sdk-seshat-python 0.3.16__tar.gz → 0.4.1__tar.gz

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sdk-seshat-python
-Version: 0.3.16
+Version: 0.4.1
 Summary: Seshat python SDK is a library to help create ML data pipelines.
 License: Commercial - see LICENSE.txt
 Author: SeshatLabs
@@ -13,29 +13,29 @@ Provides-Extra: flipside-support
 Provides-Extra: postgres-support
 Requires-Dist: backoff (>=2.2.1,<3.0.0)
 Requires-Dist: bokeh (>=3.6.0,<4.0.0)
-Requires-Dist: boto3 (>=1.35.68,<2.0.0)
+Requires-Dist: boto3 (>=1.39.4,<2.0.0)
 Requires-Dist: croniter (>=6.0.0,<7.0.0)
 Requires-Dist: cryptography (>=44.0.0,<45.0.0)
 Requires-Dist: dask[array,complete,dataframe,distributed] (>=2024.10.0,<2025.0.0)
 Requires-Dist: flipside (>=2.1.0,<3.0.0) ; extra == "flipside-support"
 Requires-Dist: langchain (>=0.3.23,<0.4.0)
 Requires-Dist: langchain-community (>=0.3.21,<0.4.0)
-Requires-Dist: langchain-openai (>=0.3.12,<0.4.0)
+Requires-Dist: langchain-openai (==0.3.28)
 Requires-Dist: loguru (>=0.7.3,<0.8.0)
 Requires-Dist: memory-profiler (>=0.61.0,<0.62.0)
 Requires-Dist: openai (>=1.73.0,<2.0.0)
-Requires-Dist: pandas (>=2.2.1,<3.0.0)
-Requires-Dist: psycopg2 (>=2.9,<3.0) ; extra == "postgres-support"
+Requires-Dist: pandas (>=2.3.1,<3.0.0)
+Requires-Dist: psycopg2-binary (>=2.9,<3.0) ; extra == "postgres-support"
 Requires-Dist: pyarmor (>=8.5.1,<9.0.0)
 Requires-Dist: pydantic (>=2.7.4,<3.0.0)
 Requires-Dist: pyspark (>=3.5.1,<4.0.0)
 Requires-Dist: python-logstash-async (>=4.0.2,<5.0.0)
-Requires-Dist: requests (==2.32.0)
-Requires-Dist: rich (>=13.9.4,<14.0.0)
+Requires-Dist: requests (>=2.32.0,<3.0.0)
+Requires-Dist: rich (>=14.0.0,<15.0.0)
 Requires-Dist: scikit-learn (>=1.4.1.post1,<2.0.0)
 Requires-Dist: sqlalchemy (>=2.0.29,<3.0.0)
 Requires-Dist: toml (>=0.10.2,<0.11.0)
-Requires-Dist: typer (>=0.12.3,<0.13.0)
+Requires-Dist: typer (>=0.16.0,<0.17.0)
 Description-Content-Type: text/markdown
 
 

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sdk-seshat-python"
-version = "0.3.16"
+version = "0.4.1"
 description = "Seshat python SDK is a library to help create ML data pipelines."
 authors =  ["SeshatLabs <info@seshatlabs.xyz>"]
 packages = [{ include = "seshat", from = "." }]
@@ -10,19 +10,19 @@ license = "Commercial - see LICENSE.txt"
 
 [tool.poetry.dependencies]
 python = "^3.11"
-pandas = "^2.2.1"
+pandas = "^2.3.1"
 scikit-learn = "^1.4.1.post1"
 pyspark = "^3.5.1"
 flipside = "^2.1.0"
 sqlalchemy = "^2.0.29"
 memory-profiler = "^0.61.0"
-typer = "^0.12.3"
+typer = "^0.16.0"
 dask = {extras = ["array", "complete", "dataframe", "distributed"], version = "^2024.10.0"}
 bokeh = "^3.6.0"
 toml = "^0.10.2"
-rich = "^13.9.4"
-boto3 = "^1.35.68"
-requests = "2.32.0"
+rich = "^14.0.0"
+boto3 = "^1.39.4"
+requests = "^2.32.0"
 backoff = "^2.2.1"
 cryptography = "^44.0.0"
 loguru = "^0.7.3"
@@ -30,15 +30,15 @@ openai = "^1.73.0"
 pydantic = "^2.7.4"
 langchain = "^0.3.23"
 langchain-community = "^0.3.21"
-langchain-openai = "^0.3.12"
+langchain-openai = "0.3.28"
 pyarmor = "^8.5.1"
 croniter = "^6.0.0"
-psycopg2 = { version = "^2.9", optional = true }
+psycopg2-binary = { version = "^2.9", optional = true }
 python-logstash-async = "^4.0.2"
 
