def plot_obs_pred(obs, pred, radius, loglog, ax = None, inset = False, sites = None):
"""Generic function to generate an observed vs predicted figure with 1:1 line"""
if not ax:
fig = plt.figure(figsize = (3.5, 3.5))
ax = plt.subplot(111)
axis_min = 0.9 * min(list(obs[obs > 0]) + list(pred[pred > 0]))
if loglog:
axis_max = 3 * max(list(obs)+list(pred))
else:
axis_max = 1.1 * max(list(obs)+list(pred))
macroecotools.plot_color_by_pt_dens(np.array(pred), np.array(obs), radius, loglog=loglog, plot_obj = ax)
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(axis_min, axis_max)
ax.tick_params(axis = 'both', which = 'major', labelsize = 6)
if loglog:
plt.annotate(r'$R^2$ = %0.2f' %macroecotools.obs_pred_rsquare(np.log10(obs[(obs != 0) * (pred != 0)]), np.log10(pred[(obs != 0) * (pred != 0)])),
xy = (0.05, 0.85), xycoords = 'axes fraction', fontsize = 7)
else:
plt.annotate(r'$R^2$ = %0.2f' %macroecotools.obs_pred_rsquare(obs, pred),
xy = (0.05, 0.85), xycoords = 'axes fraction', fontsize = 7)
if inset:
axins = inset_axes(ax, width="30%", height="30%", loc=4)
if loglog:
hist_mete_r2(sites[(obs != 0) * (pred != 0)], np.log10(obs[(obs != 0) * (pred != 0)]),
np.log10(pred[(obs != 0) * (pred != 0)]))
else:
hist_mete_r2(sites, obs, pred)
plt.setp(axins, xticks=[], yticks=[])
return ax
def plot_numsp_obs_pred(sites, obs_ab, min_abundance, max_abundance):
"""Observed vs. predicted plot of the number of species in an abundance range
Drops communities where there are 0 species that occur within the range so
that the results can be displayed on log-scaled axes. Prints the number of
dropped communities to the screen.
"""
sites = np.array(sites)
usites = np.unique(sites)
obs_ab = np.array(obs_ab)
pred = []
obs = []
for site in usites:
site_abs = obs_ab[sites==site]
site_range_abundances = site_abs[(site_abs >= min_abundance) &
(site_abs <= max_abundance)]
obs_richness = len(site_range_abundances)
pred_richness = mete.get_mete_sad(len(site_abs), sum(site_abs),
bin_edges=[min_abundance,
max_abundance + 1])
obs.append(obs_richness)
pred.append(pred_richness)
pred = np.array(list(itertools.chain.from_iterable(pred)))
obs = np.array(obs)
obs_pred_data = np.column_stack((obs, pred))
np.savetxt('temp_sp_obs_pred_data', obs_pred_data)
num_dropped_communities = len(obs[obs==0])
pred = pred[obs > 0]
obs = obs[obs > 0]
print("%s communities out of a total of %s communities were dropped because no species were observed in the given abundance range"
% (num_dropped_communities, num_dropped_communities + len(obs)))
macroecotools.plot_color_by_pt_dens(pred, obs, 3, loglog=1)
def plot_obs_pred_sad(datasets, data_dir='./data/', radius=2):
"""Multiple obs-predicted plotter"""
fig = plt.figure()
num_datasets = len(datasets)
rows = (3 if num_datasets in (5, 6) else 2)
for i, dataset in enumerate(datasets):
obs_pred_data = import_obs_pred_data(data_dir + dataset + '_obs_pred.csv')
site = ((obs_pred_data["site"]))
obs = ((obs_pred_data["obs"]))
pred = ((obs_pred_data["pred"]))
axis_min = 0.5 * min(obs)
axis_max = 2 * max(obs)
ax = fig.add_subplot(rows,2,i+1)
macroecotools.plot_color_by_pt_dens(pred, obs, radius, loglog=1,
plot_obj=plt.subplot(rows,2,i+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(axis_min, axis_max)
plt.subplots_adjust(left=0.2, bottom=0.12, right=0.8, top=0.92,
wspace=0.29, hspace=0.21)
# Create inset for histogram of site level r^2 values
axins = inset_axes(ax, width="30%", height="30%", loc=4)
hist_mete_r2(site, np.log10(obs), np.log10(pred))
plt.setp(axins, xticks=[], yticks=[])
plt.savefig('obs_pred_plots.png', dpi=400, bbox_inches = 'tight', pad_inches=0)
def plot_obs_pred(obs_pred_data, dest_file='./obs_pred.png'):
plot_color_by_pt_dens(obs_pred_data['pred'],
obs_pred_data['obs'],
3,
loglog=1)
plt.loglog([min(obs_pred_data['pred']),
max(obs_pred_data['pred'])],
[min(obs_pred_data['pred']),
max(obs_pred_data['pred'])], 'k-')
plt.savefig(dest_file, dpi=400)
def figSuppp(figname = 'SuppFig3', data_dir=mydir, radius=2):
fig = plt.figure()
plot_dim = 2
count = 0
IN_Obs_Pred = importData.import_NSR2_data(mydir + \
'data/NSR2/Stratified/lognorm_pln_NSR2_stratify.txt')
N = np.asarray(list(((IN_Obs_Pred["N"]))))
S = np.asarray(list(((IN_Obs_Pred["S"]))))
NmaxObs = np.asarray(list(((IN_Obs_Pred["NmaxObs"]))))
NmaxPred = []
SPred = []
for i in range(len(N)):
NmaxPred_i = importPredictS.predictS(N[i], NmaxObs[i], predictNmax=True).getNmax()
SPred_i = importPredictS.predictS(N[i], NmaxObs[i], predictNmax=True).getS()
NmaxPred.append(NmaxPred_i)
SPred.append(SPred_i)
NmaxPred = np.asarray(NmaxPred)
SPred = np.asarray(SPred)
toIteratePred = [NmaxPred, SPred]
toIterateObs = [NmaxObs, S]
for x in range(2):
axis_min = 0
axis_max = 2 * max(toIteratePred[x])
#print plot_dim
ax = fig.add_subplot(plot_dim-1, plot_dim, count+1)
if x == 0:
ax.set_title(r"$\mathbf{N_{max}}$")
else:
ax.set_title(r"$\mathbf{S}$")
macroecotools.plot_color_by_pt_dens(toIteratePred[x], toIterateObs[x], radius, loglog=1,
plot_obj=plt.subplot(plot_dim-1,plot_dim,count+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(0, axis_max)
r2_all = macroecotools.obs_pred_rsquare(np.log10(toIterateObs[x]), np.log10(toIteratePred[x]))
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_all , p=2)
plt.text(0.18, 0.93, r2text, fontsize=10,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
plt.tick_params(axis='both', which='major', labelsize=7)
plt.subplots_adjust(wspace=0.5, hspace=0.3)
#axins = inset_axes(ax, width="30%", height="30%", loc=4)
ax.set(adjustable='box-forced', aspect='equal')
#plt.setp(axins, xticks=[], yticks=[])
count += 1
