kumoai 2.13.0.dev202512081731__cp313-cp313-macosx_11_0_arm64.whl → 2.14.0.dev202512151351__cp313-cp313-macosx_11_0_arm64.whl

kumoai/testing/snow.py

@@ -0,0 +1,50 @@
+import json
+import os
+
+from kumoai.experimental.rfm.backend.snow import Connection
+from kumoai.experimental.rfm.backend.snow import connect as _connect
+
+
+def connect(
+    region: str,
+    id: str,
+    account: str,
+    user: str,
+    warehouse: str,
+    database: str | None = None,
+    schema: str | None = None,
+) -> Connection:
+
+    kwargs = dict(password=os.getenv('SNOWFLAKE_PASSWORD'))
+    if kwargs['password'] is None:
+        import boto3
+        from cryptography.hazmat.primitives import serialization
+
+        client = boto3.client(
+            service_name='secretsmanager',
+            region_name=region,
+        )
+        secret_id = (f'arn:aws:secretsmanager:{region}:{id}:secret:'
+                     f'{account}.snowflakecomputing.com')
+        response = client.get_secret_value(SecretId=secret_id)['SecretString']
+        secret = json.loads(response)
+
+        private_key = serialization.load_pem_private_key(
+            secret['kumo_user_secretkey'].encode(),
+            password=None,
+        )
+        kwargs['private_key'] = private_key.private_bytes(
+            encoding=serialization.Encoding.DER,
+            format=serialization.PrivateFormat.PKCS8,
+            encryption_algorithm=serialization.NoEncryption(),
+        )
+
+    return _connect(
+        account=account,
+        user=user,
+        warehouse='WH_XS',
+        database='KUMO',
+        schema=schema,
+        session_parameters=dict(CLIENT_TELEMETRY_ENABLED=False),
+        **kwargs,
+    )

kumoai/utils/__init__.py

@@ -1,8 +1,10 @@
+from .sql import quote_ident
 from .progress_logger import ProgressLogger, InteractiveProgressLogger
 from .forecasting import ForecastVisualizer
 from .datasets import from_relbench
 
 __all__ = [
+    'quote_ident',
     'ProgressLogger',
     'InteractiveProgressLogger',
     'ForecastVisualizer',

kumoai/utils/sql.py

@@ -0,0 +1,3 @@
+def quote_ident(name: str) -> str:
+    r"""Quotes a SQL identifier."""
+    return '"' + name.replace('"', '""') + '"'

{kumoai-2.13.0.dev202512081731.dist-info → kumoai-2.14.0.dev202512151351.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kumoai
-Version: 2.13.0.dev202512081731
+Version: 2.14.0.dev202512151351
 Summary: AI on the Modern Data Stack
 Author-email: "Kumo.AI" <hello@kumo.ai>
 License-Expression: MIT
@@ -23,7 +23,7 @@ Requires-Dist: requests>=2.28.2
 Requires-Dist: urllib3
 Requires-Dist: plotly
 Requires-Dist: typing_extensions>=4.5.0
-Requires-Dist: kumo-api==0.48.0
+Requires-Dist: kumo-api==0.49.0
 Requires-Dist: tqdm>=4.66.0
 Requires-Dist: aiohttp>=3.10.0
 Requires-Dist: pydantic>=1.10.21

{kumoai-2.13.0.dev202512081731.dist-info → kumoai-2.14.0.dev202512151351.dist-info}/RECORD

