Maybe this will help:
import pickle as pkl
import matplotlib.pyplot as plt
import numpy as np
class Data_set(object):
def __init__(self, x=[], y=[], name='data', pklfile=None,
figure=None, axes=None):
"""
"""
if pklfile is None:
self.x = np.asarray(x)
self.y = np.asarray(y)
self.name = str(name)
else:
self.unpickle(pklfile)
self.fig = figure
self.ax = axes
self.bar = None
def plot(self, width=0, offset=0, figure=None, axes=None):
if self.fig is None:
if figure is None:
self.fig = plt.figure()
self.ax = self.fig.subplots(1, 1)
else:
self.fig = figure
if axes is None:
self.ax = self.fig.subplots(1, 1)
else:
self.ax = axes
# maybe there's no need to keep track of self.fig, .ax and .bar,
# but just in case...
if figure is not None:
fig_to_use = figure
if axes is not None:
ax_to_use = axes
else:
ax_to_use = fig_to_use.subplots(1, 1)
else:
fig_to_use = self.fig
ax_to_use = self.ax
if not width:
width = (self.x[1]-self.x[0]) / 2.
self.bar = ax_to_use.bar(x=self.x+offset, height=self.y, width=width)
return fig_to_use, ax_to_use, self.bar
def pickle(self, filename='', ext='.pkl'):
if filename == '':
filename = self.name
with open(filename+ext, 'w') as output_file:
pkl.dump((self.name, self.x, self.y), output_file)
def unpickle(self, filename='', ext='.pkl'):
if filename == '':
filename = self.name
with open(filename + ext, 'r') as input_file:
# the name should really come from the filename, but then the
# above would be confusing?
self.name, self.x, self.y = pkl.load(input_file)
class Data_set_manager(object):
def __init__(self, datasets={}):
self.datasets = datasets
def add_dataset(self, data_set):
self.datasets[data_set.name] = data_set
def add_dataset_from_file(self, filename, ext='.pkl'):
self.datasets[filename] = Data_set(name=filename)
self.datasets[filename].unpickle(filename=filename, ext=ext)
def compare(self, width=0, offset=0, *args):
self.fig = plt.figure()
self.ax = self.fig.subplots(1, 1)
if len(args) == 0:
args = self.datasets.keys()
args.sort()
n = len(args)
if n == 0:
return None, None
if width == 0:
min_dx = None
for dataset in self.datasets.values():
sorted_x = dataset.x.copy()
sorted_x.sort()
try:
new_min_dx = np.min(dataset.x[1:] - dataset.x[:-1])
except ValueError:
# zero-size array to reduction operation minimum which
# has no identity (empty array)
new_min_dx = None
if new_min_dx < min_dx or min_dx is None:
min_dx = new_min_dx
if min_dx is None:
min_dx = 1.
width = float(min_dx) / (n + 1)
offset = float(min_dx) / (n + 1)
offsets = offset*np.arange(n)
if n % 2 == 0:
offsets -= offsets[n/2] - offset/2.
else:
offsets -= offsets[n/2]
i = 0
for name in args:
self.datasets.get(name, Data_set()).plot(width=width,
offset=offsets[i],
figure=self.fig,
axes=self.ax)
i += 1
self.ax.legend(args)
return self.fig, self.ax
if __name__ == "__main__":
# test saving/loading
name = 'test'
to_pickle = Data_set(x=np.arange(10),
y=np.random.rand(10),
name=name)
to_pickle.pickle()
unpickled = Data_set(pklfile=name)
print unpickled.name == to_pickle.name
# test comparison
blorg = Data_set_manager({})
x_step = 1.
n_bars = 4 # also try an odd number
for n in range(n_bars):
blorg.add_dataset(Data_set(x=x_step * np.arange(n_bars),
y=np.random.rand(n_bars),
name='teste' + str(n)))
fig, ax = blorg.compare()
fig.show()
It should work with both even and odd number of bars:
And as long as you keep a record of the names you've used (tip:look in the folder where you are saving them) you can reload the data and compare it with the new one.
More checks could be made (to make sure the file exists, that the x axis is something that can be subtracted before trying to do so, etc.), and it could also use some documentation and proper testing - but this should do in a hurry.