fig.text(0.50, 0.04, r'$Predicted$', ha='center', va='center')
fig.text(0.05, 0.5, r'$Observed$', ha='center', va='center', rotation='vertical')
fig_name = str(mydir + 'figures/' + figname + '.png')
plt.savefig(fig_name, dpi=600)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def plot_obs_pred(obs_pred_data, yvar, dest_file='./obs_pred.png'):
plot_color_by_pt_dens(10**obs_pred_data[yvar + 'pred'],
10**obs_pred_data[yvar],
3,
loglog=1)
plt.loglog(
[min(10**obs_pred_data[yvar + 'pred']),
max(10**obs_pred_data[yvar])],
[min(10**obs_pred_data[yvar + 'pred']),
max(10**obs_pred_data[yvar])], 'k-')
plt.savefig(dest_file, dpi=400)
def plot_obs_pred_sad(SADModels, data_dir, radius=2):
# TAKEN FROM THE mete_sads.py script used for White et al. (2012)
# Used for Figure 3 Locey and White (2013) ########################################################################################
"""Multiple obs-predicted plotter"""
fig = plt.figure()
for i, model in enumerate(SADModels):
fig.add_subplot(2, 2, i+1)
obs_pred_data = import_obs_pred_data(data_dir + model + '.txt')
site = ((obs_pred_data["site"]))
obs = ((obs_pred_data["obs"]))
pred = ((obs_pred_data["pred"]))
axis_min = 0.5 * min(obs)
axis_max = 2 * max(obs)
macroecotools.plot_color_by_pt_dens(pred, obs, radius, loglog=1,
plot_obj=plt.subplot(2, 2, i+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(axis_min, axis_max)
plt.tick_params(axis='both', which='major', labelsize=8)
plt.subplots_adjust(wspace=0.5, hspace=0.3)
r2 = macroecotools.obs_pred_rsquare(np.log10(obs), np.log10(pred))
print model, r2
# Create inset for histogram of site level r^2 values
#axins = inset_axes(ax, width="30%", height="30%", loc=4)
#hist_mete_r2(site, np.log10(obs), np.log10(pred))
#plt.setp(axins, xticks=[], yticks=[])
plt.title(model)
#plt.text(1, 2000, r'$R^2$' + '='+ str(round(r2,3)))
plt.ylabel('Observed abundance',rotation='90',fontsize=12)
plt.xlabel('Predicted abundance',fontsize=12)
plt.savefig(mydir+'/Results/obs_pred_plots.png', dpi=600)#, bbox_inches = 'tight')#, pad_inches=0)
plt.show()
def plot_obs_pred_sad(methods, datasets, data_dir='/home/kenlocey/data1/', radius=2): # TAKEN FROM THE mete_sads.py script used for White et al. (2012)
# Used for Figure 3 Locey and White (2013) ########################################################################################
"""Multiple obs-predicted plotter"""
for i, dataset in enumerate(datasets):
for j, method in enumerate(methods):
#if method == 'mete' and dataset == 'EMP': continue
obs_pred_data = import_obs_pred_data(mydir+'/data/truedata/'+method+'_'+dataset+'_obs_pred.txt')
#site = ((obs_pred_data["site"]))
obs = ((obs_pred_data["obs"]))
pred = ((obs_pred_data["pred"]))
axis_min = 0.5 * min(obs)
axis_max = 2 * max(obs)
macroecotools.plot_color_by_pt_dens(pred, obs, radius, loglog=1,
plot_obj=plt.subplot(2, 2, j+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(axis_min, axis_max)
plt.tick_params(axis='both', which='major', labelsize=8)
plt.subplots_adjust(wspace=0.5, hspace=0.3)
r2 = macroecotools.obs_pred_rsquare(np.log10(obs), np.log10(pred))
print method, dataset, r2
#Create inset for histogram of site level r^2 values
#axins = inset_axes(ax, width="30%", height="30%", loc=4)
#hist_mete_r2(site, np.log10(obs), np.log10(pred))
#plt.setp(axins, xticks=[], yticks=[])
if method == 'mete': plt.title("Log-series")
else: plt.title("Geometric series")
plt.text(1, 2000, r'$R^2$' + '='+ str(round(r2,3)))
plt.ylabel('Observed abundance',rotation='90',fontsize=12)
plt.xlabel('Predicted abundance',fontsize=12)
plt.savefig(mydir+'/obs_pred_plots.png', dpi=600)#, bbox_inches = 'tight')#, pad_inches=0)
def fig4(figname = 'Fig4', data_dir=mydir, radius=1.5, saveAs = 'png'):
fig = plt.figure()
fig.subplots_adjust(bottom= 0.15)
plot_dim = 1
count = 0
models = ['geom', 'lognorm', 'mete', 'zipf']
#modelSlopes = [0.647520323289, 0.942904468437, 0.769214774397, 0.954497727096]
#modelInterepts = [0.116508916992, 0.292527611072, 0.19240314275, 0.189954627996]
modelSlopes = []
modelInterepts = []
for g, model in enumerate(models):
if model == 'geom':
IN_Obs_Pred = importData.import_NSR2_data(mydir + \
'data/NSR2/Stratified/geom_NSR2_stratify.txt')
nsr2 = importData.import_NSR2_data(data_dir + \
'data/NSR2/Stratified_Test/' + model + '_NSR2_stratify.txt')
elif model == 'lognorm':
IN_Obs_Pred = importData.import_NSR2_data(mydir + \
'data/NSR2/Stratified/lognorm_pln_NSR2_stratify.txt')
nsr2 = importData.import_NSR2_data(data_dir + \
'data/NSR2/Stratified_Test/' + model + '_'+ 'pln' + '_NSR2_stratify.txt')
elif model == 'mete':
IN_Obs_Pred = importData.import_NSR2_data(mydir + \
'data/NSR2/Stratified/mete_NSR2_stratify.txt')
nsr2 = importData.import_NSR2_data(data_dir + \
'data/NSR2/Stratified_Test/' + model + '_NSR2_stratify.txt')
elif model == 'zipf':
IN_Obs_Pred = importData.import_NSR2_data(mydir + \
'data/NSR2/Stratified/zipf_mle_NSR2_stratify.txt')
nsr2 = importData.import_NSR2_data(data_dir + \
'data/NSR2/Stratified_Test/' + model + '_mle' + '_NSR2_stratify.txt')
N = np.asarray(list(((IN_Obs_Pred["N"]))))
N_All = np.asarray(list(((nsr2["N"]))))
domSlope = np.mean(((nsr2["NmaxPredSlope"])))
domIntercept = 10 ** np.mean(((nsr2["NmaxPredIntercept"])))
NmaxObs = np.asarray(list(((IN_Obs_Pred["NmaxObs"]))))
NmaxObsAll = np.asarray(list(((nsr2["NmaxObs"]))))
NmaxPred = []
NmaxPredAll = []
for i in range(len(N)):
NmaxPred_i = mo.predictNmax(N[i]).getNmax(b = domIntercept, slope = domSlope)
NmaxPred.append(NmaxPred_i)
NmaxPred = np.asarray(NmaxPred)
NmaxPred_obs = [k for k in zip(NmaxObs, NmaxPred) if k[0] < 200000 ]
NmaxObs = np.asarray([k[0] for k in NmaxPred_obs])