@@ -1,7 +1,7 @@
 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=W0EIBX5oPkQ0eXYnfNBgKMhonz56bp9ySi_IPtjQoCA,39
+kumoai/_version.py,sha256=bOoqsL1s-b_8ovgo8rxykwFD8SfZQM7pj8skKFtYz5U,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
@@ -11,24 +11,24 @@ 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=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/graph.py,sha256=awVJSk4cWRMacS5CJvJtR8TR56FEbrJPcQCukNydQOc,40392
 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/rfm.py,sha256=YyUzoyu7STVnmGnKWTgAPVB4GlMng_n1PDXv45o9oJM,49976
 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/sqlite/__init__.py,sha256=cA-PZL1oTaLxthZbfLSudexImtF6jRsGkdjSp-66dCM,914
+kumoai/experimental/rfm/backend/sqlite/table.py,sha256=fSn-CsOKK584Qgn8a-k8eymykoOrIX5w0CCzOBNW0Zk,4677
+kumoai/experimental/rfm/backend/sqlite/sampler.py,sha256=SsQCJB04DyNoz7Vyy6oF4sfaqCZt5aHpE1Kxf1qEGco,14467
 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=L1S2qxvkS_O8wy4K-czTxojPmklRrReTR8P3-e_8-hM,3823
-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/backend/local/table.py,sha256=-R_9nncosByAfSMfUt6HgCUNoW_MLGJW3F5SnAd4Ru0,3744
+kumoai/experimental/rfm/backend/local/graph_store.py,sha256=5cHuExHljU_Z56KV3s-PwzeiLuPKgh2mCxcjTMmPZ8E,11928
+kumoai/experimental/rfm/backend/local/sampler.py,sha256=85HoHCDiFOiuD_vFPZRx9JCyQUlLsqgsuB3NAw50wNw,10836
+kumoai/experimental/rfm/backend/snow/__init__.py,sha256=BYfsiuJ4Ee30GjG9EuUtitMHXnRfvVKi85zNlIwldV4,993
+kumoai/experimental/rfm/backend/snow/table.py,sha256=--kC_jh4kbXDulvWWwqERjZOKUQrAP506ksKtzQY7qk,4841
+kumoai/experimental/rfm/backend/snow/sampler.py,sha256=vp_Z2Ov6IUaT9x5_tuPGFaz3XX_jQPLQZhkKX9AS5cI,10341
 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
@@ -38,10 +38,11 @@ kumoai/experimental/rfm/infer/id.py,sha256=ZIO0DWIoiEoS_8MVc5lkqBfkTWWQ0yGCgjkwL
 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=3haYsIYypeL-U-9RuOOPnRdWaRlh-g_yE4ACJ2KLjOY,335
-kumoai/experimental/rfm/base/table.py,sha256=yaY7Auvq2KblXOid3-a_Pw6RgnPK5Y1zGAY2xi1D2gg,19843
-kumoai/experimental/rfm/base/sampler.py,sha256=b45kllqSm-lpXbP9XbrGQPMx_hEIfesJILViAanh6rk,13456
-kumoai/experimental/rfm/base/source.py,sha256=8_waFQVsctryHkm9BwmFZ9-vw5cXAXfjk7KDmcl_kic,272
+kumoai/experimental/rfm/base/sql_sampler.py,sha256=ibLn1pT2zLhs1VpK4PUf9E89aUO5q9iT1S2jmGYkKP4,1644
+kumoai/experimental/rfm/base/__init__.py,sha256=8nCg154X94HTLVOATcO54tX3axFm8QlZG9T1M3ZasnI,549
+kumoai/experimental/rfm/base/table.py,sha256=neGldEZaweoJ8VRgnEnaSpAISSkSTkgXxItuuywBM4E,20010
+kumoai/experimental/rfm/base/sampler.py,sha256=aCD98t0CUhAvGXEFv24Vq2g4otuclpKkkyL1rMR_mFg,31449
+kumoai/experimental/rfm/base/source.py,sha256=RqlI_kBoRV0ADb8KdEKn15RNHMdFUzEVzb57lIoyBM4,294
 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
@@ -52,8 +53,9 @@ kumoai/artifact_export/config.py,sha256=jOPDduduxv0uuB-7xVlDiZglfpmFF5lzQhhH1SMk
 kumoai/artifact_export/job.py,sha256=GEisSwvcjK_35RgOfsLXGgxMTXIWm765B_BW_Kgs-V0,3275
 kumoai/artifact_export/__init__.py,sha256=BsfDrc3mCHpO9-BqvqKm8qrXDIwfdaoH5UIoG4eQkc4,238
