refactor!: move subsection enums outside section classes (#160)

Resolves #107

edvart/report.py

@@ -14,14 +14,20 @@
 import pandas as pd
 
 from edvart.data_types import is_date
-from edvart.report_sections.bivariate_analysis import BivariateAnalysis
+from edvart.report_sections.bivariate_analysis import BivariateAnalysis, BivariateAnalysisSubsection
 from edvart.report_sections.code_string_formatting import code_dedent
-from edvart.report_sections.dataset_overview import Overview
+from edvart.report_sections.dataset_overview import Overview, OverviewSubsection
 from edvart.report_sections.group_analysis import GroupAnalysis
-from edvart.report_sections.multivariate_analysis import MultivariateAnalysis
+from edvart.report_sections.multivariate_analysis import (
+    MultivariateAnalysis,
+    MultivariateAnalysisSubsection,
+)
 from edvart.report_sections.section_base import Section, Verbosity
 from edvart.report_sections.table_of_contents import TableOfContents
-from edvart.report_sections.timeseries_analysis import TimeseriesAnalysis
+from edvart.report_sections.timeseries_analysis import (
+    TimeseriesAnalysis,
+    TimeseriesAnalysisSubsection,
+)
 from edvart.report_sections.univariate_analysis import UnivariateAnalysis
 from edvart.utils import env_var
 
@@ -322,7 +328,7 @@ def add_section(
     def add_overview(
         self,
         columns: Optional[List[str]] = None,
-        subsections: Optional[List[Overview.OverviewSubsection]] = None,
+        subsections: Optional[List[OverviewSubsection]] = None,
         verbosity: Optional[Verbosity] = None,
         verbosity_quick_info: Optional[Verbosity] = None,
         verbosity_data_types: Optional[Verbosity] = None,
@@ -408,7 +414,7 @@ def add_bivariate_analysis(
         columns_x: Optional[List[str]] = None,
         columns_y: Optional[List[str]] = None,
         columns_pairs: Optional[List[Tuple[str, str]]] = None,
-        subsections: Optional[List[BivariateAnalysis.BivariateAnalysisSubsection]] = None,
+        subsections: Optional[List[BivariateAnalysisSubsection]] = None,
         verbosity: Optional[Verbosity] = None,
         verbosity_correlations: Optional[Verbosity] = None,
         verbosity_pairplot: Optional[Verbosity] = None,
@@ -438,7 +444,7 @@ def add_bivariate_analysis(
             `columns`, `columns_x`, `columns_y` is specified. In that case, the first elements
             of each pair are treated as `columns_x` and the second elements as `columns_y` in
             pairplots and correlations.
-        subsections : List[BivariateAnalysis.BivariateAnalysisSubsection], optional
+        subsections : List[BivariateAnalysisSubsection], optional
             List of sub-sections to include into the BivariateAnalysis section.
             If None, all subsections are added.
         verbosity : Verbosity, optional
@@ -473,7 +479,7 @@ def add_bivariate_analysis(
     def add_multivariate_analysis(
         self,
         columns: Optional[List[str]] = None,
-        subsections: Optional[List[MultivariateAnalysis.MultivariateAnalysisSubsection]] = None,
+        subsections: Optional[List[MultivariateAnalysisSubsection]] = None,
         verbosity: Optional[Verbosity] = None,
         verbosity_pca: Optional[Verbosity] = None,
         verbosity_umap: Optional[Verbosity] = None,
@@ -488,7 +494,7 @@ def add_multivariate_analysis(
         columns : List[str], optional
             Columns which to analyze.
             If None, all columns are used.
-        subsections : List[MultivariateAnalysis.MultivariateAnalysisSubsection], optional
+        subsections : List[MultivariateAnalysisSubsection], optional
             List of sub-sections to include into the BivariateAnalysis section.
             If None, all subsections are added.
         verbosity : Verbosity, optional
@@ -733,7 +739,7 @@ def __init__(
     def add_timeseries_analysis(
         self,
         columns: Optional[List[str]] = None,
-        subsections: Optional[List[TimeseriesAnalysis.TimeseriesAnalysisSubsection]] = None,
+        subsections: Optional[List[TimeseriesAnalysisSubsection]] = None,
         verbosity: Optional[Verbosity] = None,
         verbosity_time_series_line_plot: Optional[Verbosity] = None,
         verbosity_rolling_statistics: Optional[Verbosity] = None,

edvart/report_sections/bivariate_analysis.py

@@ -17,6 +17,18 @@
 from edvart.report_sections.section_base import ReportSection, Section, Verbosity
 
 
+# pylint:disable=invalid-name
+class BivariateAnalysisSubsection(IntEnum):
+    """Enum of all implemented bivariate analysis subsections."""
+
+    CorrelationPlot = 0
+    PairPlot = 1
+    ContingencyTable = 2
+
+    def __str__(self):
+        return self.name
+
+
 class BivariateAnalysis(ReportSection):
     """Generates the Bivariate analysis section of the report.
 
