modified summarizer (#704)

feat: enable setting of typeset/summarizer
refactor: summarizer extends handler

src/pandas_profiling/model/handler.py

@@ -1,69 +1,80 @@
-from functools import reduce
-from typing import Type
-
-import networkx as nx
-from visions import VisionsBaseType
-
-from pandas_profiling.model import typeset as ppt
-
-
-def compose(functions):
-    """
-    Compose a sequence of functions
-    :param functions: sequence of functions
-    :return: combined functions, e.g. [f(x), g(x)] -> g(f(x))
-    """
-
-    def func(f, g):
-        def func2(*x):
-            res = g(*x)
-            if type(res) == bool:
-                return f(*x)
-            else:
-                return f(*res)
-
-        return func2
-
-    return reduce(func, reversed(functions), lambda *x: x)
-
-
-class Handler:
-    def __init__(self, mapping, typeset, *args, **kwargs):
-        self.mapping = mapping
-        self.typeset = typeset
-
-        self._complete_dag()
-
-    def _complete_dag(self):
-        for from_type, to_type in nx.topological_sort(
-            nx.line_graph(self.typeset.base_graph)
-        ):
-            self.mapping[to_type] = self.mapping[from_type] + self.mapping[to_type]
-
-    def handle(self, dtype: Type[VisionsBaseType], *args, **kwargs) -> dict:
-        """
-
-        Returns:
-            object:
-        """
-        op = compose(self.mapping.get(dtype, []))
-        return op(*args)
-
-
-def get_render_map():
-    import pandas_profiling.report.structure.variables as render_algorithms
-
-    render_map = {
-        ppt.Boolean: render_algorithms.render_boolean,
-        ppt.Numeric: render_algorithms.render_real,
-        ppt.Complex: render_algorithms.render_complex,
-        ppt.DateTime: render_algorithms.render_date,
-        ppt.Categorical: render_algorithms.render_categorical,
-        ppt.URL: render_algorithms.render_url,
-        ppt.Path: render_algorithms.render_path,
-        ppt.File: render_algorithms.render_file,
-        ppt.Image: render_algorithms.render_image,
-        ppt.Unsupported: render_algorithms.render_generic,
-    }
-
-    return render_map
+from functools import reduce
+from typing import Callable, Dict, List, Type
+
+import networkx as nx
+from visions import VisionsBaseType, VisionsTypeset
+
+from pandas_profiling.model import typeset as ppt
+
+
+def compose(functions):
+    """
+    Compose a sequence of functions
+    :param functions: sequence of functions
+    :return: combined functions, e.g. [f(x), g(x)] -> g(f(x))
+    """
+
+    def func(f, g):
+        def func2(*x):
+            res = g(*x)
+            if type(res) == bool:
+                return f(*x)
+            else:
+                return f(*res)
+
+        return func2
+
+    return reduce(func, reversed(functions), lambda *x: x)
+
+
+class Handler:
+    """A generic handler
+
+    Allows any custom mapping between data types and functions
+    """
+
+    def __init__(
+        self,
+        mapping: Dict[Type[VisionsBaseType], List[Callable]],
+        typeset: VisionsTypeset,
+        *args,
+        **kwargs
+    ):
+        self.mapping = mapping
+        self.typeset = typeset
+
+        self._complete_dag()
+
+    def _complete_dag(self):
+        for from_type, to_type in nx.topological_sort(
+            nx.line_graph(self.typeset.base_graph)
+        ):
+            self.mapping[to_type] = self.mapping[from_type] + self.mapping[to_type]
+
+    def handle(self, dtype: Type[VisionsBaseType], *args, **kwargs) -> dict:
+        """
+
+        Returns:
+            object:
+        """
+        op = compose(self.mapping.get(dtype, []))
+        return op(*args)
+
+
+def get_render_map():
+    import pandas_profiling.report.structure.variables as render_algorithms
+
+    render_map = {
+        ppt.Boolean: render_algorithms.render_boolean,
+        ppt.Numeric: render_algorithms.render_real,
+        ppt.Complex: render_algorithms.render_complex,
+        ppt.DateTime: render_algorithms.render_date,
+        ppt.Categorical: render_algorithms.render_categorical,
+        ppt.URL: render_algorithms.render_url,
+        ppt.Path: render_algorithms.render_path,
+        ppt.File: render_algorithms.render_file,
+        ppt.Image: render_algorithms.render_image,
+        ppt.Unsupported: render_algorithms.render_generic,
+    }
+
+    return render_map

src/pandas_profiling/model/summarizer.py

@@ -1,11 +1,10 @@
 from typing import Type
 
-import networkx as nx
 import numpy as np
 import pandas as pd
 from visions import VisionsBaseType
 