 kumoai/utils/datasets.py,sha256=ptKIUoBONVD55pTVNdRCkQT3NWdN_r9UAUu4xewPa3U,2928
-kumoai/utils/__init__.py,sha256=wGDC_31XJ-7ipm6eawjLAJaP4EfmtNOH8BHzaetQ9Ko,268
+kumoai/utils/__init__.py,sha256=cF5ACzp1X61sqhlCHc6biQk6fc4gW_oyhGsBrjx-SoM,316
 kumoai/utils/progress_logger.py,sha256=pngEGzMHkiOUKOa6fbzxCEc2xlA4SJKV4TDTVVoqObM,5062
+kumoai/utils/sql.py,sha256=f6lR6rBEW7Dtk0NdM26dOZXUHDizEHb1WPlBCJrwoq0,118
 kumoai/utils/forecasting.py,sha256=-nDS6ucKNfQhTQOfebjefj0wwWH3-KYNslIomxwwMBM,7415
 kumoai/codegen/generate.py,sha256=SvfWWa71xSAOjH9645yQvgoEM-o4BYjupM_EpUxqB_E,7331
 kumoai/codegen/naming.py,sha256=_XVQGxHfuub4bhvyuBKjltD5Lm_oPpibvP_LZteCGk0,3021
@@ -71,6 +73,7 @@ kumoai/codegen/handlers/__init__.py,sha256=k8TB_Kn-1BycBBi51kqFS2fZHCpCPgR9-3J9g
 kumoai/codegen/handlers/utils.py,sha256=58b2GCgaTBUp2aId7BLMXMV0ENrusbNbfw7mlyXAXPE,1447
 kumoai/codegen/handlers/connector.py,sha256=afGf_GreyQ9y6qF3QTgSiM416qtUcP298SatNqUFhvQ,3828
 kumoai/codegen/handlers/table.py,sha256=POHpA-GFYFGTSuerGmtigYablk-Wq1L3EBvsOI-iFMQ,3956
+kumoai/testing/snow.py,sha256=ubx3yJP0UHxsNiar1-jNdv8ZfszKc8Js3_Gg70uf008,1487
 kumoai/testing/__init__.py,sha256=goHIIo3JE7uHV7njo4_aTd89mVVR74BEAZ2uyBaOR0w,170
 kumoai/testing/decorators.py,sha256=83tMifuPTpUqX7zHxMttkj1TDdB62EBtAP-Fjj72Zdo,1607
 kumoai/connector/glue_connector.py,sha256=HivT0QYQ8-XeB4QLgWvghiqXuq7jyBK9G2R1py_NnE4,4697
@@ -84,10 +87,10 @@ kumoai/connector/utils.py,sha256=wlqQxMmPvnFNoCcczGkKYjSu05h8OhWh4fhTzQm_2bQ,646
 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
-kumoai/pquery/predictive_query.py,sha256=oUqwdOWLLkPM-G4PhpUk_6mwSJGBtaD3t37Wp5Oow8M,24971
+kumoai/pquery/predictive_query.py,sha256=UXn1s8ztubYZMNGl4ijaeidMiGlFveb1TGw9qI5-TAo,24901
 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/pquery.py,sha256=IQ8As-OOJOkuMoMosphOsA5hxQYLCbzOQJO7RezK8uY,7091
 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
@@ -106,8 +109,8 @@ 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.dev202512081731.dist-info/RECORD,,
-kumoai-2.13.0.dev202512081731.dist-info/WHEEL,sha256=oqGJCpG61FZJmvyZ3C_0aCv-2mdfcY9e3fXvyUNmWfM,136
-kumoai-2.13.0.dev202512081731.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
-kumoai-2.13.0.dev202512081731.dist-info/METADATA,sha256=ulcPeS_yowF-CWxGh5m_20ummlecVuiXBDNMgvXH-VU,2510
-kumoai-2.13.0.dev202512081731.dist-info/licenses/LICENSE,sha256=TbWlyqRmhq9PEzCaTI0H0nWLQCCOywQM8wYH8MbjfLo,1102
+kumoai-2.14.0.dev202512151351.dist-info/RECORD,,
+kumoai-2.14.0.dev202512151351.dist-info/WHEEL,sha256=oqGJCpG61FZJmvyZ3C_0aCv-2mdfcY9e3fXvyUNmWfM,136
+kumoai-2.14.0.dev202512151351.dist-info/top_level.txt,sha256=YjU6UcmomoDx30vEXLsOU784ED7VztQOsFApk1SFwvs,7
+kumoai-2.14.0.dev202512151351.dist-info/METADATA,sha256=RzqzEYc4ILs4XE1EIMufUNuB-yVzeuwDctT3Qb65zdk,2510
+kumoai-2.14.0.dev202512151351.dist-info/licenses/LICENSE,sha256=TbWlyqRmhq9PEzCaTI0H0nWLQCCOywQM8wYH8MbjfLo,1102

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.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:
-    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,
-        )