_sampler.py

@@ -1,3 +1,4 @@
+import re
 from typing import Dict, List, Optional, Tuple
 
 import numpy as np
@@ -6,8 +7,48 @@ from kumoapi.rfm.context import EdgeLayout, Link, Subgraph, Table
 from kumoapi.typing import Stype
 
 import kumoai.kumolib as kumolib
-from kumoai.experimental.rfm.local_graph_store import LocalGraphStore
-from kumoai.experimental.rfm.utils import normalize_text
+from kumoai.experimental.rfm.backend.local import LocalGraphStore
+
+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
 
 
 class LocalGraphSampler:

kumoai/experimental/rfm/local_pquery_driver.py

@@ -17,7 +17,7 @@ from kumoapi.task import TaskType
 from kumoapi.typing import AggregationType, DateOffset, Stype
 
 import kumoai.kumolib as kumolib
-from kumoai.experimental.rfm.local_graph_store import LocalGraphStore
+from kumoai.experimental.rfm.backend.local import LocalGraphStore
 from kumoai.experimental.rfm.pquery import PQueryPandasExecutor
 
 _coverage_warned = False

kumoai/experimental/rfm/rfm.py

@@ -32,9 +32,9 @@ from kumoapi.task import TaskType
 
 from kumoai.client.rfm import RFMAPI
 from kumoai.exceptions import HTTPException
-from kumoai.experimental.rfm import LocalGraph
+from kumoai.experimental.rfm import Graph
+from kumoai.experimental.rfm.backend.local import LocalGraphStore
 from kumoai.experimental.rfm.local_graph_sampler import LocalGraphSampler
-from kumoai.experimental.rfm.local_graph_store import LocalGraphStore
 from kumoai.experimental.rfm.local_pquery_driver import (
     LocalPQueryDriver,
     date_offset_to_seconds,
@@ -123,17 +123,17 @@ class KumoRFM:
     :class:`KumoRFM` is a foundation model to generate predictions for any
     relational dataset without training.
     The model is pre-trained and the class provides an interface to query the
-    model from a :class:`LocalGraph` object.
+    model from a :class:`Graph` object.
 
     .. code-block:: python
 
-        from kumoai.experimental.rfm import LocalGraph, KumoRFM
+        from kumoai.experimental.rfm import Graph, KumoRFM
 
         df_users = pd.DataFrame(...)
         df_items = pd.DataFrame(...)
         df_orders = pd.DataFrame(...)
 
-        graph = LocalGraph.from_data({
+        graph = Graph.from_data({
             'users': df_users,
             'items': df_items,
             'orders': df_orders,
@@ -150,26 +150,16 @@ class KumoRFM:
 
     Args:
         graph: The graph.
-        preprocess: Whether to pre-process the data in advance during graph
-            materialization.
-            This is a runtime trade-off between graph materialization and model
-            processing speed.
-            It can be benefical to preprocess your data once and then run many
-            queries on top to achieve maximum model speed.
-            However, if activiated, graph materialization can take potentially
-            much longer, especially on graphs with many large text columns.
-            Best to tune this option manually.
         verbose: Whether to print verbose output.
     """
     def __init__(
         self,
-        graph: LocalGraph,
-        preprocess: bool = False,
+        graph: Graph,
         verbose: Union[bool, ProgressLogger] = True,
     ) -> None:
         graph = graph.validate()
         self._graph_def = graph._to_api_graph_definition()
-        self._graph_store = LocalGraphStore(graph, preprocess, verbose)
+        self._graph_store = LocalGraphStore(graph, verbose)
         self._graph_sampler = LocalGraphSampler(self._graph_store)
 
         self._client: Optional[RFMAPI] = None

kumoai/experimental/rfm/sagemaker.py

@@ -2,15 +2,22 @@ import base64
 import json
 from typing import Any, Dict, List, Tuple
 
-import boto3
 import requests
-from mypy_boto3_sagemaker_runtime.client import SageMakerRuntimeClient
-from mypy_boto3_sagemaker_runtime.type_defs import InvokeEndpointOutputTypeDef
 
 from kumoai.client import KumoClient
 from kumoai.client.endpoints import Endpoint, HTTPMethod
 from kumoai.exceptions import HTTPException
 
+try:
+    # isort: off
+    from mypy_boto3_sagemaker_runtime.client import SageMakerRuntimeClient
+    from mypy_boto3_sagemaker_runtime.type_defs import (
+        InvokeEndpointOutputTypeDef, )
+    # isort: on
+except ImportError:
+    SageMakerRuntimeClient = Any
+    InvokeEndpointOutputTypeDef = Any
+
 
 class SageMakerResponseAdapter(requests.Response):
     def __init__(self, sm_response: InvokeEndpointOutputTypeDef):
@@ -34,6 +41,7 @@ class SageMakerResponseAdapter(requests.Response):
 
 class KumoClient_SageMakerAdapter(KumoClient):
     def __init__(self, region: str, endpoint_name: str):
+        import boto3
         self._client: SageMakerRuntimeClient = boto3.client(
             service_name="sagemaker-runtime", region_name=region)
         self._endpoint_name = endpoint_name

