oracle-ads 2.11.13__py3-none-any.whl → 2.11.15__py3-none-any.whl

ads/opctl/operator/lowcode/recommender/model/svd.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+from typing import Tuple, Dict, Any
+
+# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+import pandas as pd
+from pandas import DataFrame
+
+from .recommender_dataset import RecommenderDatasets
+from ..operator_config import RecommenderOperatorConfig
+from .factory import RecommenderOperatorBaseModel
+from surprise import Dataset, Reader
+from surprise.model_selection import train_test_split
+from surprise import SVD
+from surprise.accuracy import rmse, mae
+import report_creator as rc
+from ..constant import SupportedMetrics
+
+
+class SVDOperatorModel(RecommenderOperatorBaseModel):
+    """Class representing scikit surprise SVD operator model."""
+
+    def __init__(self, config: RecommenderOperatorConfig, datasets: RecommenderDatasets):
+        super().__init__(config, datasets)
+        self.interactions = datasets.interactions
+        self.users = datasets.users
+        self.items = datasets.items
+        self.user_id = config.spec.user_column
+        self.item_id = config.spec.item_column
+        self.interaction_column = config.spec.interaction_column
+        self.test_size = 0.2
+        self.algo = SVD()
+
+    def _get_recommendations(self, user_id, n):
+        all_item_ids = self.items[self.item_id].unique()
+        rated_items = self.interactions[self.interactions[self.user_id] == user_id][self.item_id]
+        unrated_items = [item_id for item_id in all_item_ids if item_id not in rated_items.values]
+        predictions = [self.algo.predict(user_id, item_id) for item_id in unrated_items]
+        predictions.sort(key=lambda x: x.est, reverse=True)
+        top_n_recommendations = predictions[:n]
+        return [(pred.iid, pred.est) for pred in top_n_recommendations]
+
+    def _build_model(self) -> Tuple[DataFrame, Dict]:
+        min_rating = self.interactions[self.interaction_column].min()
+        max_rating = self.interactions[self.interaction_column].max()
+        reader = Reader(rating_scale=(min_rating, max_rating))
+        data = Dataset.load_from_df(self.interactions[[self.user_id, self.item_id, self.interaction_column]], reader)
+        trainset, testset = train_test_split(data, test_size=self.test_size)
+        self.algo.fit(trainset)
+        predictions = self.algo.test(testset)
+
+        metric = {}
+        metric[SupportedMetrics.RMSE] = rmse(predictions, verbose=True)
+        metric[SupportedMetrics.MAE] = mae(predictions, verbose=True)
+        all_recommendations = []
+        for user_id in self.users[self.user_id]:
+            recommendations = self._get_recommendations(user_id, n=self.spec.top_k)
+            for item_id, est_rating in recommendations:
+                all_recommendations.append({
+                    self.user_id: user_id,
+                    self.item_id: item_id,
+                    self.interaction_column: est_rating
+                })
+        recommendations_df = pd.DataFrame(all_recommendations)
+        return recommendations_df, metric
+
+    def _generate_report(self):
+        model_description = """
+            Singular Value Decomposition (SVD) is a matrix factorization technique used in recommendation systems to
+            decompose a user-item interaction matrix into three constituent matrices. These matrices capture the
+            latent factors that explain the observed interactions.
+            """
+        new_user_recommendations = self._get_recommendations("__new_user__", self.spec.top_k)
+        new_recommendations = []
+        for item_id, est_rating in new_user_recommendations:
+            new_recommendations.append({
+                self.user_id: "__new_user__",
+                self.item_id: item_id,
+                self.interaction_column: est_rating
+            })
+        title = rc.Heading("Recommendations for new users", level=2)
+        other_sections = [title, rc.DataTable(new_recommendations)]
+        return (
+            model_description,
+            other_sections
+        )

ads/opctl/operator/lowcode/recommender/operator_config.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2023 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+import os
+from dataclasses import dataclass, field
+
+from ads.common.serializer import DataClassSerializable
+from ads.opctl.operator.common.operator_config import OperatorConfig, InputData
+from ads.opctl.operator.common.utils import _load_yaml_from_uri
+from ads.opctl.operator.lowcode.common.utils import find_output_dirname
+from .constant import SupportedModels
+
+
+@dataclass(repr=True)
+class OutputDirectory(DataClassSerializable):
+    """Class representing operator specification output directory details."""
