Move to Report Creator

THIRD_PARTY_LICENSES.txt

@@ -18,6 +18,12 @@ asteval
 * Source code: https://github.com/newville/asteval
 * Project home: https://github.com/newville/asteval
 
+autots
+* Copyright (c) 2024 Colin Catlin
+* License: MIT License
+* Source code: https://github.com/winedarksea/AutoTS
+* Project home: https://winedarksea.github.io/AutoTS/build/html/index.html
+
 bokeh
 * Copyright Copyright (c) 2012 - 2021, Anaconda, Inc., and Bokeh Contributors
 * License: BSD 3-Clause "New" or "Revised" License
@@ -169,6 +175,12 @@ nbformat
 * Source code: https://github.com/jupyter/nbconvert
 * Project home: https://jupyter.org/
 
+neuralprophet
+* Copyright (c) 2020 Oskar Triebe
+* License: MIT License
+* Source Code: https://github.com/ourownstory/neural_prophet
+* Project Home: https://neuralprophet.com
+
 numpy
 * Copyright (c) 2005-2021, NumPy Developers.
 * License: BSD 3-Clause "New" or "Revised" License
@@ -247,6 +259,18 @@ plotly
 * Source code: https://github.com/plotly/plotly.py
 * Project home: https://plotly.com/
 
+pmdarima
+* Copyright (c) 2017 Taylor G Smith
+* License: MIT License
+* Source code: https://github.com/alkaline-ml/pmdarima
+* Project home: https://alkaline-ml.com/pmdarima/
+
+prophet
+* Copyright (c) Facebook, Inc. and its affiliates.
+* License: MIT License
+* Source code: https://github.com/facebook/prophet
+* Project home: https://facebook.github.io/prophet/
+
 protobuf
 * Copyright 2008 Google Inc.  All rights reserved.
 * License: Google Protobuf License
@@ -289,6 +313,12 @@ PyYAML
 * Source code: https://github.com/yaml/pyyaml/
 * Project home: https://pyyaml.org/
 
+report-creator
+* Copyright 2024 Daren Race
+* License: MIT License
+* Source code: https://github.com/darenr/report_creator
+* Project home: https://darenr.github.io/report_creator/
+
 requests
 * Copyright 2023 Kenneth Reitz
 * License: Apache-2.0 license

ads/llm/serializers/runnable_parallel.py

@@ -1,3 +1,9 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*--
+
+# Copyright (c) 2024 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
 from langchain.schema.runnable import RunnableParallel
 from langchain.load.dump import dumpd
 from langchain.load.load import load
@@ -10,7 +16,7 @@ def type():
 
     @staticmethod
     def load(config: dict, **kwargs):
-        steps = config["kwargs"]["steps"]
+        steps = config.get("kwargs", dict()).get("steps", dict())
         steps = {k: load(v, **kwargs) for k, v in steps.items()}
         return RunnableParallel(**steps)
 