NmaxPred = np.asarray([k[1] for k in NmaxPred_obs])
axis_min = 10
axis_max = 1000000
ax = fig.add_subplot(2, 2, count+1)
if model == 'geom':
ax.set_title("Broken-stick")
elif model == 'lognorm':
ax.set_title("Lognormal")
elif model == 'mete':
ax.set_title("Log-series")
elif model == 'zipf':
ax.set_title("Zipf")
#plot_color_by_pt_dens(NmaxPred, NmaxObs, radius, loglog=1,
# plot_obj=plt.subplot(2,2,count+1))
#if model == 'lognorm':
# radius = 1.3
macroecotools.plot_color_by_pt_dens(NmaxPred, NmaxObs, radius, loglog=1,
plot_obj=plt.subplot(2,2,count+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(axis_min, axis_max)
ax.set_xlim(axis_min, axis_max)
ax.set_ylim(axis_min, axis_max )
r2_all = macroecotools.obs_pred_rsquare(np.log10(NmaxObs), np.log10(NmaxPred))
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_all , p=2)
plt.text(0.72, 0.12, r2text, fontsize=13,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
plt.tick_params(axis='both', which='major', labelsize=12)
plt.subplots_adjust(wspace=0.00001, hspace=0.3)
ax.set(adjustable='box-forced', aspect='equal')
count += 1
fig.text(0.50, 0.055 , 'Predicted, ' +r'$log_{10}(N_{max})$', ha='center', va='center', fontsize = 19)
fig.text(0.09, 0.5, 'Observed, ' +r'$log_{10}(N_{max})$', ha='center', va='center', rotation='vertical',\
fontsize = 19)
fig_name = str(mydir + 'figures/' + figname + '_RGB.' + saveAs)
plt.savefig(fig_name, dpi=600, format = saveAs)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def fig3(figname = 'Fig3', \
zipfType = 'mle', lognormType = 'pln', Stratified = True, data_dir= mydir, \
saveAs = 'eps'):
methods = ['geom', 'lognorm', 'mete', 'zipf']
fig = plt.figure()
count = 0
params = ['N']
removeSADs = []
for i, param in enumerate(params):
for j, method in enumerate(methods):
if method == 'zipf':
obs_pred_data = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/'+ method + '_'+ zipfType + '_NSR2_stratify.txt')
elif method == 'lognorm':
obs_pred_data = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/'+ method + '_'+ lognormType +'_NSR2_stratify.txt')
else:
obs_pred_data = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/'+ method +'_NSR2_stratify.txt')
site = np.asarray(list(((obs_pred_data["site"]))))
y = np.asarray(list(((obs_pred_data["R2"]))))
x = np.log10(np.asarray(list(((obs_pred_data[param])))))
#print "nmax" + str(np.mean(np.asarray(list(((obs_pred_data["NmaxObs"]))))))
mean_x = np.mean(x)
mean_y = np.mean(y)
std_error = sp.stats.sem(y)
print method, param
print "mean modified r2 = " + str(mean_y)
print "modified r2 standard error = " + str(std_error)
print "mean " + param + " is " + str(np.mean(np.asarray(list(((obs_pred_data[param]))))))
ax = fig.add_subplot(2, 2, count+1)
macroecotools.plot_color_by_pt_dens(x, y, 0.1, loglog=0,
plot_obj=plt.subplot(2, 2, count+1))
slope, intercept, r_value, p_value, std_err = stats.linregress(x,y)
print "slope is " + str(slope)
print "r2-value is " + str(r_value **2)
print "p-value is " + str(p_value)
print "NmaxPred ", method
NmaxPred = np.log10(np.asarray(list(((obs_pred_data["NmaxPred"])))))
slope1, intercept1, r_value1, p_value1, std_err1 = stats.linregress(x,NmaxPred)
diff1 = slope1 - 1
p_diff1 = (np.absolute(diff1) / ( 0.5 *(slope1 + 1) )) * 100
print "percent difference " + str(p_diff1)
print "evennessPred ",method
evennessPred = np.log10(np.asarray(list(((obs_pred_data["evennessPred"])))))
slope2, intercept2, r_value2, p_value2, std_err2 = stats.linregress(x,evennessPred)
diff2 = slope2 - (-0.31)
p_diff2 = (np.absolute(diff2) / ( 0.5 *(slope1 + 1) )) * 100
print "percent difference " + str(p_diff2)
print "skewnessPred ",method
skewnessPred = np.log10(np.asarray(list(((obs_pred_data["skewnessPred"])))))
slope3, intercept3, r_value3, p_value3, std_err3 = stats.linregress(x,skewnessPred)
diff3 = slope3 - 0.13
p_diff3 = (np.absolute(diff3) / ( 0.5 *(slope1 + 1) )) * 100
print "percent difference " + str(p_diff3)
plt.xlim(np.amin(x), np.amax(x))
plt.ylim(-1.5,1.5)
predict_y = intercept + slope * x
pred_error = y - predict_y
degrees_of_freedom = len(x) - 2
residual_std_error = np.sqrt(np.sum(pred_error**2) / degrees_of_freedom)
plt.plot(x, predict_y, 'k-')
plt.axhline(linewidth=2, color='darkgrey',ls='--')
plt.tick_params(axis='both', which='major', labelsize=10)
if i == 0 and j == 0:
ax.set_title("Broken-stick", fontsize = 15)
ax.set_ylabel(r'$r^{2}_{m}$', fontsize = 22)
if i == 0 and j == 1:
ax.set_title("Lognormal", fontsize = 15)
if i == 0 and j == 2:
ax.set_title("Log-series", fontsize = 15)
ax.set_xlabel('Abundance, ' +r'$log_{10}$', fontsize = 17)
ax.set_ylabel(r'$r^{2}_{m}$', fontsize = 22)
if i == 0 and j == 3:
ax.set_title("Zipf", fontsize = 15)
ax.set_xlabel('Abundance, ' +r'$log_{10}$', fontsize = 17)
ax.tick_params(axis='x', labelsize=12)
ax.tick_params(axis='y', labelsize=12)
count += 1
plt.tight_layout(pad=0.8, w_pad=0.8, h_pad=0.8)
fig_name = str(mydir + 'figures/' + figname + '_RGB.' + saveAs)
plt.savefig(fig_name, bbox_inches = "tight", pad_inches = 0.4, dpi = 600, \
format = saveAs)
plt.close()
def plot_obs_pred(obs_pred_data, dest_file='./obs_pred.png'):
plot_color_by_pt_dens(obs_pred_data['pred'], obs_pred_data['obs'], 3, loglog=1)
plt.loglog([min(obs_pred_data['pred']), max(obs_pred_data['pred'])],
[min(obs_pred_data['pred']), max(obs_pred_data['pred'])], 'k-')
plt.savefig(dest_file, dpi = 400)
def plot_obs_pred(obs_pred_data, yvar, dest_file='./obs_pred.png'):
plot_color_by_pt_dens(10**obs_pred_data[yvar + 'pred'], 10**obs_pred_data[yvar],
3, loglog=1)
plt.loglog([min(10**obs_pred_data[yvar + 'pred']), max(10**obs_pred_data[yvar])],
