def SetAxes(legend=False):
f_b = 0.164
f_star = 0.01
err_b = 0.006
err_star = 0.004
f_gas = f_b - f_star
err_gas = np.sqrt(err_b**2 + err_star**2)
plt.axhline(y=f_gas, ls='--', c='k', label='', zorder=-1)
x = np.linspace(.0,2.,1000)
plt.fill_between(x, y1=f_gas - err_gas, y2=f_gas + err_gas, color='k', alpha=0.3, zorder=-1)
plt.text(.6, f_gas+0.006, r'f$_{gas}$', verticalalignment='bottom', size='large')
plt.xlabel(r'r/r$_{vir}$', size='x-large')
plt.ylabel(r'f$_{gas}$ ($<$ r)', size='x-large')
plt.xscale('log')
plt.xticks([1./1.9, 1.33/1.9, 1, 1.5, 2.],[r'r$_{500}$', r'r$_{200}$', 1, 1.5, 2], size='large')
#plt.yticks([.1, .2], ['0.10', '0.20'])
plt.tick_params(length=10, which='major')
plt.tick_params(length=5, which='minor')
plt.xlim([0.4,1.5])
plt.minorticks_on()
if legend:
plt.legend(loc=0, prop={'size':'small'}, markerscale=0.7, numpoints=1, ncol=2)
def plot_twoscales(name, dict_array, xlabel='', ylabel='', title='', linetypes=['b','r','g','k'], labels=[], xlog=None, ylim=None):
plt.clf()
if len(xlabel) > 0:
plt.xlabel(xlabel)
if len(ylabel) > 0:
plt.ylabel(ylabel)
if len(title) > 0:
plt.title(title)
if xlog:
plt.xscale('log', basex=xlog)
if ylim:
plt.ylim(ylim)
ax1 = plt.figure().add_subplot(111)
dicty1 = zip(*sorted(dict_array[0].iteritems()))
dicty2 = zip(*sorted(dict_array[1].iteritems()))
ax1.plot(dicty1[0], dicty1[1], linetypes[0], label=labels[0])
for tl in ax1.get_yticklabels():
tl.set_color(linetypes[0])
ax1.set_ylabel(labels[0], color=linetypes[0])
ax2 = ax1.twinx()
ax2.plot(dicty2[0], dicty2[1], linetypes[1], label=labels[1])
for tl in ax2.get_yticklabels():
tl.set_color(linetypes[1])
ax2.set_ylabel(labels[1], color=linetypes[1])
plt.savefig('%s.eps' % name)
def _scatter(actual, prediction, args):
plt.figure()
plt.plot(actual, prediction, 'b'+args['plot_scatter_marker'])
xmin=min(actual)
xmax=max(actual)
ymin=min(prediction)
ymax=max(prediction)
diagxmin=min(math.fabs(x) for x in actual)
diagymin=min(math.fabs(y) for y in prediction)
diagpmin=min(diagxmin,diagymin)
pmin=min(xmin,ymin)
pmax=max(xmax,ymax)
plt.plot([diagpmin,pmax],[diagpmin,pmax],'k-')
if args['plot_identifier'] != 'NoName':
plt.title(args['plot_identifier'])
plt.xlabel('Observed')
plt.ylabel('Modeled')
if args['plot_performance_log'] == True:
plt.yscale('log')
plt.xscale('log')
if args['plot_scatter_free'] != True:
plt.axes().set_aspect('equal')
if args['plot_dump'] == True:
pfname=os.path.join(args['plot_dir'],args['plot_identifier']+'_eiger_scatter.pdf')
plt.savefig(pfname,format="pdf")
else:
plt.show()
def create_scatter(datax, datay, x_label, y_label, filename, title=None,
log=False, set_same=False, colors=None,
num_colors=None, color_map=None, xlims=None, ylims=None):
"""Given a set of data, create a scatter plot of the data, optionally
in log format
"""
plt.figure()
plt.grid()
if colors is not None:
plt.scatter(datax, datay, marker='x', c=colors, s=num_colors,
cmap=color_map)
else:
plt.scatter(datax, datay, marker='x')
plt.xlabel(x_label)
plt.ylabel(y_label)
if log:
plt.xscale('log')
if xlims is not None:
plt.xlim(xlims)
if ylims is not None:
plt.ylim(ylims)
if set_same:
ylims = plt.ylim()
plt.xlim(ylims)
if title is not None:
plt.title(title)
plt.tight_layout()
plt.savefig(filename, fmt='pdf')
def plot_figure_commute(file_name):
f = open(file_name)
lines = f.readlines()
lines[0] = lines[0][:-1]
f.close()
probabilities = lines[0].split(" ")
xx = xrange(len(probabilities))
probabilities = [float(x) for x in probabilities]
plt.figure(figsize=(12, 10))
plt.plot(xx, probabilities, label="D(degree > x)")
plt.ylabel('Percentage of vertices which degree> x')
plt.xlabel('Degree')
plt.title("Cumulative function for degrees")
plt.legend(loc='upper right')
name = "results_graphs/"
if file_name == "temp_degrees/cumulative_temp.txt":
name += "ful_cumulative"
else:
name += "good_cumulative"
plt.savefig(name + '.png')
plt.figure(figsize=(12, 10))
plt.plot(xx, probabilities, label="log(D(degree > x))")
plt.legend(loc='upper right')
plt.title("Cumulative function for degrees in log/log coords")
plt.ylabel('Log of percentage of vertices which degree> x')
plt.xlabel('Log of degrees')
plt.xscale('log')
plt.yscale('log')
plt.savefig(name + '_log' + '.png')
def Config(**options):
"""Configures the plot.
Pulls options out of the option dictionary and passes them to
title, xlabel, ylabel, xscale, yscale, xticks, yticks, axis, legend,
and loc.
