feast-custom 0.64.0__py3-none-any.whl

docs/conf.py

@@ -0,0 +1,200 @@
+# -*- coding: utf-8 -*-
+#
+# Feast documentation build configuration file, created by
+# sphinx-quickstart on Sat Nov 30 15:06:53 2019.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath("../../feast"))
+sys.path.insert(0, os.path.abspath("../.."))
+
+
+# -- Build protos ---------------------------------------------------------
+
+# For an unknown reason, the Python protos stopped being built correctly.
+# See https://readthedocs.org/projects/feast/builds/17686555/ for an
+# example where the Python protos did not build, which subsequently broke
+# the RTD build. In order to fix this, we manually compile the protos.
+import subprocess
+from pathlib import Path
+
+# cwd will be feast/sdk/python/docs/source
+cwd = Path(os.getcwd())
+
+# Change to feast/
+os.chdir(cwd.parent.parent.parent.parent)
+
+# Compile Python protos
+result = subprocess.run(
+    ["python", "infra/scripts/generate_protos.py"], capture_output=True
+)
+stdout = result.stdout.decode("utf-8")
+stderr = result.stderr.decode("utf-8")
+print(f"Apply stdout:\n{stdout}")
+print(f"Apply stderr:\n{stderr}")
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx.ext.doctest",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.todo",
+    "sphinx.ext.coverage",
+    "sphinx.ext.mathjax",
+    "sphinx.ext.ifconfig",
+    "sphinx.ext.viewcode",
+    "sphinx.ext.githubpages",
+    "sphinx.ext.napoleon",
+    "sphinx.ext.autodoc",
+    "sphinx_rtd_theme",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = ".rst"
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "Feast"
+copyright = "2021, Feast Authors"
+author = "Feast Authors"
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+
+# TODO: Add the below versions back to documentation building.
+# version = (
+#     os.popen("git describe --tags $(git rev-list --tags --max-count=1)").read().strip()
+# )
+# The full version, including alpha/beta/rc tags.
+# release = (
+#     os.popen("git describe --tags $(git rev-list --tags --max-count=1)").read().strip()
+# )
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = []
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = "sphinx_rtd_theme"
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "Feastdoc"
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, "Feast.tex", "Feast Documentation", "Feast Authors", "manual")
+]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [(master_doc, "feast", "Feast Documentation", [author], 1)]
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (
+        master_doc,
+        "Feast",
+        "Feast Documentation",
+        author,
+        "Feast",
+        "One line description of project.",
+        "Miscellaneous",
+    )
+]
+
+
+# Example configuration for intersphinx: refer to the Python standard library.
+intersphinx_mapping = {"https://docs.python.org/": None}

docs/source/conf.py

@@ -0,0 +1,200 @@
+# -*- coding: utf-8 -*-
+#
+# Feast documentation build configuration file, created by
+# sphinx-quickstart on Sat Nov 30 15:06:53 2019.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath("../../feast"))
+sys.path.insert(0, os.path.abspath("../.."))
+
+
+# -- Build protos ---------------------------------------------------------
+
+# For an unknown reason, the Python protos stopped being built correctly.
+# See https://readthedocs.org/projects/feast/builds/17686555/ for an
+# example where the Python protos did not build, which subsequently broke
+# the RTD build. In order to fix this, we manually compile the protos.
+import subprocess
+from pathlib import Path
+
+# cwd will be feast/sdk/python/docs/source
+cwd = Path(os.getcwd())
+
+# Change to feast/
+os.chdir(cwd.parent.parent.parent.parent)
+
+# Compile Python protos
+result = subprocess.run(
+    ["python", "infra/scripts/generate_protos.py"], capture_output=True
+)
+stdout = result.stdout.decode("utf-8")
+stderr = result.stderr.decode("utf-8")
+print(f"Apply stdout:\n{stdout}")
+print(f"Apply stderr:\n{stderr}")
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx.ext.doctest",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.todo",
+    "sphinx.ext.coverage",
+    "sphinx.ext.mathjax",
+    "sphinx.ext.ifconfig",
+    "sphinx.ext.viewcode",
+    "sphinx.ext.githubpages",
+    "sphinx.ext.napoleon",
+    "sphinx.ext.autodoc",
+    "sphinx_rtd_theme",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = ".rst"
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "Feast"
+copyright = "2021, Feast Authors"
+author = "Feast Authors"
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+
+# TODO: Add the below versions back to documentation building.
+# version = (
+#     os.popen("git describe --tags $(git rev-list --tags --max-count=1)").read().strip()
+# )
+# The full version, including alpha/beta/rc tags.
+# release = (
+#     os.popen("git describe --tags $(git rev-list --tags --max-count=1)").read().strip()
+# )
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = []
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = "sphinx_rtd_theme"
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "Feastdoc"
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, "Feast.tex", "Feast Documentation", "Feast Authors", "manual")
+]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [(master_doc, "feast", "Feast Documentation", [author], 1)]
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (
+        master_doc,
+        "Feast",
+        "Feast Documentation",
+        author,
+        "Feast",
+        "One line description of project.",
+        "Miscellaneous",
+    )
+]
+
+
+# Example configuration for intersphinx: refer to the Python standard library.
+intersphinx_mapping = {"https://docs.python.org/": None}

