added file plotting function

jdh2358 · jdh2358 · commit f8164611e97d · 2007-06-08T14:40:52.000Z
svn path=/trunk/matplotlib/; revision=3374
diff --git a/CHANGELOG b/CHANGELOG
@@ -1,3 +1,6 @@
+2007-06-08 Added gnuplot file plotfile function to pylab -- see
+           examples/plotfile_demo.py - JDH
+
 2007-06-07 Disable build of numarray and Numeric extensions for
            internal MPL use and the numerix layer. - ADS
 
diff --git a/examples/plotfile_demo.py b/examples/plotfile_demo.py
@@ -0,0 +1,22 @@
+from pylab import plotfile, show
+
+fname = 'data/msft.csv'    
+
+# test 1; use ints
+plotfile(fname, (0,5,6))
+
+# test 2; use names
+plotfile(fname, ('date', 'volume', 'adj_close'))
+
+# test 3; use semilogy for volume
+plotfile(fname, ('date', 'volume', 'adj_close'), plotfuncs={'volume': 'semilogy'})
+
+# test 4; use semilogy for volume
+plotfile(fname, (0,5,6), plotfuncs={5:'semilogy'})
+
+# test 5; use bar for volume
+plotfile(fname, (0,5,6), plotfuncs={5:'bar'})
+
+show()
+
+
diff --git a/lib/matplotlib/mlab.py b/lib/matplotlib/mlab.py
@@ -1358,7 +1358,7 @@ def load(fname,comments='#',delimiter=None, converters=None,skiprows=0,
     if unpack: return transpose(X)
     else:  return X
 
-def csv2rec(fname, comments='#', skiprows=0, checkrows=1):
+def csv2rec(fname, comments='#', skiprows=0, checkrows=5, delimiter=','):
     """
     Load ASCII data from fname into a numpy recarray and return the
     numpy recarray.
@@ -1389,7 +1389,7 @@ def csv2rec(fname, comments='#', skiprows=0, checkrows=1):
     
     
     fh = to_filehandle(fname)
-    reader = csv.reader(fh)
+    reader = csv.reader(fh, delimiter=delimiter)
 
     def process_skiprows(reader):
         if skiprows:
@@ -1399,18 +1399,23 @@ def process_skiprows(reader):
         return fh, reader
 
     process_skiprows(reader)
-    
+
+
+
     def get_func(item, func):
         # promote functions in this order
-        funcmap = {None:int, int:float, float:parsedate, parsedate:str}
+        funcmap = {int:float, float:dateutil.parser.parse, dateutil.parser.parse:str}
         try: func(item)
-        except: return funcmap[func]
-        else: return func
-    
+        except:
+            if func==str:
+                raise ValueError('Could not find a working conversion function')
+            else: return get_func(item, funcmap[func])    # recurse
+        else: return func     
 
 
     def get_converters(reader):
 
+        converters = None
         for i, row in enumerate(reader):
             if i==0:
                 converters = [int]*len(row)
@@ -1429,14 +1434,19 @@ def get_converters(reader):
     delete.add('"')
 
     names = []
+    
     for i, item in enumerate(header):
         item = item.strip().lower().replace(' ', '_')
         item = ''.join([c for c in item if c not in delete])
+        if not len(item):
+            item = 'column%d'%i
         names.append(item)
         
     # get the converter functions by inspecting checkrows
     converters = get_converters(reader)
-
+    if converters is None:
+        raise ValueError('Could not find any valid data in CSV file')
+    
     # reset the reader and start over
     fh.seek(0)
     process_skiprows(reader)
diff --git a/lib/matplotlib/pylab.py b/lib/matplotlib/pylab.py
@@ -213,6 +213,11 @@
 from artist import getp, get
 from artist import setp as _setp
 
+
+
+import matplotlib.cbook as cbook
+from matplotlib.mlab import csv2rec
+
 # a hack to keep old versions of ipython working with mpl after bug
 # fix #1209354
 if 'IPython.Shell' in  sys.modules:
@@ -1500,6 +1505,103 @@ def box(on=None):
     ax.set_frame_on(on)
     draw_if_interactive()
 