"""
title = options.get('title', '')
pyplot.title(title)
xlabel = options.get('xlabel', '')
pyplot.xlabel(xlabel)
ylabel = options.get('ylabel', '')
pyplot.ylabel(ylabel)
if 'xscale' in options:
pyplot.xscale(options['xscale'])
if 'xticks' in options:
pyplot.xticks(options['xticks'])
if 'yscale' in options:
pyplot.yscale(options['yscale'])
if 'yticks' in options:
pyplot.yticks(options['yticks'])
if 'axis' in options:
pyplot.axis(options['axis'])
loc = options.get('loc', 0)
legend = options.get('legend', True)
if legend:
pyplot.legend(loc=loc)
def main():
sample='q'
sm_bin='10.0_10.5'
catalogue = 'sm_9.5_s0.2_sfr_c-0.75_250'
#load in fiducial mock
filepath = './'
filename = 'sm_9.5_s0.2_sfr_c-0.8_Chinchilla_250_wp_fiducial_'+sample+'_'+sm_bin+'_cov.npy'
cov = np.matrix(np.load(filepath+filename))
diag = np.diagonal(cov)
filepath = cu.get_output_path() + 'analysis/central_quenching/observables/'
filename = 'sm_9.5_s0.2_sfr_c-0.8_Chinchilla_250_wp_fiducial_'+sample+'_'+sm_bin+'.dat'
data = ascii.read(filepath+filename)
rbins = np.array(data['r'])
mu = np.array(data['wp'])
#load in comparison mock
plt.figure()
plt.errorbar(rbins, mu, yerr=np.sqrt(np.diagonal(cov)), color='black')
plt.plot(rbins, wp, color='red')
plt.xscale('log')
plt.yscale('log')
plt.show()
inv_cov = cov.I
Y = np.matrix((wp-mu))
X = Y*inv_cov*Y.T
print(X)
def t90_dist(self):
""" Plots T90 distribution, gives the mean and median T90 values of the
sample and calculates the number of short, long bursts in the sample """
t90s = []
for i in range(0,len(self.t90s),1):
try:
t90s.append(float(self.t90s[i]))
except ValueError:
continue
t90s = np.array(t90s)
mean_t90 = np.mean(t90s)
median_t90 = np.median(t90s)
print('Mean T90 time =',mean_t90,'s')
print('Median T90 time=',median_t90,'s')
mask = np.ma.masked_where(t90s < 2, t90s)
short_t90s = t90s[mask == False]
long_t90s = t90s[mask != False]
print('Number of Short/Long GRBs =',len(short_t90s),'/',len(long_t90s))
plt.figure()
plt.xlabel('T$_{90}$ (s)')
plt.ylabel('Number of GRBs')
plt.xscale('log')
minimum, maximum, = min(short_t90s), max(long_t90s)
plt.axvline(mean_t90,color='red',linestyle='-')
plt.axvline(median_t90,color='blue',linestyle='-')
plt.hist(t90s,bins= 10**np.linspace(np.log10(minimum),np.log10(maximum),20),color='grey',alpha=0.5)
plt.show()
def fluence_dist(self):
""" Plots the fluence distribution and gives the mean and median fluence
values of the sample """
fluences = []
for i in range(0,len(self.fluences),1):
try:
fluences.append(float(self.fluences[i]))
except ValueError:
continue
fluences = np.array(fluences)
mean_fluence = np.mean(fluences)
median_fluence = np.median(fluences)
print('Mean Fluence =',mean_fluence,'(15-150 keV) [10^-7 erg cm^-2]')
print('Median Fluence =',median_fluence,'(15-150 keV) [10^-7 erg cm^-2]')
plt.figure()
plt.xlabel('Fluence (15-150 keV) [$10^{-7}$ erg cm$^{-2}$]')
plt.ylabel('Number of GRBs')
plt.xscale('log')
minimum, maximum = min(fluences), max(fluences)
plt.axvline(mean_fluence,color='red',linestyle='-')
plt.axvline(median_fluence,color='blue',linestyle='-')
plt.hist(fluences,bins= 10**np.linspace(np.log10(minimum),np.log10(maximum),20),color='grey',alpha=0.5)
plt.show()
def dim_sensitivity_plot(x, Y, fname, show_legend=True):
plt.rc('text', usetex=True)
plt.rc('font', family='serif')
plt.figure(figsize=(3, 3))
plt.xlabel('$d$', size=FONTSIZE)
plt.ylabel('ROC AUC', size=FONTSIZE)
plt.set_cmap('Set2')
lines = []
for i, label in enumerate(KEYS):
line_data = Y.get(label)
if line_data is None:
continue
line, = plt.plot(x, line_data, label=label, marker=MARKERS[i],
markersize=0.5 * FONTSIZE, color=COLORS[i])
lines.append(line)
if show_legend:
plt.legend(handles=lines)
plt.legend(loc='lower right')
plt.xscale('log', basex=2)
plt.xticks(x, [str(y) for y in x], size=FONTSIZE)
plt.yticks(size=FONTSIZE)
plt.tight_layout()
plt.savefig(fname)
def plot_a_func_time(aes, times, which_are_final_bodies=None,year_unit='kyr',title=None):
"""This function takes a list of each individual body's semimajor axes,
which itself can be stored as a list, as well as a list of lists of the
times corresponding to semimajor axes passed with the first argument
and then plots semi-major axis as a function of time for the objects
passed to me.
which_are_final_bodies: pass the index of the final bodies if you want
those lines plotted thicker
"""
year_unit_dict = {"Myr":1.e6,"kyr":1.e3}
fig = pp.figure()
for i in range(len(aes)):
pp.plot(np.divide(times[i],year_unit_dict[year_unit]),aes[i],color='blue',linewidth=0.5)
if which_are_final_bodies != None:
for i in range(len(which_are_final_bodies)):
#print " final body plotting as red: " + str(i)
pp.plot(np.divide(times[which_are_final_bodies[i]],year_unit_dict[year_unit]),aes[which_are_final_bodies[i]],color='red')#,color='blue',linewidth=1.5)
pp.xscale(u'log')
if title != None:
pp.title(title)
pp.xlabel("Time ("+year_unit+")")
pp.ylabel("Semimajor axis (AU)")
return fig
def make_plot(filename, title, arguments, methods, scale):
if not support_plots:
return
is_linear = (scale == 'linear')
plot_size = LINEAR_PLOT_SIZE if is_linear else OTHER_PLOT_SIZE
plt.figure(figsize=plot_size)
for name, func, measures in methods:
plt.plot(arguments, measures, 'o-', label=name, markersize=3)
if is_linear:
axis = plt.axis()
plt.axis((0, axis[1], 0, axis[3]))
plt.xscale(scale)
plt.yscale(scale)
plt.xticks(fontsize=NORMAL_FONT_SIZE)
plt.yticks(fontsize=NORMAL_FONT_SIZE)
plt.grid(True)
plt.title(title, fontsize=LABEL_FONT_SIZE)
plt.xlabel('Argument', fontsize=NORMAL_FONT_SIZE)
plt.ylabel('Time (seconds)', fontsize=NORMAL_FONT_SIZE)
plt.legend(loc='upper left', fontsize=NORMAL_FONT_SIZE)
plt.tight_layout(0.2)
path = os.path.join(PLOTS_DIR, filename)
plt.savefig(path)
print '[*] Saved plot "%s"' % path
def initPlot(name):
plt.xlabel("fppi")
plt.ylabel("miss rate")
plt.title(name)
plt.grid(True)
plt.xscale('log')
plt.yscale('log')
def avgDegree(G):
print "Nodes: ",
print G.number_of_nodes()
print "Edges: ",
print G.number_of_edges()
# avg degree
degrees = defaultdict(int)
total = 0
for node in G.nodes():
neighbors = G.neighbors(node)
degrees[len(neighbors)] += 1
total += len(neighbors)
max_degree = max(degrees.keys())
degrees_arr = (max_degree+1) * [0]
for index, count in degrees.iteritems():
degrees_arr[index] = count
plt.plot(range(max_degree+1), degrees_arr, '.')
plt.xscale('log', basex=2)
plt.xlabel('degree')
plt.yscale('log', basex=2)
plt.ylabel('# of people')
plt.savefig('degree_distribution.png')
plt.close()
def dose_plot(df,err,cols,scale='linear'):
n_rows = int(np.ceil(len(cols)/3.0))
plt.figure(figsize=(20,4 * n_rows))
subs = gridspec.GridSpec(n_rows, 3)
plt.subplots_adjust(hspace=0.54,wspace=0.27)
for col,sub in zip(cols,subs):
plt.subplot(sub)
for base in df['Base'].unique():
for drug in get_drugs_with_multiple_doses(filter_rows(df,'Base',base)):
data = thread_first(df,
(filter_rows,'Drug',drug),
(filter_rows,'Base',base),
(DF.sort, 'Dose'))
error = thread_first(err,
(filter_rows,'Drug',drug),
(filter_rows,'Base',base),
(DF.sort, 'Dose'))
if scale == 'linear':
plt.errorbar(data['Dose'],data[col],yerr=error[col])
title = "{} vs. Dose".format(col)
else:
plt.errorbar(data['Dose'],data[col],yerr=error[col])
plt.xscale('log')
title = "{} vs. Dose (Log Scale)".format(col)
plt.xticks(data['Dose'].values,data['Dose'].values)
plt.xlim(0.06,15)
label('Dose ({})'.format(data.Unit.values[0]), col,title,fontsize = 15)
plt.legend(df['Base'].unique(), loc = 0)
def set_axis_properties(p,metric,varying_parameter,group):
#Set major x-axis label
plt.xlabel(xlabel_names[varying_parameter])
#Set x-axis scale
xscale_args = xscale_arguments[(metric,varying_parameter)]
plt.xscale(xscale_args[0],**xscale_args[1])
#Set x-axis tick labels
#Get tick values
ticks = list(sp.unique(group[varying_parameter]))
#If an item is not in the tick dictionary for the bar plot, add it
if pltkind[(metric,varying_parameter)] is 'bar':
for item in ticks:
if item not in varying_xlabels[varying_parameter].keys():
varying_xlabels[varying_parameter][item] = '$' + str(item) +'$'
xlabels = [ varying_xlabels[varying_parameter][item] for item in ticks]
if pltkind[(metric,varying_parameter)] is 'bar':
p.set_xticks(sp.arange(len(ticks))+0.5)
plt.setp(p.set_xticklabels(xlabels), rotation=0)
else:
plt.xticks(ticks,xlabels)
plt.ylabel(ylabel_names[metric])
plt.grid('on')
def plot_citation_graph(citation_graph, filename, plot_title):
# find the indegree_distribution
indeg_dist = in_degree_distribution(citation_graph)
# sort freq by keys
number_citations = sorted(indeg_dist.keys())
indeg_freq = [indeg_dist[n] for n in number_citations]
# normalize
total = sum(indeg_freq)
indeg_freq_norm = [freq / float(total) for freq in indeg_freq]
# calculate log/log, except for the first one (0)
#log_number_citations = [math.log10(x) for x in number_citations[1:]]
#log_indeg_freq_norm = [math.log10(x) for x in indeg_freq_norm[1:]]
plot(number_citations[1:], indeg_freq_norm[1:], 'o')
xscale("log")
yscale("log")
xlabel("log10 #citations")
ylabel("log10 Norm.Freq.")
