logml.configuration.report

class logml.configuration.report.BaselineKitWorkflowSection

Bases: pydantic.main.BaseModel

Defines workflow for BaselineKit.

Show JSON schema

{
   "title": "BaselineKitWorkflowSection",
   "description": "Defines workflow for BaselineKit.",
   "type": "object",
   "properties": {
      "produce_and_execute_strata_notebooks": {
         "title": "Produce And Execute Strata Notebooks",
         "description": "Enables creation and execution of strata-level notebooks for BaselineKit report. The main purpose of this option is to enable parallelization of report generation process.",
         "default": true,
         "type": "boolean"
      },
      "produce_and_execute_global_notebooks": {
         "title": "Produce And Execute Global Notebooks",
         "description": "Enables creation and execution of global-level notebooks for BaselineKit report. The main purpose of this option is to enable parallelization of report generation process.",
         "default": true,
         "type": "boolean"
      },
      "generate_report": {
         "title": "Generate Report",
         "description": "Enables BaselineKit report generation: TOC is created, strata-level notebooks are moved to the target global folder, rendering with Jupyterbook. The main purpose of this option is to enable parallelization of report generation process, additionally it allows a user to manually re-run some notebooks and regenerate the report having \"produce_and_execute_*\" flags turned off.",
         "default": true,
         "type": "boolean"
      }
   }
}

Fields

generate_report (bool)
produce_and_execute_global_notebooks (bool)
produce_and_execute_strata_notebooks (bool)

field produce_and_execute_strata_notebooks: bool = True: Enables creation and execution of strata-level notebooks for BaselineKit report. The main purpose of this option is to enable parallelization of report generation process.

field produce_and_execute_global_notebooks: bool = True: Enables creation and execution of global-level notebooks for BaselineKit report. The main purpose of this option is to enable parallelization of report generation process.

field generate_report: bool = True: Enables BaselineKit report generation: TOC is created, strata-level notebooks are moved to the target global folder, rendering with Jupyterbook. The main purpose of this option is to enable parallelization of report generation process, additionally it allows a user to manually re-run some notebooks and regenerate the report having “produce_and_execute_*” flags turned off.

class logml.configuration.report.MasterSummarySection

Bases: pydantic.main.BaseModel

Defines which sections to include to the Master Summary.

Show JSON schema

{
   "title": "MasterSummarySection",
   "description": "Defines which sections to include to the Master Summary.",
   "type": "object",
   "properties": {
      "enable": {
         "title": "Enable",
         "description": "Enables Master Summary section that contains highlights from multiple sections.",
         "default": false,
         "type": "boolean"
      },
      "eda": {
         "title": "Eda",
         "description": "Turns on EDA section highlights. This requires EDA artifacts to be generated (see `ed` section.)",
         "default": false,
         "type": "boolean"
      },
      "feature_importance": {
         "title": "Feature Importance",
         "description": "Enables Feature Importance summary for a given modeling problem \"setup id\".",
         "default": "",
         "type": "string"
      },
      "survival_feature_importance": {
         "title": "Survival Feature Importance",
         "description": "Enables Survival Feature Importance summary for a given modeling problem \"setup id\".",
         "default": "",
         "type": "string"
      },
      "baseline_modeling": {
         "title": "Baseline Modeling",
         "description": "Enables Model Search/Selection summary for a given modeling problem \"setup id\".",
         "default": "",
         "type": "string"
      },
      "survival_analysis": {
         "title": "Survival Analysis",
         "description": "Enables Survival Analysis summary for a given survival problem \"setup id\".",
         "default": "",
         "type": "string"
      }
   }
}

Fields

baseline_modeling (str)
eda (bool)
enable (bool)
feature_importance (str)
survival_analysis (str)
survival_feature_importance (str)

field enable: bool = False: Enables Master Summary section that contains highlights from multiple sections.

field eda: bool = False: Turns on EDA section highlights. This requires EDA artifacts to be generated (see ed section.)

field feature_importance: str = '': Enables Feature Importance summary for a given modeling problem “setup id”.

field survival_feature_importance: str = '': Enables Survival Feature Importance summary for a given modeling problem “setup id”.

field baseline_modeling: str = '': Enables Model Search/Selection summary for a given modeling problem “setup id”.

field survival_analysis: str = '': Enables Survival Analysis summary for a given survival problem “setup id”.

list_modeling_problems() → List[str]: Returns all mentioned modeling problems.

list_survival_problems() → List[str]: Returns all mentioned survival problems.

class logml.configuration.report.ReportStructure

Bases: pydantic.main.BaseModel

Defines BaselineKit report structure (topics) and expected params. Please refer to EligibleBaselineKitNotebooks for details on supported fields.