-from pandas_profiling.model.handler import compose
+from pandas_profiling.model.handler import Handler
 from pandas_profiling.model.summary_algorithms import (
     describe_categorical_1d,
     describe_counts,
@@ -31,33 +30,25 @@
 )
 
 
-class BaseSummarizer:
-    def __init__(self, summary_map, typeset, *args, **kwargs):
-        self.summary_map = summary_map
-        self.typeset = typeset
+class BaseSummarizer(Handler):
+    """A base summarizer
 
-        self._complete_summaries()
-
-    def _complete_summaries(self):
-        for from_type, to_type in nx.topological_sort(
-            nx.line_graph(self.typeset.base_graph)
-        ):
-            self.summary_map[to_type] = (
-                self.summary_map[from_type] + self.summary_map[to_type]
-            )
+    Can be used to define custom summarizations
+    """
 
     def summarize(self, series: pd.Series, dtype: Type[VisionsBaseType]) -> dict:
         """
 
         Returns:
             object:
         """
-        summarizer_func = compose(self.summary_map.get(dtype, []))
-        _, summary = summarizer_func(series, {"type": dtype})
+        _, summary = self.handle(dtype, series, {"type": dtype})
         return summary
 
 
 class PandasProfilingSummarizer(BaseSummarizer):
+    """The default Pandas Profiling summarizer"""
+
     def __init__(self, typeset, *args, **kwargs):
         summary_map = {
             Unsupported: [

src/pandas_profiling/profile_report.py

@@ -7,13 +7,18 @@
 import numpy as np
 import pandas as pd
 from tqdm.auto import tqdm
+from visions import VisionsTypeset
 
 from pandas_profiling.config import config
 from pandas_profiling.expectations_report import ExpectationsReport
 from pandas_profiling.model.describe import describe as describe_df
 from pandas_profiling.model.messages import MessageType
 from pandas_profiling.model.sample import Sample
-from pandas_profiling.model.summarizer import PandasProfilingSummarizer, format_summary
+from pandas_profiling.model.summarizer import (
+    BaseSummarizer,
+    PandasProfilingSummarizer,
+    format_summary,
+)
 from pandas_profiling.model.typeset import ProfilingTypeSet
 from pandas_profiling.report import get_report_structure
 from pandas_profiling.report.presentation.flavours.html.templates import (
@@ -27,7 +32,7 @@
 class ProfileReport(SerializeReport, ExpectationsReport):
     """Generate a profile report from a Dataset stored as a pandas `DataFrame`.
 
-    Used has is it will output its content as an HTML report in a Jupyter notebook.
+    Used as is, it will output its content as an HTML report in a Jupyter notebook.
     """
 
     def __init__(
@@ -41,6 +46,8 @@ def __init__(
         sample: Optional[dict] = None,
         config_file: Union[Path, str] = None,
         lazy: bool = True,
+        typeset: Optional[VisionsTypeset] = None,
+        summarizer: Optional[BaseSummarizer] = None,
         **kwargs,
     ):
         """Generate a ProfileReport based on a pandas DataFrame
@@ -51,6 +58,8 @@ def __init__(
             config_file: a config file (.yml), mutually exclusive with `minimal`
             lazy: compute when needed
             sample: optional dict(name="Sample title", caption="Caption", data=pd.DataFrame())
+            typeset: optional user typeset to use for type inference
+            summarizer: optional user summarizer to generate custom summary output
             **kwargs: other arguments, for valid arguments, check the default configuration file.
         """
         config.clear()  # to reset (previous) config.
@@ -92,8 +101,8 @@ def __init__(
         self._html = None
         self._widgets = None
         self._json = None
-        self._typeset = None
-        self._summarizer = None
+        self._typeset = typeset
+        self._summarizer = summarizer
 
         if df is not None:
             # preprocess df