sdk-seshat-python 0.4.6__tar.gz → 0.5.3__tar.gz

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sdk-seshat-python
-Version: 0.4.6
+Version: 0.5.3
 Summary: Seshat python SDK is a library to help create ML data pipelines.
 License: Commercial - see LICENSE.txt
 Author: SeshatLabs
@@ -9,35 +9,36 @@ Requires-Python: >=3.11,<4.0
 Classifier: License :: Other/Proprietary License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
-Provides-Extra: flipside-support
-Provides-Extra: postgres-support
 Requires-Dist: backoff (>=2.2.1,<3.0.0)
+Requires-Dist: beautifulsoup4 (>=4.14.3,<5.0.0)
 Requires-Dist: bokeh (>=3.6.0,<4.0.0)
-Requires-Dist: boto3 (>=1.35.68,<2.0.0)
+Requires-Dist: boto3 (==1.40.51)
 Requires-Dist: croniter (>=6.0.0,<7.0.0)
-Requires-Dist: cryptography (>=44.0.0,<45.0.0)
+Requires-Dist: cryptography (==46.0.2)
 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-aws (>=0.2.31,<0.3.0)
-Requires-Dist: langchain-community (>=0.3.21,<0.4.0)
-Requires-Dist: langchain-openai (>=0.3.12,<0.4.0)
+Requires-Dist: google-cloud-aiplatform (>=1.120.0,<2.0.0)
+Requires-Dist: langchain (==0.3.27)
+Requires-Dist: langchain-aws (==0.2.35)
+Requires-Dist: langchain-community (==0.3.31)
+Requires-Dist: langchain-google-vertexai (>=2.1.2,<3.0.0)
+Requires-Dist: langchain-openai (==0.3.35)
 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: openai (==2.3.0)
 Requires-Dist: pandas (>=2.2.1,<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: psycopg2-binary (==2.9.11)
+Requires-Dist: pyarmor (>=9.1.9,<10.0.0)
+Requires-Dist: pydantic (==2.12.1)
 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 (==2.32.5)
+Requires-Dist: rich (==14.2.0)
 Requires-Dist: scikit-learn (>=1.4.1.post1,<2.0.0)
 Requires-Dist: setuptools (>=80.9.0,<81.0.0)
+Requires-Dist: simplejson (>=3.20.2,<4.0.0)
 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 (>=0.19.2,<0.20.0)
 Description-Content-Type: text/markdown
 
 

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/pyproject.toml

@@ -1,8 +1,8 @@
 [tool.poetry]
 name = "sdk-seshat-python"
-version = "0.4.6"
+version = "0.5.3"
 description = "Seshat python SDK is a library to help create ML data pipelines."
-authors =  ["SeshatLabs <info@seshatlabs.xyz>"]
+authors = ["SeshatLabs <info@seshatlabs.xyz>"]
 packages = [{ include = "seshat", from = "." }]
 readme = "README.md"
 license = "Commercial - see LICENSE.txt"
@@ -13,40 +13,41 @@ python = "^3.11"
 pandas = "^2.2.1"
 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"
-dask = {extras = ["array", "complete", "dataframe", "distributed"], version = "^2024.10.0"}
+typer = "^0.19.2"
+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 = "14.2.0"
+boto3 = "1.40.51"
+requests = "2.32.5"
 backoff = "^2.2.1"
-cryptography = "^44.0.0"
+cryptography = "46.0.2"
 loguru = "^0.7.3"
-openai = "^1.73.0"
-pydantic = "^2.7.4"
-langchain = "^0.3.23"
-langchain-community = "^0.3.21"
-langchain-openai = "^0.3.12"
-pyarmor = "^8.5.1"
+openai = "2.3.0"
+pydantic = "2.12.1"
+langchain = "0.3.27"
+langchain-community = "0.3.31"
+langchain-openai = "0.3.35"
+pyarmor = "^9.1.9"
 python-logstash-async = "^4.0.2"
 croniter = "^6.0.0"
-psycopg2-binary = { version = "^2.9", optional = true }
+psycopg2-binary = "2.9.11"
 setuptools = "^80.9.0"
-langchain-aws = "^0.2.31"
+langchain-aws = "0.2.35"
+langchain-google-vertexai = "^2.1.2"
+google-cloud-aiplatform = "^1.120.0"
+simplejson = "^3.20.2"
+beautifulsoup4 = "^4.14.3"
 