feast/__init__.py

@@ -0,0 +1,82 @@
+from importlib.metadata import PackageNotFoundError
+from importlib.metadata import version as _version
+
+from feast.demos import copy_demo_notebooks
+from feast.infra.offline_stores.bigquery_source import BigQuerySource
+from feast.infra.offline_stores.contrib.athena_offline_store.athena_source import (
+    AthenaSource,
+)
+from feast.infra.offline_stores.contrib.oracle_offline_store.oracle_source import (
+    OracleSource,
+)
+from feast.infra.offline_stores.file_source import FileSource
+from feast.infra.offline_stores.redshift_source import RedshiftSource
+from feast.infra.offline_stores.snowflake_source import SnowflakeSource
+
+from .aggregation import Aggregation
+from .batch_feature_view import BatchFeatureView
+from .chunker import BaseChunker, ChunkingConfig, TextChunker
+from .data_source import KafkaSource, KinesisSource, PushSource, RequestSource
+from .dataframe import DataFrameEngine, FeastDataFrame
+from .doc_embedder import DocEmbedder, SchemaTransformFn
+from .embedder import BaseEmbedder, EmbeddingConfig, MultiModalEmbedder
+from .entity import Entity
+from .feature import Feature
+from .feature_service import FeatureService
+from .feature_store import FeatureStore
+from .feature_view import FeatureView, FeatureViewState
+from .field import Field
+from .labeling import ConflictPolicy, LabelView
+from .on_demand_feature_view import OnDemandFeatureView
+from .project import Project
+from .repo_config import RepoConfig
+from .stream_feature_view import StreamFeatureView
+from .value_type import ValueType
+from .vector_store import FeastVectorStore
+
+try:
+    __version__ = _version("feast-custom")
+except PackageNotFoundError:
+    # package is not installed
+    pass
+
+__all__ = [
+    "Aggregation",
+    "BatchFeatureView",
+    "copy_demo_notebooks",
+    "DataFrameEngine",
+    "Entity",
+    "KafkaSource",
+    "KinesisSource",
+    "FeastDataFrame",
+    "Feature",
+    "Field",
+    "FeatureService",
+    "FeatureStore",
+    "FeatureView",
+    "FeatureViewState",
+    "LabelView",
+    "ConflictPolicy",
+    "OnDemandFeatureView",
+    "RepoConfig",
+    "StreamFeatureView",
+    "ValueType",
+    "BigQuerySource",
+    "FileSource",
+    "RedshiftSource",
+    "SnowflakeSource",
+    "PushSource",
+    "RequestSource",
+    "AthenaSource",
+    "OracleSource",
+    "Project",
+    "FeastVectorStore",
+    "DocEmbedder",
+    "SchemaTransformFn",
+    "BaseChunker",
+    "TextChunker",
+    "ChunkingConfig",
+    "BaseEmbedder",
+    "MultiModalEmbedder",
+    "EmbeddingConfig",
+]

