def weighted_mean_and_err(tau, ccf, cut_off=0.5):
### Limit to range of ccf function ##
max_ccf = np.max(ccf)
lim = cut_off * max_ccf
tau = tau[ccf > lim]
ccf = ccf[ccf > lim]
### find weighted mean and standard error on the mean ###
tau_mean = ws.numpy_weighted_mean(tau, weights=ccf)
tau_var = ws.numpy_weighted_mean((tau - tau_mean)**2, weights=ccf)
tau_std = np.sqrt(tau_var)
tau_SE = tau_std / len(tau)
return tau_mean, tau_SE
])
### Unpack values ###
ccf = out[:, 0]
ccf_err = out[:, 1]
#%% Fit a parabola for those points around the centre of the ccf function ###
sub_tau = np.arange(-10, 10)
test_ccf = ccf[np.isin(tau_arr, sub_tau)]
fit_params, pcov = scipy.optimize.curve_fit(parabola, sub_tau, test_ccf)
plot_tau = np.linspace(-5, 6, 30)
ccf_fit = parabola(plot_tau, *fit_params)
max_lag_fit[n] = plot_tau[np.argmax(ccf_fit)]
#%% Find weighted mean and skew of ccf ###
mean_lag[n] = ws.numpy_weighted_mean(sub_tau, weights=test_ccf)
median_lag[n] = ws.numpy_weighted_median(sub_tau, weights=test_ccf)
max_lag[n] = sub_tau[np.argmax(test_ccf)]
#%% Make plots ###
plt.figure(2, figsize=[10, 10])
#plt.subplot(211)
#plt.plot(tau_arr, ccf,'o')
plt.errorbar(tau_arr,
ccf,
yerr=ccf_err,
fmt='o',
color='C' + str(n),
label=label)
# plt.vlines(mean_lag[n], -0.015,0.02, color='C'+str(n), linestyle='dashed')
# plt.vlines(median_lag[n], -0.015,0.02, color='C'+str(n), linestyle='dotted')
def run(self, scaffold_stats):
"""Calculate statistics for genomes.
Parameters
----------
scaffold_stats : ScaffoldStats
Statistics for individual scaffolds.
"""
self.logger.info(
"Calculating statistics for {:,} genomes over {:,} scaffolds.".
format(scaffold_stats.num_genomes(),
scaffold_stats.num_scaffolds()))
self.coverage_headers = scaffold_stats.coverage_headers
self.signature_headers = scaffold_stats.signature_headers
genome_size = defaultdict(int)
scaffold_length = defaultdict(list)
gc = defaultdict(list)
coverage = defaultdict(list)
signature = defaultdict(list)
for _scaffold_id, stats in scaffold_stats.stats.items():
if stats.genome_id == scaffold_stats.unbinned:
continue
genome_size[stats.genome_id] += stats.length
scaffold_length[stats.genome_id].append(stats.length)
gc[stats.genome_id].append(stats.gc)
coverage[stats.genome_id].append(stats.coverage)
signature[stats.genome_id].append(stats.signature)
# record statistics for each genome
genomic_signature = GenomicSignature(0)
self.genome_stats = {}
for genome_id in genome_size:
# calculate weighted mean and median statistics
weights = np_array(scaffold_length[genome_id])
len_array = np_array(scaffold_length[genome_id])
mean_len = ws.numpy_weighted_mean(len_array, weights)
median_len = ws.numpy_weighted_median(len_array, weights)
gc_array = np_array(gc[genome_id])
mean_gc = ws.numpy_weighted_mean(gc_array, weights)
median_gc = ws.numpy_weighted_median(gc_array, weights)
cov_array = np_array(coverage[genome_id]).T
mean_cov = ws.numpy_weighted_mean(cov_array, weights)
median_cov = []
for i in range(cov_array.shape[0]):
median_cov.append(
ws.numpy_weighted_median(cov_array[i, :], weights))
