CLN: Centralised _check_percentile (#27584)

Author: hedonhermdev

pandas/core/algorithms.py

@@ -246,7 +246,6 @@ def _get_hashtable_algo(values):
 
 
 def _get_data_algo(values, func_map):
-
     if is_categorical_dtype(values):
         values = values._values_for_rank()
 
@@ -297,7 +296,6 @@ def match(to_match, values, na_sentinel=-1):
     result = table.lookup(to_match)
 
     if na_sentinel != -1:
-
         # replace but return a numpy array
         # use a Series because it handles dtype conversions properly
         from pandas import Series
@@ -1163,7 +1161,6 @@ def compute(self, method):
 
         # slow method
         if n >= len(self.obj):
-
             reverse_it = self.keep == "last" or method == "nlargest"
             ascending = method == "nsmallest"
             slc = np.s_[::-1] if reverse_it else np.s_[:]

pandas/core/frame.py

@@ -31,7 +31,11 @@
     deprecate_kwarg,
     rewrite_axis_style_signature,
 )
-from pandas.util._validators import validate_axis_style_args, validate_bool_kwarg
+from pandas.util._validators import (
+    validate_axis_style_args,
+    validate_bool_kwarg,
+    validate_percentile,
+)
 
 from pandas.core.dtypes.cast import (
     cast_scalar_to_array,
@@ -8178,7 +8182,7 @@ def quantile(self, q=0.5, axis=0, numeric_only=True, interpolation="linear"):
         C        1 days 12:00:00
         Name: 0.5, dtype: object
         """
-        self._check_percentile(q)
+        validate_percentile(q)
 
         data = self._get_numeric_data() if numeric_only else self
         axis = self._get_axis_number(axis)

pandas/core/generic.py

@@ -32,7 +32,11 @@
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import Appender, Substitution, rewrite_axis_style_signature
-from pandas.util._validators import validate_bool_kwarg, validate_fillna_kwargs
+from pandas.util._validators import (
+    validate_bool_kwarg,
+    validate_fillna_kwargs,
+    validate_percentile,
+)
 
 from pandas.core.dtypes.common import (
     ensure_int64,
@@ -10168,7 +10172,7 @@ def describe(self, percentiles=None, include=None, exclude=None):
             percentiles = list(percentiles)
 
             # get them all to be in [0, 1]
-            self._check_percentile(percentiles)
+            validate_percentile(percentiles)
 
             # median should always be included
             if 0.5 not in percentiles:
@@ -10272,21 +10276,6 @@ def describe_1d(data):
         d.columns = data.columns.copy()
         return d
 
-    def _check_percentile(self, q):
-        """
-        Validate percentiles (used by describe and quantile).
-        """
-
-        msg = "percentiles should all be in the interval [0, 1]. Try {0} instead."
-        q = np.asarray(q)
-        if q.ndim == 0:
-            if not 0 <= q <= 1:
-                raise ValueError(msg.format(q / 100.0))
-        else:
-            if not all(0 <= qs <= 1 for qs in q):
-                raise ValueError(msg.format(q / 100.0))
-        return q
-
     _shared_docs[
         "pct_change"
     ] = """

pandas/core/series.py

@@ -16,7 +16,7 @@
 from pandas.compat import PY36
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender, Substitution, deprecate
-from pandas.util._validators import validate_bool_kwarg
+from pandas.util._validators import validate_bool_kwarg, validate_percentile
 
 from pandas.core.dtypes.common import (
     _is_unorderable_exception,
@@ -2317,7 +2317,7 @@ def quantile(self, q=0.5, interpolation="linear"):
         dtype: float64
         """
 
-        self._check_percentile(q)
+        validate_percentile(q)
 
         # We dispatch to DataFrame so that core.internals only has to worry
         #  about 2D cases.

pandas/util/_validators.py

@@ -2,8 +2,11 @@
 Module that contains many useful utilities
 for validating data or function arguments
 """
+from typing import Iterable, Union
 import warnings
 
+import numpy as np
+
 from pandas.core.dtypes.common import is_bool
 
 
@@ -370,3 +373,35 @@ def validate_fillna_kwargs(value, method, validate_scalar_dict_value=True):
         raise ValueError("Cannot specify both 'value' and 'method'.")
 
     return value, method
+
+
+def validate_percentile(q: Union[float, Iterable[float]]) -> np.ndarray:
+    """
+    Validate percentiles (used by describe and quantile).
+
+    This function checks if the given float oriterable of floats is a valid percentile
+    otherwise raises a ValueError.
+
+    Parameters
+    ----------
+    q: float or iterable of floats
+        A single percentile or an iterable of percentiles.
+
+    Returns
+    -------
+    ndarray
+        An ndarray of the percentiles if valid.
+
+    Raises
+    ------
+    ValueError if percentiles are not in given interval([0, 1]).
+    """
+    msg = "percentiles should all be in the interval [0, 1]. Try {0} instead."
+    q_arr = np.asarray(q)
+    if q_arr.ndim == 0:
+        if not 0 <= q_arr <= 1:
+            raise ValueError(msg.format(q_arr / 100.0))
+    else:
+        if not all(0 <= qs <= 1 for qs in q_arr):
+            raise ValueError(msg.format(q_arr / 100.0))
+    return q_arr