-[tool.poetry.extras]
-flipside_support = ["flipside"]
-postgres_support = ["psycopg2-binary"]
 
 [tool.poetry.group.dev.dependencies]
 flake8 = "^7.0.0"
 black = "^24.3.0"
 pre-commit = "^3.7.0"
 pytest = "^8.3.4"
+pytest-xdist = "^3.8.0"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/__init__.py

@@ -6,6 +6,7 @@ import typer
 from rich.console import Console
 from rich.table import Table
 
+from seshat.general.command import SubmitCommand
 from seshat.general.command import (
     SubmitCommand,
     JobMetadata,
@@ -13,6 +14,7 @@ from seshat.general.command import (
     ExecutionMode,
 )
 from seshat.general.command.code_inspect import CodeInspectCommand
+from seshat.general.command.generate_story import GenerateStoryCommand
 from seshat.general.command.job_status import JobStatusCommand
 from seshat.general.command.setup_project import RECOMMENDATION, SetUpProjectCommand
 from seshat.general.exceptions import NoConfigSetError, RestClientException
@@ -430,6 +432,27 @@ def job_status(
         raise typer.Exit(1)
 
 
+@app.command(name="generate-story")
+def generate_story(
+    file_path: Path = typer.Option(
+        None,
+        "--file",
+        "-f",
+        help="Path to output story.json file (default: ./story.json)",
+    )
+):
+    result = GenerateStoryCommand().generate()
+    if file_path is None:
+        file_path = Path("story.json")
+    try:
+        with open(file_path, "w") as f:
+            f.write(result)
+        typer.echo(f"Story written to {file_path}")
+    except Exception as e:
+        typer.echo(f"Failed to write story to {file_path}: {e}", err=True)
+        raise typer.Exit(1)
+
+
 @app.callback()
 def main(verbose: bool = False):
     state["verbose"] = verbose

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/data_class/base.py

@@ -1,5 +1,5 @@
 import copy
-from typing import Dict, Iterable, Type, List
+from typing import Dict, Iterable, Type, List, Any
 
 from seshat.general import configs
 from seshat.general.exceptions import (
@@ -43,10 +43,14 @@ class SFrame:
     def __deepcopy__(self, memo):
         return type(self)(copy.deepcopy(self.data, memo))
 
-    def to_raw(self) -> object:
+    @property
+    def empty(self, default_key=configs.DEFAULT_SF_KEY):
+        pass
+
+    def to_raw(self) -> Any:
         return self.data
 
-    def set_raw(self, key: str, data: object):
+    def set_raw(self, key: str, data: Any):
         self.data = data
 
     def get(self, key: str) -> "SFrame":
@@ -185,6 +189,10 @@ class GroupSFrame(SFrame):
     def __deepcopy__(self, memo):
         return type(self)(copy.deepcopy(self.children, memo), self.sframe_class)
 
+    @property
+    def empty(self, default_key=configs.DEFAULT_SF_KEY):
+        return self[default_key].empty()
+
     def to_raw(self) -> Dict[str, object]:
         raw = {}
         for key, sf in self.children.items():

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/data_class/pandas.py

@@ -14,6 +14,10 @@ class DFrame(SFrame):
     frame_name = "df"
     data: DataFrame
 
+    @property
+    def empty(self, default_key=configs.DEFAULT_SF_KEY):
+        return self.data.empty
+
     def make_group(self, default_key=configs.DEFAULT_SF_KEY):
         return GroupSFrame({default_key: self}, sframe_class=self.__class__)
 
@@ -37,7 +41,7 @@ class DFrame(SFrame):
 
     def extend_vertically(self, other: DataFrame):
         super().extend_vertically(other)
-        self.data = pd.concat([self.data, other], axis=0)
+        self.data = pd.concat([self.data, other], axis=0).reset_index(drop=True)
 
     def extend_horizontally(
         self, other: DataFrame, on: str, left_on: str, right_on: str, how: str