title(plot_title)
grid(True)
savefig(filename)
show()
def PlotEDepSummary(gFiles,nFiles,figureName='EDepSummary.png',tParse=GetThickness,
histKey='eDepHist'):
""" PlotEDepSummary
Plotss the energy deposition summary
"""
# Extrating the average values
gT = list()
gDep = list()
gDepError = list()
nT = list()
nDep = list()
nDepError = list()
for fname in gFiles:
f = TFile(fname,'r')
hist = f.Get(histKey)
gT.append(GetThickness(fname))
gDep.append(hist.GetMean())
gDepError.append(hist.GetMeanError())
for fname in nFiles:
f = TFile(fname,'r')
hist = f.Get(histKey)
nT.append(GetThickness(fname))
nDep.append(hist.GetMean())
nDepError.append(hist.GetMeanError())
# Plotting
plt.errorbar(gT,gDep,yerr=gDepError,fmt='r+')
plt.hold(True)
plt.errorbar(nT,nDep,yerr=nDepError,fmt='go')
plt.xlabel("Thickness (mm)")
plt.ylabel("Average Energy Deposition (MeV)")
plt.legend(["Co-60","Cf-252"])
plt.xscale("log")
plt.yscale("log")
plt.grid(True)
plt.savefig(figureName)
def setDiffsPlot(CF,d0,ySym = True):
CFtext = [str(j)+',' for j in CF]
bText = [CFtext[0],r'...,$a_i$+c,...',CFtext[-1]]
CFtext = ''.join(CFtext)
bText= ''.join(bText)
CFtext = '[' + CFtext[:-1] + ']'
bText = '[' + bText[:-1] + ']'
print(CFtext)
plt.ylabel(r'$d^{crit}_b - d^{crit}_a$',fontsize=20)
plt.xlabel(r'Element changed',fontsize=20)
xmin, xmax, ymin, ymax = plt.axis()
if ySym:
plt.yscale('symlog',linthreshy=1e-15)
yLoc = [y*ymax for y in [.1, .01, .001]]
else:
yLoc = [y*(ymax-ymin)+ymin for y in [0.95, 0.85, 0.75]]
plt.plot([0,xmax],[0,0],'k--',label='_')
plt.text((xmax-xmin)*0.15,yLoc[0],r'$a = [a_i] =$'+CFtext,fontsize=15)
plt.text((xmax-xmin)*0.15,yLoc[1],r'$b_i = $'+bText,fontsize=15)
plt.text((xmax-xmin)*0.15,yLoc[2],r'$d_a^{crit} = $'+str(float(d0)),fontsize=15)
plt.legend(loc='best')
plt.xscale('symlog',linthreshx=1e-14)
# plt.yscale('log')
plt.show()
def __save(self, n, plot, sfile):
p.figure(figsize=sfile)
p.xlabel(plot.xlabel)
p.ylabel(plot.ylabel)
p.xscale(plot.xscale)
p.yscale(plot.yscale)
p.grid()
for curvetype, args, kwargs in plot.curves:
if curvetype == "plot":
p.plot(*args, **kwargs)
elif curvetype == "imshow":
p.imshow(*args, **kwargs)
elif curvetype == "hist":
p.hist(*args, **kwargs)
elif curvetype == "bar":
p.bar(*args, **kwargs)
p.axes().set_aspect(plot.aspect)
if plot.legend:
p.legend(shadow=0, loc=plot.loc)
if not os.path.isdir(plot.dir):
os.mkdir(plot.dir)
if plot.pgf:
p.savefig(plot.dir + plot.name + ".pgf")
print(plot.name + ".pgf")
if plot.pdf:
p.savefig(plot.dir + plot.name + ".pdf", bbox_inches="tight")
print(plot.name + ".pdf")
p.close()
def main():
counter = n36.main()
plt.figure()
plt.xscale('log')
plt.yscale('log')
plt.plot(sorted(list(counter.values()), reverse=True), range(1, len(list(counter)) + 1))
plt.savefig('fig39.png')
def nlp39(words):
# Zipfの法則：https://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%83%E3%83%97%E3%81%AE%E6%B3%95%E5%89%87
# 語彙頻度
freq = {}
for word in words:
if word['pos'] == '動詞':
if not word['base'] in freq:
freq[word['base']] = 1
else:
freq[word['base']] += 1
count = 1
x = []
y = []
for word in sorted(freq, key=freq.get, reverse=True):
x.append(count)
y.append(freq[word])
count += 1
plt.xscale('log')
plt.yscale('log')
plt.plot(x, y, 'o')
plt.show()
def make_coefficient_plot(table, positive_words, negative_words, l2_penalty_list):
cmap_positive = plt.get_cmap('Reds')
cmap_negative = plt.get_cmap('Blues')
xx = l2_penalty_list
plt.plot(xx, [0.]*len(xx), '--', lw=1, color='k')
table_positive_words = table.filter_by(column_name='word', values=positive_words)
table_negative_words = table.filter_by(column_name='word', values=negative_words)
del table_positive_words['word']
del table_negative_words['word']
for i in xrange(len(positive_words)):
color = cmap_positive(0.8*((i+1)/(len(positive_words)*1.2)+0.15))
plt.plot(xx, table_positive_words[i:i+1].to_numpy().flatten(),
'-', label=positive_words[i], linewidth=4.0, color=color)
for i in xrange(len(negative_words)):
color = cmap_negative(0.8*((i+1)/(len(negative_words)*1.2)+0.15))
plt.plot(xx, table_negative_words[i:i+1].to_numpy().flatten(),
'-', label=negative_words[i], linewidth=4.0, color=color)
plt.legend(loc='best', ncol=3, prop={'size':16}, columnspacing=0.5)
plt.axis([1, 1e5, -1, 2])
plt.title('Coefficient path')
plt.xlabel('L2 penalty ($\lambda$)')
plt.ylabel('Coefficient value')
plt.xscale('log')
plt.rcParams.update({'font.size': 18})
plt.tight_layout()
def Validation():
numSamples = 1000000
theta = np.random.rand(numSamples)*np.pi
ECo60 = np.array([1.117,1.332])
Ef0,Ee0 = Compton(ECo60[0],theta)
Ef1,Ee1 = Compton(ECo60[1],theta)
dSdE0 = diffXSElectrons(ECo60[0],theta)
dSdE1 = diffXSElectrons(ECo60[1],theta)
# Sampling Values
values = list()
piMax = np.max([dSdE0,dSdE1])
while (len(values) < numSamples):
values.append(SampleRejection(piMax,ComptonScattering))
# Binning the data
bins = np.logspace(-3,0.2,100)
counts = np.histogram(values,bins)
counts = counts[0]/float(len(values))
binCenters = 0.5*(bins[1:]+bins[:-1])
# Plotting
plt.figure()
plt.plot(binCenters,counts,ls='steps')
#plt.bar(binCenters,counts,align='center')
plt.grid(True)
plt.xlim((1E-3,1.4))
plt.xlabel('Electron Energy (MeV)')
plt.ylabel('Frequency per Photon')
plt.yscale('log')
plt.xscale('log')
plt.savefig('ValComptonScatteringXS.png')
def plotCurves(losses,rateOfExceedance,return_periods,lossLevels):
plt.figure(1, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')
plt.scatter(losses,rateOfExceedance,s=20)
if len(return_periods) > 0:
annual_rate_exc = 1.0/np.array(return_periods)
for rate in annual_rate_exc:
if rate > min(rateOfExceedance):
plt.plot([min(losses),max(losses)],[rate,rate],color='red')
plt.annotate('%.6f' % rate,xy=(max(losses),rate),fontsize = 12)
plt.yscale('log')
plt.xscale('log')
plt.ylim([min(rateOfExceedance),1])
plt.xlim([min(losses),max(losses)])
plt.xlabel('Losses', fontsize = 16)
plt.ylabel('Annual rate of exceedance', fontsize = 16)
setReturnPeriods = 1/rateOfExceedance
plt.figure(2, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')
plt.scatter(setReturnPeriods,losses,s=20)
if len(return_periods) > 0:
for period in return_periods:
if period < max(setReturnPeriods):
plt.plot([period,period],[min(losses),max(losses)],color='red')
plt.annotate(str(period),xy=(period,max(losses)),fontsize = 12)
plt.xscale('log')
plt.xlim([min(setReturnPeriods),max(setReturnPeriods)])
plt.ylim([min(losses),max(losses)])
plt.xlabel('Return period (years)', fontsize = 16)
plt.ylabel('Losses', fontsize = 16)
def plot(self, debug = False):
"""plot figures for population, nuisance parameters"""
# first figure out what scheme is used
self.list_scheme()
# next get MABR sampling done
self.MBAR_analysis()
# load in precomputed P and dP from MBAR analysis
pops0, pops1 = self.P_dP[:,0], self.P_dP[:,self.K-1]
dpops0, dpops1 = self.P_dP[:,self.K], self.P_dP[:,2*self.K-1]
t0 = self.traj[0]
t1 = self.traj[self.K-1]
# Figure Plot SETTINGS
label_fontsize = 12
legend_fontsize = 10
fontfamily={'family':'sans-serif','sans-serif':['Arial']}
plt.rc('font', **fontfamily)
# determine number of row and column
if (len(self.scheme)+1)%2 != 0:
c,r = 2, (len(self.scheme)+2)/2
else:
c,r = 2, (len(self.scheme)+1)/2
plt.figure( figsize=(4*c,5*r) )
# Make a subplot in the upper left
plt.subplot(r,c,1)
plt.errorbar( pops0, pops1, xerr=dpops0, yerr=dpops1, fmt='k.')