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.dev202512061731.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kumoai
-Version: 2.13.0.dev202511261731
+Version: 2.13.0.dev202512061731
 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 +38,16 @@ 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"
+Requires-Dist: pyyaml; 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.dev202512061731.dist-info}/RECORD

@@ -1,8 +1,8 @@
 kumoai/kumolib.cpython-313-darwin.so,sha256=waBv-DiZ3WcasxiCQ-OM9EbSTgTtCfBTZIibXAK-JiQ,232816
 kumoai/_logging.py,sha256=U2_5ROdyk92P4xO4H2WJV8EC7dr6YxmmnM-b7QX9M7I,886
 kumoai/mixin.py,sha256=MP413xzuCqWhxAPUHmloLA3j4ZyF1tEtfi516b_hOXQ,812
-kumoai/_version.py,sha256=P7PbPaqmt6kLq-80AyouMRr_ZBx8A7_nPBBPEXW44ag,39
-kumoai/__init__.py,sha256=L3yOOtpSdwe3PYQlJBLkiQd3Ypp8iB5ChXkzprk3Si4,10546
+kumoai/_version.py,sha256=_62zq1gHlGnw4_Vj3YHa8OxfDzDGt7wK4h63pJl50_s,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/jobs.py,sha256=NrdLEFNo7oeCYSy-kj2nAvCFrz9BZ_xrhkqHFHk5ksY,2496
@@ -11,24 +11,38 @@ kumoai/databricks.py,sha256=e6E4lOFvZHXFwh4CO1kXU1zzDU3AapLQYMxjiHPC-HQ,476
 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=5DbhL9h0usFKSJfnx7HjLMPcG54qwJ48M2tmONqxXyY,6672
-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=wKfMKTxfuJNH1GCWGZ7-288HXil0tsCuXqg-BAFctZE,6812
-kumoai/experimental/rfm/utils.py,sha256=3IiBvT_aLBkkcJh3H11_50yt_XlEzHR0cm9Kprrtl8k,11123
-kumoai/experimental/rfm/sagemaker.py,sha256=e0rRQ28WcgAk_ALqUyU20d193c8_68rCkSengZIHu3Y,4823
-kumoai/experimental/rfm/local_table.py,sha256=r8xZ33Mjs6JD8ud6h23tZ99Dag2DvZ4h6tWjmGrKQg4,19605
-kumoai/experimental/rfm/rfm.py,sha256=lu0Qrt4uoGggxOsPI-jALQm5yGV9sxmLY6EQVsd48oo,48329
-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=cLs0mJEoKWvfG-Wgm7tr_7DbwhliMLX8V0DyQqfGgtc,4613
+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/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=BD_oGL5sqYqGGPMR1EHQIZYYkOoM5dBFnYE5FNvON0U,295
+kumoai/experimental/rfm/base/table.py,sha256=yaY7Auvq2KblXOid3-a_Pw6RgnPK5Y1zGAY2xi1D2gg,19843
+kumoai/experimental/rfm/base/sampler.py,sha256=ylJqCTJFBMCwXBsB6DDaYesQsOyqq7urq8pmpR2JdUI,10241
+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
@@ -58,7 +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
@@ -66,7 +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
@@ -92,8 +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-2.13.0.dev202511261731.dist-info/RECORD,,
-kumoai-2.13.0.dev202511261731.dist-info/WHEEL,sha256=oqGJCpG61FZJmvyZ3C_0aCv-2mdfcY9e3fXvyUNmWfM,136
-kumoai-2.13.0.dev202511261731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
-kumoai-2.13.0.dev202511261731.dist-info/METADATA,sha256=syvJLAUjDpnS7z3qqleu5LlV0NiyjCY0WnnPVlN1Vlg,2475
-kumoai-2.13.0.dev202511261731.dist-info/licenses/LICENSE,sha256=TbWlyqRmhq9PEzCaTI0H0nWLQCCOywQM8wYH8MbjfLo,1102
+kumoai-2.13.0.dev202512061731.dist-info/RECORD,,
+kumoai-2.13.0.dev202512061731.dist-info/WHEEL,sha256=oqGJCpG61FZJmvyZ3C_0aCv-2mdfcY9e3fXvyUNmWfM,136
+kumoai-2.13.0.dev202512061731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
+kumoai-2.13.0.dev202512061731.dist-info/METADATA,sha256=XT8M-fpeDwjsGaY1j8UtUESdReLI24cbccBCSF0k-Jo,2510
+kumoai-2.13.0.dev202512061731.dist-info/licenses/LICENSE,sha256=TbWlyqRmhq9PEzCaTI0H0nWLQCCOywQM8wYH8MbjfLo,1102