@@ -69,17 +81,6 @@ class BivariateAnalysis(ReportSection):
         If exactly one of `columns_x`, `columns_y` is specified.
     """
 
-    # pylint:disable=invalid-name
-    class BivariateAnalysisSubsection(IntEnum):
-        """Enum of all implemented bivariate analysis subsections."""
-
-        CorrelationPlot = 0
-        PairPlot = 1
-        ContingencyTable = 2
-
-        def __str__(self):
-            return self.name
-
     # By default use all subsections
     _DEFAULT_SUBSECTIONS_TO_SHOW = list(BivariateAnalysisSubsection)
 
@@ -100,13 +101,11 @@ def __init__(
         verbosity_pairplot = verbosity_pairplot or verbosity
         verbosity_contingency_table = verbosity_contingency_table or verbosity
 
-        subsec = BivariateAnalysis.BivariateAnalysisSubsection
-
         # Store subsection verbosities
         self.subsection_verbosities = {
-            subsec.CorrelationPlot: verbosity_correlations,
-            subsec.PairPlot: verbosity_pairplot,
-            subsec.ContingencyTable: verbosity_contingency_table,
+            BivariateAnalysisSubsection.CorrelationPlot: verbosity_correlations,
+            BivariateAnalysisSubsection.PairPlot: verbosity_pairplot,
+            BivariateAnalysisSubsection.ContingencyTable: verbosity_contingency_table,
         }
 
         if subsections is None:
@@ -130,17 +129,17 @@ def __init__(
             columns_x_no_pairs = columns_x
             columns_y_no_pairs = columns_y
         enum_to_implementation = {
-            subsec.CorrelationPlot: CorrelationPlot(
+            BivariateAnalysisSubsection.CorrelationPlot: CorrelationPlot(
                 verbosity_correlations, columns, columns_x_no_pairs, columns_y_no_pairs
             ),
-            subsec.PairPlot: PairPlot(
+            BivariateAnalysisSubsection.PairPlot: PairPlot(
                 verbosity_pairplot,
                 columns,
                 columns_x_no_pairs,
                 columns_y_no_pairs,
                 color_col=color_col,
             ),
-            subsec.ContingencyTable: ContingencyTable(
+            BivariateAnalysisSubsection.ContingencyTable: ContingencyTable(
                 verbosity_contingency_table, columns, columns_x, columns_y, columns_pairs
             ),
         }
@@ -177,7 +176,7 @@ def add_cells(self, cells: List[Dict[str, Any]], df: pd.DataFrame) -> None:
             code = "show_bivariate_analysis(df=df"
             if self.subsections_to_show_with_low_verbosity != self._DEFAULT_SUBSECTIONS_TO_SHOW:
                 arg_subsections_names = [
-                    f"BivariateAnalysis.BivariateAnalysisSubsection.{str(sub)}"
+                    f"BivariateAnalysisSubsection.{str(sub)}"
                     for sub in self.subsections_to_show_with_low_verbosity
                 ]
 
@@ -213,7 +212,9 @@ def required_imports(self) -> List[str]:
 
         imports = {"from edvart.report_sections.bivariate_analysis import show_bivariate_analysis"}
         if self.subsections_to_show_with_low_verbosity != self._DEFAULT_SUBSECTIONS_TO_SHOW:
-            imports.add("from edvart.report_sections.bivariate_analysis import BivariateAnalysis")
+            imports.add(
+                "from edvart.report_sections.bivariate_analysis import BivariateAnalysisSubsection"
+            )
         for subsec in self.subsections:
             if subsec.verbosity > Verbosity.LOW:
                 imports.update(subsec.required_imports())
@@ -234,7 +235,7 @@ def show(self, df: pd.DataFrame) -> None:
 
 def show_bivariate_analysis(
     df: pd.DataFrame,
-    subsections: Optional[List[BivariateAnalysis.BivariateAnalysisSubsection]] = None,
+    subsections: Optional[List[BivariateAnalysisSubsection]] = None,
     columns: Optional[List[str]] = None,
     columns_x: Optional[List[str]] = None,
     columns_y: Optional[List[str]] = None,

edvart/report_sections/dataset_overview.py

@@ -21,6 +21,24 @@
 from edvart.report_sections.section_base import ReportSection, Section, Verbosity
 
 
+# pylint: disable=invalid-name
+class OverviewSubsection(IntEnum):
+    """
+    Enum of possible subsections of the Overview section.
+    """
+
+    QuickInfo = 1
+    DataTypes = 2
+    DataPreview = 3
+    MissingValues = 4
+    RowsWithMissingValue = 5
+    ConstantOccurrence = 6
+    DuplicateRows = 7
+
+    def __str__(self):
+        return self.name
+
+
 class Overview(ReportSection):
     """Generates the Overview section of the report.
 