plt.hold(True)
plt.plot([1e-6, 1], [1e-6, 1], color='k', linestyle='-', linewidth=2)
plt.xlim(1e-6, 1.)
plt.ylim(1e-6, 1.)
plt.xlabel('$p_i$ (exp)', fontsize=label_fontsize)
plt.ylabel('$p_i$ (sim+exp)', fontsize=label_fontsize)
plt.xscale('log')
plt.yscale('log')
# label key states
plt.hold(True)
for i in range(len(pops1)):
if (i==0) or (pops1[i] > 0.05):
plt.text( pops0[i], pops1[i], str(i), color='g' )
for k in range(len(self.scheme)):
plt.subplot(r,c,k+2)
plt.step(t0['allowed_'+self.scheme[k]], t0['sampled_'+self.scheme[k]], 'b-')
plt.hold(True)
plt.xlim(0,5)
plt.step(t1['allowed_'+self.scheme[k]], t1['sampled_'+self.scheme[k]], 'r-')
plt.legend(['exp', 'sim+exp'], fontsize=legend_fontsize)
if self.scheme[k].find('cs') == -1:
plt.xlabel("$\%s$"%self.scheme[k], fontsize=label_fontsize)
plt.ylabel("$P(\%s)$"%self.scheme[k], fontsize=label_fontsize)
plt.yticks([])
else:
plt.xlabel("$\sigma_{%s}$"%self.scheme[k][6:],fontsize=label_fontsize)
plt.ylabel("$P(\sigma_{%s})$"%self.scheme[k][6:],fontsize=label_fontsize)
plt.yticks([])
plt.tight_layout()
plt.savefig(self.picfile)
def plot_netload_cache_size_sensitivity(show=True, save=True):
"""
Plot sensitivity of network load vs cache size
"""
# Parameters
T = TOPOLOGIES
C = C_RANGE
A = ALPHA_C_PLOT
LT = LINK_TYPES
# Execution
for t in T:
for a in [str(al) for al in A]:
for lt in LT:
plt.figure()
plt.title('Network load: LINK=%s T=%s A=%s' % (lt, t, a))
plt.ylabel('Average link load (Mbps)')
plt.xlabel('Cache to population ratio')
plt.xscale('log')
S = SummaryAnalyzer(path.join(SUMMARY_LOG_DIR, 'SUMMARY_NETWORK_LOAD.txt'))
for strategy in NETLOAD_STRATEGIES:
cond = (S.param['T'] == t) & (S.param['A'] == a) & (S.param['S'] == strategy) & (S.data['LinkType'] == lt)
plt.plot(S.param['C'][cond], S.data['NetworkLoad'][cond], style_dict[strategy])
plt.xlim(min(C), max(C))
plt.legend(tuple(netload_legend_list), prop={'size': LEGEND_SIZE}, loc='lower left')
if show: plt.show()
if save: plt.savefig(path.join(GRAPHS_DIR ,'NETLOAD_C_SENS_LT=%s@T=%s@A=%s.pdf' % (lt, t, a)), bbox_inches='tight')
def plot(objects, xscales={}, yscales={}, title=""):
from matplotlib.pyplot import plot, show, close, subplot,\
xscale, yscale, gcf
'''
Plots current state of objects in subplots.
Define xscales and yscales as dict of indexes.
'''
if not isinstance(objects, list):
objects = [objects]
l = len(objects)
first = round(l / 2.0) + 1
second = round(l / 2.0)
for i in range(0, l):
subplot(first, second, i + 1)
if i in xscales:
xscale(xscales[i])
if i in yscales:
yscale(yscales[i])
fig = gcf()
fig.suptitle(title, fontsize="x-large")
values = objects[i].get_y_values()
x, y = values.shape
for j in range(x):
plot(objects[i].get_t_values(), values[j, :])
show()
close()
def pareto_graph(database, objectives=None):
'''Constructs a visualization of the movement of the best front over generations
The argument 'objectives' must be a list indicating the indices of the fitness values to be used.
The first two will be consumed. If the list has less than two elements, or if is not given, the
graph will be produced using the first two fitness values.