Show JSON schema

{
   "title": "ReportStructure",
   "description": "Defines BaselineKit report structure (topics) and expected params.\nPlease refer to `EligibleBaselineKitNotebooks` for details on supported fields.",
   "type": "object",
   "properties": {
      "master_summary": {
         "title": "Master Summary",
         "default": {
            "enable": false,
            "eda": false,
            "feature_importance": "",
            "survival_feature_importance": "",
            "baseline_modeling": "",
            "survival_analysis": ""
         },
         "allOf": [
            {
               "$ref": "#/definitions/MasterSummarySection"
            }
         ]
      },
      "eda": {
         "title": "Eda",
         "description": "Enables multiple EDA sections: dataset overview, numericals/categoricals analysis, dimensionality reduction, correlation analysis, etc.",
         "default": false,
         "type": "boolean"
      },
      "modeling": {
         "title": "Modeling",
         "description": "Target modeling problems/setups for which Modeling Report sections should be produced.",
         "default": [],
         "type": "array",
         "items": {
            "type": "string"
         }
      },
      "cross_strata_fi_summary": {
         "title": "Cross Strata Fi Summary",
         "description": "Target modeling problems/setups for which cross-strata analysis/comparison sections should be produced. NOTE: survival feature importance is supported as well.",
         "default": [],
         "type": "array",
         "items": {
            "type": "string"
         }
      },
      "survival_analysis": {
         "title": "Survival Analysis",
         "description": "Target survival problems/setups for which survival analysis sections should be produced.",
         "default": [],
         "type": "array",
         "items": {
            "type": "string"
         }
      },
      "greedy_split": {
         "title": "Greedy Split",
         "description": "Target analysis items (referenced by \"name\") of \"greedy_split\" type.",
         "default": [],
         "type": "array",
         "items": {
            "type": "string"
         }
      },
      "rnaseq_differential_expression": {
         "title": "Rnaseq Differential Expression",
         "description": "Target analysis items (referenced by \"name\") of \"rnaseq_differential_expression\" type.",
         "default": [],
         "type": "array",
         "items": {
            "type": "string"
         }
      },
      "rnaseq_enrichment_analysis": {
         "title": "Rnaseq Enrichment Analysis",
         "description": "Target analysis items (referenced by \"name\") of \"rnaseq_enrichment_analysis\" type.",
         "default": [],
         "type": "array",
         "items": {
            "type": "string"
         }
      },
      "report_diagnostics": {
         "title": "Report Diagnostics",
         "description": "Enables report diagnostic view.",
         "default": true,
         "type": "boolean"
      },
      "report_summary": {
         "title": "Report Summary",
         "description": "Enables report summary view.",
         "default": true,
         "type": "boolean"
      }
   },
   "definitions": {
      "MasterSummarySection": {
         "title": "MasterSummarySection",
         "description": "Defines which sections to include to the Master Summary.",
         "type": "object",
         "properties": {
            "enable": {
               "title": "Enable",
               "description": "Enables Master Summary section that contains highlights from multiple sections.",
               "default": false,
               "type": "boolean"
            },
            "eda": {
               "title": "Eda",
               "description": "Turns on EDA section highlights. This requires EDA artifacts to be generated (see `ed` section.)",
               "default": false,
               "type": "boolean"
            },
            "feature_importance": {
               "title": "Feature Importance",
               "description": "Enables Feature Importance summary for a given modeling problem \"setup id\".",
               "default": "",
               "type": "string"
            },
            "survival_feature_importance": {
               "title": "Survival Feature Importance",
               "description": "Enables Survival Feature Importance summary for a given modeling problem \"setup id\".",
               "default": "",
               "type": "string"
            },
            "baseline_modeling": {
               "title": "Baseline Modeling",
               "description": "Enables Model Search/Selection summary for a given modeling problem \"setup id\".",
               "default": "",
               "type": "string"
            },
            "survival_analysis": {
               "title": "Survival Analysis",
               "description": "Enables Survival Analysis summary for a given survival problem \"setup id\".",
               "default": "",
               "type": "string"
            }
         }
      }
   }
}

Fields

cross_strata_fi_summary (List[str])
eda (bool)
greedy_split (List[str])
master_summary (logml.configuration.report.MasterSummarySection)
modeling (List[str])
report_diagnostics (bool)
report_summary (bool)
rnaseq_differential_expression (List[str])
rnaseq_enrichment_analysis (List[str])
survival_analysis (List[str])

field master_summary: logml.configuration.report.MasterSummarySection = MasterSummarySection(enable=False, eda=False, feature_importance='', survival_feature_importance='', baseline_modeling='', survival_analysis='')

field eda: bool = False: Enables multiple EDA sections: dataset overview, numericals/categoricals analysis, dimensionality reduction, correlation analysis, etc.