[min(10**obs_pred_data[yvar + 'pred']), max(10**obs_pred_data[yvar])], 'k-')
plt.savefig(dest_file, dpi = 400)
def plot_obs_pred_sad(methods, datasets, data_dir= mydir, radius=2): # TAKEN FROM THE mete_sads.py script used for White et al. (2012)
# Used for Figure 3 Locey and White (2013) ########################################################################################
"""Multiple obs-predicted plotter"""
fig = plt.figure()
#xs = [[60,1], [100,1], [20,1], [60,1], [40,1], [200,1], [800,1.5], [200,1.5]]
#rs = ['0.93','0.77','0.84','0.81','0.78','0.83','0.58','0.76']
count = 0
#ax = fig.add_subplot(111)
for i, dataset in enumerate(datasets):
for j, method in enumerate(methods):
#if method == 'mete' and dataset == 'EMP': continue
#obs_pred_data = import_obs_pred_data(data_dir + 'ObsPred/' + method+'_'+dataset+'_obs_pred_test.txt')
if str(dataset) == 'EMPclosed' or str(dataset) == 'EMPopen':
obs_pred_data = import_obs_pred_data(data_dir + 'ObsPred/' + method+'_'+dataset+'_obs_pred_subset.txt')
elif str(dataset) == 'HMP':
obs_pred_data = import_obs_pred_data(data_dir + 'ObsPred/' + method+'_'+dataset+'_obs_pred.txt')
else:
obs_pred_data = import_obs_pred_data(data_dir + 'ObsPred/' + method + '_' + 'MGRAST' + dataset +'_obs_pred.txt')
print method, dataset
site = ((obs_pred_data["site"]))
obs = ((obs_pred_data["obs"]))
pred = ((obs_pred_data["pred"]))
axis_min = 0.5 * min(obs)
axis_max = 2 * max(obs)
ax = fig.add_subplot(4, 2, count+1)
if j == 0:
if i == 0:
ax.set_ylabel("HMP", rotation=90, size=8)
elif i == 1:
ax.set_ylabel("EMP closed", rotation=90, size=8)
elif i == 2:
ax.set_ylabel("EMP open", rotation=90, size=8)
elif i == 3:
ax.set_ylabel('MGRAST', rotation=90, size=8)
if i == 0 and j == 0:
ax.set_title("Broken-stick")
elif i == 0 and j == 1:
ax.set_title("METE")
macroecotools.plot_color_by_pt_dens(pred, obs, radius, loglog=1,
plot_obj=plt.subplot(4,2,count+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(axis_min, axis_max)
plt.tick_params(axis='both', which='major', labelsize=8)
plt.subplots_adjust(wspace=0.5, hspace=0.3)
#plt.text(xs[0][1],xs[0][0],dataset+'\n'+rs[0],fontsize=8)
#xs.pop(0)
#rs.pop(0)
# Create inset for histogram of site level r^2 values
axins = inset_axes(ax, width="30%", height="30%", loc=4)
if str(dataset) == 'EMPclosed' or str(dataset) == 'EMPopen':
INh2 = import_NSR2_data(data_dir + 'NSR2/' + method+'_'+dataset+'_NSR2.txt')
r2s = ((INh2["R2"]))
hist_r2 = np.histogram(r2s, range=(0, 1))
xvals = hist_r2[1] + (hist_r2[1][1] - hist_r2[1][0])
xvals = xvals[0:len(xvals)-1]
yvals = hist_r2[0]
plt.plot(xvals, yvals, 'k-', linewidth=2)
plt.axis([0, 1, 0, 1.1 * max(yvals)])
else:
hist_mete_r2(site, np.log10(obs), np.log10(pred))
plt.setp(axins, xticks=[], yticks=[])
count += 1
#ax.set_xlabel(-8,-80,'Rank-abundance at the centre of the feasible set',fontsize=10)
#ax.set_ylabel(-8.5,500,'Observed rank-abundance',rotation='90',fontsize=10)
#ax.set_ylabel('Rank-abundance at the centre of the feasible set',rotation='90',fontsize=10)
fig.text(0.06, 0.5, 'Observed rank-abundance', ha='center', va='center', rotation='vertical')
fig.text(0.5, 0.04, 'Rank-abundance at the centre of the feasible set', ha='center', va='center')
#ax.set_xlabel('Observed rank-abundance',fontsize=10)
plt.savefig('obs_pred_plots.png', dpi=600)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def fig4(figname="Fig4", data_dir=mydir, radius=2, saveAs="eps"):
fig = plt.figure()
fig.subplots_adjust(bottom=0.15)
plot_dim = 1
count = 0
IN_Obs_Pred = importData.import_NSR2_data(mydir + "data/NSR2/Stratified/lognorm_pln_NSR2_stratify.txt")
N = np.asarray(list(((IN_Obs_Pred["N"]))))
S = np.asarray(list(((IN_Obs_Pred["S"]))))
NmaxObs = np.asarray(list(((IN_Obs_Pred["NmaxObs"]))))
models = ["geom", "lognorm", "mete", "zipf"]
modelSlopes = [0.647520323289, 0.942904468437, 0.769214774397, 0.954497727096]
modelInterepts = [0.116508916992, 0.292527611072, 0.19240314275, 0.189954627996]
for g, model in enumerate(models):
NmaxPred = []
SPred = []
for i in range(len(N)):
NmaxPred_i = mo.predictS(N[i], NmaxObs[i], predictNmax=True).getNmax(
b=modelInterepts[g], slope=modelSlopes[g]
)
SPred_i = mo.predictS(N[i], NmaxObs[i], predictNmax=True).getS()
NmaxPred.append(NmaxPred_i)
SPred.append(SPred_i)
NmaxPred = np.asarray(NmaxPred)
SPred = np.asarray(SPred)
axis_min = 0
axis_max = 2 * max(NmaxObs)
ax = fig.add_subplot(2, 2, count + 1)
if model == "zipf":
OUT2 = importData.import_NSR2_data(
data_dir + "data/NSR2/Stratified_Test/" + model + "_mle_NSR2_stratify.txt"
)
elif model == "lognorm":
OUT2 = importData.import_NSR2_data(
data_dir + "data/NSR2/Stratified_Test/" + model + "_pln_NSR2_stratify.txt"
)
else:
OUT2 = importData.import_NSR2_data(data_dir + "data/NSR2/Stratified_Test/" + model + "_NSR2_stratify.txt")
NmaxObs_BS = np.asarray(list(((OUT2["NmaxObs"]))))
NmaxPred_BS = np.asarray(list(((OUT2["NmaxPred"]))))
if model == "geom":
ax.set_title("Broken-stick")
elif model == "lognorm":
ax.set_title("Lognormal")
elif model == "mete":
ax.set_title("Log-series")
elif model == "zipf":
ax.set_title("Zipf")
macroecotools.plot_color_by_pt_dens(NmaxPred, NmaxObs, radius, loglog=1, plot_obj=plt.subplot(2, 2, count + 1))
plt.plot([axis_min, axis_max], [axis_min, axis_max], "k-")
plt.xlim(axis_min, axis_max)
plt.ylim(0, axis_max)
r2_all = macroecotools.obs_pred_rsquare(np.log10(NmaxObs), np.log10(NmaxPred))
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format("r", r2_all, p=2)
plt.text(
0.72,
0.12,
r2text,
fontsize=13,
horizontalalignment="center",
verticalalignment="center",
transform=ax.transAxes,
)
plt.tick_params(axis="both", which="major", labelsize=12)