'''
if objectives is None or len(objectives) < 2:
objectives = [0, 1]
generations = []
if database.properties['highest_population'] < FRONT_COUNT:
generations = list(range(1, database.properties['highest_population'] + 1))
else:
step = database.properties['highest_population'] / FRONT_COUNT
generations = [round(i * step) for i in range(1, FRONT_COUNT + 1)]
for i, gen in enumerate(generations, start=1):
database.select(gen)
individual_data = [val for key, val in database.load_report().items()
if key.startswith('I') and val['rank'] == 1]
x_values = [val['fitness'][objectives[0]] for val in individual_data]
y_values = [val['fitness'][objectives[1]] for val in individual_data]
plt.plot(x_values, y_values,
color=str((FRONT_COUNT - i) / FRONT_COUNT),
linestyle='None',
marker='o',
markeredgecolor='white')
plt.title('Movement of best front')
plt.xscale('log')
plt.yscale('log')
plt.xlabel(database.properties['objective_names'][objectives[0]])
plt.ylabel(database.properties['objective_names'][objectives[1]])
plt.show()
def check_hod(self, z, prop):
data = np.genfromtxt(LOCATION + "/data/" + prop + "z" + str(z))
if prop == "ncen":
if PLOT:
plt.clf()
plt.plot(self.hod.hmf.M,
self.hod.n_cen,
label="mine")
plt.plot(data[:, 0] * self.hod.cosmo.h, data[:, 1], label="charles")
plt.legend()
plt.xscale('log')
plt.yscale('log')
plt.savefig(join(pref, "ncen" + prop + "z" + str(z) + ".pdf"))
assert max_diff_rel(self.hod.n_cen, data[:, 1], 0.01)
elif prop == "nsat":
if PLOT:
plt.clf()
plt.plot(self.hod.hmf.M,
self.hod.n_sat,
label="mine")
plt.plot(data[:, 0] * self.hod.cosmo.h, data[:, 1], label="charles")
plt.legend()
plt.xscale('log')
plt.yscale('log')
plt.savefig(join(pref, "nsat" + prop + "z" + str(z) + ".pdf"))
assert max_diff_rel(self.hod.n_sat, data[:, 1], 0.01)
def figure11():
original_maze = Maze()
params_prioritized = DynaParams()
params_prioritized.theta = 0.0001
params_prioritized.planning_steps = 5
params_prioritized.alpha = 0.5
params_prioritized.gamma = 0.95
params_dyna = DynaParams()
params_dyna.planning_steps = 5
params_dyna.alpha = 0.5
params_dyna.gamma = 0.95
# track the # of backups
backups = defaultdict(list)
runs = 10
params = [params_dyna,params_dyna]
# set up models for planning
models = [HeuristicModel,TrivialModel]
method_names = ['Focused Dyna','Random Dyna']
# due to limitation of my machine, I can only perform experiments for 5 mazes
# assuming the 1st maze has w * h states, then k-th maze has w * h * k * k states
num_of_mazes = 1
# build all the mazes
mazes = [original_maze.extend_maze(i*2) for i in range(1, num_of_mazes + 1)]
methods = [dyna_h,dyna_q]
for run in tqdm(range(0, runs)):
for i in range(0, len(method_names)):
for mazeIndex, maze in zip(range(0, len(mazes)), mazes):
#print('run %d, %s, maze size %d' % (run, method_names[i], maze.WORLD_HEIGHT * maze.WORLD_WIDTH))
# initialize the state action values
q_value = np.zeros(maze.q_size)
# track steps / backups for each episode
stepss = []
# generate the model
model = models[i]()
# play for an episode
while True:
stepss.append(methods[i](q_value, model, maze, params[i]))
# print best actions w.r.t. current state-action values
# printActions(currentStateActionValues, maze)
# check whether the (relaxed) optimal path is found
if check_path(q_value, maze):
break
# update the total steps / backups for this maze
backups[method_names[i]].extend(stepss)
# Dyna-Q performs several backups per step
for i in method_names:
plt.plot(sorted(backups[i], reverse=True), label=i)
plt.xlabel('Backups')
plt.ylabel('Steps to Goal')
plt.ylim((0, 10000))
plt.xscale('log')
plt.legend()
plt.savefig('figure11.png')
plt.close()
df.rating.hist(bins=30, alpha=0.4)
plt.axvline(meanrat, 0, 0.75, color='r', label='Mean')
plt.xlabel("average rating of book")
plt.ylabel("Counts")
plt.title("Ratings Histogram")
plt.legend()
#sns.despine()
# In[32]:
df.review_count.hist(bins=np.arange(0, 40000, 400))
# In[33]:
df.review_count.hist(bins=100)
plt.xscale("log")
# In[34]:
plt.scatter(df.year, df.rating, lw=0, alpha=.08)
plt.xlim([1900, 2010])
plt.xlabel("Year")
plt.ylabel("Rating")
# In[35]:
alist = [1, 2, 3, 4, 5]
# In[36]:
asquaredlist = [i * i for i in alist]
horizontalalignment='center',
verticalalignment='center',
color=xy_color_dict[xaxis],
backgroundcolor='white')
plt.text(5e5,
5e5 * 0.500,
'2x',
fontsize=14,
horizontalalignment='center',
verticalalignment='center',
color=xy_color_dict[xaxis],
backgroundcolor='white')
# main plot
plt.scatter(df[xvar], df[yvar], s=80, edgecolor='black', facecolor='none')
plt.xscale('log')
plt.yscale('log')
plt.xlabel(xlabel)
plt.ylabel(ylabel)
plt.axis(axis_limits)
# highlight genes
pathway_list = pathway_csv.split(',')
pathway_color = color_csv.split(',')
for i in range(len(pathway_list)):
# get VF list from pathway
gene_list = gene_dict[pathway_list[i]]
# gene colors
gene_color = sns.xkcd_rgb[pathway_color[i]]
plt.scatter(df[xvar][gene_list],
ax.set_xlabel('xyz')
# set x axis range
plt.xlim(0,1)
ax.set_xlim([0., 1])
# x,y axis start from same position
plt.margins(0)
# move x-axis where y=0
pos1 = ax.spines['bottom'].set_position('zero') or
plt.margins(0)
# To shift the tick labels relative to the ticks use pad
ax.tick_params(which='both', direction='out', pad=5)
# set log scale
ax.set_yscale('log')
# turn off minor ticks
plt.minorticks_off()
plt.xscale('log', subsx=[2, 3, 4, 5, 6, 7, 8, 9])
ax.minorticks_off()
############################
#----------marker----------#
############################
# ================ ===============================
# character description
# ================ ===============================
# - solid line style
# -- dashed line style
# -. dash-dot line style
# : dotted line style
# . point marker
# , pixel marker
def timeseries_smooth(adata,
genes='none',
gene_symbols='none',
key='louvain',
groups='all',
style='-b',
n_restarts_optimizer=10,
likelihood_landscape=False,
normalize_y=False,
noise_level=0.5,
noise_level_bounds=(1e-2, 1e+1),
length_scale=1,
length_scale_bounds=(1e-2, 1e+1),
save='none',
title='long'):
"""
Plot a timeseries of some genes in pseudotime
Keyword arguments:
adata -- anndata object
genes -- list of genes. If 'none', the first 5 genes are plotted
gene_symbols -- variable annotation. If 'none', the index is used
key -- observation annotation.
groups -- basically branches, chosen from the annotations in key
style -- line plotting style
"""
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors as colors
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.gaussian_process.kernels import RBF, ConstantKernel as C, WhiteKernel
# select one branch
if groups != 'all':
adata_selected = adata[np.in1d(adata.obs[key], groups)]
else:
adata_selected = adata
# select genes
if genes == 'none':
# no genes specified, we just use the first 5
genes = adata_selected.var_names.values[0:5]
m = {'Mapped': genes, 'Original': genes}
elif gene_symbols != 'none':
# a gene annotation is used, we map the gene names
mapping_table = pd.DataFrame(adata_selected.var[gene_symbols])
name_mapping = mapping_table.set_index(gene_symbols)
name_mapping['Ensembl'] = mapping_table.index
genes_mapped = name_mapping.loc[genes, :]
# save in dict
m = {'Mapped': genes_mapped['Ensembl'], 'Original': genes}