+
+    url: str = None
+    name: str = None
+
+
+@dataclass(repr=True)
+class RecommenderOperatorSpec(DataClassSerializable):
+    """Class representing Recommender operator specification."""
+
+    user_data: InputData = field(default_factory=InputData)
+    item_data: InputData = field(default_factory=InputData)
+    interactions_data: InputData = field(default_factory=InputData)
+    output_directory: OutputDirectory = field(default_factory=OutputDirectory)
+    top_k: int = None
+    model_name: str = None
+    user_column: str = None
+    item_column: str = None
+    interaction_column: str = None
+    recommendations_filename: str = None
+    generate_report: bool = None
+    report_filename: str = None
+
+
+    def __post_init__(self):
+        """Adjusts the specification details."""
+        self.output_directory = self.output_directory or OutputDirectory(url=find_output_dirname(self.output_directory))
+        self.model_name = self.model_name or SupportedModels.SVD
+        self.recommendations_filename = self.recommendations_filename or "recommendations.csv"
+        # For Report Generation. When user doesn't specify defaults to True
+        self.generate_report = (
+            self.generate_report if self.generate_report is not None else True
+        )
+        self.report_filename = self.report_filename or "report.html"
+
+
+@dataclass(repr=True)
+class RecommenderOperatorConfig(OperatorConfig):
+    """Class representing Recommender operator config.
+
+    Attributes
+    ----------
+    kind: str
+        The kind of the resource. For operators it is always - `operator`.
+    type: str
+        The type of the operator. For Recommender operator it is always - `Recommender`
+    version: str
+        The version of the operator.
+    spec: RecommenderOperatorSpec
+        The Recommender operator specification.
+    """
+
+    kind: str = "operator"
+    type: str = "Recommender"
+    version: str = "v1"
+    spec: RecommenderOperatorSpec = field(default_factory=RecommenderOperatorSpec)
+
+    @classmethod
+    def _load_schema(cls) -> str:
+        """Loads operator schema."""
+        return _load_yaml_from_uri(
+            os.path.join(os.path.dirname(os.path.abspath(__file__)), "schema.yaml")
+        )

ads/opctl/operator/lowcode/recommender/schema.yaml

@@ -0,0 +1,265 @@
+kind:
+  allowed:
+    - operator
+  required: true
+  type: string
+  default: operator
+  meta:
+    description: "Which service are you trying to use? Common kinds: `operator`, `job`"
+
+version:
+  allowed:
+    - "v1"
+  required: true
+  type: string
+  default: v1
+  meta:
+    description: "Operators may change yaml file schemas from version to version, as well as implementation details. Double check the version to ensure compatibility."
+
+type:
+  required: true
+  type: string
+  default: recommender
+  meta:
+    description: "Type should always be `recommender` when using a recommender operator"
+
+
+spec:
+  required: true
+  type: dict
+  schema:
+    user_data:
+      required: true
+      type: dict
+      default: {"url": "user_data.csv"}
+      meta:
+        description: "This should contain user related attribute."