plt.subplots_adjust(wspace=0.00001, hspace=0.3)
ax.set(adjustable="box-forced", aspect="equal")
count += 1
fig.text(0.50, 0.055, "Predicted, " + r"$log_{10}(N_{max})$", ha="center", va="center", fontsize=19)
fig.text(
0.09, 0.5, "Observed, " + r"$log_{10}(N_{max})$", ha="center", va="center", rotation="vertical", fontsize=19
)
fig_name = str(mydir + "figures/" + figname + "_RGB." + saveAs)
plt.savefig(fig_name, dpi=600, format=saveAs) # , bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def fig4(figname = 'Fig4', data_dir=mydir, radius=2):
fig = plt.figure()
plot_dim = 1
count = 0
IN_Obs_Pred = importData.import_NSR2_data(mydir + \
'data/NSR2/Stratified/lognorm_pln_NSR2_stratify.txt')
N = np.asarray(list(((IN_Obs_Pred["N"]))))
S = np.asarray(list(((IN_Obs_Pred["S"]))))
NmaxObs = np.asarray(list(((IN_Obs_Pred["NmaxObs"]))))
# order
models = ['geom', 'lognorm', 'mete', 'zipf']
modelSlopes = [0.647520323289, 0.942904468437, 0.769214774397, 0.954497727096]
modelInterepts = [0.116508916992, 0.292527611072, 0.19240314275, 0.189954627996]
for g, model in enumerate(models):
NmaxPred = []
SPred = []
for i in range(len(N)):
NmaxPred_i = importPredictS.predictS(N[i], NmaxObs[i], \
predictNmax=True).getNmax(b = modelInterepts[g], slope = modelSlopes[g])
SPred_i = importPredictS.predictS(N[i], NmaxObs[i], predictNmax=True).getS()
NmaxPred.append(NmaxPred_i)
SPred.append(SPred_i)
NmaxPred = np.asarray(NmaxPred)
SPred = np.asarray(SPred)
axis_min = 0
axis_max = 2 * max(NmaxObs)
ax = fig.add_subplot(2, 2, count+1)
#ax.set_title(r"$\mathbf{N_{max}}$", y=1.03)
if model == 'geom':
ax.set_title(r"$\mathbf{Broken-stick}$")
elif model == 'lognorm':
ax.set_title(r"$\mathbf{Lognormal}$")
elif model == 'mete':
ax.set_title(r"$\mathbf{Log-series}$")
elif model == 'zipf':
ax.set_title(r"$\mathbf{Zipf}$")
macroecotools.plot_color_by_pt_dens(NmaxPred, NmaxObs, radius, loglog=1,
plot_obj=plt.subplot(2,2,count+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(axis_min, axis_max)
plt.ylim(0, axis_max)
print max(NmaxPred)
r2_all = macroecotools.obs_pred_rsquare(np.log10(NmaxObs), np.log10(NmaxPred))
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_all , p=2)
plt.text(0.22, 0.91, r2text, fontsize=13,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
plt.tick_params(axis='both', which='major', labelsize=7)
plt.subplots_adjust(wspace=0.5, hspace=0.3)
#axins = inset_axes(ax, width="30%", height="30%", loc=4)
ax.set(adjustable='box-forced', aspect='equal')
#plt.setp(axins, xticks=[], yticks=[])
count += 1
fig.text(0.50, 0.04, r'$Predicted\, log_{10}(N_{max})$', ha='center', va='center', fontsize = 16)
fig.text(0.04, 0.5, r'$Observed\,log_{10}(N_{max})$', ha='center', va='center', rotation='vertical',\
fontsize = 16)
fig_name = str(mydir + 'figures/' + figname + '.png')
plt.savefig(fig_name, dpi=600)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def Supp(figname = 'Supp', data_dir=mydir, radius=2):
# TAKEN FROM THE mete_sads.py script used for White et al. (2012)
# Used for Figure 3 Locey and White (2013)
"""Multiple obs-predicted plotter"""
fig = plt.figure()
count = 0
plot_dim = 2
IN_Obs_Pred = importData.import_obs_pred_data(mydir + \
'data/ObsPred/Stratified/lognorm_75_25_obs_pred_stratify_test.txt')
site = np.asarray(list(((IN_Obs_Pred["site"]))))
obs = np.asarray(list(((IN_Obs_Pred["obs"]))))
pred7525 = np.asarray(list(((IN_Obs_Pred["pred7525"]))))
predPln = np.asarray(list(((IN_Obs_Pred["predPln"]))))
toIterate = [pred7525, predPln]
for x in range(2):
axis_min = 0
axis_max = 2 * max(obs)
#print plot_dim
ax = fig.add_subplot(plot_dim, plot_dim, count+1)
if x == 0:
ax.set_title(r"$\mathbf{75:25\, Simulation}$")
else:
ax.set_title(r"$\mathbf{Lognormal\, MLE}$")
macroecotools.plot_color_by_pt_dens(toIterate[x], obs, radius, loglog=1,
plot_obj=plt.subplot(plot_dim,plot_dim,count+1))
#
#plt.text(0.1, 0.9,'matplotlib', ha='center', va='center', transform=ax.transAxes)
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
#r2s = ((INh2["R2"]))
#r2s = r2s.astype(float)
# insert r2 of all data
r2_all = macroecotools.obs_pred_rsquare(np.log10(obs), np.log10(toIterate[x]))
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_all , p=2)
plt.text(0.18, 0.93, r2text, fontsize=10,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
plt.tick_params(axis='both', which='major', labelsize=7)
plt.subplots_adjust(wspace=0.5, hspace=0.3)
axins = inset_axes(ax, width="30%", height="30%", loc=4)
#hist_r2 = np.histogram(r2s, range=(0, 1))
#xvals = hist_r2[1] + (hist_r2[1][1] - hist_r2[1][0])
#xvals = xvals[0:len(xvals)-1]
#yvals = hist_r2[0]
#plt.plot(xvals, yvals, 'k-', linewidth=2)
#plt.axis([0, 1, 0, 1.1 * max(yvals)])
ax.set(adjustable='box-forced', aspect='equal')
#plt.setp(axins, xticks=[], yticks=[])
count += 1
fig.text(0.50, 0.04, r'$Predicted \; rank-abundance$', ha='center', va='center')
fig.text(0.05, 0.5, r'$Observed \; rank-abundance$', ha='center', va='center', rotation='vertical')
fig_name = str(mydir + 'figures/' + figname + '.png')
plt.savefig(fig_name, dpi=600)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
"""Multiple obs-predicted plotter"""
fig = plt.figure()
ax1 = fig.add_subplot(2, 2, 1)
filename = mydir+'/data/emp_mete_obs_pred.txt'
data = import_obs_pred_data(filename)
site = np.asarray(list(((data["site"]))))
obs = np.asarray(list(((data["obs"]))))
pred = np.asarray(list(((data["pred"]))))
axis_min = 0
axis_max = 2 * max(obs)
radius=2
mct.plot_color_by_pt_dens(pred, obs, radius, loglog=1, plot_obj=ax1)
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
