def plot_emp_dist(dist_type, emp_dist, colname, fpath):
'''Plot a CDF or CCDF'''
fig = PdfPages(fpath + '.pdf')
ax = emp_dist.plot()
if emp_dist.index.values.std() > co.LOGX_LIM:
try:
ax.semilogx()
except:
ax.set_xscale(u'linear')
print 'Data seems not to be heavy-tailed. No log-scaling.'
ax.set_xlabel(printing.get_xlabel( colname ))
ax.set_ylabel(printing.get_ylabel( dist_type ))
fig.savefig()
fig.close()
plt.close()
def plot_rankview(series, fpath):
fig = PdfPages(fpath + '.pdf')
ax = plt.subplot(111)
if type(series) == dict:
for lbl in sorted(series.iterkeys()):
sercpy = pan.Series(series[lbl])
sercpy.sort()
plt.loglog(range(1, len(sercpy) + 1), sercpy[::-1], '-', label=lbl)
del sercpy
ax.legend(loc='best')
elif type(series) == pan.Series:
sercpy = pan.Series(series)
sercpy.sort()
plt.loglog(range(1, len(sercpy) + 1), sercpy[::-1], 'b-')
del sercpy
ax.set_xlabel(printing.get_xlabel( 'rvp' ))
ax.set_ylabel(printing.get_ylabel( 'rvp' ))
fig.savefig()
fig.close()
plt.close()
def plot_df_cdfs(df, fpath, return_plot=False):
fig = PdfPages(fpath + '.pdf')
ax = plt.subplot(111)
logx = False
for col in df.names:
col_cdf = shelp.get_cdf(df[col])
col_cdf.plot(label=col)
if col_cdf.index.values.std() > co.LOGX_LIM:
logx = True
if logx:
ax.semilogx()
ax.set_ylabel(printing.get_ylabel( 'cdf' ))
ax.legend(loc='best')
if return_plot:
return fig
else:
fig.savefig()
fig.close()
plt.close()
def plot_multi_rankview(series, labels, fpath, fig=None):
'''Plot multiple stats_helper.get_cdf()'s
Parameters
----------
cdfs : list of stats_helper.get_cdf()
labels : list of strings
fpath : file path were to save the plot
'''
if fig == None:
fig = PdfPages(fpath + '.pdf')
ax = plt.subplot(111)
for ser, labl in zip(series, labels):
cdf.plot(label=labl)
if cdf.index.values.std() > co.LOGX_LIM:
logx = True
if logx:
ax.semilogx()
ax.set_ylabel(printing.get_ylabel( 'cdf' ))
ax.legend(loc='best')
fig.savefig()
fig.close()
plt.close()