+      schema:
+        connect_args:
+          nullable: true
+          required: false
+          type: dict
+        format:
+          allowed:
+            - csv
+            - json
+            - clipboard
+            - excel
+            - feather
+            - sql_table
+            - sql_query
+            - hdf
+            - tsv
+          required: false
+          type: string
+        columns:
+          required: false
+          type: list
+          schema:
+            type: string
+        filters:
+          required: false
+          type: list
+          schema:
+            type: string
+        options:
+          nullable: true
+          required: false
+          type: dict
+        sql:
+          required: false
+          type: string
+        table_name:
+          required: false
+          type: string
+        url:
+          required: false
+          type: string
+          meta:
+            description: "The url can be local, or remote. For example: `oci://<bucket>@<namespace>/data.csv`"
+        limit:
+          required: false
+          type: integer
+
+    item_data:
+      required: true
+      type: dict
+      default: {"url": "item_data.csv"}
+      meta:
+        description: "This should contain item related attribute"
+      schema:
+        connect_args:
+          nullable: true
+          required: false
+          type: dict
+        format:
+          allowed:
+            - csv
+            - json
+            - clipboard
+            - excel
+            - feather
+            - sql_table
+            - sql_query
+            - hdf
+            - tsv
+          required: false
+          type: string
+        columns:
+          required: false
+          type: list
+          schema:
+            type: string
+        filters:
+          required: false
+          type: list
+          schema:
+            type: string
+        options:
+          nullable: true
+          required: false
+          type: dict
+        sql:
+          required: false
+          type: string
+        table_name:
+          required: false
+          type: string
+        url:
+          required: false
+          type: string
+          meta:
+            description: "The url can be local, or remote. For example: `oci://<bucket>@<namespace>/data.csv`"
+        limit:
+          required: false
+          type: integer
+
+    interactions_data:
+      required: true
+      default: {"url": "interactions_data.csv"}
+      meta:
+        description: "This should include interactions between items and users"
+      schema:
+        connect_args:
+          nullable: true
+          required: false
+          type: dict
+        format:
+          allowed:
+            - csv
+            - json
+            - clipboard
+            - excel
+            - feather
+            - sql_table
+            - sql_query
+            - hdf
+            - tsv
+          required: false
+          type: string
+        columns:
+          required: false
+          type: list
+          schema:
+            type: string
+        filters:
+          required: false
+          type: list
+          schema:
+            type: string
+        options:
+          nullable: true
+          required: false
+          type: dict
+        sql:
+          required: false
+          type: string
+        table_name:
+          required: false
+          type: string
+        url:
+          required: false
+          type: string
+          meta:
+            description: "The url can be local, or remote. For example: `oci://<bucket>@<namespace>/data.csv`"
+        limit:
+          required: false
+          type: integer
+      type: dict
+
+    top_k:
+      required: true
+      type: integer
+      default: 1
+
+    output_directory:
+      required: false
+      schema:
+        connect_args:
+          nullable: true
+          required: false