ads/opctl/operator/lowcode/anomaly/README.md

@@ -35,7 +35,7 @@ All generated configurations should be ready to use without the need for any add
 To run anomaly detection locally, create and activate a new conda environment (`ads-anomaly`). Install all the required libraries listed in the `environment.yaml` file.
 
 ```yaml
-- datapane
+- report-creator
 - cerberus
 - oracle-automlx==23.4.1
 - oracle-automlx[classic]==23.4.1

ads/opctl/operator/lowcode/anomaly/environment.yaml

@@ -5,7 +5,7 @@ dependencies:
   - python=3.8
   - pip
   - pip:
-      - datapane
+      - report-creator
       - cerberus
       - oracle-automlx==23.4.1
       - oracle-automlx[classic]==23.4.1

ads/opctl/operator/lowcode/anomaly/model/automlx.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# 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
@@ -27,8 +27,13 @@ class AutoMLXOperatorModel(AnomalyOperatorBaseModel):
     def _build_model(self) -> pd.DataFrame:
         from automlx import init
         import logging
+
         try:
-            init(engine="ray", engine_opts={"ray_setup": {"_temp_dir": "/tmp/ray-temp"}}, loglevel=logging.CRITICAL)
+            init(
+                engine="ray",
+                engine_opts={"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},
+                loglevel=logging.CRITICAL,
+            )
         except Exception as e:
             logger.info("Ray already initialized")
         date_column = self.spec.datetime_column.name
@@ -68,21 +73,21 @@ def _build_model(self) -> pd.DataFrame:
         return anomaly_output
 
     def _generate_report(self):
-        import datapane as dp
+        import report_creator as rc
 
         """The method that needs to be implemented on the particular model level."""
-        selected_models_text = dp.Text(
-            f"## Selected Models Overview \n "
-            "The following tables provide information regarding the chosen model."
-        )
-        all_sections = [selected_models_text]
+        other_sections = [
+            rc.Heading("Selected Models Overview", level=2),
+            rc.Text(
+                "The following tables provide information regarding the chosen model."
+            ),
+        ]
 
-        model_description = dp.Text(
+        model_description = rc.Text(
             "The automlx model automatically pre-processes, selects and engineers "
             "high-quality features in your dataset, which then given to an automatically "
             "chosen and optimized machine learning model.."
         )
-        other_sections = all_sections
 
         return (
             model_description,

ads/opctl/operator/lowcode/anomaly/model/autots.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# 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
@@ -81,21 +81,20 @@ def _build_model(self) -> AnomalyOutput:
         return anomaly_output
 
     def _generate_report(self):
-        import datapane as dp
+        import report_creator as rc
 
         """The method that needs to be implemented on the particular model level."""
-        selected_models_text = dp.Text(
-            f"## Selected Models Overview \n "
-            "The following tables provide information regarding the chosen model."
-        )
-        all_sections = [selected_models_text]
-
-        model_description = dp.Text(
+        other_sections = [
+            rc.Heading("Selected Models Overview", level=2),
+            rc.Text(
+                "The following tables provide information regarding the chosen model."
+            ),
+        ]
+        model_description = rc.Text(
             "The automlx model automatically pre-processes, selects and engineers "
             "high-quality features in your dataset, which then given to an automatically "
             "chosen and optimized machine learning model.."
         )
-        other_sections = all_sections
 
         return (
             model_description,

ads/opctl/operator/lowcode/anomaly/model/base_model.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# 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
@@ -57,7 +57,7 @@ def __init__(self, config: AnomalyOperatorConfig, datasets: AnomalyDatasets):
 
     def generate_report(self):
         """Generates the report."""
-        import datapane as dp
+        import report_creator as rc
         import matplotlib.pyplot as plt
 
         start_time = time.time()
@@ -79,12 +79,10 @@ def generate_report(self):
                 anomaly_output, test_data, elapsed_time
             )
         table_blocks = [
-            dp.DataTable(df, label=col)
+            rc.DataTable(df, label=col, index=True)
             for col, df in self.datasets.full_data_dict.items()
         ]
-        data_table = (
-            dp.Select(blocks=table_blocks) if len(table_blocks) > 1 else table_blocks[0]
-        )
+        data_table = rc.Select(blocks=table_blocks)
         date_column = self.spec.datetime_column.name
 
         blocks = []
@@ -106,44 +104,42 @@ def generate_report(self):
                 plt.xlabel(date_column)
                 plt.ylabel(col)
                 plt.title(f"`{col}` with reference to anomalies")
-                figure_blocks.append(ax)
-            blocks.append(dp.Group(blocks=figure_blocks, label=target))
-        plots = dp.Select(blocks=blocks) if len(blocks) > 1 else blocks[0]
+                figure_blocks.append(rc.Widget(ax))
+            blocks.append(rc.Group(*figure_blocks, label=target))
+        plots = rc.Select(blocks)
 
         report_sections = []
-        title_text = dp.Text("# Anomaly Detection Report")
-
-        yaml_appendix_title = dp.Text(f"## Reference: YAML File")
-        yaml_appendix = dp.Code(code=self.config.to_yaml(), language="yaml")
