Fix merge conflict

RELEASE.rst

@@ -30,6 +30,7 @@ pandas 0.8.1
 **New features**
 
   - Can pass dict of per-column line styles to DataFrame.plot (#1559)
+  - Add new ``bootstrap_plot`` function
 
 **Improvements to existing features**
 
@@ -43,6 +44,7 @@ pandas 0.8.1
   - Fix resampling bug to lower case daily frequency (#1588)
   - Fix kendall/spearman DataFrame.corr bug with no overlap (#1595)
   - Fix bug in DataFrame.set_index (#1592)
+  - Don't ignore axes in boxplot if by specified (#1565)
 
 pandas 0.8.0
 ============

doc/source/visualization.rst

@@ -300,6 +300,27 @@ of the same class will usually be closer together and form larger structures.
    @savefig andrews_curves.png width=6in
    andrews_curves(data, 'Name')
 
+Parallel Coordinates
+~~~~~~~~~~~~~~~~~~~~
+
+Parallel coordinates is a plotting technique for plotting multivariate data.
+It allows one to see clusters in data and to estimate other statistics visually.
+Using parallel coordinates points are represented as connected line segments.
+Each vertical line represents one attribute. One set of connected line segments
+represents one data point. Points that tend to cluster will appear closer together.
+
+.. ipython:: python
+
+   from pandas import read_csv
+   from pandas.tools.plotting import parallel_coordinates
+
+   data = read_csv('data/iris.data')
+
+   plt.figure()
+
+   @savefig parallel_coordinates.png width=6in
+   parallel_coordinates(data, 'Name')
+
 Lag Plot
 ~~~~~~~~
 

pandas/tests/test_graphics.py

@@ -319,6 +319,14 @@ def test_andrews_curves(self):
         df = read_csv(path)
         _check_plot_works(andrews_curves, df, 'Name')
 
+    @slow
+    def test_parallel_coordinates(self):
+        from pandas import read_csv
+        from pandas.tools.plotting import parallel_coordinates
+        path = os.path.join(curpath(), 'data/iris.csv')
+        df = read_csv(path)
+        _check_plot_works(parallel_coordinates, df, 'Name')
+
     @slow
     def test_plot_int_columns(self):
         df = DataFrame(np.random.randn(100, 4)).cumsum()

pandas/tools/plotting.py

@@ -251,6 +251,53 @@ def bootstrap_plot(series, fig=None, size=50, samples=500, **kwds):
         plt.setp(axis.get_yticklabels(), fontsize=8)
     return fig
 
+def parallel_coordinates(data, class_column, cols=None, ax=None, **kwds):
+    """Parallel coordinates plotting.
+
+    Parameters:
+    -----------
+    data: A DataFrame containing data to be plotted
+    class_column: Column name containing class names
+    cols: A list of column names to use, optional
+    ax: matplotlib axis object, optional
+    kwds: A list of keywords for matplotlib plot method
+
+    Returns:
+    --------
+    ax: matplotlib axis object
+    """
+    import matplotlib.pyplot as plt
+    import random
+    def random_color(column):
+        random.seed(column)
+        return [random.random() for _ in range(3)]
+    n = len(data)
+    classes = set(data[class_column])
+    class_col = data[class_column]
+    if cols == None:
+        columns = [data[col] for col in data.columns if (col != class_column)]
+    else:
+        columns = [data[col] for col in cols]
+    used_legends = set([])
+    x = range(len(columns))
+    if ax == None:
+        ax = plt.gca()
+    for i in range(n):
+        row = [columns[c][i] for c in range(len(columns))]
+        y = row
+        label = None
+        if str(class_col[i]) not in used_legends:
+            label = str(class_col[i])
+            used_legends.add(label)
+        ax.plot(x, y, color=random_color(class_col[i]), label=label, **kwds)
+    for i, col in enumerate(columns):
+        ax.axvline(i, linewidth=1, color='black')
+    ax.set_xticks(range(len(columns)))
+    ax.set_xticklabels([col for col in data.columns if col != class_column])
+    ax.legend(loc='upper right')
+    ax.grid()
+    return ax
+
 def lag_plot(series, ax=None, **kwds):
     """Lag plot for time series.