+          type: dict
+        format:
+          allowed:
+            - csv
+            - json
+            - clipboard
+            - excel
+            - feather
+            - sql_table
+            - sql_query
+            - hdf
+            - tsv
+          required: false
+          type: string
+        columns:
+          required: false
+          type: list
+          schema:
+            type: string
+        filters:
+          required: false
+          type: list
+          schema:
+            type: string
+        options:
+          nullable: true
+          required: false
+          type: dict
+        sql:
+          required: false
+          type: string
+        table_name:
+          required: false
+          type: string
+        url:
+          required: false
+          type: string
+          meta:
+            description: "The url can be local, or remote. For example: `oci://<bucket>@<namespace>/data.csv`"
+        limit:
+          required: false
+          type: integer
+      type: dict
+
+    report_filename:
+      required: false
+      type: string
+      default: report.html
+      meta:
+        description: "Placed into output_directory location. Defaults to report.html"
+
+    user_column:
+      type: string
+      required: true
+      default: "user_id"
+
+    item_column:
+      type: string
+      required: true
+      default: "item_id"
+
+    interaction_column:
+      type: string
+      required: true
+      default: "rating"

ads/opctl/operator/lowcode/recommender/utils.py

@@ -0,0 +1,13 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+import os
+
+
+def default_signer(**kwargs):
+    os.environ["EXTRA_USER_AGENT_INFO"] = "Recommender-Operator"
+    from ads.common.auth import default_signer
+    return default_signer(**kwargs)

{oracle_ads-2.11.13.dist-info → oracle_ads-2.11.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: oracle_ads
-Version: 2.11.13
+Version: 2.11.15
 Summary: Oracle Accelerated Data Science SDK
 Keywords: Oracle Cloud Infrastructure,OCI,Machine Learning,ML,Artificial Intelligence,AI,Data Science,Cloud,Oracle
 Author: Oracle Data Science
@@ -13,6 +13,7 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: PyYAML>=6
 Requires-Dist: asteval>=0.9.25
 Requires-Dist: cerberus>=1.3.4
@@ -20,8 +21,8 @@ Requires-Dist: cloudpickle>=1.6.0
 Requires-Dist: fsspec>=0.8.7
 Requires-Dist: gitpython>=3.1.2
 Requires-Dist: jinja2>=2.11.2
-Requires-Dist: matplotlib>=3.1.3, <=3.8.4
-Requires-Dist: numpy>=1.19.2, <2.0.0
+Requires-Dist: matplotlib>=3.1.3,<=3.8.4
+Requires-Dist: numpy>=1.19.2,<2.0.0
 Requires-Dist: oci>=2.125.3
 Requires-Dist: ocifs>=1.1.3
 Requires-Dist: pandas>1.2.1; python_version<'3.9'
@@ -40,7 +41,7 @@ Requires-Dist: jupyter_server ; extra == "aqua"
 Requires-Dist: hdfs[kerberos] ; extra == "bds"
 Requires-Dist: ibis-framework[impala] ; extra == "bds"
 Requires-Dist: sqlalchemy ; extra == "bds"
-Requires-Dist: lightgbm<4.0.0 ; extra == "boosted"
+Requires-Dist: lightgbm ; extra == "boosted"
 Requires-Dist: xgboost ; extra == "boosted"
 Requires-Dist: datefinder>=0.7.1 ; extra == "data"
 Requires-Dist: fastavro>=0.24.2 ; extra == "data"
@@ -48,7 +49,7 @@ Requires-Dist: htmllistparse>=0.6.0 ; extra == "data"
 Requires-Dist: openpyxl>=3.0.7 ; extra == "data"
 Requires-Dist: oracledb>=1.0 ; extra == "data"
 Requires-Dist: pandavro>=1.6.0 ; extra == "data"
-Requires-Dist: sqlalchemy>=1.4.1, <=1.4.46 ; extra == "data"
+Requires-Dist: sqlalchemy>=1.4.1,<=1.4.46 ; extra == "data"
 Requires-Dist: oracle-ads[opctl] ; extra == "feature-store-marketplace"
 Requires-Dist: kubernetes ; extra == "feature-store-marketplace"
 Requires-Dist: conda-pack ; extra == "forecast"
@@ -73,20 +74,21 @@ Requires-Dist: statsmodels ; extra == "forecast"
 Requires-Dist: plotly ; extra == "forecast"
 Requires-Dist: oracledb ; extra == "forecast"
 Requires-Dist: report-creator==1.0.9 ; extra == "forecast"
