kumoai 2.13.0.dev202512040651__cp312-cp312-win_amd64.whl → 2.14.0.dev202512111731__cp312-cp312-win_amd64.whl

{kumoai-2.13.0.dev202512040651.dist-info → kumoai-2.14.0.dev202512111731.dist-info}/RECORD

@@ -1,13 +1,13 @@
-kumoai/__init__.py,sha256=qu-qohU2cQlManX1aZIlzA3ivKl52m-cSQBPSW8urUU,10837
+kumoai/__init__.py,sha256=aDhb7KGetDnOz54u1Fd45zfM2N8oAha6XT2CvJqOvgc,11146
 kumoai/_logging.py,sha256=qL4JbMQwKXri2f-SEJoFB8TY5ALG12S-nobGTNWxW-A,915
 kumoai/_singleton.py,sha256=i2BHWKpccNh5SJGDyU0IXsnYzJAYr8Xb0wz4c6LRbpo,861
-kumoai/_version.py,sha256=ubLFhwaEt9iOGqPjskQWNn61rU80l153XB_V_RDASDU,39
+kumoai/_version.py,sha256=1P4-kFh0Np-63qTmspyV3KEawGdIIMPl6ZARL87NM3s,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.cp312-win_amd64.pyd,sha256=3QbQYqFqTG9ug5pa5KodhP122ajN9gnn0g5ckd8-gWc,198144
+kumoai/kumolib.cp312-win_amd64.pyd,sha256=tgu5bJkhFo3Yc524MI6sVvovE0yUuQ-dEnGPbKaFBIE,198144
 kumoai/mixin.py,sha256=IaiB8SAI0VqOoMVzzIaUlqMt53-QPUK6OB0HikG-V9E,840
 kumoai/spcs.py,sha256=KWfENrwSLruprlD-QPh63uU0N6npiNrwkeKfBk3EUyQ,4260
 kumoai/artifact_export/__init__.py,sha256=UXAQI5q92ChBzWAk8o3J6pElzYHudAzFZssQXd4o7i8,247
@@ -55,23 +55,23 @@ kumoai/encoder/__init__.py,sha256=8FeP6mUyCeXxr1b8kUIi5dxe5vEXQRft9tPoaV1CBqg,18
 kumoai/experimental/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kumoai/experimental/rfm/__init__.py,sha256=EFZz6IvvskmeO85Vig6p1m_6jdimS_BkeREOndHuRsc,6247
 kumoai/experimental/rfm/authenticate.py,sha256=G89_4TMeUpr5fG_0VTzMF5sdNhaciitA1oc2loTlTmo,19321
-kumoai/experimental/rfm/graph.py,sha256=ymPw8nNYeXeDnuyL2ioRL6wDHLmp3_gm9PQadLBCkL8,40096
-kumoai/experimental/rfm/local_graph_sampler.py,sha256=dQ3JnuozTNeZyUFRu2h8OTMNmV1RAoaCA0gvkpgOstg,8110
-kumoai/experimental/rfm/local_graph_store.py,sha256=6jY1ciVIlnBBhZCxWwBTl7SKX1fxRIDLszwrftD0Cdk,13485
-kumoai/experimental/rfm/local_pquery_driver.py,sha256=Yd_yHIrvuDj16IC1pvsqiQvZS41vvOOCRMiuDGtN6Fk,26851
-kumoai/experimental/rfm/rfm.py,sha256=vOnL8ecHTo1TX2B8_T8xaWGou8qYYz8DyVENu1H93mM,48834
+kumoai/experimental/rfm/graph.py,sha256=SL3-WinoLnkZC6VVjebYGLuQJJyEVFJdCm6h3FNE0e4,40816
+kumoai/experimental/rfm/rfm.py,sha256=jauaV5MuuSPsWDI2VwzMxxnsXpQ6Jp3nhgPTmxUMeh8,50304
 kumoai/experimental/rfm/sagemaker.py,sha256=sEJSyfEFBA3-7wKinBEzSooKHEn0BgPjrgRnPhYo79g,5120
 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/__init__.py,sha256=8JbLaai0yhtldFcDkddphIJKMiKc0XnodvYBWkrGPXI,1056
+kumoai/experimental/rfm/backend/local/graph_store.py,sha256=m1eHot4hRSl6OY1trPRDEH0U89hVoRqMfWhA9f-SyQU,12234
+kumoai/experimental/rfm/backend/local/sampler.py,sha256=GRMaBtfrSTJtX_9_uwi4MXV0V8SHYAsJJ68d5qrvJJg,11051
 kumoai/experimental/rfm/backend/local/table.py,sha256=1PqNOROzlnK3SaZHNcU2hyzeifs0N4wssQAS3-Z0Myc,3674
 kumoai/experimental/rfm/backend/snow/__init__.py,sha256=viMeR9VWpB1kjRdSWCTNFMdM7a8Mj_Dtck1twJW8dV8,962
-kumoai/experimental/rfm/backend/snow/table.py,sha256=f6of849A7n-Om1ExRFPfy42Ba_2we7y__ECi6V2KgYg,4374
+kumoai/experimental/rfm/backend/snow/table.py,sha256=Rf4hUPOUtsjpaIc9vBKWPZ3yz20OOg6DZqCGeih4KC8,4372
 kumoai/experimental/rfm/backend/sqlite/__init__.py,sha256=xw5NNLrWSvUvRkD49X_9hZYjas5EuP1XDANPy0EEjOg,874
 kumoai/experimental/rfm/backend/sqlite/table.py,sha256=mBiZC21gQwfR4demFrP37GmawMHfIm-G82mLQeBqIZo,3901
-kumoai/experimental/rfm/base/__init__.py,sha256=oXPkeBemtuDxRUK61-0sOT84GZB_oQ6HvaZNU1KFNaw,199