 [tool.poetry.extras]
 flipside_support = ["flipside"]
-postgres_support = ["psycopg2"]
+postgres_support = ["psycopg2-binary"]
 
 [tool.poetry.group.dev.dependencies]
 flake8 = "^7.0.0"

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/__init__.py

@@ -20,6 +20,7 @@ from seshat.general.exceptions import NoConfigSetError, RestClientException
 app = typer.Typer()
 console = Console()
 DEFAULT_DATA_SIZE = 1_000_000  # 1 GB
+DEFAULT_EXPIRATION = 86400
 
 state = {"verbose": False}
 
@@ -141,7 +142,12 @@ def submit_job(
         identifier = manager.store_code(package)
 
         job_response = manager.submit_job(
-            identifier, name, version, executor_image_tag, job_metadata
+            identifier,
+            name,
+            version,
+            executor_image_tag,
+            job_metadata,
+            expiration=config.get("aws", {}).get("expiration", DEFAULT_EXPIRATION),
         )
         job_response_data = job_response.get("data", {})
 

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/data_class/pandas.py

@@ -1,10 +1,9 @@
 from __future__ import annotations
 
-from typing import Iterable, List, Dict
+from typing import Dict, Iterable, List
 
 import pandas as pd
 from pandas import DataFrame
-from pyspark.sql import SparkSession
 
 from seshat.data_class import SFrame
 from seshat.data_class.base import GroupSFrame
@@ -33,7 +32,7 @@ class DFrame(SFrame):
     def to_spf(self) -> SFrame:
         from seshat.data_class import SPFrame
 
-        spark = SparkSession.builder.appName(configs.SPARK_APP_NAME).getOrCreate()
+        spark = SPFrame.get_spark()
         return SPFrame.from_raw(spark.createDataFrame(self.data))
 
     def extend_vertically(self, other: DataFrame):

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/data_class/pyspark.py

@@ -1,9 +1,10 @@
-from typing import Iterable, List, Dict
+from typing import Dict, Iterable, List
 
 from pandas import DataFrame
-from pyspark.sql import DataFrame as PySparkDataFrame, SparkSession
+from pyspark.sql import DataFrame as PySparkDataFrame
+from pyspark.sql import SparkSession
 
-from seshat.data_class import SFrame, DFrame
+from seshat.data_class import DFrame, SFrame
 from seshat.data_class.base import GroupSFrame
 from seshat.general import configs
 
@@ -56,6 +57,8 @@ class SPFrame(SFrame):
     def from_raw(cls, data, *args, **kwargs) -> "SPFrame":
         if isinstance(data, DataFrame):
             data = DFrame.from_raw(data).convert(cls).to_raw()
+        elif not isinstance(data, PySparkDataFrame) and data:
+            data = cls.get_spark().createDataFrame(data or [])
         return cls(data)
 
     @staticmethod

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/feature_view/base.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Dict, Callable
+from typing import Callable, Dict, Optional
 
 from seshat.data_class import SFrame
 from seshat.evaluation.base import Evaluation
@@ -7,6 +7,7 @@ from seshat.profiler import ProfileConfig
 from seshat.profiler.base import profiler
 from seshat.source import Source
 from seshat.source.saver import Saver
+from seshat.transformer.base import Transformer
 from seshat.transformer.pipeline import Pipeline
 from seshat.transformer.splitter import Splitter
 
@@ -36,7 +37,8 @@ class FeatureView:
     saver : Saver, optional
         An optional component responsible for saving the processed data during training
         Required only in offline mode.
-
+    on_save_finished : Transformer, Optional
+        A Transformer to be called after the save operation completes.
     Examples
     --------
     Define feature view:
@@ -81,6 +83,7 @@ class FeatureView:
     saver: Saver = None
     profile_config = ProfileConfig(logging.INFO, default_tracking=True)
     evaluation: Evaluation
+    on_save_finished: Optional[Transformer] = None
 
     def __call__(self, *args, **kwargs):
         source = self._get_source()
@@ -143,6 +146,8 @@ class FeatureView:
                 if hasattr(self, "splitter")
                 else self.saver(self.data)
             )
+        if self.on_save_finished is not None:
+            self.on_save_finished(self.data)
 
     def _split(self, *args, **kwargs):
         self.split_data = self.splitter(self.data, *args, **kwargs)

