From ed575e7cfd17cd2cf9aa70c1c863798e3d8fc6da Mon Sep 17 00:00:00 2001
From: Marco Biasini <mvbiasini@gmail.com>
Date: Fri, 10 Aug 2012 13:43:54 +0200
Subject: [PATCH] Added percentiles function to table
---
modules/base/pymod/table.py | 39 ++++++++++++++++++++++++++++++++
modules/base/tests/test_table.py | 9 +++++++-
2 files changed, 47 insertions(+), 1 deletion(-)
diff --git a/modules/base/pymod/table.py b/modules/base/pymod/table.py
index 77951c634..dae603fb6 100644
--- a/modules/base/pymod/table.py
+++ b/modules/base/pymod/table.py
@@ -1511,6 +1511,45 @@ class Table(object):
self.AddCol(mean_col_name, 'f', mean_rows)
+ def Percentiles(self, col, nths):
+ """
+ returns the percentiles of column *col* given in *nths*.
+
+ The percentils are calculated as
+
+ .. code-block:: python
+
+ values[min(len(values), int(round(len(values)*p/100+0.5)-1))]
+
+ where values are the sorted values of *col* not equal to none
+ :param: nths: list of percentiles to be calculated. Each percentil is a number
+ between 0 and 100.
+
+ :raises: :class:`TypeError` if column type is ``string``
+ :returns: List of percentils in the same order as given in *nths*
+ """
+ idx = self.GetColIndex(col)
+ col_type = self.col_types[idx]
+ if col_type!='int' and col_type!='float' and col_type!='bool':
+ raise TypeError("Median can only be used on numeric column types")
+
+ for nth in nths:
+ if nth < 0 or nth > 100:
+ raise ValueError("percentiles must be between 0 and 100")
+ vals=[]
+ for v in self[col]:
+ if v!=None:
+ vals.append(v)
+ vals=sorted(vals)
+ if len(vals)==0:
+ return [None]*len(nths)
+ percentiles=[]
+
+ for nth in nths:
+ p=vals[min(len(vals)-1, int(round(len(vals)*nth/100.0+0.5)-1))]
+ percentiles.append(p)
+ return percentiles
+
def Median(self, col):
"""
Returns the median of the given column. Cells with None are ignored. Returns
diff --git a/modules/base/tests/test_table.py b/modules/base/tests/test_table.py
index 13afa0437..b4242473e 100644
--- a/modules/base/tests/test_table.py
+++ b/modules/base/tests/test_table.py
@@ -196,7 +196,14 @@ class TestTable(unittest.TestCase):
self.assertEquals(type(z[0][1]),int)
self.assertEquals(type(z[1][1]),int)
self.assertRaises(ValueError, tab.Zip, 'col5', 'col3')
-
+ def testPercentiles(self):
+ tab = Table(['nums'], 'i')
+ self.assertEqual(tab.Percentiles('nums', [0,100]), [None, None])
+ self.assertRaises(ValueError, tab.Percentiles, 'nums', [101])
+ self.assertRaises(ValueError, tab.Percentiles, 'nums', [-1])
+ for i in (35,15,50,40,20):
+ tab.AddRow([i])
+ self.assertEqual(tab.Percentiles('nums', [0,30,40,100]), [15,20,35,50])
def testTableInitEmpty(self):
'''
empty table
--
GitLab