else:
m = {'Mapped': genes, 'Original': genes}
# construct a look up table
gene_table = pd.DataFrame(data=m)
# extract the pseudotime
time = adata_selected.obs['dpt_pseudotime']
# construct a data frame which has time as index
exp_data = pd.DataFrame(data=adata_selected[:, gene_table['Mapped']].X,
index=time,
columns=[gene_table['Original'].values])
# sort according to pseudotime
exp_data.sort_index(inplace=True)
()
# remove the last entry
(m, n) = exp_data.shape
exp_data = exp_data.iloc[:m - 1, :]
# loop counter
i = 0
# loop over all genes we wish to plot
for index, row in gene_table.iterrows():
# select data
data_selected = exp_data.loc[:, row['Original']].reset_index()
# create the labels
X = np.atleast_2d(data_selected['dpt_pseudotime'].values)
# create the targets
y = data_selected[row['Original']].values.ravel()
# Mesh the input space for evaluations of the prediction and
# its MSE
x = np.atleast_2d(np.linspace(0, 1, 1000)).T
# Initiate a Gaussian process modell. We use a sum of two kernels here, this allows
# us to estimate the noice level via optimisation of the marginal likelihood as well
kernel = 1.0 * RBF(length_scale=length_scale, length_scale_bounds=length_scale_bounds) \
+ WhiteKernel(noise_level=noise_level, noise_level_bounds=noise_level_bounds)
gp = GaussianProcessRegressor(
kernel=kernel,
alpha=0.0,
n_restarts_optimizer=n_restarts_optimizer,
normalize_y=normalize_y).fit(X, y)
# obtain a prediction from this model. Also return the covariance matrix, so we can calculate
# confidence intervals
y_mean, y_cov = gp.predict(x, return_cov=True)
# plot current genes
plt.figure(num=i, figsize=(8, 6), dpi=80, facecolor='w', edgecolor='k')
plt.plot(x, y_mean, 'k', lw=3, zorder=9, label='Prediction')
plt.fill_between(x.ravel(),
y_mean - np.sqrt(np.diag(y_cov)),
y_mean + np.sqrt(np.diag(y_cov)),
alpha=0.5,
color='k')
plt.scatter(X,
y,
c='r',
s=50,
zorder=10,
edgecolors=(0, 0, 0),
label='Observation')
if title == 'long':
plt.title(
"Gene: %s\nInitial: %s\nOptimum: %s\nLog-Marginal-Likelihood: %s"
% (row['Original'], kernel, gp.kernel_,
gp.log_marginal_likelihood(gp.kernel_.theta)))
else:
plt.title("Gene: %s" % (row['Original']))
plt.xlabel('$t_{pseudo}$')
plt.ylabel('Expression')
plt.legend(loc='upper left')
if save != 'none':
plt.savefig(save + row['Original'] + '_dynamics.pdf')
if likelihood_landscape == True:
# Plot LML landscape
i += 1
plt.figure(num=i,
figsize=(8, 6),
dpi=80,
facecolor='w',
edgecolor='k')
theta0 = np.logspace(-2, 3, 49) # length scale
theta1 = np.logspace(-1.5, 0, 50) # Noise level
Theta0, Theta1 = np.meshgrid(theta0, theta1)
LML = [[
gp.log_marginal_likelihood(
np.log([0.36, Theta0[i, j], Theta1[i, j]]))
for i in range(Theta0.shape[0])
] for j in range(Theta0.shape[1])]
LML = np.array(LML).T
vmin, vmax = (-LML).min(), (-LML).max()
#vmax = 50
level = np.around(np.logspace(np.log10(vmin), np.log10(vmax), 50),
decimals=1)
plt.contour(Theta0,
Theta1,
-LML,
levels=level,
norm=colors.LogNorm(vmin=vmin, vmax=vmax))
plt.colorbar()
plt.xscale("log")
plt.yscale("log")
plt.xlabel("Length-scale")
plt.ylabel("Noise-level")
plt.title("Log-marginal-likelihood")
#plt.tight_layout()
plt.show()
# increase loop counter
i += 1
def ahmet_ali_nuhoglu_21602149_hw2(question):
if question == '1':
print("Question 1")
print("Part A")
with h5py.File('hw3_data2.mat', 'r') as file:
Xn, Yn = list(file['Xn']), list(file['Yn'])
Xn = np.array(Xn).T
Yn = np.array(Yn).flatten()
def ridge_regression(X, y, lmbd):
return np.linalg.inv(
X.T.dot(X) + lmbd * np.identity(np.shape(X)[1])).dot(
X.T).dot(y)
def r_squared(Y, pred):
return (np.corrcoef(Y, pred)[0, 1])**2
def cross_validation(X, y, K, lmbd):
part_len = int(np.size(y) / K)
valid_means_d = dict()
test_means_d = dict()
for i in range(K):
valid_data_start = i * part_len
test_data_start = (i + 1) * part_len
train_data_start = (i + 2) * part_len
train_data_ind, test_data_ind, valid_data_ind = [], [], []
for j in range(valid_data_start, test_data_start):
valid_data_ind.append(j % np.size(y))
for j in range(test_data_start, train_data_start):
test_data_ind.append(j % np.size(y))
for j in range(train_data_start,
valid_data_start + np.size(y)):
train_data_ind.append(j % np.size(y))
x_valid, x_test, x_train = X[valid_data_ind], X[
test_data_ind], X[train_data_ind]
y_valid, y_test, y_train = y[valid_data_ind], y[
test_data_ind], y[train_data_ind]
for l in lmbd:
weight = ridge_regression(x_train, y_train, l)
valid_means_d.setdefault(l, []).append(
r_squared(y_valid, x_valid.dot(weight)))
test_means_d.setdefault(l, []).append(
r_squared(y_test, x_test.dot(weight)))
valid_means_d = dict(
(lmbd, np.mean(val)) for lmbd, val in valid_means_d.items())
test_means_d = dict(
(lmbd, np.mean(val)) for lmbd, val in test_means_d.items())
return valid_means_d, test_means_d
lambda_values = np.logspace(0, 12, num=500, base=10)
dict_valid, dict_test = cross_validation(Xn, Yn, 10, lambda_values)
lambda_opt = max(dict_valid, key=lambda k: dict_valid[k])
x_val, y_val = zip(*sorted(dict_valid.items()))
x_tst, y_tst = zip(*sorted(dict_test.items()))
plt.figure()
plt.plot(x_tst, y_tst)
plt.plot(x_val, y_val)
plt.legend([
'Test Data',
'Validation Data',
])
plt.ylabel(r'$R^2$')
plt.xlabel(r'$\lambda$')
plt.title(r'$R^2$' ' vs ' '$\lambda$')
plt.xscale('log')
plt.grid()
plt.show(block=False)
print("Optimal Lambda Value: ", lambda_opt)
print("Part B")
np.random.seed(3)
def bootstrap(iter_num, x, y, lmbd):
weight_new = []
for i in range(iter_num):
new_ind = np.random.choice(np.arange(np.size(y)), np.size(y))
x_new, y_new = Xn[new_ind], Yn[new_ind]
weight_r = ridge_regression(x_new, y_new, lmbd)
weight_new.append(weight_r)
return weight_new
def find_significant_w(arr_mean, arr_std):
p_values = 2 * (1 - norm.cdf(np.abs(arr_mean / arr_std)))
significant_weights = np.where(p_values < 0.05)
return significant_weights
weight_new = []
weight_new = bootstrap(500, Xn, Yn, 0)
weight_new_mean = np.mean(weight_new, axis=0)
weight_new_std = np.std(weight_new, axis=0)
plt.figure(figsize=(20, 10))
plt.grid()
plt.errorbar(np.arange(1, 101),
weight_new_mean,
yerr=2 * weight_new_std,
ecolor='r',
fmt='o-k',
capsize=5)
plt.ylabel(r'Resampled Weight Values')
plt.xlabel(r'Weight Indices')
plt.title(r'Ridge Regression with ' r'$\lambda = 0$' '\nand %95 CI')
plt.show(block=False)
print(
"Indices of the Resampled Weights which are significantly different than zero:"
)
print(find_significant_w(weight_new_mean, weight_new_std)[0])
print("Part C")
weight_new_ridge = []
weight_new_ridge = bootstrap(500, Xn, Yn, lambda_opt)
weight_newR_mean = np.mean(weight_new_ridge, axis=0)
weight_newR_std = np.std(weight_new_ridge, axis=0)
plt.figure(figsize=(20, 10))
plt.grid()
plt.errorbar(np.arange(1, 101),
weight_newR_mean,
yerr=2 * weight_newR_std,
ecolor='r',
fmt='o-k',
capsize=5)
plt.ylabel(r'Resampled Weight Values')
plt.xlabel(r'Weight Indices')
plt.title(r'Ridge Regression with '
r'$\lambda = \lambda_{opt}$'
'\nand %95 CI')
plt.show(block=False)
print(
"Indices of the Resampled Weights which are significantly different than zero:"
)
print(find_significant_w(weight_newR_mean, weight_newR_std)[0])
elif question == '2':
print("Question 2")