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/general/command/submit_to_network.py

@@ -313,6 +313,7 @@ class SubmitCommand(BaseTyperCommand):
         version: str,
         executor_image_tag: str,
         metadata: JobMetadata,
+        expiration=86400,
     ) -> dict:
         """Submit job to API after successful upload"""
         if not self.job_config.base_url or not self.job_config.auth_token:
@@ -320,7 +321,7 @@ class SubmitCommand(BaseTyperCommand):
                 "API configuration missing. Please set base_url and auth_token"
             )
 
-        presigned_url = self.backend.generate_presigned_url(s3_key)
+        presigned_url = self.backend.generate_presigned_url(s3_key, expiration)
         executor_label = self.config.get("executor", {}).get("label")
 
         payload = {

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/source/local/base.py

@@ -5,24 +5,29 @@ from seshat.source import Source
 
 class LocalSource(Source):
     """
-    LocalSource is a source that can read data from csv file.
+    LocalSource is a data source that can read from a local file or an in-memory source.
     """
 
     def __init__(
         self,
-        path,
+        data_source,
         query=None,
         schema=None,
         mode=configs.DEFAULT_MODE,
     ):
         super().__init__(query, schema, mode)
-        self.path = path
+        self.data_source = data_source
 
     def convert_data_type(self, data) -> SFrame:
         return self.data_class.from_raw(data)
 
     def fetch(self) -> SFrame:
-        d = self.data_class.read_csv(path=self.path)
+        d = (
+            self.data_class.read_csv(path=self.data_source)
+            if isinstance(self.data_source, str)
+            else self.data_source
+        )
+
         return self.convert_data_type(d)
 
     def calculate_complexity(self):

{sdk_seshat_python-0.3.16 → sdk_seshat_python-0.4.1}/seshat/source/saver/database.py

@@ -35,7 +35,13 @@ class SQLDBSaver(SQLMixin, Saver):
             self.create_index(config)
 
             selected_sf = sf.get(config.sf_key)
-            selected_sf = self.drop_nan_ids(selected_sf, config.schema)
+            has_id = False
+            for col in config.schema.cols:
+                if col.is_id:
+                    has_id = True
+                break
+            if has_id:
+                selected_sf = self.drop_nan_ids(selected_sf, config.schema)
 
             if config.clear_table:
                 self.delete(config.table)
@@ -65,6 +71,11 @@ class SQLDBSaver(SQLMixin, Saver):
         table, _ = self.get_table(table_name, autoload=True)
         self.write_on_db(table.delete())
 
+    def drop_table(self, table_name):
+        if table_name in inspect(self.get_engine()).get_table_names():
+            table, _ = self.get_table(table_name, autoload=True)
+            table.drop(self.get_engine())
+
     def insert(self, selected_sf: SFrame, config: SaveConfig):
         values = self.prepare_sf_to_insert(selected_sf, config).to_dict()
         table, _ = self.get_table(config.table, autoload=True)

sdk_seshat_python-0.4.1/seshat/transformer/deriver/__init__.py

@@ -0,0 +1,25 @@
+from .base import (
+    FeatureForAddressDeriver,
+    InteractedSymbolsToSentenceDeriver,
+    OperationOnColsDeriver,
+    PercentileTransactionValueDeriver,
+    SFrameFromColsDeriver,
+    StaticValueColumnAdder,
+    TimeWindowTransformer,
+    FractionDeriver,
+    ProfitLossDeriver,
+    DateTimeTypeDeriver,
+    ComprehensiveFeaturesDeriver,
+    GroupByDeriverCount,
+    GroupByDeriverMeanMax,
+    ChangingOverTimeDeriver,
+    TokenLastPriceDeriver,
+    GroupByTimeWindowDeriver,
+    OneColumnPercentileFilterDeriver,
+    SenderReceiverTokensDeriver,
+    TokenPriceDeriver,
+    TokenSwapTradeDeriver,
+    TokenFeatureTransformationDeriver,
+)
+
+from .from_database import FromSQLDBDeriver