Adding reports

Author: JBris

deepchecks (1).html

@@ -0,0 +1,91 @@
+import os
+os.environ['WHYLOGS_NO_ANALYTICS']='True'
+
+from deepchecks.tabular.suites import full_suite
+from evidently.metric_preset import (
+    DataDriftPreset, DataQualityPreset, TargetDriftPreset, RegressionPreset, ClassificationPreset
+)
+
+from evidently.report import Report
+from evidently.test_preset import (
+    DataStabilityTestPreset, DataQualityTestPreset, 
+    BinaryClassificationTestPreset, BinaryClassificationTopKTestPreset,
+    DataDriftTestPreset, MulticlassClassificationTestPreset, 
+    RegressionTestPreset
+)
+
+from evidently.test_suite import TestSuite
+from sklearn.datasets import load_iris
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import train_test_split
+import whylogs as why
+from whylogs.viz import NotebookProfileVisualizer
+
+from ydata_profiling import ProfileReport
+
+
+def run_why(df):
+    why_results = why.log(df)
+    prof_view = why_results.view()
+    visualization = NotebookProfileVisualizer()
+    visualization.set_profiles(target_profile_view=prof_view, reference_profile_view=prof_view)
+    
+    visualization.write(
+        rendered_html=visualization.profile_summary(),
+        html_file_name=os.getcwd() + "/why_profile_summary",
+    )
+
+    visualization.write(
+        rendered_html=visualization.double_histogram(feature_name=df.columns),
+        html_file_name=os.getcwd() + "/why_double_histogram",
+    )
+
+    visualization.write(
+        rendered_html=visualization.feature_statistics(feature_name=df.columns),
+        html_file_name=os.getcwd() + "/why_feature_statistics",
+    )
+
+def run_evidently(df):
+    evidently_test_report= TestSuite(tests=[
+        DataStabilityTestPreset(), DataQualityTestPreset(), BinaryClassificationTestPreset(),
+        DataDriftTestPreset(), 
+        MulticlassClassificationTestPreset(), RegressionTestPreset()
+    ])
+
+    evidently_test_report.run(current_data=df.iloc[:60], reference_data=df.iloc[60:], column_mapping=None)
+    evidently_test_report.save_html("evidently_test_report.html")
+
+    evidently_metric_report = Report(metrics=[
+        DataDriftPreset(), DataQualityPreset(), TargetDriftPreset(), 
+        RegressionPreset(), ClassificationPreset()
+    ])
+
+    evidently_metric_report.run(current_data=df.iloc[:60], reference_data=df.iloc[60:], column_mapping=None)
+    evidently_metric_report.save_html("evidently_metric_report.html")
+
+def run_deepchecks(df):
+    suite = full_suite()
+    train_df = train_dataset=df.iloc[:60]
+    test_df = test_dataset=df.iloc[60:]
+
+    model = LogisticRegression().fit(train_df.drop(columns="target"), train_df["target"])
+    suite_result = suite.run(train_dataset=train_df, test_dataset=test_df, model=model)
+    suite_result.save_as_html("deepchecks.html") 
+
+def run_profiler(df):
+    profile = ProfileReport(df, title="Profiling Report")
+    profile.to_file("ydata_profiling.html")
+
+def main():
+    iris = load_iris(as_frame=True)
+    df = iris["data"]
+    df["target"] = iris["target"]
+    df["prediction"] = iris["target"]
+
+    run_why(df)
+    run_evidently(df)
+    run_deepchecks(df)
+    run_profiler(df)
+
+if __name__ == "__main__":
+    main()

deepchecks (2).html

@@ -0,0 +1,31 @@
+[tool.poetry]
+name = "python-data-profiler-comp"
+version = "0.1.0"
+description = ""
+authors = ["James Bristow <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.11,<3.12"
+ydata-profiling = "^4.6.5"
+pandas = "<=2.0.3"
+numpy = "<1.26"
+matplotlib = "<3.8.0"
+statsmodels = "^0.14.1"
+seaborn = "<0.13"
+pydantic = "^2.6.3"
+evidently = "^0.4.16"
+httpx = "^0.27.0"
+scikit-learn = "<=1.3.0"
+plotly = "^5.19.0"
+deepchecks = "<0.17.3"
+scipy = "<1.11.4"
+whylogs = {extras = ["viz"], version = "^1.3.24"}
+great-expectations = "^0.18.10"
+kaleido = "0.2.1"
+pycaret = "<=3.0.4"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