+kumoai/experimental/rfm/base/__init__.py,sha256=FX1DonqdQLD-q0SBqhNIelr6HUN2LNiutviCmdikDok,282
 kumoai/experimental/rfm/base/column.py,sha256=OE-PRQ8HO4uTq0e3_3eHJFfhp5nzw79zd-43g3iMh4g,2385
+kumoai/experimental/rfm/base/sampler.py,sha256=277THFQGvQK_OkBBKHQ7166oGpnL_zVPFble7Ehlu3c,31805
 kumoai/experimental/rfm/base/source.py,sha256=H5yN9xAwK3i_69EdqOV_x58muPGKQiI8ev5BhHQDZEo,290
-kumoai/experimental/rfm/base/table.py,sha256=glyAg4LCQdddM3lIRClJSA7qMyfoHUVAGBf1rEs6B8Y,20113
+kumoai/experimental/rfm/base/table.py,sha256=6GlWUz3tAu2g1QqTA5idWGmfo2KEJoNApDFZRn8e0pg,20388
 kumoai/experimental/rfm/infer/__init__.py,sha256=qKg8or-SpgTApD6ePw1PJ4aUZPrOLTHLRCmBIJ92hrk,486
 kumoai/experimental/rfm/infer/categorical.py,sha256=bqmfrE5ZCBTcb35lA4SyAkCu3MgttAn29VBJYMBNhVg,893
 kumoai/experimental/rfm/infer/dtype.py,sha256=Hf_drluYNuN59lTSe-8GuXalg20Pv93kCktB6Hb9f74,2686
@@ -82,14 +82,14 @@ kumoai/experimental/rfm/infer/time_col.py,sha256=G98Cgz1m9G9VA-ApnCmGYnJxEFwp1jf
 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
-kumoai/experimental/rfm/pquery/pandas_executor.py,sha256=QQpOZ_ArH3eSAkenaY3J-gW1Wn5A7f85RiqZxaO5u1Q,19019
+kumoai/experimental/rfm/pquery/pandas_executor.py,sha256=h5F2hrnyqAPqaqH4RwTdgkeedfCcDTpph9sF0lwIrx4,19024
 kumoai/graph/__init__.py,sha256=QGk3OMwRzQJSGESdcc7hcQH6UDmNVJYTdqnRren4c7Q,240
 kumoai/graph/column.py,sha256=cQhioibTbIKIBZ-bf8-Bt4F4Iblhidps-CYWrkxRPnE,4295
 kumoai/graph/graph.py,sha256=Pq-dxi4MwoDtrrwm3xeyUB9Hl7ryNfHq4rMHuvyNB3c,39239
 kumoai/graph/table.py,sha256=BB-4ezyd7hrrj6QZwRBa80ySH0trwYb4fmhRn3xoK-k,34726
 kumoai/pquery/__init__.py,sha256=FF6QUTG_xrz2ic1I8NcIa8O993Ae98eZ9gkvQ4rapgo,558
 kumoai/pquery/prediction_table.py,sha256=hWG4L_ze4PLgUoxCXNKk8_nkYxVXELQs8_X8KGOE9yk,11063
-kumoai/pquery/predictive_query.py,sha256=GWhQpQxf6apyyu-bvE3z63mX6NLd8lKbyu_jzj7rNms,25608
+kumoai/pquery/predictive_query.py,sha256=I5Ntc7YO1qEGxKrLuhAzZO3SySr8Wnjhde8eDbbB7zk,25542
 kumoai/pquery/training_table.py,sha256=L1QjaVlY4SAPD8OUmTaH6YjZzBbPOnS9mnAT69znWv0,16233
 kumoai/testing/__init__.py,sha256=XBQ_Sa3WnOYlpXZ3gUn8w6nVfZt-nfPhytfIBeiPt4w,178
 kumoai/testing/decorators.py,sha256=p79ZCQqPY_MHWy0_l7-xQ6wUIqFTn4AbrGWTHLvpbQY,1664
@@ -104,8 +104,8 @@ 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.dev202512040651.dist-info/licenses/LICENSE,sha256=ZUilBDp--4vbhsEr6f_Upw9rnIx09zQ3K9fXQ0rfd6w,1111
-kumoai-2.13.0.dev202512040651.dist-info/METADATA,sha256=7uIT7UzASJE2vNRDcrBRyZ0i0YkGVX4wTq8ClqiKCWM,2580
-kumoai-2.13.0.dev202512040651.dist-info/WHEEL,sha256=8UP9x9puWI0P1V_d7K2oMTBqfeLNm21CTzZ_Ptr0NXU,101
-kumoai-2.13.0.dev202512040651.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
-kumoai-2.13.0.dev202512040651.dist-info/RECORD,,
+kumoai-2.14.0.dev202512111731.dist-info/licenses/LICENSE,sha256=ZUilBDp--4vbhsEr6f_Upw9rnIx09zQ3K9fXQ0rfd6w,1111
+kumoai-2.14.0.dev202512111731.dist-info/METADATA,sha256=BTYN5IeO5MXS1lF5aA-O_p7x32QpVK0kuMMp6Wy2S-A,2580
+kumoai-2.14.0.dev202512111731.dist-info/WHEEL,sha256=8UP9x9puWI0P1V_d7K2oMTBqfeLNm21CTzZ_Ptr0NXU,101
+kumoai-2.14.0.dev202512111731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
+kumoai-2.14.0.dev202512111731.dist-info/RECORD,,

kumoai/experimental/rfm/local_graph_sampler.py

@@ -1,223 +0,0 @@
-import re
-from typing import Dict, List, Optional, Tuple
-