print("Part A")
with h5py.File('hw3_data3.mat', 'r') as file:
pop1, pop2 = np.array(list(file['pop1'])).flatten(), np.array(
list(file['pop2'])).flatten()
def bootstrap(iter_num, x, seed=6):
np.random.seed(seed)
x_new = []
for i in range(iter_num):
new_ind = np.random.choice(np.arange(np.size(x)), np.size(x))
x_sample = x[new_ind]
x_new.append(x_sample)
return np.array(x_new)
def mean_difference(x, y, iterations):
xy_concat = np.concatenate((x, y))
xy_boot = bootstrap(iterations, xy_concat)
x_boot = np.zeros((iterations, np.size(x)))
y_boot = np.zeros((iterations, np.size(y)))
for i in range(np.size(xy_concat)):
if i < np.size(x):
x_boot[:, i] = xy_boot[:, i]
else:
y_boot[:, i - np.size(x)] = xy_boot[:, i]
x_means = np.mean(x_boot, axis=1)
y_means = np.mean(y_boot, axis=1)
mean_diff = x_means - y_means
return mean_diff
mean_diff = mean_difference(pop1, pop2, 10000)
def find_z_and_p(x, mu):
mu_0 = np.mean(x)
sigma = np.std(x)
z = np.abs((mu - mu_0) / sigma)
p = (1 - norm.cdf(z))
return z, p
plt.figure()
plt.title('Population Mean Difference')
plt.xlabel('Difference of Means')
plt.ylabel('P(x)')
plt.yticks([])
plt.hist(mean_diff, bins=60, density=True, edgecolor='black')
plt.show(block=False)
z, p = find_z_and_p(mean_diff, np.mean(pop1) - np.mean(pop2))
print("z-score: ", z)
print("two sided p-value: ", 2 * p)
print("Part B")
with h5py.File('hw3_data3.mat', 'r') as file:
vox1, vox2 = np.array(list(file['vox1'])).flatten(), np.array(
list(file['vox2'])).flatten()
vox1_boot = bootstrap(10000, vox1)
vox2_boot = bootstrap(10000, vox2)
corr_boot = np.zeros(10000)
for i in range(10000):
corr_boot[i] = np.corrcoef(vox1_boot[i], vox2_boot[i])[0, 1]
corr_mean = np.mean(corr_boot)
sorted_corr = np.sort(corr_boot)
dif = np.size(sorted_corr) / 40
corr_lower = sorted_corr[int(dif)]
corr_upper = sorted_corr[int(np.size(sorted_corr) - dif)]
print("Mean: ", corr_mean)
print("%95 CI: (", corr_lower, ", ", corr_upper, ")")
zero_corr = np.where(corr_boot < 10**(-2))
print("Number of elements with zero correlation: ", np.size(zero_corr))
print("Part C")
vox1_indep = bootstrap(10000, vox1, 13)
vox2_indep = bootstrap(10000, vox2, 5)
corr_boot_indep = np.zeros(10000)
for i in range(10000):
corr_boot_indep[i] = np.corrcoef(vox1_indep[i], vox2_indep[i])[0,
1]
plt.figure()
plt.title('Correlation between vox1 and vox2')
plt.xlabel('Correlation (x)')
plt.ylabel('P(x)')
plt.yticks([])
plt.hist(corr_boot_indep, bins=60, density=True, edgecolor='black')
plt.show(block=False)
z, p = find_z_and_p(corr_boot_indep, np.corrcoef(vox1, vox2)[0, 1])
print("z-score: ", z)
print("one sided p value: ", p)
print("Part D")
with h5py.File('hw3_data3.mat', 'r') as file:
building, face = np.array(list(
file['building'])).flatten(), np.array(list(
file['face'])).flatten()
mean_diff_d = np.zeros(10000)
diff_options = np.zeros(4)
choices = np.zeros(20)
for i in range(10000):
for j in range(20):
ind = np.random.choice(20)
diff_options[0:1] = 0
diff_options[2] = building[ind] - face[ind]
diff_options[3] = -1 * diff_options[2]
choices[j] = diff_options[np.random.choice(4)]
mean_diff_d[i] = np.mean(choices)
plt.figure()
plt.title(
'Difference of Means\nBuilding - Face\n(Subject Population = Same)'
)
plt.xlabel('Difference of Means (x)')
plt.ylabel('P(x)')
plt.yticks([])
plt.hist(mean_diff_d, bins=60, density=True, edgecolor='black')
plt.show(block=False)
z, p = find_z_and_p(mean_diff_d, np.mean(building) - np.mean(face))
print("z-score: ", z)
print("Two sided p value: ", 2 * p)
print("Part E")
mean_diff_e = mean_difference(building, face, 10000)
plt.figure()
plt.title(
'Difference of Means\nBuilding - Face\n(Subject Population = Different)'
)
plt.xlabel('Difference of Means (x)')
plt.ylabel('P(x)')
plt.yticks([])
plt.hist(mean_diff_e, bins=60, density=True, edgecolor='black')
plt.show(block=False)
z_e, p_e = find_z_and_p(mean_diff_e, np.mean(building) - np.mean(face))
print("z-score: ", z_e)
print("Two sided p value: ", 2 * p_e)
def PlotInject(self,filename=None):
'''
Function that uses the global parameters str_min and str_step as well as the global results sigma_ar to
generate a plot.
Argument :
fliename : Name of the file in which the plot will be saved. If None, the plot will be just shown
but not saved. Default to None.
'''
# Get the x-values (signal strength)
if(self.str_scale=='lin'):
sig_str = np.arange(self.str_min,self.str_min+self.str_step*len(self.sigma_ar),step=self.str_step)
else:
sig_str = np.array([i%10*10**(self.str_min+i//10) for i in range(len(self.sigma_ar)+len(self.sigma_ar)//10+1) if i%10!=0])
# If filename is not None and log scale must check
if(filename!=None and self.str_scale=='log'):
if(type(filename)==type('str')):
print('WARNING : log plot for signal injection will not be saved !')
nolog = True
else:
nolog = False
# Do the plot
F = plt.figure(figsize=(12,8))
plt.title('Significance vs signal strength')
plt.errorbar(sig_str,self.sigma_ar[:,0],
xerr=0,yerr=[self.sigma_ar[:,1],self.sigma_ar[:,2]],
linewidth=2,marker='o')
plt.xlabel('Signal strength',size='large')
plt.ylabel('Significance',size='large')
if(filename is None):
plt.show()
else:
if(self.str_scale=='log' and nolog is False):
plt.savefig(filename[0],bbox_inches='tight')
else:
plt.savefig(filename,bbox_inches='tight')
plt.close(F)
# If log scale, do also a log plot
if(self.str_scale=='log'):
F = plt.figure(figsize=(12,8))
plt.title('Significance vs signal strength (log scale)')
plt.errorbar(sig_str,self.sigma_ar[:,0],
xerr=0,yerr=[self.sigma_ar[:,1],self.sigma_ar[:,2]],
linewidth=2,marker='o')
plt.xlabel('Signal strength',size='large')
plt.ylabel('Significance',size='large')
plt.xscale('log')
if(filename is None):
plt.show()
else:
if(nolog is False):
plt.savefig(filename[1],bbox_inches='tight')
plt.close(F)
return
# See documentation for description of each column
M = pd.read_csv("M.dat",
sep=' ',
names=[
"NDim", "Iter", "N_init", "NPF", "GD", "SS", "HV",
"HausDist", "Cover", "GDPS", "SSPS", "HDPS", "Prob", "q",
"Front"
])
ZG = {}
Keys = []
Metric = "GD"
fig = pl.figure(Metric)
ZG = M.\
groupby("NPF").get_group(100).\
groupby("Iter").agg(np.mean).reset_index()
pl.plot(ZG["Iter"], ZG[Metric], 'o')
print(ZG[Metric])
pl.legend()
pl.grid()
pl.xscale("log")
pl.yscale("log")
fig.show()
def pol_cl_parse(pol_cl_out_file,
pol_cov_out_file,
wl_array=None,
cn=0,
rebin=None,
nbin=25,
lmin=1,
lmax=1500,
bin_type='lin',
custom_bins=None,
show=False):
"""
Parser of the txt output file of PolSpice, which contains the angular power spectrum (APS).
Parameters
----------
pol_cl_out_file : str
ascii output file created by PolSpice
pol_cov_out_file : str
.fits file containing the covariance matrix created by PolSpice
raw_corr : (float, numpy array)
must be a python list with 2 entries: the first one must be the
white poissonian noise, the second must be the array (or the spline)
of the Wbeam function as a funcion of l integrated in a energy bin.
rebin : list (or array)
if not None, it has to be the list defining the edges of the new binning.
Returns
-------
array, array, array
in order: array of the ells, array of the Cls, array of the Cls errors
(estimated from the covariance matrix). If rebin is not None the arrays are
the rebinned array.