field modeling: List[str] = []: Target modeling problems/setups for which Modeling Report sections should be produced.

field cross_strata_fi_summary: List[str] = []: Target modeling problems/setups for which cross-strata analysis/comparison sections should be produced. NOTE: survival feature importance is supported as well.

field survival_analysis: List[str] = []: Target survival problems/setups for which survival analysis sections should be produced.

field greedy_split: List[str] = []: Target analysis items (referenced by “name”) of “greedy_split” type.

field rnaseq_differential_expression: List[str] = []: Target analysis items (referenced by “name”) of “rnaseq_differential_expression” type.

field rnaseq_enrichment_analysis: List[str] = []: Target analysis items (referenced by “name”) of “rnaseq_enrichment_analysis” type.

field report_diagnostics: bool = True: Enables report diagnostic view.

field report_summary: bool = True: Enables report summary view.

is_notebook_enabled(notebook_alias: str) → bool: Returns true when notebook enabled.

list_modeling_problems() → List[str]: Returns all mentioned modeling problems.

list_survival_problems() → List[str]: Returns all mentioned modeling problems.

class logml.configuration.report.ReportSection

Bases: pydantic.main.BaseModel

Defines BaselineKit section.

Show JSON schema

{
   "title": "ReportSection",
   "description": "Defines BaselineKit section.",
   "type": "object",
   "properties": {
      "enable": {
         "title": "Enable",
         "description": "Enables BaselineKit report generation: underlying Jupyter notebooks generation (for target scopes) + report rendering via JupyterBook.",
         "default": true,
         "type": "boolean"
      },
      "report_structure": {
         "title": "Report Structure",
         "default": {
            "master_summary": {
               "enable": false,
               "eda": false,
               "feature_importance": "",
               "survival_feature_importance": "",
               "baseline_modeling": "",
               "survival_analysis": ""
            },
            "eda": false,
            "modeling": [],
            "cross_strata_fi_summary": [],
            "survival_analysis": [],
            "greedy_split": [],
            "rnaseq_differential_expression": [],
            "rnaseq_enrichment_analysis": [],
            "report_diagnostics": true,
            "report_summary": true
         },
         "allOf": [
            {
               "$ref": "#/definitions/ReportStructure"
            }
         ]
      },
      "workflow": {
         "title": "Workflow",
         "default": {
            "produce_and_execute_strata_notebooks": true,
            "produce_and_execute_global_notebooks": true,
            "generate_report": true
         },
         "allOf": [
            {
               "$ref": "#/definitions/BaselineKitWorkflowSection"
            }
         ]
      }
   },
   "definitions": {
      "MasterSummarySection": {
         "title": "MasterSummarySection",
         "description": "Defines which sections to include to the Master Summary.",
         "type": "object",
         "properties": {
            "enable": {
               "title": "Enable",
               "description": "Enables Master Summary section that contains highlights from multiple sections.",
               "default": false,
               "type": "boolean"
            },
            "eda": {
               "title": "Eda",
               "description": "Turns on EDA section highlights. This requires EDA artifacts to be generated (see `ed` section.)",
               "default": false,
               "type": "boolean"
            },
            "feature_importance": {
               "title": "Feature Importance",
               "description": "Enables Feature Importance summary for a given modeling problem \"setup id\".",
               "default": "",
               "type": "string"
            },
            "survival_feature_importance": {
               "title": "Survival Feature Importance",
               "description": "Enables Survival Feature Importance summary for a given modeling problem \"setup id\".",
               "default": "",
               "type": "string"
            },
            "baseline_modeling": {
               "title": "Baseline Modeling",
               "description": "Enables Model Search/Selection summary for a given modeling problem \"setup id\".",
               "default": "",
               "type": "string"
            },
            "survival_analysis": {
               "title": "Survival Analysis",
               "description": "Enables Survival Analysis summary for a given survival problem \"setup id\".",
               "default": "",
               "type": "string"
            }
         }
      },
      "ReportStructure": {
         "title": "ReportStructure",
         "description": "Defines BaselineKit report structure (topics) and expected params.\nPlease refer to `EligibleBaselineKitNotebooks` for details on supported fields.",
         "type": "object",
         "properties": {
            "master_summary": {
               "title": "Master Summary",
               "default": {
                  "enable": false,
                  "eda": false,
                  "feature_importance": "",
                  "survival_feature_importance": "",
                  "baseline_modeling": "",
                  "survival_analysis": ""
               },
               "allOf": [
                  {
                     "$ref": "#/definitions/MasterSummarySection"