r2_all = mct.obs_pred_rsquare(np.log10(obs), np.log10(pred))
r2text = r"${}^{{2}} = {:.{p}f} $".format('r',r2_all , p=2)
plt.text(2, 30000, r2text, fontsize=14)
plt.text(28, 800000, 'Log-series', fontsize=14)
plt.text(5, 0.1, 'Predicted rank-abundance', fontsize=10)
plt.text(0.1, 60000, 'Observed rank-abundance', rotation='vertical', fontsize=10)
plt.tick_params(axis='both', which='major', labelsize=7)
def NSR2_regression(methods, datasets, data_dir= mydir):
fig = plt.figure()
count = 0
test_count = 0
for i, dataset in enumerate(datasets):
for k, param in enumerate(params):
for j, method in enumerate(methods):
nsr2_data = import_NSR2_data(data_dir + 'NSR2/' + method+'_'+dataset+'_NSR2.txt')
#nsr2_data[[~np.isnan(nsr2_data).any(axis=1)]]
#nsr2_data[~np.isinf(nsr2_data).any(axis=1)]
#nsr2_data[~np.isnan(nsr2_data).any(1)]
list = ['nan', 'NAN', '-inf', 'inf']
#for x in nsr2_data:
# print type(x)
# value = str(x[3])
#if np.isinf(x[3]) == True:
# print "infinity"
#mask = np.all(np.isinf(nsr2_data), axis=1)
y = ((nsr2_data["R2"]))
mean = np.mean(y)
std_error = sp.stats.sem(y)
print method, param, dataset
print "mean = " + str(mean)
print "standard error = " + str(std_error)
#print method, dataset, param
ax = fig.add_subplot(3, 8, count+1)
if param == "N" or param == "S":
x = np.log10(((nsr2_data[param])))
else:
N_count = ((nsr2_data["N"]))
S_count = ((nsr2_data["S"]))
print dataset, method
print "mean N is " + str(np.mean(N_count))
print "mean S is " + str(np.mean(S_count))
x = np.divide(N_count, S_count)
x = np.log10(x)
#elif str(n_or_s).capitalize() == 'S'
#x = ((nsr2_data["N"]))
macroecotools.plot_color_by_pt_dens(x, y, 0.1, loglog=0,
plot_obj=plt.subplot(3, 8, count+1))
slope, intercept, r_value, p_value, std_err = stats.linregress(x,y)
#if param == 'N/S':
# plt.xlim(np.amin(x), 1000)
#else:
plt.xlim(np.amin(x), np.amax(x))
plt.ylim(-1,1)
predict_y = intercept + slope * x
pred_error = y - predict_y
degrees_of_freedom = len(x) - 2
residual_std_error = np.sqrt(np.sum(pred_error**2) / degrees_of_freedom)
plt.plot(x, predict_y, 'k-')
plt.axhline(linewidth=2, color='lightgray')
plt.subplots_adjust(wspace=0.2, hspace=0.3)
# Plotting
plt.xlabel(param)
if j == 0 and k == 0:
plt.title('Broken-stick', fontsize = 'large')
elif j == 1 and k == 0:
plt.title('METE', fontsize = 'large')
#plt.ylabel(r'$r^{2}$',fontsize=16)
#r_2 = "r2 =" + str(round(r_value,2))
#p_s = "p =" + str(round(p_value,2))
#plt.text(0, 1, r'$p$'+ ' = '+str(round(p_value,2)), fontsize=12)
#plt.text(0, 1, r'$r_{2}$'+ ' = '+str(round(r_value,2)), fontsize=12)
#ax.text(0.05, 0.95, textstr, transform=ax.transAxes, fontsize=14, verticalalignment='top', bbox=props)
leg = plt.legend(loc=1,prop={'size':10})
#leg.draw_frame(False)
#plt.legend(loc='upper left')
print r_value, p_value
count += 1
#ax.set_ylabel('common ylabel')
plt.tight_layout()
fig.text(0.02, 0.5, r'$r^{2}$', ha='center', va='center', rotation='vertical', size = 'medium')
#ax.set_ylabel('common ylabel')
#fig.text(-8,-80,'Rank-abundance at the centre of the feasible set',fontsize=10)
#plt.suptitle(-8.5,500,r'$r^{2}$',rotation='90',fontsize=10)
fig_name = 'NSR2_GeomMete' + str(dataset) + '.png'
plt.savefig(fig_name)
#plt.xscale()
plt.close()
def figS1(n=35289, figname = 'FigS1', data_dir=mydir, radius=2, zipfType = 'mle', \
saveAs = 'eps', lognormType = 'pln'):
methods = ['geom', 'lognorm', 'mete', 'zipf']
datasets = ['95', '97', '99']
fig = plt.figure()
count = 0
rows = len(datasets)
columns = len(methods)
for i, dataset in enumerate(datasets):
for j, method in enumerate(methods):
print count
if method == 'zipf':
obs_pred_data = importData.import_obs_pred_data(data_dir + 'data/ObsPred/Stratified/'+ method + '_'+ zipfType+'_obs_pred_stratify.txt')
INh2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/' + method + '_mle' + '_NSR2_stratify.txt')
elif method == 'lognorm':
obs_pred_data = importData.import_obs_pred_data(data_dir + 'data/ObsPred/Stratified/'+ method + '_'+ lognormType+'_obs_pred_stratify.txt')
INh2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/' + method + '_'+ lognormType + '_NSR2_stratify.txt')
else:
obs_pred_data = importData.import_obs_pred_data(data_dir + 'data/ObsPred/Stratified/'+ method +'_obs_pred_stratify.txt')
INh2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/' + method + '_NSR2_stratify.txt')
obs = np.asarray(list(((obs_pred_data["obs"]))))
pred = np.asarray(list(((obs_pred_data["pred"]))))
site = np.asarray(list(((obs_pred_data["site"]))))
obs2 = []
pred2 = []
site2 = []
obs_all = np.asarray(obs)
pred_all = np.asarray(pred)
site_all = np.asarray(site)
if n == 'all' or len(obs) <= n:
obs2 = list(obs)
pred2 = list(pred)
site2 = list(site)
else:
if len(obs) > n:
inds = np.random.choice(range(len(site)), size=n, replace=False)
for ind in inds:
obs2.append(obs[ind])
pred2.append(pred[ind])
site2.append(site[ind])
obs = np.asarray(obs2)
pred = np.asarray(pred2)
site = np.asarray(site2)
print "number of points " + str(len(obs))
if method == 'zipf':
axis_min = 0
axis_max = 2 * max(pred)
else:
axis_min = 0
axis_max = 2 * max(obs)
ax = fig.add_subplot(rows, columns, count+1)
if i == 0 and j == 0:
ax.set_title("Broken-stick")
elif i == 0 and j == 1:
ax.set_title("Lognormal")
elif i == 0 and j == 2:
ax.set_title("Log-series")
elif i == 0 and j == 3:
ax.set_title("Zipf")
if j == 0:
if dataset == '95':
ax.set_ylabel("MG-RAST 95%", rotation=90, size=12)
elif dataset == '97':
ax.set_ylabel("MG-RAST 97%", rotation=90, size=12)
elif dataset == '99':
ax.set_ylabel("MG-RAST 99%", rotation=90, size=12)
macroecotools.plot_color_by_pt_dens(pred, obs, radius, loglog=1,