feast/aggregation/__init__.py

@@ -0,0 +1,141 @@
+"""
+Aggregation module for Feast.
+"""
+
+from datetime import timedelta
+from typing import Any, Dict, Iterable, Optional, Tuple
+
+from google.protobuf.duration_pb2 import Duration
+from typeguard import typechecked
+
+from feast.protos.feast.core.Aggregation_pb2 import Aggregation as AggregationProto
+
+
+@typechecked
+class Aggregation:
+    """
+    NOTE: Feast-handled aggregations are not yet supported. This class provides a way to register user-defined aggregations.
+
+    Attributes:
+        column: str  # Column name of the feature we are aggregating.
+        function: str  # Provided built in aggregations sum, max, min, count, mean, count_distinct
+        time_window: timedelta  # The time window for this aggregation.
+        slide_interval: timedelta # The sliding window for these aggregations
+        name: str  # Optional override for the output feature name (defaults to {function}_{column})
+    """
+
+    column: str
+    function: str
+    time_window: Optional[timedelta]
+    slide_interval: Optional[timedelta]
+    name: str
+
+    def __init__(
+        self,
+        column: Optional[str] = "",
+        function: Optional[str] = "",
+        time_window: Optional[timedelta] = None,
+        slide_interval: Optional[timedelta] = None,
+        name: Optional[str] = None,
+    ):
+        self.column = column or ""
+        self.function = function or ""
+        self.time_window = time_window
+        if not slide_interval:
+            self.slide_interval = self.time_window
+        else:
+            self.slide_interval = slide_interval
+        self.name = name or ""
+
+    def to_proto(self) -> AggregationProto:
+        window_duration = None
+        if self.time_window is not None:
+            window_duration = Duration()
+            window_duration.FromTimedelta(self.time_window)
+
+        slide_interval_duration = None
+        if self.slide_interval is not None:
+            slide_interval_duration = Duration()
+            slide_interval_duration.FromTimedelta(self.slide_interval)
+
+        return AggregationProto(
+            column=self.column,
+            function=self.function,
+            time_window=window_duration,
+            slide_interval=slide_interval_duration,
+            name=self.name,
+        )
+
+    @classmethod
+    def from_proto(cls, agg_proto: AggregationProto):
+        time_window = (
+            timedelta(days=0)
+            if agg_proto.time_window.ToNanoseconds() == 0
+            else agg_proto.time_window.ToTimedelta()
+        )
+
+        slide_interval = (
+            timedelta(days=0)
+            if agg_proto.slide_interval.ToNanoseconds() == 0
+            else agg_proto.slide_interval.ToTimedelta()
+        )
+        aggregation = cls(
+            column=agg_proto.column,
+            function=agg_proto.function,
+            time_window=time_window,
+            slide_interval=slide_interval,
+            name=agg_proto.name or None,
+        )
+        return aggregation
+
+    def __eq__(self, other):
+        if not isinstance(other, Aggregation):
+            raise TypeError("Comparisons should only involve Aggregations.")
+
+        if (
+            self.column != other.column
+            or self.function != other.function
+            or self.time_window != other.time_window
+            or self.slide_interval != other.slide_interval
+            or self.name != other.name
+        ):
+            return False
+
+        return True
+
+    def resolved_name(self, time_window: Optional[timedelta] = None) -> str:
+        """Return the output feature name for this aggregation.
+
+        If ``name`` is set it is returned as-is.  Otherwise the name is
+        derived as ``{function}_{column}``, with ``_{seconds}s`` appended
+        when *time_window* is provided.
+        """
+        if self.name:
+            return self.name
+        base = f"{self.function}_{self.column}"
+        if time_window is not None and time_window.total_seconds() > 0:
+            return f"{base}_{int(time_window.total_seconds())}s"
+        return base
+
+
+_FUNCTION_ALIASES: Dict[str, str] = {
+    "count_distinct": "nunique",
+}
+
+
+def aggregation_specs_to_agg_ops(
+    agg_specs: Iterable[Any],
+    *,
+    time_window_unsupported_error_message: str,
+) -> Dict[str, Tuple[str, str]]:
+    agg_ops: Dict[str, Tuple[str, str]] = {}
+    for agg in agg_specs:
+        if getattr(agg, "time_window", None) is not None:
+            raise ValueError(time_window_unsupported_error_message)
+        alias = getattr(agg, "name", None) or f"{agg.function}_{agg.column}"
+        func_name = _FUNCTION_ALIASES.get(agg.function, agg.function)
+        agg_ops[alias] = (func_name, agg.column)
+    return agg_ops
+
+
+__all__ = ["Aggregation", "aggregation_specs_to_agg_ops"]

feast/aggregation/tiling/__init__.py

@@ -0,0 +1,27 @@
+"""
+Tiling for efficient time-windowed aggregations.
+
+This module provides tiling algorithms and interfaces
+that can be implemented by any compute engine (Spark, Ray, etc.).
+
+Architecture:
+1. Engine nodes: Convert to pandas (e.g., dataset.to_pandas(), toPandas())
+2. orchestrator.py: Generate cumulative tiles
+3. tile_subtraction.py: Convert cumulative tiles to windowed aggregations
+4. Engine nodes: Convert back to engine format (e.g., from_pandas(), createDataFrame())
+"""
+
+from feast.aggregation.tiling.base import IRMetadata, get_ir_metadata_for_aggregation
+from feast.aggregation.tiling.orchestrator import apply_sawtooth_window_tiling
+from feast.aggregation.tiling.tile_subtraction import (
+    convert_cumulative_to_windowed,
+    deduplicate_keep_latest,
+)
+
+__all__ = [
+    "IRMetadata",
+    "get_ir_metadata_for_aggregation",
+    "apply_sawtooth_window_tiling",
+    "convert_cumulative_to_windowed",
+    "deduplicate_keep_latest",
+]