                  }
               ]
            },
            "eda": {
               "title": "Eda",
               "description": "Enables multiple EDA sections: dataset overview, numericals/categoricals analysis, dimensionality reduction, correlation analysis, etc.",
               "default": false,
               "type": "boolean"
            },
            "modeling": {
               "title": "Modeling",
               "description": "Target modeling problems/setups for which Modeling Report sections should be produced.",
               "default": [],
               "type": "array",
               "items": {
                  "type": "string"
               }
            },
            "cross_strata_fi_summary": {
               "title": "Cross Strata Fi Summary",
               "description": "Target modeling problems/setups for which cross-strata analysis/comparison sections should be produced. NOTE: survival feature importance is supported as well.",
               "default": [],
               "type": "array",
               "items": {
                  "type": "string"
               }
            },
            "survival_analysis": {
               "title": "Survival Analysis",
               "description": "Target survival problems/setups for which survival analysis sections should be produced.",
               "default": [],
               "type": "array",
               "items": {
                  "type": "string"
               }
            },
            "greedy_split": {
               "title": "Greedy Split",
               "description": "Target analysis items (referenced by \"name\") of \"greedy_split\" type.",
               "default": [],
               "type": "array",
               "items": {
                  "type": "string"
               }
            },
            "rnaseq_differential_expression": {
               "title": "Rnaseq Differential Expression",
               "description": "Target analysis items (referenced by \"name\") of \"rnaseq_differential_expression\" type.",
               "default": [],
               "type": "array",
               "items": {
                  "type": "string"
               }
            },
            "rnaseq_enrichment_analysis": {
               "title": "Rnaseq Enrichment Analysis",
               "description": "Target analysis items (referenced by \"name\") of \"rnaseq_enrichment_analysis\" type.",
               "default": [],
               "type": "array",
               "items": {
                  "type": "string"
               }
            },
            "report_diagnostics": {
               "title": "Report Diagnostics",
               "description": "Enables report diagnostic view.",
               "default": true,
               "type": "boolean"
            },
            "report_summary": {
               "title": "Report Summary",
               "description": "Enables report summary view.",
               "default": true,
               "type": "boolean"
            }
         }
      },
      "BaselineKitWorkflowSection": {
         "title": "BaselineKitWorkflowSection",
         "description": "Defines workflow for BaselineKit.",
         "type": "object",
         "properties": {
            "produce_and_execute_strata_notebooks": {
               "title": "Produce And Execute Strata Notebooks",
               "description": "Enables creation and execution of strata-level notebooks for BaselineKit report. The main purpose of this option is to enable parallelization of report generation process.",
               "default": true,
               "type": "boolean"
            },
            "produce_and_execute_global_notebooks": {
               "title": "Produce And Execute Global Notebooks",
               "description": "Enables creation and execution of global-level notebooks for BaselineKit report. The main purpose of this option is to enable parallelization of report generation process.",
               "default": true,
               "type": "boolean"
            },
            "generate_report": {
               "title": "Generate Report",
               "description": "Enables BaselineKit report generation: TOC is created, strata-level notebooks are moved to the target global folder, rendering with Jupyterbook. The main purpose of this option is to enable parallelization of report generation process, additionally it allows a user to manually re-run some notebooks and regenerate the report having \"produce_and_execute_*\" flags turned off.",
               "default": true,
               "type": "boolean"
            }
         }
      }
   }
}

Fields

enable (bool)
report_structure (logml.configuration.report.ReportStructure)
workflow (logml.configuration.report.BaselineKitWorkflowSection)

field enable: bool = True: Enables BaselineKit report generation: underlying Jupyter notebooks generation (for target scopes) + report rendering via JupyterBook.

field report_structure: logml.configuration.report.ReportStructure = ReportStructure(master_summary=MasterSummarySection(enable=False, eda=False, feature_importance='', survival_feature_importance='', baseline_modeling='', survival_analysis=''), eda=False, modeling=[], cross_strata_fi_summary=[], survival_analysis=[], greedy_split=[], rnaseq_differential_expression=[], rnaseq_enrichment_analysis=[], report_diagnostics=True, report_summary=True)

field workflow: logml.configuration.report.BaselineKitWorkflowSection = BaselineKitWorkflowSection(produce_and_execute_strata_notebooks=True, produce_and_execute_global_notebooks=True, generate_report=True)