plot_obj=plt.subplot(rows,columns,count+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
if method == 'zipf':
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
else:
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
r2s = ((INh2["R2"]))
r2s = r2s.astype(float)
mean_r2s = np.mean(r2s)
std_r2s = np.std(r2s)
print method, dataset
print "Mean r2 " + str(mean_r2s)
print "Standard dev. " + str(std_r2s)
if method == 'zipf':
getR2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified_Test/SequenceSimilarity/'+ method + '_mle_' +dataset +'_NSR2_stratify.txt')
elif method == 'lognorm':
getR2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified_Test/SequenceSimilarity/'+ method + '_' + lognormType + '_' +dataset +'_NSR2_stratify.txt')
else:
getR2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified_Test/SequenceSimilarity/'+ method + '_' +dataset +'_NSR2_stratify.txt')
r2_mean = np.mean(((getR2["R2"])))
if method == 'geom':
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_mean , p=3)
else:
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_mean , p=2)
if method == 'geom':
plt.text(0.28, 0.90, r2text, fontsize=10,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
else:
plt.text(0.25, 0.90, r2text, fontsize=10,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
plt.tick_params(axis='both', which='major', labelsize=8)
plt.subplots_adjust(wspace=0.0000000001, hspace=0.5)
axins = inset_axes(ax, width="30%", height="30%", loc=4)
hist_r2 = np.histogram(r2s, range=(0, 1))
xvals = hist_r2[1] + (hist_r2[1][1] - hist_r2[1][0])
xvals = xvals[0:len(xvals)-1]
yvals = hist_r2[0]
plt.plot(xvals, yvals, 'k-', linewidth=2)
plt.axis([0, 1, 0, 1.1 * max(yvals)])
ax.set(adjustable='box-forced', aspect='equal')
plt.setp(axins, xticks=[], yticks=[])
count += 1
plt.tight_layout(pad=1.5, w_pad=0.8, h_pad=0.8)
fig.subplots_adjust(left=0.1)
fig.text(0.50, 0.02, 'Predicted abundance', ha='center', va='center', fontsize=14)
fig.text(0.03, 0.5, 'Observed abundance', ha='center', va='center', rotation='vertical', fontsize=14)
fig_name = str(mydir + 'figures/' + figname + '_RGB.' + saveAs)
plt.savefig(fig_name, dpi=600, format = saveAs)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def figS2(
n=35289,
figname="FigS2",
data_dir=mydir,
stratify=True,
radius=2,
remove=1,
zipfType="mle",
RGF=False,
saveAs="eps",
lognormType="pln",
):
# TAKEN FROM THE mete_sads.py script used for White et al. (2012)
# Used for Figure 3 Locey and White (2013)
"""Multiple obs-predicted plotter"""
fig = plt.figure()
count = 0
plot_dim = 2
fig.subplots_adjust(bottom=0.30)
methods = ["geom", "lognorm", "mete", "zipf"]
for i, method in enumerate(methods):
if method == "zipf":
obs_pred_data = importData.import_obs_pred_data(
data_dir + "data/ObsPred/Remove_1s/Stratified/" + method + "_" + zipfType + "_obs_pred_1_stratify.txt"
)
INh2 = importData.import_NSR2_data(
data_dir + "data/NSR2/Remove_1s/Stratified/" + method + "_mle" + "_NSR2_1_stratify.txt"
)
elif method == "lognorm":
obs_pred_data = importData.import_obs_pred_data(
data_dir
+ "data/ObsPred/Remove_1s/Stratified/"
+ method
+ "_"
+ lognormType
+ "_obs_pred_1_stratify.txt"
)
INh2 = importData.import_NSR2_data(
data_dir + "data/NSR2/Remove_1s/Stratified/" + method + "_" + lognormType + "_NSR2_1_stratify.txt"
)
else:
obs_pred_data = importData.import_obs_pred_data(
data_dir + "data/ObsPred/Remove_1s/Stratified/" + method + "_obs_pred_1_stratify.txt"
)
INh2 = importData.import_NSR2_data(
data_dir + "data/NSR2/Remove_1s/Stratified/" + method + "_NSR2_1_stratify.txt"
)
obs = np.asarray(list(((obs_pred_data["obs"]))))
pred = np.asarray(list(((obs_pred_data["pred"]))))
site = np.asarray(list(((obs_pred_data["site"]))))
obs2 = []
pred2 = []
site2 = []
obs_all = np.asarray(obs)
pred_all = np.asarray(pred)
site_all = np.asarray(site)
if n == "all" or len(obs) <= n:
obs2 = list(obs)
pred2 = list(pred)
site2 = list(site)
else:
if len(obs) > n:
inds = np.random.choice(range(len(site)), size=n, replace=False)
for ind in inds:
obs2.append(obs[ind])
pred2.append(pred[ind])
site2.append(site[ind])
obs = np.asarray(obs2)
pred = np.asarray(pred2)
site = np.asarray(site2)
if method == "zipf":
axis_min = 0
axis_max = 2 * max(pred)
else:
axis_min = 0
axis_max = 2 * max(obs)
ax = fig.add_subplot(plot_dim, plot_dim, count + 1)
if method == "zipf":
NSR2_BS = importData.import_NSR2_data(
data_dir + "data/NSR2/Stratified_Test/Remove_1s/" + method + "_mle_NSR2_1_stratify.txt"
)
elif method == "lognorm":
NSR2_BS = importData.import_NSR2_data(
data_dir + "data/NSR2/Stratified_Test/Remove_1s/" + method + "_pln_NSR2_1_stratify.txt"
)
else:
NSR2_BS = importData.import_NSR2_data(
data_dir + "data/NSR2/Stratified_Test/Remove_1s/" + method + "_NSR2_1_stratify.txt"
)
if method == "geom":
ax.set_title("Broken-stick")
elif method == "lognorm":
ax.set_title("Lognormal")
elif method == "mete":
ax.set_title("Log-series")
elif method == "zipf":
ax.set_title("Zipf")
macroecotools.plot_color_by_pt_dens(
pred, obs, radius, loglog=1, plot_obj=plt.subplot(plot_dim, plot_dim, count + 1)
)
plt.plot([axis_min, axis_max], [axis_min, axis_max], "k-")
if method == "zipf":
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
else:
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
r2s = INh2["R2"]
r2s = r2s.astype(float)
# insert r2 of all data
r2_all = np.mean(((NSR2_BS["R2"])))
print method
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format("r", r2_all, p=2)
if method == "geom":
plt.text(
0.25,
0.90,
r2text,
fontsize=14,
horizontalalignment="center",
verticalalignment="center",
transform=ax.transAxes,
)
else:
plt.text(
0.22,
0.90,