signature_array = np_array(signature[genome_id]).T
mean_signature = ws.numpy_weighted_mean(signature_array, weights)
# calculate mean and median tetranucleotide distance
td = []
for scaffold_id in scaffold_stats.scaffolds_in_genome[genome_id]:
stats = scaffold_stats.stats[scaffold_id]
td.append(
genomic_signature.manhattan(stats.signature,
mean_signature))
self.genome_stats[genome_id] = self.GenomeStats(
genome_size[genome_id], mean_len, median_len, mean_gc,
median_gc, mean_cov, median_cov, mean_signature, np_mean(td),
np_median(td))
return self.genome_stats
#%% Fit a parabola for those points around the centre of the ccf function ###
sub_tau = np.arange(-7, 8)
test_ccf = ccf[np.isin(tau_arr, sub_tau)]
test_ccf_err = ccf_err[np.isin(tau_arr, sub_tau)]
fit_params, pcov = scipy.optimize.curve_fit(parabola,
sub_tau,
test_ccf,
sigma=test_ccf_err)
plot_tau = np.linspace(-7, 7, 100)
ccf_fit = parabola(plot_tau, *fit_params)
max_lag_fit[n] = plot_tau[np.argmax(ccf_fit)]
max_lag_fit_err[n] = bootstrapping_max(plot_tau, ccf_fit)
#%% Find mean lag (centroid) in the centre ###
mean_lag_test[n] = ws.numpy_weighted_mean(sub_tau, weights=test_ccf)
mean_lag[n], mean_lag_err[n] = weighted_mean_and_err(tau_arr, ccf)
median_lag[n] = ws.numpy_weighted_median(sub_tau, weights=test_ccf)
#%% Find lag where ccf is max in centre ###
max_lag[n] = sub_tau[np.argmax(test_ccf)]
max_ccf[n] = np.nanmax(test_ccf)
#%% Create and save ccfs if prompted ###
if save_ccf == True:
plt.figure(figsize=[8, 8])
plt.title('DR11 ID: ' + str(bindata['ID']) + ' $\chi^{2}$ = ' +
str(bindata['Chi_K']))
plt.errorbar(tau_arr,
ccf,
yerr=ccf_err,
import weightedstats as ws my_data = [1, 2, 3, 4, 5] my_weights = [10, 1, 1, 1, 9] # Ordinary (unweighted) mean and median print(ws.mean(my_data)) # equivalent to ws.weighted_mean(my_data) ws.median(my_data) # equivalent to ws.weighted_median(my_data) # Weighted mean and median ws.weighted_mean(my_data, weights=my_weights) ws.weighted_median(my_data, weights=my_weights) # Special weighted mean and median functions for use with numpy arrays ws.numpy_weighted_mean(my_data, weights=my_weights) ws.numpy_weighted_median(my_data, weights=my_weights)
#%% Calculate the CCF at various tau values ###
out = np.array([
vari_funcs.cross_correlation.cross_correlate(corr_test_k_flux,
corr_test_j_flux,
tau,
type='dcf')
for tau in tau_arr
])
### Unpack values ###
ccf = out[:, 0]
ccf_err = out[:, 1]
#%% Find weighted mean and skew of ccf ###
mean_lag[n] = ws.numpy_weighted_mean(tau_arr, weights=ccf)
median_lag[n] = ws.numpy_weighted_median(tau_arr, weights=ccf)
ccf_skew[n] = skew(ccf)
#%% Make plots ###
plt.figure(2, figsize=[10, 10])
#plt.subplot(211)
#plt.plot(tau_arr, ccf,'o')
plt.errorbar(tau_arr, ccf, yerr=ccf_err, fmt='o', label=label)
# plt.vlines(mean_lag[n], -0.015,0.02, color='C'+str(n), linestyle='dashed')
# plt.vlines(median_lag[n], -0.015,0.02, color='C'+str(n), linestyle='dotted')
plt.xlabel('Lag (months)')
plt.ylabel('Discrete Cross-Correlation Function')
plt.ylim(-0.5, 0.9)
plt.grid(True)
plt.legend(loc='lower center')