deepchecks.html

@@ -0,0 +1,193 @@
+altair==4.2.2
+annotated-types==0.6.0
+anyio==4.3.0
+appdirs==1.4.4
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+attrs==23.2.0
+backcall==0.2.0
+beautifulsoup4==4.12.3
+bleach==6.1.0
+blinker==1.7.0
+category-encoders==2.6.3
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpickle==3.0.0
+colorama==0.4.6
+comm==0.2.1
+contourpy==1.2.0
+cryptography==42.0.5
+cycler==0.12.1
+Cython==3.0.8
+dacite==1.8.1
+dash==2.15.0
+dash-core-components==2.0.0
+dash-html-components==2.0.0
+dash-table==5.0.0
+debugpy==1.8.1
+decorator==5.1.1
+deepchecks==0.17.2
+defusedxml==0.7.1
+deprecation==2.1.0
+distro==1.9.0
+dynaconf==3.2.4
+entrypoints==0.4
+evidently==0.4.16
+Faker==23.3.0
+fastjsonschema==2.19.1
+filelock==3.13.1
+Flask==3.0.2
+fonttools==4.49.0
+fsspec==2024.2.0
+great-expectations==0.18.10
+h11==0.14.0
+htmlmin==0.1.12
+httpcore==1.0.4
+httpx==0.27.0
+idna==3.6
+ImageHash==4.3.1
+imbalanced-learn==0.12.0
+importlib-metadata==7.0.1
+ipykernel==6.27.1
+ipython==7.34.0
+ipython-genutils==0.2.0
+ipywidgets==7.8.1
+iterative-telemetry==0.0.8
+itsdangerous==2.1.2
+jedi==0.19.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonpatch==1.33
+jsonpickle==3.0.3
+jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+jupyter_client==8.6.0
+jupyter_core==5.7.1
+jupyter-server==1.16.0
+jupyterlab_pygments==0.3.0
+jupyterlab-widgets==1.1.7
+kaleido==0.2.1
+kiwisolver==1.4.5
+lightgbm==4.3.0
+litestar==2.6.1
+llvmlite==0.41.1
+makefun==1.15.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.0
+matplotlib==3.7.5
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mistune==3.0.2
+msgspec==0.18.6
+multidict==6.0.5
+multimethod==1.11.2
+mypy-extensions==1.0.0
+nbclassic==1.0.0
+nbclient==0.9.0
+nbconvert==7.16.1
+nbformat==5.9.2
+nest-asyncio==1.6.0
+networkx==3.2.1
+nltk==3.8.1
+notebook==6.5.4
+notebook_shim==0.2.4
+numba==0.58.1
+numpy==1.24.4
+orjson==3.9.15
+packaging==23.2
+pandas==1.5.3
+pandocfilters==1.5.1
+parso==0.8.3
+patsy==0.5.6
+pexpect==4.9.0
+phik==0.12.4
+pickleshare==0.7.5
+Pillow==9.5.0
+pip==23.3.1
+platformdirs==3.11.0
+plotly==5.19.0
+plotly-resampler==0.9.2
+pmdarima==2.0.4
+polyfactory==2.14.1
+prometheus_client==0.20.0
+prompt-toolkit==3.0.43
+protobuf==4.25.3
+psutil==5.9.8
+ptyprocess==0.7.0
+pybars3==0.9.7
+pycaret==3.0.0
+pycparser==2.21
+pydantic==2.6.3
+pydantic_core==2.16.3
+Pygments==2.17.2
+PyMeta3==0.5.1
+PyNomaly==0.3.3
+pyod==1.1.3
+pyparsing==3.1.1
+python-dateutil==2.9.0
+python-utils==3.8.2
+pytz==2024.1
+PyWavelets==1.5.0
+PyYAML==6.0.1
+pyzmq==23.2.1
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+retrying==1.3.4
+rich==13.7.1
+rich-click==1.7.3
+rpds-py==0.18.0
+ruamel.yaml==0.17.17
+schemdraw==0.18
+scikit-base==0.7.3
+scikit-learn==1.3.0
+scikit-plot==0.3.7
+scipy==1.11.3
+seaborn==0.12.2
+Send2Trash==1.8.2
+setuptools==69.1.1
+six==1.16.0
+sktime==0.27.0
+sniffio==1.3.1
+soupsieve==2.5
+statsmodels==0.14.1
+tangled-up-in-unicode==0.2.0
+tbats==1.1.3
+tenacity==8.2.3
+terminado==0.18.0
+threadpoolctl==3.3.0
+tinycss2==1.2.1
+toolz==0.12.1
+tornado==6.4
+tqdm==4.66.2
+traitlets==5.14.1
+tsdownsample==0.1.2
+typeguard==4.1.5
+typer==0.9.0
+types-requests==2.31.0.20240218
+typing_extensions==4.10.0
+typing-inspect==0.9.0
+tzdata==2024.1
+tzlocal==5.2
+urllib3==2.2.1
+uvicorn==0.27.1
+visions==0.7.5
+watchdog==4.0.0
+wcwidth==0.2.13
+webencodings==0.5.1
+websocket-client==1.7.0
+Werkzeug==3.0.1
+whylabs-client==0.5.10
+whylogs==1.3.24
+whylogs-sketching==3.4.1.dev3
+widgetsnbextension==3.6.6
+wordcloud==1.9.3
+wurlitzer==3.0.3
+xxhash==3.4.1
+ydata-profiling==4.6.5
+yellowbrick==1.5
+zipp==3.17.0