-        summary = dp.Blocks(
-            blocks=[
-                dp.Group(
-                    dp.Text(f"You selected the **`{self.spec.model}`** model."),
-                    dp.Text(
-                        "Based on your dataset, you could have also selected "
-                        f"any of the models: `{'`, `'.join(SupportedModels.keys())}`."
-                    ),
-                    dp.BigNumber(
-                        heading="Analysis was completed in ",
-                        value=human_time_friendly(elapsed_time),
-                    ),
-                    label="Summary",
-                )
-            ]
+        title_text = rc.Heading("Anomaly Detection Report", level=1)
+
+        yaml_appendix_title = rc.Heading("Reference: YAML File", level=2)
+        yaml_appendix = rc.Yaml(self.config.to_dict())
+        summary = rc.Block(
+            rc.Group(
+                rc.Text(f"You selected the **`{self.spec.model}`** model."),
+                rc.Text(
+                    "Based on your dataset, you could have also selected "
+                    f"any of the models: `{'`, `'.join(SupportedModels.keys())}`."
+                ),
+                rc.Metric(
+                    heading="Analysis was completed in ",
+                    value=human_time_friendly(elapsed_time),
+                ),
+                label="Summary",
+            )
         )
-        sec_text = dp.Text(f"## Train Evaluation Metrics")
-        sec = dp.DataTable(self._evaluation_metrics(anomaly_output))
+        sec_text = rc.Heading("Train Evaluation Metrics", level=2)
+        sec = rc.DataTable(self._evaluation_metrics(anomaly_output), index=True)
         evaluation_metrics_sec = [sec_text, sec]
 
         test_metrics_sections = []
         if total_metrics is not None and not total_metrics.empty:
-            sec_text = dp.Text(f"## Test Data Evaluation Metrics")
-            sec = dp.DataTable(total_metrics)
+            sec_text = rc.Heading("Test Data Evaluation Metrics", level=2)
+            sec = rc.DataTable(total_metrics, index=True)
             test_metrics_sections = test_metrics_sections + [sec_text, sec]
 
         if summary_metrics is not None and not summary_metrics.empty:
-            sec_text = dp.Text(f"## Test Data Summary Metrics")
-            sec = dp.DataTable(summary_metrics)
+            sec_text = rc.Heading("Test Data Summary Metrics", level=2)
+            sec = rc.DataTable(summary_metrics, index=True)
             test_metrics_sections = test_metrics_sections + [sec_text, sec]
 
         report_sections = (
@@ -248,7 +244,7 @@ def _save_report(
         test_metrics: pd.DataFrame,
     ):
         """Saves resulting reports to the given folder."""
-        import datapane as dp
+        import report_creator as rc
 
         unique_output_dir = find_output_dirname(self.spec.output_directory)
 
@@ -257,11 +253,12 @@ def _save_report(
         else:
             storage_options = dict()
 
-        # datapane html report
+        # report-creator html report
         with tempfile.TemporaryDirectory() as temp_dir:
             report_local_path = os.path.join(temp_dir, "___report.html")
             disable_print()
-            dp.save_report(report_sections, report_local_path)
+            with rc.ReportCreator("My Report") as report:
+                report.save(rc.Block(*report_sections), report_local_path)
             enable_print()
             with open(report_local_path) as f1:
                 with fsspec.open(

ads/opctl/operator/lowcode/anomaly/model/tods.py

@@ -1,7 +1,7 @@
 # #!/usr/bin/env python
 # # -*- coding: utf-8 -*--
 
-# # Copyright (c) 2023 Oracle and/or its affiliates.
+# # 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 importlib
@@ -97,16 +97,16 @@
 #         return anomaly_output
 
 #     def _generate_report(self):
-#         import datapane as dp
+#         import report_creator as rc
 
 #         """The method that needs to be implemented on the particular model level."""
-#         selected_models_text = dp.Text(
+#         selected_models_text = rc.Text(
 #             f"## Selected Models Overview \n "
 #             "The following tables provide information regarding the chosen model."
 #         )
 #         all_sections = [selected_models_text]
 
-#         model_description = dp.Text(
+#         model_description = rc.Text(
 #             "The tods model is a full-stack automated machine learning system for outlier detection "
 #             "on univariate / multivariate time-series data. It provides exhaustive modules for building "
 #             "machine learning-based outlier detection systems and wide range of algorithms."

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

@@ -323,7 +323,7 @@ spec:
             missing_value_imputation:
               type: boolean
               required: false
-              default: true
+              default: false
 
     generate_report:
       type: boolean

ads/opctl/operator/lowcode/forecast/README.md

@@ -35,7 +35,7 @@ To run forecasting locally, create and activate a new conda environment (`ads-fo
 - neuralprophet
 - pmdarima
 - statsmodels
-- datapane
+- report-creator
 - cerberus
 - sktime
 - optuna==3.1.0

ads/opctl/operator/lowcode/forecast/environment.yaml

@@ -10,12 +10,12 @@ dependencies:
       - neuralprophet
       - pmdarima
       - statsmodels
-      - datapane
+      - report-creator
       - cerberus
       - sktime
       - shap
       - autots[additional]
-      - optuna==3.1.0
-      - oracle-automlx==23.4.1
-      - oracle-automlx[forecasting]==23.4.1
+      - optuna
+      - oracle-automlx>=23.4.1
+      - oracle-automlx[forecasting]>=23.4.1
       - fire