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/data_class/pyspark.py

@@ -3,6 +3,7 @@ from typing import Dict, Iterable, List
 from pandas import DataFrame
 from pyspark.sql import DataFrame as PySparkDataFrame
 from pyspark.sql import SparkSession
+from pyspark.sql import functions as F
 
 from seshat.data_class import DFrame, SFrame
 from seshat.data_class.base import GroupSFrame
@@ -13,6 +14,10 @@ class SPFrame(SFrame):
     frame_name = "spf"
     data: PySparkDataFrame
 
+    @property
+    def empty(self, default_key=configs.DEFAULT_SF_KEY):
+        return self.data.isEmpty()
+
     def make_group(self, default_key=configs.DEFAULT_SF_KEY):
         return GroupSFrame({default_key: self}, sframe_class=self.__class__)
 
@@ -34,6 +39,19 @@ class SPFrame(SFrame):
 
     def extend_vertically(self, other: PySparkDataFrame):
         super().extend_vertically(other)
+        # Get all columns from both DataFrames
+        self_cols = set(self.data.columns)
+        other_cols = set(other.columns)
+
+        # Add missing columns to self.data
+        for col in other_cols - self_cols:
+            self.data = self.data.withColumn(col, F.lit(None).cast("string"))
+
+        # Add missing columns to other
+        for col in self_cols - other_cols:
+            other = other.withColumn(col, F.lit(None).cast("string"))
+
+        # Ensure column order matches
         self.data = self.data.unionByName(other)
 
     def extend_horizontally(

sdk_seshat_python-0.5.3/seshat/general/command/generate_story.py

@@ -0,0 +1,38 @@
+from typing import Type
+
+import simplejson as json
+
+import seshat
+from seshat.general.transformer_story.base import (
+    BaseTransformerStory,
+    BaseChallenge,
+    Describable,
+)
+from seshat.utils.find_classes import find_classes
+
+
+class GenerateStoryCommand:
+    def generate(self):
+        return json.dumps(
+            {
+                "transformers": self.get_doc(BaseTransformerStory),
+                "challenges": self.get_doc(BaseChallenge),
+            },
+            indent=4,
+            default=str,
+            ignore_nan=True,
+        )
+
+    def get_doc(self, target: Type[Describable]):
+        docs = []
+        for d in find_classes(seshat, target):
+            try:
+                docs.append(d().generate_doc())
+            except Exception:
+                import traceback
+
+                print(f"ERROR generating doc for {d}:")
+                print(f"  Class: {d}")
+                traceback.print_exc()
+                raise
+        return docs

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/general/config.py

@@ -11,7 +11,6 @@ TOKEN_PRICE_COL = "token_price"
 BLOCK_NUM_COL = "block_number"
 BLOCK_TIMESTAMP_COL = "block_timestamp"
 DURATION_LABEL_COL = "duration"
-FLIPSIDE_URL = "https://api-v2.flipsidecrypto.xyz"
 DEFAULT_SOURCE_STORE = "./data/source_save/"
 STORE_SIZE_CHECKPOINT = 41943040
 DEFAULT_SF_KEY = "default"

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/general/template/env-templ

@@ -1,3 +1,2 @@
 SESHAT_CONFIG_MODULE=./config
 DB_URL=
-FLIPSIDE_API_KEY=

{sdk_seshat_python-0.4.6 → sdk_seshat_python-0.5.3}/seshat/general/template/recommender.py-tmpl

@@ -20,15 +20,10 @@ class TokenRecommendationView(FeatureView):
         schema=Schema([Col("some_column", "new_name"), Col("another_col")]),
     )
     online_source = ...
-    # The source can be local, database, or flipside.
+    # The source can be local, database or else.
     # for local source, you can use current defined and for
     # sql database source:
     # SQLDBSource(url=DB_URL, table_name="your_table_name")
-    # if you need retrieve data from flipside use this:
-    # FlipSideSource(
-    #    api_key=os.getenv("FLIPSIDE_API_KEY"),
-    #    filters={"BLOCK_NUMBER": {"val": 19710819, "op": ">="}, },
-    # )
 
     offline_pipeline = Pipeline(pipes=[])
     online_pipeline = Pipeline(pipes=[])