+
+
+
+def plotfile(fname, cols=(0,), plotfuncs=None,
+             comments='#', skiprows=0, checkrows=5, delimiter=',',
+             **kwargs):
+    """
+    plot the data in fname
+
+    cols is a sequence of column identifiers to plot.  An identifier
+    is either an int or a string.  if it is an int, it indicates the
+    column number.  If it is a string, it indicates the column header.
+    mpl will make column headers lower case, replace spaces with
+    strings, and remove all illegal characters; so 'Adj Close*' will
+    have name 'adj_close'
+
+    if len(cols)==1, only that column will be plotted on the y axis.
+    if len(cols)>1, the first element will be an identifier for data
+    for the x axis and the remaining elements will be the column
+    indexes for multiple subplots
+
+    plotfuncs, if not None, is a dictionary mapping identifier to an
+    Axes plotting function as a string.  Default is 'plot', other
+    choices are 'semilogy', 'fill', 'bar', etc...  You must use the
+    same type of identifier in the cols vector as you use in the
+    plotfuncs dictionary, eg integer column numbers in both or column
+    names in both.
+
+    comments, skiprows, checkrows, and delimiter are all passed on to
+    matplotlib.mlab.csv2rec to load the data into a record array
+
+    kwargs are passed on to plotting functions
+
+    Example usage:
+
+      # plot the 2nd and 4th column against the 1st in two subplots
+      plotfile(fname, (0,1,3))  
+
+      # plot using column names; specify an alternate plot type for volume
+      plotfile(fname, ('date', 'volume', 'adj_close'), plotfuncs={'volume': 'semilogy'})
+    """
+
+    fig = figure()
+    if len(cols)<1:
+        raise ValueError('must have at least one column of data')
+
+    if plotfuncs is None:
+        plotfuncs = dict()
+    r = csv2rec(fname, comments=comments,
+                skiprows=skiprows, checkrows=checkrows, delimiter=delimiter)
+
+    def getname_val(identifier):
+        'return the name and column data for identifier'
+        if cbook.is_string_like(identifier):
+            return identifier, r[identifier]
+        elif cbook.is_numlike(identifier):            
+            name = r.dtype.names[int(identifier)]
+            return name, r[name]
+
+
+    xname, x = getname_val(cols[0])
+
+    if len(cols)==1:
+        ax1 = fig.add_subplot(N,1,i)
+        funcname = plotfuncs.get(cols[0], 'plot')
+        func = getattr(ax1, funcname)
+        func(x, **kwargs)
+        ax1.set_xlabel(xname)
+    else:
+        N = len(cols)
+        for i in range(1,N):
+            if i==1:
+                ax = ax1 = fig.add_subplot(N-1,1,i)
+                ax.grid(True)
+            else:
+                ax = fig.add_subplot(N-1,1,i, sharex=ax1)
+                ax.grid(True)
+
+
+            yname, y = getname_val(cols[i])
+
+            funcname = plotfuncs.get(cols[i], 'plot')
+            func = getattr(ax, funcname)
+            
+            func(x, y, **kwargs)
+            ax.set_ylabel(yname)
+            if ax.is_last_row():
+                ax.set_xlabel(xname)
+            else:
+                ax.set_xlabel('')
+
+
+    if xname=='date':
+        fig.autofmt_xdate()
+        
+
+
 ### Deprecated functions:
 def scatter_classic(*args, **kwargs):
     return gca().scatter_classic(*args, **kwargs)
@@ -1511,6 +1613,8 @@ def pcolor_classic(*args, **kwargs):
 if Axes.pcolor_classic.__doc__ is not None:
     pcolor_classic.__doc__ = dedent(Axes.pcolor_classic.__doc__)
 
+
+
 ### Do not edit below this point
 # This function was autogenerated by boilerplate.py.  Do not edit as
 # changes will be lost