r2text,
fontsize=14,
horizontalalignment="center",
verticalalignment="center",
transform=ax.transAxes,
)
plt.tick_params(axis="both", which="major", labelsize=10)
plt.subplots_adjust(wspace=0.0000000001, hspace=0.5)
axins = inset_axes(ax, width="30%", height="30%", loc=4)
hist_r2 = np.histogram(r2s, range=(0, 1))
xvals = hist_r2[1] + (hist_r2[1][1] - hist_r2[1][0])
xvals = xvals[0 : len(xvals) - 1]
yvals = hist_r2[0]
plt.plot(xvals, yvals, "k-", linewidth=2)
plt.axis([0, 1, 0, 1.1 * max(yvals)])
ax.set(adjustable="box-forced", aspect="equal")
plt.setp(axins, xticks=[], yticks=[])
count += 1
plt.tight_layout(pad=1.5, w_pad=0.8, h_pad=0.8)
fig.text(0.50, 0.02, "Predicted abundance", ha="center", va="center", fontsize=16)
fig.text(0.08, 0.5, "Observed abundance", ha="center", va="center", rotation="vertical", fontsize=16)
fig_name = str(mydir + "figures/" + figname + "_RGB." + saveAs)
plt.savefig(fig_name, dpi=600, format=saveAs) # , bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def fig2(n=352899, figname = 'Fig2', data_dir=mydir, \
stratify = True, radius=2, remove = 0, zipfType = 'mle', RGF = False, \
lognormType = 'pln', saveAs = 'eps'):
# TAKEN FROM THE mete_sads.py script used for White et al. (2012)
# Used for Figure 3 Locey and White (2013)
"""Multiple obs-predicted plotter"""
fig = plt.figure()
count = 0
plot_dim = 2
methods = ['geom', 'lognorm', 'mete', 'zipf']
fig.subplots_adjust(bottom= 0.30)
for i, method in enumerate(methods):
if method == 'zipf':
obs_pred_data = importData.import_obs_pred_data(data_dir + 'data/ObsPred/Stratified/'+ method + '_'+ zipfType+'_obs_pred_stratify.txt')
INh2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/' + method + '_mle' + '_NSR2_stratify.txt')
elif method == 'lognorm':
obs_pred_data = importData.import_obs_pred_data(data_dir + 'data/ObsPred/Stratified/'+ method + '_'+ lognormType+'_obs_pred_stratify.txt')
INh2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/' + method + '_'+ lognormType + '_NSR2_stratify.txt')
else:
obs_pred_data = importData.import_obs_pred_data(data_dir + 'data/ObsPred/Stratified/'+ method +'_obs_pred_stratify.txt')
INh2 = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified/' + method + '_NSR2_stratify.txt')
obs = np.asarray(list(((obs_pred_data["obs"]))))
pred = np.asarray(list(((obs_pred_data["pred"]))))
site = np.asarray(list(((obs_pred_data["site"]))))
obs2 = []
pred2 = []
site2 = []
obs_all = np.asarray(obs)
pred_all = np.asarray(pred)
site_all = np.asarray(site)
if n == 'all' or len(obs) <= n:
obs2 = list(obs)
pred2 = list(pred)
site2 = list(site)
else:
if len(obs) > n:
inds = np.random.choice(range(len(site)), size=n, replace=False)
for ind in inds:
obs2.append(obs[ind])
pred2.append(pred[ind])
site2.append(site[ind])
obs = np.asarray(obs2)
pred = np.asarray(pred2)
site = np.asarray(site2)
if method == 'zipf':
axis_min = 0
axis_max = 2 * max(pred)
else:
axis_min = 0
axis_max = 2 * max(obs)
ax = fig.add_subplot(plot_dim, plot_dim, count+1)
if method == 'zipf':
NSR2_BS = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified_Test/'+ method + '_mle_NSR2_stratify.txt')
elif method == 'lognorm':
NSR2_BS = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified_Test/'+ method + '_pln_NSR2_stratify.txt')
else:
NSR2_BS = importData.import_NSR2_data(data_dir + 'data/NSR2/Stratified_Test/'+ method +'_NSR2_stratify.txt')
if method == 'geom':
ax.set_title("Broken-stick")
elif method == 'lognorm':
ax.set_title("Lognormal")
elif method == 'mete':
ax.set_title("Log-series")
elif method == 'zipf':
ax.set_title("Zipf")
print len(pred), len(obs)
macroecotools.plot_color_by_pt_dens(pred, obs, radius, loglog=1,
plot_obj=plt.subplot(plot_dim,plot_dim,count+1))
plt.plot([axis_min, axis_max],[axis_min, axis_max], 'k-')
if method == 'zipf':
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
else:
plt.xlim(0, axis_max)
plt.ylim(0, axis_max)
r2s = ((INh2["R2"]))
r2s = r2s.astype(float)
# insert r2 of all data
r2_all = np.mean(((NSR2_BS["R2"])))
print method + ' mean = ' + str(r2_all)
print method + ' std dev = ' +str(np.std(r2_all))
r2text = r"${}^{{2}}_{{m}} = {:.{p}f} $".format('r',r2_all , p=2)
if method == 'geom':
plt.text(0.25, 0.90, r2text, fontsize=14,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
else:
plt.text(0.22, 0.90, r2text, fontsize=14,
horizontalalignment='center',
verticalalignment='center',transform = ax.transAxes)
plt.tick_params(axis='both', which='major', labelsize=10)
plt.subplots_adjust(wspace=0.0000000001, hspace=0.5)
axins = inset_axes(ax, width="30%", height="30%", loc=4)
hist_r2 = np.histogram(r2s, range=(0, 1))
xvals = hist_r2[1] + (hist_r2[1][1] - hist_r2[1][0])
xvals = xvals[0:len(xvals)-1]
yvals = hist_r2[0]
plt.plot(xvals, yvals, 'k-', linewidth=2)
plt.axis([0, 1, 0, 1.1 * max(yvals)])
ax.set(adjustable='box-forced', aspect='equal')
plt.setp(axins, xticks=[], yticks=[])
count += 1
plt.tight_layout(pad=1.5, w_pad=0.8, h_pad=0.8)
fig.text(0.50, 0.03, 'Predicted abundance', ha='center', va='center', fontsize=16)
fig.text(0.08, 0.5, 'Observed abundance', ha='center', va='center', rotation='vertical', fontsize=16)
fig_name = str(mydir + 'figures/' + figname + '_RGB.' + saveAs)
plt.savefig(fig_name, dpi=600, format = saveAs)#, bbox_inches = 'tight')#, pad_inches=0)
plt.close()
def plot_obs_pred(sad_data, envpred_sads, dest_file='./obs_pred.png'):
plot_color_by_pt_dens(envpred_sads['EnvPred'], sad_data['Obs'], 3, loglog=1)
plt.loglog([min(envpred_sads['EnvPred']), max(envpred_sads['EnvPred'])],
[min(envpred_sads['EnvPred']), max(envpred_sads['EnvPred'])], 'k-')
plt.savefig(dest_file, dpi = 400)
