Merge branch 'master' of git://github.com/pydata/pandas into panelnd

Author: jreback

.travis.yml

@@ -1,14 +1,12 @@
 language: python
 
 python:
-  - 2.5
   - 2.6
   - 2.7
   - 3.1
   - 3.2
 
 install:
-  - "if [[ $TRAVIS_PYTHON_VERSION == '2.5' ]]; then pip install --use-mirrors simplejson; fi"
   - pip install --use-mirrors cython numpy nose pytz python-dateutil
 
 script:

RELEASE.rst

@@ -25,7 +25,7 @@ Where to get it
 pandas 0.9.1
 ============
 
-**Release date:** NOT YET RELEASED
+**Release date:** 2012-11-14
 
 **New features**
 
@@ -102,6 +102,15 @@ pandas 0.9.1
     e.g. DataFrame.index (#2200)
   - Fix conversion of mixed-type DataFrame to ndarray with dup columns (#2236)
   - Fix duplicate columns issue (#2218, #2219)
+  - Fix SparseSeries.__pow__ issue with NA input (#2220)
+  - Fix icol with integer sequence failure (#2228)
+  - Fixed resampling tz-aware time series issue (#2245)
+  - SparseDataFrame.icol was not returning SparseSeries (#2227, #2229)
+  - Enable ExcelWriter to handle PeriodIndex (#2240)
+  - Fix issue constructing DataFrame from empty Series with name (#2234)
+  - Use console-width detection in interactive sessions only (#1610)
+  - Fix parallel_coordinates legend bug with mpl 1.2.0 (#2237)
+  - Make tz_localize work in corner case of empty Series (#2248)
 
 pandas 0.9.0
 ============

doc/source/v0.9.1.txt

@@ -1,7 +1,7 @@
 .. _whatsnew_0901:
 
-v0.9.1 (November 8, 2012)
--------------------------
+v0.9.1 (November 14, 2012)
+--------------------------
 
 This is a bugfix release from 0.9.0 and includes several new features and
 enhancements along with a large number of bug fixes. The new features include
@@ -42,14 +42,44 @@ New features
   - DataFrame has new `where` and `mask` methods to select values according to a
     given boolean mask (GH2109_, GH2151_)
 
-    .. ipython:: python
+	DataFrame currently supports slicing via a boolean vector the same length as the DataFrame (inside the `[]`).
+	The returned DataFrame has the same number of columns as the original, but is sliced on its index.
+
+        .. ipython:: python
+
+    	    df = DataFrame(np.random.randn(5, 3), columns = ['A','B','C'])
+
+	    df
+
+	    df[df['A'] > 0]
+
+	If a DataFrame is sliced with a DataFrame based boolean condition (with the same size as the original DataFrame),
+	then a DataFrame the same size (index and columns) as the original is returned, with
+	elements that do not meet the boolean condition as `NaN`. This is accomplished via
+	the new method `DataFrame.where`. In addition, `where` takes an optional `other` argument for replacement.
+
+	.. ipython:: python
+
+	   df[df>0]
+	
+	   df.where(df>0)
+
+	   df.where(df>0,-df)
+
+	Furthermore, `where` now aligns the input boolean condition (ndarray or DataFrame), such that partial selection
+	with setting is possible. This is analagous to partial setting via `.ix` (but on the contents rather than the axis labels)
+
+	.. ipython:: python
 
-        df = DataFrame(np.random.randn(5, 3))
+	   df2 = df.copy()
+   	   df2[ df2[1:4] > 0 ] = 3
+	   df2
 
-        df.where(df > 0, -df)
+	`DataFrame.mask` is the inverse boolean operation of `where`.
 
