richard
/
geinf
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Adjust x-axis ticks for large SFSs

master
tforest 2023-11-30 22:07:45 +01:00
parent 87bef76e28
commit 46a2990a2d
1 changed files with 43 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
swp2.py
View File

@ -4,6 +4,7 @@ import numpy as np
import math import math
from scipy.special import gammaln from scipy.special import gammaln
from matplotlib.backends.backend_pdf import PdfPages from matplotlib.backends.backend_pdf import PdfPages
from matplotlib.ticker import MaxNLocator
def log_facto(k): def log_facto(k):
k = int(k) k = int(k)
@ -320,7 +321,7 @@ def plot_all_epochs_thetafolder(folder_path, mu, tgen, title = "Title", theta_sc
plt.title(title) plt.title(title)
plt.savefig(title+'_Breakpts_Likelihood_AIC.pdf') plt.savefig(title+'_Breakpts_Likelihood_AIC.pdf')
def plot_test_theta(folder_path, mu, tgen, title = "Title", theta_scale = True, breaks_max = 5): def plot_test_theta(folder_path, mu, tgen, title = "Title", theta_scale = True, breaks_max = 12):
""" """
Use theta values as is to do basic plots. Use theta values as is to do basic plots.
""" """
@ -338,10 +339,17 @@ def plot_test_theta(folder_path, mu, tgen, title = "Title", theta_scale = True,
epochs[k] = thetas epochs[k] = thetas
print("\n*******\n"+title+"\n--------\n"+"mu="+str(mu)+"\ntgen="+str(tgen)+"\nbreaks="+str(k)+"\n*******\n") print("\n*******\n"+title+"\n--------\n"+"mu="+str(mu)+"\ntgen="+str(tgen)+"\nbreaks="+str(k)+"\n*******\n")
print(cpt, "theta file(s) have been scanned.") print(cpt, "theta file(s) have been scanned.")
# intialize figure 1 # intialize figure 1
my_dpi = 300 my_dpi = 300
plt.figure(figsize=(5000/my_dpi, 2800/my_dpi), dpi=my_dpi) # plt.figure(figsize=(5000/my_dpi, 2800/my_dpi), dpi=my_dpi)
# multiple fig
fig, ax = plt.subplots(figsize=(5000/my_dpi, 2800/my_dpi), dpi=my_dpi)
# Add some extra space for the second axis at the bottom
fig.subplots_adjust(bottom=0.15)
twin = ax.twiny()
# Offset the right spine of twin2
# twin.spines.right.set_position(("axes", 1.2))
plots = []
for epoch, theta in epochs.items(): for epoch, theta in epochs.items():
groups = np.array(list(theta.values()), dtype=object)[:, 1].tolist() groups = np.array(list(theta.values()), dtype=object)[:, 1].tolist()
x = [] x = []
@ -352,21 +360,38 @@ def plot_test_theta(folder_path, mu, tgen, title = "Title", theta_scale = True,
y += list(np.repeat(thetas[i], len(group))) y += list(np.repeat(thetas[i], len(group)))
if epoch == 0: if epoch == 0:
N0 = y[0] N0 = y[0]
# compute the proportion of information used at each bin of the SFS
sum_theta_i = 0
for i in range(2, len(y)+2):
sum_theta_i+=y[i-2] / (i-1)
prop = []
for k in range(2, len(y)+2):
prop.append(y[k-2] / (k - 1) / sum_theta_i)
prop = prop[::-1]
# print(prop, "\n", sum(prop))
# normalise to N0 (N0 of epoch1)
for i in range(len(y)): for i in range(len(y)):
y[i] = y[i]/N0 y[i] = y[i]/N0
# compute the proportion of information used at each bin of the SFS # plot
sum_theta_i = 0 #plt.plot(x, y, 'o', linestyle="dotted", alpha=0.75, lw=2, label = str(epoch)+' brks')
for i in range(2, len(y)-1): p, = ax.plot(x, y, 'o', linestyle="dotted", alpha=0.75, lw=2, label = str(epoch)+' brks')
sum_theta_i+=y[i] / (i-1) # add plot to the list of all plots to superimpose
prop = [] plots.append(p)
for k in range(2, len(y)-1): # virtual line to get the second x axis for proportions
prop.append(y[k] / (k - 1) / sum_theta_i) p0, = twin.plot(prop, y, alpha = 0, label="Proportion")
# plot # Move twinned axis ticks and label from top to bottom
plt.plot(x, y, 'o', linestyle="dotted", alpha=0.75, lw=2, label = str(epoch)+' brks') twin.xaxis.set_ticks_position("bottom")
plt.xlabel("# breaks") twin.xaxis.set_label_position("bottom")
plt.ylabel("theta") # Offset the twin axis below the host
plt.legend(loc='upper right') twin.spines["bottom"].set_position(("axes", -0.1))
plt.savefig(title+'_test'+str(k)+'.pdf') #ax.legend(handles=[p0]+plots)
ax.set_xlabel("# breaks")
# Set the x-axis locator to reduce the number of ticks = 10
ax.xaxis.set_major_locator(MaxNLocator(nbins=10))
ax.set_ylabel("theta")
# twin.set_ylabel("Proportion")
plt.legend(handles=plots, loc='upper right')
plt.savefig(title+'_raw'+str(k)+'.pdf')
# fig 2 & 3 # fig 2 & 3
plt.figure(figsize=(5000/my_dpi, 2800/my_dpi), dpi=my_dpi) plt.figure(figsize=(5000/my_dpi, 2800/my_dpi), dpi=my_dpi)
for epoch, theta in epochs.items(): for epoch, theta in epochs.items():
@ -394,14 +419,14 @@ def plot_test_theta(folder_path, mu, tgen, title = "Title", theta_scale = True,
plt.xlabel("# breaks") plt.xlabel("# breaks")
plt.ylabel("theta") plt.ylabel("theta")
plt.legend(loc='upper right') plt.legend(loc='upper right')
plt.savefig(title+'_test'+str(k)+'.pdf') plt.savefig(title+'_plot2_'+str(k)+'.pdf')
# Plotting (fig 3) which is the same but log scale for x # Plotting (fig 3) which is the same but log scale for x
plt.plot(x_2, y, 'o', linestyle="dotted", alpha=0.75, lw=2, label = str(epoch)+' brks') plt.plot(x_2, y, 'o', linestyle="dotted", alpha=0.75, lw=2, label = str(epoch)+' brks')
plt.xscale('log') plt.xscale('log')
plt.xlabel("# breaks") plt.xlabel("# breaks")
plt.ylabel("theta") plt.ylabel("theta")
plt.legend(loc='upper right') plt.legend(loc='upper right')
plt.savefig(title+'_test'+str(k)+'_log.pdf') plt.savefig(title+'_plot3_'+str(k)+'_log.pdf')
def save_multi_image(filename): def save_multi_image(filename):
pp = PdfPages(filename) pp = PdfPages(filename)