-Requires-Dist: geopandas ; extra == "geo"
+Requires-Dist: geopandas<1.0.0 ; extra == "geo"
 Requires-Dist: oracle_ads[viz] ; extra == "geo"
 Requires-Dist: transformers ; extra == "huggingface"
+Requires-Dist: tf-keras ; extra == "huggingface"
 Requires-Dist: langchain-community<0.0.32 ; extra == "llm"
 Requires-Dist: langchain>=0.1.10,<0.1.14 ; extra == "llm"
 Requires-Dist: evaluate>=0.4.0 ; extra == "llm"
 Requires-Dist: ipython>=7.23.1, <8.0 ; extra == "notebook"
 Requires-Dist: ipywidgets~=7.6.3 ; extra == "notebook"
-Requires-Dist: lightgbm<4.0.0 ; extra == "onnx"
-Requires-Dist: onnx>=1.12.0 ; extra == "onnx"
+Requires-Dist: lightgbm ; extra == "onnx"
+Requires-Dist: onnx>=1.12.0,<=1.15.0 ; extra == "onnx"
 Requires-Dist: onnxmltools>=1.10.0 ; extra == "onnx"
-Requires-Dist: onnxruntime>=1.10.0,<1.16 ; extra == "onnx"
+Requires-Dist: onnxruntime~=1.17.0,!=1.16.0 ; extra == "onnx"
 Requires-Dist: oracle_ads[viz] ; extra == "onnx"
-Requires-Dist: protobuf<=3.20 ; extra == "onnx"
+Requires-Dist: protobuf ; extra == "onnx"
 Requires-Dist: skl2onnx>=1.10.4 ; extra == "onnx"
 Requires-Dist: tf2onnx ; extra == "onnx"
 Requires-Dist: xgboost<=1.7 ; extra == "onnx"
@@ -112,16 +114,16 @@ Requires-Dist: scrubadub_spacy ; extra == "pii"
 Requires-Dist: spacy-transformers==1.2.5 ; extra == "pii"
 Requires-Dist: spacy==3.6.1 ; extra == "pii"
 Requires-Dist: report-creator==1.0.9 ; extra == "pii"
+Requires-Dist: oracle_ads[opctl] ; extra == "recommender"
+Requires-Dist: scikit-surprise ; extra == "recommender"
+Requires-Dist: plotly ; extra == "recommender"
+Requires-Dist: report-creator==1.0.9 ; extra == "recommender"
 Requires-Dist: pyspark>=3.0.0 ; extra == "spark"
 Requires-Dist: oracle_ads[viz] ; extra == "tensorflow"
-Requires-Dist: tensorflow ; extra == "tensorflow"
-Requires-Dist: dask==2023.5.0 ; extra == "testsuite" and ( python_version=='3.8')
-Requires-Dist: dask==2023.10.1 ; extra == "testsuite" and ( python_version>='3.9')
+Requires-Dist: tensorflow<=2.15.1 ; extra == "tensorflow"
 Requires-Dist: arff ; extra == "testsuite"
 Requires-Dist: category_encoders==2.6.3 ; extra == "testsuite"
 Requires-Dist: cohere==4.53 ; extra == "testsuite"
-Requires-Dist: dask==2023.10.1 ; extra == "testsuite" and ( python_version>='3.9')
-Requires-Dist: dask==2023.5.0 ; extra == "testsuite" and ( python_version=='3.8')
 Requires-Dist: faiss-cpu ; extra == "testsuite"
 Requires-Dist: fastparquet==2024.2.0 ; extra == "testsuite"
 Requires-Dist: imbalanced-learn ; extra == "testsuite"
@@ -132,17 +134,18 @@ Requires-Dist: notebook==6.4.12 ; extra == "testsuite"
 Requires-Dist: opensearch-py ; extra == "testsuite"
 Requires-Dist: pdfplumber ; extra == "testsuite"
 Requires-Dist: py4j ; extra == "testsuite"
-Requires-Dist: pyarrow ; extra == "testsuite"
+Requires-Dist: pyarrow>=15.0.0 ; extra == "testsuite"
 Requires-Dist: statsmodels ; extra == "testsuite" and ( python_version=='3.8')
 Requires-Dist: statsmodels>=0.14.1 ; extra == "testsuite" and ( python_version>='3.9')
 Requires-Dist: tables ; extra == "testsuite"
+Requires-Dist: tables>3.9.0 ; extra == "testsuite" and ( python_version>='3.9')
 Requires-Dist: xlrd>=1.2.0 ; extra == "testsuite"
-Requires-Dist: spacy ; extra == "text"
+Requires-Dist: spacy>=3.4.2 ; extra == "text"
 Requires-Dist: wordcloud>=1.8.1 ; extra == "text"
 Requires-Dist: oracle_ads[viz] ; extra == "torch"
 Requires-Dist: torch ; extra == "torch"
 Requires-Dist: torchvision ; extra == "torch"
-Requires-Dist: bokeh>=3.0.0, <3.2.0 ; extra == "viz"
+Requires-Dist: bokeh>=3.0.0,<3.2.0 ; extra == "viz"
 Requires-Dist: folium>=0.12.1 ; extra == "viz"
 Requires-Dist: graphviz<0.17 ; extra == "viz"
 Requires-Dist: scipy>=1.5.4 ; extra == "viz"
@@ -164,6 +167,7 @@ Provides-Extra: onnx
 Provides-Extra: opctl
 Provides-Extra: optuna
 Provides-Extra: pii
+Provides-Extra: recommender
 Provides-Extra: spark
 Provides-Extra: tensorflow
 Provides-Extra: testsuite