@@ -52,23 +70,6 @@ class Overview(ReportSection):
         Duplicate rows subsection code verbosity.
     """
 
-    # pylint: disable=invalid-name
-    class OverviewSubsection(IntEnum):
-        """
-        Enum of possible subsections of the Overview section.
-        """
-
-        QuickInfo = 1
-        DataTypes = 2
-        DataPreview = 3
-        MissingValues = 4
-        RowsWithMissingValue = 5
-        ConstantOccurrence = 6
-        DuplicateRows = 7
-
-        def __str__(self):
-            return self.name
-
     # By default use all subsections
     _DEFAULT_SUBSECTIONS_TO_SHOW = list(OverviewSubsection)
 
@@ -95,17 +96,15 @@ def __init__(
         verbosity_constant_occurrence = verbosity_constant_occurrence or verbosity
         verbosity_duplicate_rows = verbosity_duplicate_rows or verbosity
 
-        subsec = Overview.OverviewSubsection
-
         # Store subsection verbosities
         self.subsection_verbosities = {
-            subsec.QuickInfo: verbosity_quick_info,
-            subsec.DataTypes: verbosity_data_types,
-            subsec.DataPreview: verbosity_data_preview,
-            subsec.MissingValues: verbosity_missing_values,
-            subsec.RowsWithMissingValue: verbosity_rows_with_missing_value,
-            subsec.ConstantOccurrence: verbosity_constant_occurrence,
-            subsec.DuplicateRows: verbosity_duplicate_rows,
+            OverviewSubsection.QuickInfo: verbosity_quick_info,
+            OverviewSubsection.DataTypes: verbosity_data_types,
+            OverviewSubsection.DataPreview: verbosity_data_preview,
+            OverviewSubsection.MissingValues: verbosity_missing_values,
+            OverviewSubsection.RowsWithMissingValue: verbosity_rows_with_missing_value,
+            OverviewSubsection.ConstantOccurrence: verbosity_constant_occurrence,
+            OverviewSubsection.DuplicateRows: verbosity_duplicate_rows,
         }
 
         if subsections is None:
@@ -121,15 +120,17 @@ def __init__(
 
         # Construct objects that implement subsections
         enum_to_implementation = {
-            subsec.QuickInfo: QuickInfo(verbosity_quick_info, columns),
-            subsec.DataTypes: DataTypes(verbosity_data_types, columns),
-            subsec.DataPreview: DataPreview(verbosity_data_preview, columns),
-            subsec.MissingValues: MissingValues(verbosity_missing_values, columns),
-            subsec.RowsWithMissingValue: RowsWithMissingValue(
+            OverviewSubsection.QuickInfo: QuickInfo(verbosity_quick_info, columns),
+            OverviewSubsection.DataTypes: DataTypes(verbosity_data_types, columns),
+            OverviewSubsection.DataPreview: DataPreview(verbosity_data_preview, columns),
+            OverviewSubsection.MissingValues: MissingValues(verbosity_missing_values, columns),
+            OverviewSubsection.RowsWithMissingValue: RowsWithMissingValue(
                 verbosity_rows_with_missing_value, columns
             ),
-            subsec.ConstantOccurrence: ConstantOccurrence(verbosity_constant_occurrence, columns),
-            subsec.DuplicateRows: DuplicateRows(verbosity_duplicate_rows, columns),
+            OverviewSubsection.ConstantOccurrence: ConstantOccurrence(
+                verbosity_constant_occurrence, columns
+            ),
+            OverviewSubsection.DuplicateRows: DuplicateRows(verbosity_duplicate_rows, columns),
         }
 
         subsections_implementations = [
@@ -153,7 +154,9 @@ def required_imports(self) -> List[str]:
         if self.verbosity == Verbosity.LOW:
             imports = {"from edvart.report_sections.dataset_overview import show_overview"}
             if self.subsections_to_show_with_low_verbosity != self._DEFAULT_SUBSECTIONS_TO_SHOW:
-                imports.add("from edvart.report_sections.dataset_overview import Overview")
+                imports.add(
+                    "from edvart.report_sections.dataset_overview import OverviewSubsection"
+                )
 
             for subsec in self.subsections:
                 if subsec.verbosity > Verbosity.LOW:
@@ -181,7 +184,7 @@ def add_cells(self, cells: List[Dict[str, Any]], df: pd.DataFrame) -> None:
             code = "show_overview(df=df"
             if self.subsections_to_show_with_low_verbosity != self._DEFAULT_SUBSECTIONS_TO_SHOW:
                 arg_subsections_names = [
-                    f"Overview.OverviewSubsection.{str(sub)}"
+                    f"OverviewSubsection.{str(sub)}"
                     for sub in self.subsections_to_show_with_low_verbosity
                 ]
                 code += f", subsections={arg_subsections_names}".replace("'", "")
@@ -209,7 +212,7 @@ def show(self, df: pd.DataFrame) -> None:
 
 def show_overview(
     df: pd.DataFrame,
-    subsections: Optional[List[Overview.OverviewSubsection]] = None,
+    subsections: Optional[List[OverviewSubsection]] = None,
     columns: Optional[List[str]] = None,
 ) -> None:
     """Generates overview analysis for df.