-import numpy as np
-import pandas as pd
-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
-
-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:
-    def __init__(self, graph_store: LocalGraphStore) -> None:
-        self._graph_store = graph_store
-        self._sampler = kumolib.NeighborSampler(
-            self._graph_store.node_types,
-            self._graph_store.edge_types,
-            {
-                '__'.join(edge_type): colptr
-                for edge_type, colptr in self._graph_store.colptr_dict.items()
-            },
-            {
-                '__'.join(edge_type): row
-                for edge_type, row in self._graph_store.row_dict.items()
-            },
-            self._graph_store.time_dict,
-        )
-
-    def __call__(
-        self,
-        entity_table_names: Tuple[str, ...],
-        node: np.ndarray,
-        time: np.ndarray,
-        num_neighbors: List[int],
-        exclude_cols_dict: Dict[str, List[str]],
-    ) -> Subgraph:
-
-        (
-            row_dict,
-            col_dict,
-            node_dict,
-            batch_dict,
-            num_sampled_nodes_dict,
-            num_sampled_edges_dict,
-        ) = self._sampler.sample(
-            {
-                '__'.join(edge_type): num_neighbors
-                for edge_type in self._graph_store.edge_types
-            },
-            {},  # time interval based sampling
-            entity_table_names[0],
-            node,
-            time // 1000**3,  # nanoseconds to seconds
-        )
-
-        table_dict: Dict[str, Table] = {}
-        for table_name, node in node_dict.items():
-            batch = batch_dict[table_name]
-
-            if len(node) == 0:
-                continue
-
-            df = self._graph_store.df_dict[table_name]
-
-            num_sampled_nodes = num_sampled_nodes_dict[table_name].tolist()
-            stype_dict = {  # Exclude target columns:
-                column_name: stype
-                for column_name, stype in
-                self._graph_store.stype_dict[table_name].items()
-                if column_name not in exclude_cols_dict.get(table_name, [])
-            }
-            primary_key: Optional[str] = None
-            if table_name in entity_table_names:
-                primary_key = self._graph_store.pkey_name_dict.get(table_name)
-
-            columns: List[str] = []
-            if table_name in entity_table_names:
-                columns += [self._graph_store.pkey_name_dict[table_name]]
-            columns += list(stype_dict.keys())
-
-            if len(columns) == 0:
-                table_dict[table_name] = Table(
-                    df=pd.DataFrame(index=range(len(node))),
-                    row=None,
-                    batch=batch,
-                    num_sampled_nodes=num_sampled_nodes,
-                    stype_dict=stype_dict,
-                    primary_key=primary_key,
-                )
-                continue
-
-            row: Optional[np.ndarray] = None
-            if table_name in self._graph_store.end_time_column_dict:
-                # Set end time to NaT for all values greater than anchor time:
-                df = df.iloc[node].reset_index(drop=True)
-                col_name = self._graph_store.end_time_column_dict[table_name]
-                ser = df[col_name]