-        df.mask(df < 0)
+	.. ipython:: python
 
+	   df.mask(df<=0)
 
   - Enable referencing of Excel columns by their column names (GH1936_)
 

pandas/core/common.py

@@ -1073,6 +1073,14 @@ def _concat_compat(to_concat, axis=0):
     else:
         return np.concatenate(to_concat, axis=axis)
 
+def in_interactive_session():
+    """ check if we're running in an interactive shell
+
+    returns True if running under python/ipython interactive shell
+    """
+    import __main__ as main
+    return not hasattr(main, '__file__')
+
 # Unicode consolidation
 # ---------------------
 #

pandas/core/frame.py

@@ -321,6 +321,7 @@ class DataFrame(NDFrame):
     _auto_consolidate = True
     _verbose_info = True
     _het_axis = 1
+    _col_klass = Series
 
     _AXIS_NUMBERS = {
         'index': 0,
@@ -581,13 +582,15 @@ def _need_info_repr_(self):
         else:
             # save us
             if (len(self.index) > max_rows or
-                len(self.columns) > terminal_width // 2):
+                (com.in_interactive_session() and
+                len(self.columns) > terminal_width // 2)):
                 return True
             else:
                 buf = StringIO()
                 self.to_string(buf=buf)
                 value = buf.getvalue()
-                if max([len(l) for l in value.split('\n')]) > terminal_width:
+                if (max([len(l) for l in value.split('\n')]) > terminal_width and
+                    com.in_interactive_session()):
                     return True
                 else:
                     return False
@@ -1179,8 +1182,12 @@ def _helper_csvexcel(self, writer, na_rep=None, cols=None,
                 encoded_cols = list(cols)
                 writer.writerow(encoded_cols)
 
-        nlevels = getattr(self.index, 'nlevels', 1)
-        for j, idx in enumerate(self.index):
+        data_index = self.index
+        if isinstance(self.index, PeriodIndex):
+            data_index = self.index.to_timestamp()
+
+        nlevels = getattr(data_index, 'nlevels', 1)
+        for j, idx in enumerate(data_index):
             row_fields = []
             if index:
                 if nlevels == 1:
@@ -1726,10 +1733,22 @@ def icol(self, i):
         else:
             label = self.columns[i]
             if isinstance(label, Index):
-                return self.reindex(columns=label)
+                if self.columns.inferred_type == 'integer':
+                    # XXX re: #2228
+                    return self.reindex(columns=label)
+                else:
+                    return self.ix[:, i]
 
             values = self._data.iget(i)
-            return Series.from_array(values, index=self.index, name=label)
+            if hasattr(self,'default_fill_value'):
+                s = self._col_klass.from_array(values, index=self.index,
+                                               name=label,
+                                               fill_value= self.default_fill_value)
+            else:
+                s = self._col_klass.from_array(values, index=self.index,
+                                               name=label)
+
+            return s
 
     def _ixs(self, i, axis=0):
         if axis == 0:
@@ -5079,6 +5098,9 @@ def extract_index(data):
 
 def _prep_ndarray(values, copy=True):
     if not isinstance(values, np.ndarray):
+        if len(values) == 0:
+            return np.empty((0, 0), dtype=object)
+
         arr = np.asarray(values)
         # NumPy strings are a pain, convert to object
         if issubclass(arr.dtype.type, basestring):
@@ -5091,11 +5113,7 @@ def _prep_ndarray(values, copy=True):
             values = values.copy()
 
     if values.ndim == 1:
-        N = values.shape[0]
-        if N == 0:
-            values = values.reshape((values.shape[0], 0))
-        else:
-            values = values.reshape((values.shape[0], 1))
+        values = values.reshape((values.shape[0], 1))
     elif values.ndim != 2:
         raise Exception('Must pass 2-d input')
 

pandas/core/series.py

@@ -110,7 +110,10 @@ def na_op(x, y):
                 y = lib.list_to_object_array(y)
 
             if isinstance(y, np.ndarray):
-                result = lib.vec_compare(x, y, op)
+                if y.dtype != np.object_:
+                    result = lib.vec_compare(x, y.astype(np.object_), op)
+                else:
+                    result = lib.vec_compare(x, y, op)
             else:
                 result = lib.scalar_compare(x, y, op)
         else:
@@ -2753,7 +2756,15 @@ def tz_localize(self, tz, copy=True):
         -------
         localized : TimeSeries
         """
-        new_index = self.index.tz_localize(tz)
+        from pandas.tseries.index import DatetimeIndex
+
+        if not isinstance(self.index, DatetimeIndex):
+            if len(self.index) > 0:
+                raise Exception('Cannot tz-localize non-time series')
+
+            new_index = DatetimeIndex([], tz=tz)
+        else:
+            new_index = self.index.tz_localize(tz)
 
         new_values = self.values
         if copy: