BUG: cut/qcut bin formatting bugs. close #1979

RELEASE.rst

@@ -47,6 +47,7 @@ pandas 0.9.1
 
 **Bug fixes**
 
+  - Fix bar plot color cycle issues (#2082)
   - Implement comparisons on date offsets with fixed delta (#2078)
   - Handle inf/-inf correctly in read_* parser functions (#2041)
   - Fix matplotlib unicode interaction bug
@@ -66,6 +67,7 @@ pandas 0.9.1
   - Don't lose index names in Panel.to_frame/DataFrame.to_panel (#2163)
   - Work around length-0 boolean indexing NumPy bug (#2096)
   - Fix partial integer indexing bug in DataFrame.xs (#2107)
+  - Fix variety of cut/qcut string-bin formatting bugs (#1978, #1979)
 
 pandas 0.9.0
 ============

pandas/tools/tests/test_tile.py

@@ -1,3 +1,4 @@
+import os
 import nose
 import unittest
 
@@ -180,6 +181,43 @@ def test_label_formatting(self):
 
         result = cut(np.arange(11.) / 1e10, 2)
 
+        # #1979, negative numbers
+
+        result = tmod._format_label(-117.9998, precision=3)
+        self.assertEquals(result, '-118')
+        result = tmod._format_label(117.9998, precision=3)
+        self.assertEquals(result, '118')
+
+
+    def test_qcut_binning_issues(self):
+        # #1978, 1979
+        path = os.path.join(curpath(), 'cut_data.csv')
+
+        arr = np.loadtxt(path)
+
+        result = qcut(arr, 20)
+
+        starts = []
+        ends = []
+        for lev in result.levels:
+            s, e = lev[1:-1].split(',')
+
+            self.assertTrue(s != e)
+
+            starts.append(float(s))
+            ends.append(float(e))
+
+        for (sp, sn), (ep, en) in zip(zip(starts[:-1], starts[1:]),
+                                      zip(ends[:-1], ends[1:])):
+            self.assertTrue(sp < sn)
+            self.assertTrue(ep < en)
+            self.assertTrue(ep <= sn)
+
+def curpath():
+    pth, _ = os.path.split(os.path.abspath(__file__))
+    return pth
+
+
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__,'-vvs','-x','--pdb', '--pdb-failure'],
                    exit=False)

pandas/tools/tile.py

@@ -157,15 +157,18 @@ def _bins_to_cuts(x, bins, right=True, labels=None, retbins=False,
 
     if labels is not False:
         if labels is None:
-            fmt = lambda v: _format_label(v, precision=precision)
-            if right:
-                levels = ['(%s, %s]' % (fmt(a), fmt(b))
-                           for a, b in zip(bins, bins[1:])]
-                if include_lowest:
-                    levels[0] = '[' + levels[0][1:]
-            else:
-                levels = ['[%s, %s)' % (fmt(a), fmt(b))
-                           for a, b in zip(bins, bins[1:])]
+            increases = 0
+            while True:
+                try:
+                    levels = _format_levels(bins, precision, right=right,
+                                            include_lowest=include_lowest)
+                except ValueError:
+                    increases += 1
+                    precision += 1
+                    if increases >= 20:
+                        raise
+                else:
+                    break
 
         else:
             if len(labels) != len(bins) - 1:
@@ -187,6 +190,29 @@ def _bins_to_cuts(x, bins, right=True, labels=None, retbins=False,
 
     return fac, bins
 
+def _format_levels(bins, prec, right=True,
+                   include_lowest=False):
+    fmt = lambda v: _format_label(v, precision=prec)
+    if right:
+        levels = []
+        for a, b in zip(bins, bins[1:]):
+            fa, fb = fmt(a), fmt(b)
+
+            if a != b and fa == fb:
+                raise ValueError('precision too low')
+
+            formatted = '(%s, %s]' % (fa, fb)
+
+            levels.append(formatted)
+
+        if include_lowest:
+            levels[0] = '[' + levels[0][1:]
+    else:
+        levels = ['[%s, %s)' % (fmt(a), fmt(b))
+                   for a, b in zip(bins, bins[1:])]
+
+    return levels
+
 
 def _format_label(x, precision=3):
     fmt_str = '%%.%dg' % precision
@@ -196,6 +222,14 @@ def _format_label(x, precision=3):
         whole = abs(whole)
         if frac != 0.0:
             val = fmt_str % frac
+
+            # rounded up or down
+            if '.' not in val:
+                if x < 0:
+                    return '%d' % (-whole - 1)
+                else:
+                    return '%d' % (whole + 1)
+
             if 'e' in val:
                 return _trim_zeros(fmt_str % x)
             else:

setup.py

@@ -655,6 +655,7 @@ def srcpath(name=None, suffix='.pyx', subdir='src'):
                                    'tests/*.xls',
                                    'tests/*.xlsx',
                                    'tests/*.table'],
+                    'pandas.tools': ['tests/*.csv'],
                     'pandas.tests' : ['data/*.pickle',
                                       'data/*.csv'],
                     'pandas.tseries.tests' : ['data/*.pickle',