-                value = ser.astype('datetime64[ns]').astype(int).to_numpy()
-                mask = value > time[batch]
-                df.loc[mask, col_name] = pd.NaT
-            else:
-                # Only store unique rows in `df` above a certain threshold:
-                unique_node, inverse = np.unique(node, return_inverse=True)
-                if len(node) > 1.05 * len(unique_node):
-                    df = df.iloc[unique_node].reset_index(drop=True)
-                    row = inverse
-                else:
-                    df = df.iloc[node].reset_index(drop=True)
-
-            # Filter data frame to minimal set of columns:
-            df = df[columns]
-
-            # Normalize text (if not already pre-processed):
-            for column_name, stype in stype_dict.items():
-                if stype == Stype.text:
-                    df[column_name] = normalize_text(df[column_name])
-
-            table_dict[table_name] = Table(
-                df=df,
-                row=row,
-                batch=batch,
-                num_sampled_nodes=num_sampled_nodes,
-                stype_dict=stype_dict,
-                primary_key=primary_key,
-            )
-
-        link_dict: Dict[Tuple[str, str, str], Link] = {}
-        for edge_type in self._graph_store.edge_types:
-            edge_type_str = '__'.join(edge_type)
-
-            row = row_dict[edge_type_str]
-            col = col_dict[edge_type_str]
-
-            if len(row) == 0:
-                continue
-
-            # Do not store reverse edge type if it is a replica:
-            rev_edge_type = Subgraph.rev_edge_type(edge_type)
-            rev_edge_type_str = '__'.join(rev_edge_type)
-            if (rev_edge_type in link_dict
-                    and np.array_equal(row, col_dict[rev_edge_type_str])
-                    and np.array_equal(col, row_dict[rev_edge_type_str])):
-                link = Link(
-                    layout=EdgeLayout.REV,
-                    row=None,
-                    col=None,
-                    num_sampled_edges=(
-                        num_sampled_edges_dict[edge_type_str].tolist()),
-                )
-                link_dict[edge_type] = link
-                continue
-
-            layout = EdgeLayout.COO
-            if np.array_equal(row, np.arange(len(row))):
-                row = None
-            if np.array_equal(col, np.arange(len(col))):
-                col = None
-
-            # Store in compressed representation if more efficient:
-            num_cols = table_dict[edge_type[2]].num_rows
-            if col is not None and len(col) > num_cols + 1:
-                layout = EdgeLayout.CSC
-                colcount = np.bincount(col, minlength=num_cols)
-                col = np.empty(num_cols + 1, dtype=col.dtype)
-                col[0] = 0
-                np.cumsum(colcount, out=col[1:])
-
-            link = Link(
-                layout=layout,
-                row=row,
-                col=col,
-                num_sampled_edges=(
-                    num_sampled_edges_dict[edge_type_str].tolist()),
-            )
-            link_dict[edge_type] = link
-
-        return Subgraph(
-            anchor_time=time,
-            table_dict=table_dict,
-            link_dict=link_dict,
-        )