"""
if pol_cov_out_file:
hdu = pf.open(pol_cov_out_file)
_cov = hdu[0].data[0]
_invcov = np.linalg.inv(_cov)
f = open(pol_cl_out_file, 'r')
_l, _cl = [], []
for line in f:
try:
l, cl = [float(item) for item in line.split()]
_l.append(l)
_cl.append(cl)
except:
pass
_l = np.array(_l)
_cl = np.array(_cl)
if len(_cl) < lmax:
logger.info('ATT: Setting new l_max=%i ...' % len(_cl))
lmax = len(_cl)
if wl_array is not None:
wl = wl_array[:lmax]
_l = _l[:lmax]
_cl = (_cl[:lmax] - cn) / (wl**2)
if pol_cov_out_file:
_cov_ = np.array([_cov[i][:len(wl)] for i in range(0, len(wl))])
_cov_ = _cov_ / (wl**2)
for l in range(len(wl)):
_cov_[l] = _cov_[l] / (wl**2)
else:
_clerr = np.sqrt(2 / (2 * _l + 1)) * (_cl + cn / wl**2)
print(len(_clerr))
else:
_clerr = np.sqrt(2 / (2 * _l + 1)) * (_cl)
pass
if rebin:
logger.info('Rebinning in multipole range')
_lr, _clr, _clerrr = [], [], []
if custom_bins is not None:
logger.info('Custom multipole binning.')
rebinning = new_binning(lmin,
lmax,
nbin,
bin_type=bin_type,
custom_bins=custom_bins)
else:
rebinning = new_binning(lmin, lmax, nbin, bin_type=bin_type)
for bmin, bmax in zip(rebinning[:-1], rebinning[1:]):
logger.info('considering %i < li < %i' % (bmin, bmax))
_index = np.where(np.logical_and(_l >= bmin, _l < bmax))[0]
_index = _index.astype(int)
if bin_type == 'log':
_lmean = np.sqrt(bmin * bmax)
if bin_type == 'lin':
_lmean = (bmin + bmax) / 2
_lr.append(_lmean)
_clmean = np.mean(_cl[_index])
_clr.append(_clmean)
logger.info('cl_mean %.3e' % _clmean)
if pol_cov_out_file:
_clerr = np.sqrt(np.mean(_cov[bmin:bmax, bmin:bmax]))
logger.info('cl_mean err %.3e' % _clerr)
_clerrr.append(_clerr)
else:
_cler = np.mean(_clerr[_index])
logger.info('cl_mean err %.3e' % _cler)
_clerrr.append(_cler)
_l = np.array(_lr)
_cl = np.array(_clr)
_clerr = np.array(_clerrr)
else:
if pol_cov_out_file:
_clerr = np.array([np.sqrt(_cov[i][i]) for i in _l.astype(int)])
else:
pass
if show:
plt.figure()
plt.errorbar(_l, _cl, yerr=_clerr, fmt='.')
plt.plot([_l[0], _l[-1]], [0, 0], c='silver', linewidth=1)
plt.title('CAPS', size=20)
plt.xlabel('$\ell$', size=18)
plt.ylabel('C$_{\ell}$', size=18)
plt.xscale('log')
plt.show()
return np.array(_l), np.array(_cl), np.array(_clerr)
def plot_data(input_txt_file, plot_position, plot_color):
plt.subplot(plot_position)
coll_criterion_name = os.path.basename(input_txt_file)[9:-4]
plt.annotate(coll_criterion_name + " criterion",
xy=(0.03, 0.075),
xycoords='axes fraction',
weight='heavy',
color=plot_color,
fontsize=40)
# Get data from file
data = np.genfromtxt(input_txt_file,
names=('Ncoll', 'Nevents', 't_run', 'V', 'sigma', 'N',
'Ntest', 'T', 'dt'))
with open(input_txt_file, 'r') as f:
smash_version = f.readlines()[-1].strip('# \n')
# Sort by x axis variable
data = data[data[xvar].argsort()]
x = data[xvar]
y = data['Ncoll']
# Make a text label about the properties of the used box
s = []
s.append('Elastic Box$:$')
if (xvar != 'V'): s.append("$V$ = %.1f fm$^3$" % data['V'][0])
if (xvar != 'sigma'): s.append("$\sigma$ = %.1f fm$^2$" % data['sigma'][0])
if (xvar != 'N'): s.append("$N$ = %i" % data['N'][0])
if (xvar != 'Ntest'): s.append("$N_{test}$ = %i" % data['Ntest'][0])
if (xvar != 'T'): s.append("$T$ = %.3f GeV" % data['T'][0])
if (xvar != 'dt'): s.append("$dt$ = %s fm/c" % data['dt'][0])
s.append("$t_{tot}$ = %.1f fm/c" % data['t_run'][0])
s.append("$N_{ev}$ = %i" % data['Nevents'][0])
box_label = '\n'.join(s)
if plot_position == 211: # only print title and input box once
plt.annotate(box_label,
xy=(1.02, 0.97),
ha="left",
va="top",
xycoords='axes fraction',
fontsize=30)
plt.title('only $\pi^0$, only elastic collisions', fontsize=30, y=1.02)
if plot_position == 212:
plt.annotate(y_label_defintion,
xy=(0.62, 0.125),
xycoords='axes fraction',
fontsize=40)
# Number of collisions is expected to be equal to this norm (for <v> = c)
norm = data['Nevents'] * data['t_run'] * (data['sigma'] * 0.5 * data['N'] *
data['N'] * data['Ntest'] /
data['V'])
# Average relative velocity factor, arXiv:1311.4494, matters only at m/T < 0.7
a = 0.135 / data['T'] # m_pi0/T
v_rel = 4. / a * sp.kn(3, 2.0 * a) / np.power(sp.kn(2, a), 2)
norm *= v_rel
y = y / norm
y_error = np.sqrt(data['Ncoll']) / norm
plt.errorbar(x,
y,
yerr=y_error,
fmt='o',
capsize=10,
label=smash_version,
markersize=15,
zorder=2,
markeredgecolor=plot_color,
color=plot_color)
if args.comp_prev_version:
import comp_to_prev_version as cpv
# plot reference data from previous SMASH version
cpv.plot_previous_results('elastic_box', args.setup,
'-' + coll_criterion_name + '.txt')
plt.xlim(0.0, 1.05 * x.max())
plt.ylim(ymin=0.4, ymax=max(1.5, 1.05 * y.max()))
if (xvar == 'dt'):
plt.xscale('log')
plt.xlim(1.e-4, 2.0 * x.max())
plt.gca().tick_params(pad=10)
# store plotted data
save_table(
OrderedDict([('x', x), ('y', y), ("y_error", y_error)]),
'{}.txt'.format(args.setup + "-" + coll_criterion_name),
smash_version,
)
plt.legend(loc='upper right')
plt.axhline(1, linewidth=3, linestyle='--', color='black', zorder=0)
plt.ylabel(y_label, fontsize=50)
if plot_position == 212: plt.xlabel(x_labels[xvar])
tau[i_file, :] = data[:, 1]
tau_std[i_file, :] = data[:, 2]
i_file = i_file + 1
print 'plotting'
for j_file in [0, 1, 2]:
paras = re.split('IMFmin|IMFmax|eta|slope|.dat', files[j_file])
plt.plot(z[j_file, :],
tau[j_file, :],
label=(r'$M_{max}=$' + paras[2] + r'$[M_{\odot}]$'))
# '\n'+r'$M_{max}=$'+paras[2]+r'$M_{\odot}$'+
plt.plot(z[0, :], tau_arr, label=('Planck 2014'), color='black', linestyle='-')
plt.plot(z[0, :],
tau_arr - sig_tau,
label=(r'$1\sigma$ error'),
color='black',
linestyle='-.')
plt.plot(z[0, :], tau_arr + sig_tau, color='black', linestyle='-.')
plt.ylabel(r'Final $\tau$', size=20)
plt.xlabel(r'$z$')
plt.xscale('linear')
plt.xlim(0, 35)
# plt.yscale('log')
plt.legend(bbox_to_anchor=(1.0, 0.5))
plt.title(r'Final $\tau$')
plt.grid(b=True, which='both', color='0.65', linestyle='-')
plt.savefig('../plots/reproduced/tau_mmax.jpg', bbox_inches='tight')
plt.show()
plt.clf()