feat: initial release

Author: Pkcha

src/ydata_profiling/model/handler.py

@@ -1,60 +1,63 @@
-"""
-    Auxiliary handler methods for data summary extraction
-"""
-from typing import Any, Callable, Dict, List, Sequence
-
-import networkx as nx
-from visions import VisionsTypeset
-
-
-def compose(functions: Sequence[Callable]) -> Callable:
-    """
-    Compose a sequence of functions.
-
-    :param functions: sequence of functions
-    :return: combined function applying all functions in order.
-    """
-
-    def composed_function(*args) -> List[Any]:
-        result = args  # Start with the input arguments
-        for func in functions:
-            result = func(*result) if isinstance(result, tuple) else func(result)
-        return result  # type: ignore
-
-    return composed_function  # type: ignore
-
-
-class Handler:
-    """A generic handler
-
-    Allows any custom mapping between data types and functions
-    """
-
-    def __init__(
-        self,
-        mapping: Dict[str, List[Callable]],
-        typeset: VisionsTypeset,
-        *args,
-        **kwargs
-    ):
-        self.mapping = mapping
-        self.typeset = typeset
-        self._complete_dag()
-
-    def _complete_dag(self) -> None:
-        for from_type, to_type in nx.topological_sort(
-            nx.line_graph(self.typeset.base_graph)
-        ):
-            self.mapping[str(to_type)] = (
-                self.mapping[str(from_type)] + self.mapping[str(to_type)]
-            )
-
-    def handle(self, dtype: str, *args, **kwargs) -> dict:
-        """
-        Returns:
-            object: a tuple containing the config, the dataset series and the summary extracted
-        """
-        funcs = self.mapping.get(dtype, [])
-        op = compose(funcs)
-        summary = op(*args)[-1]
-        return summary
+"""
+    Auxiliary handler methods for data summary extraction
+"""
+from typing import Any, Callable, Dict, List, Sequence
+
+import networkx as nx
+from visions import VisionsTypeset
+
+
+def compose(functions: Sequence[Callable]) -> Callable:
+    """
+    Compose a sequence of functions.
+
+    :param functions: sequence of functions
+    :return: combined function applying all functions in order.
+    """
+
+    def composed_function(*args) -> List[Any]:
+        result = args  # Start with the input arguments
+        for func in functions:
+            result = func(*result) if isinstance(result, tuple) else func(result)
+        return result  # type: ignore
+
+    return composed_function  # type: ignore
+
+
+class Handler:
+    """A generic handler
+
+    Allows any custom mapping between data types and functions
+    """
+
+    def __init__(
+        self,
+        mapping: Dict[str, List[Callable]],
+        typeset: VisionsTypeset,
+        *args,
+        **kwargs
+    ):
+        self.mapping = mapping
+        self.typeset = typeset
+        self._complete_dag()
+
+    def _complete_dag(self) -> None:
+        for from_type, to_type in nx.topological_sort(
+            nx.line_graph(self.typeset.base_graph)
+        ):
+            self.mapping[str(to_type)] = (
+                self.mapping[str(from_type)] + self.mapping[str(to_type)]
+            )
+
+    def handle(self, dtype: str, *args, **kwargs) -> dict:
+        """
+        Returns:
+            object: a tuple containing the config, the dataset series and the summary extracted
+        """
+        funcs = self.mapping.get(dtype, [])
+        op = compose(funcs)
+        summary = op(*args)[-1]
+        return summary
+
+
+

src/ydata_profiling/model/summarizer.py

@@ -27,7 +27,7 @@
 from ydata_profiling.model.pandas.describe_supported_pandas import (
     pandas_describe_supported,
 )
-from ydata_profiling.model.summary_algorithms import (  # Check what is this method used for
+from ydata_profiling.model.summary_algorithms import (
     describe_file_1d,
     describe_image_1d,
     describe_path_1d,
@@ -50,9 +50,8 @@ def summarize(
         return self.handle(str(dtype), config, series, {"type": str(dtype)})
 
 
-# Revisit this with the correct support for Spark as well.
 class ProfilingSummarizer(BaseSummarizer):
-    """A summarizer for Pandas DataFrames."""
+    """A summarizer supporting both Pandas and Spark DataFrames."""
 
     def __init__(self, typeset: VisionsTypeset, use_spark: bool = False):
         self.use_spark = use_spark and is_pyspark_installed()

src/ydata_profiling/report/structure/__init__.py

@@ -1,31 +1 @@
 """Data structure for the report"""
-from typing import Callable, Dict
-
-
-def get_render_map() -> Dict[str, Callable]:
-    """Get the mapping of variable types to their render functions.
-
-    This function was moved from model.handler to report.structure to eliminate
-    the reverse dependency from model layer to report layer.
-
-    Returns:
-        Dictionary mapping type names to render functions.
-    """
-    import ydata_profiling.report.structure.variables as render_algorithms
-
-    render_map = {
-        "Boolean": render_algorithms.render_boolean,
-        "Numeric": render_algorithms.render_real,
-        "Complex": render_algorithms.render_complex,
-        "Text": render_algorithms.render_text,
-        "DateTime": render_algorithms.render_date,
-        "Categorical": render_algorithms.render_categorical,
-        "URL": render_algorithms.render_url,
-        "Path": render_algorithms.render_path,
-        "File": render_algorithms.render_file,
-        "Image": render_algorithms.render_image,
-        "Unsupported": render_algorithms.render_generic,
-        "TimeSeries": render_algorithms.render_timeseries,
-    }
-
-    return render_map

src/ydata_profiling/report/structure/report.py

@@ -7,7 +7,7 @@
 from ydata_profiling.config import Settings
 from ydata_profiling.model import BaseDescription
 from ydata_profiling.model.alerts import AlertType
-from ydata_profiling.report.structure import get_render_map
+from ydata_profiling.report.structure.variables import get_render_map
 from ydata_profiling.report.presentation.core import (
     HTML,
     Collapse,

src/ydata_profiling/report/structure/variables/__init__.py

@@ -1,3 +1,5 @@
+from typing import Callable, Dict
+
 from ydata_profiling.report.structure.variables.render_boolean import render_boolean
 from ydata_profiling.report.structure.variables.render_categorical import (
     render_categorical,
@@ -17,6 +19,26 @@
 )
 from ydata_profiling.report.structure.variables.render_url import render_url
 
+
+def get_render_map() -> Dict[str, Callable]:
+    render_map = {
+        "Boolean": render_boolean,
+        "Numeric": render_real,
+        "Complex": render_complex,
+        "Text": render_text,
+        "DateTime": render_date,
+        "Categorical": render_categorical,
+        "URL": render_url,
+        "Path": render_path,
+        "File": render_file,
+        "Image": render_image,
+        "Unsupported": render_generic,
+        "TimeSeries": render_timeseries,
+    }
+
+    return render_map
+
+
 __all__ = [
     "render_boolean",
     "render_categorical",
@@ -32,4 +54,5 @@
     "render_text",
     "render_timeseries",
     "render_url",
+    "get_render_map",
 ]

src/ydata_profiling/utils/backend.py

@@ -1,5 +1,5 @@
 """
-Backend detection utilities for pandas and spark.
+    File with a function to check the backend being used
 """
 import importlib