def bootstrap_SAD(name_site_combo, model, in_dir = './data/', out_dir = './out_files/', Niter = 200): """A general function of bootstrapping for SAD applying to all four models. Inputs: name_site_combo: a list with dat_name and site model - takes one of four values 'ssnt_0', 'ssnt_1', 'asne', or 'agsne' in_dir - directory of raw data out_dir - directory used both in input (obs_pred.csv file) and output Niter - number of bootstrap samples Output: Writes to disk, with one file for R^2 and one for KS statistic. """ dat_name, site = name_site_combo dat = wk.import_raw_data(in_dir + dat_name + '.csv') dat_site = dat[dat['site'] == site] dat_clean = clean_data_agsne(dat_site) G, S, N, E = get_GSNE(dat_clean) beta_ssnt = mete.get_beta(S, N, version = 'untruncated') beta_asne = mete.get_beta(S, N) lambda1, beta, lambda3 = agsne.get_agsne_lambdas(G, S, N, E) sad_agsne = mete_distributions.sad_agsne([G, S, N, E], [lambda1, beta, lambda3, agsne.agsne_lambda3_z(lambda1, beta, S) / lambda3]) dist_for_model = {'ssnt_0': stats.logser(np.exp(-beta_ssnt)), 'ssnt_1': stats.logser(np.exp(-beta_ssnt)), 'asne': md.trunc_logser(np.exp(-beta_asne), N), 'agsne': sad_agsne} dist = dist_for_model[model] pred_obs = wk.import_obs_pred_data(out_dir + dat_name + '_obs_pred_rad_' + model + '.csv') pred = pred_obs[pred_obs['site'] == site]['pred'][::-1] obs = pred_obs[pred_obs['site'] == site]['obs'][::-1] out_list_rsquare = [dat_name, site, str(mtools.obs_pred_rsquare(np.log10(obs), np.log10(pred)))] emp_cdf = mtools.get_emp_cdf(obs) out_list_ks = [dat_name, site, str(max(abs(emp_cdf - np.array([dist.cdf(x) for x in obs]))))] for i in range(Niter): obs_boot = np.array(sorted(dist.rvs(S))) cdf_boot = np.array([dist.cdf(x) for x in obs_boot]) emp_cdf_boot = mtools.get_emp_cdf(obs_boot) out_list_rsquare.append(str(mtools.obs_pred_rsquare(np.log10(obs_boot), np.log10(pred)))) out_list_ks.append(str(max(abs(emp_cdf_boot - np.array(cdf_boot))))) wk.write_to_file(out_dir + 'SAD_bootstrap_' + model + '_rsquare.txt', ",".join(str(x) for x in out_list_rsquare)) wk.write_to_file(out_dir + 'SAD_bootstrap_' + model + '_ks.txt', ",".join(str(x) for x in out_list_ks))
def bootstrap_ISD(name_site_combo, model, in_dir = './data/', out_dir = './out_files/', Niter = 200): """A general function of bootstrapping for ISD applying to all four models. Inputs: name_site_combo: a list with dat_name and site model - takes one of four values 'ssnt_0', 'ssnt_1', 'asne', or 'agsne' in_dir - directory of raw data out_dir - directory used both in input (obs_pred.csv file) and output Niter - number of bootstrap samples Output: Writes to disk, with one file for R^2 and one for KS statistic. """ dat_name, site = name_site_combo dat = wk.import_raw_data(in_dir + dat_name + '.csv') dat_site = dat[dat['site'] == site] dat_clean = clean_data_agsne(dat_site) G, S, N, E = get_GSNE(dat_clean) lambda1, beta, lambda3 = agsne.get_agsne_lambdas(G, S, N, E) isd_agsne = mete_distributions.psi_agsne([G, S, N, E], [lambda1, beta, lambda3, agsne.agsne_lambda3_z(lambda1, beta, S) / lambda3]) isd_asne = mete_distributions.psi_epsilon_approx(S, N, E) dbh_scaled = np.array(dat_clean['dbh'] / min(dat_clean['dbh'])) isd_ssnt_0 = ssnt_isd_bounded(1, N / (sum(dbh_scaled ** 1) - N)) isd_ssnt_1 = ssnt_isd_bounded(2/3, N / (sum(dbh_scaled ** (2/3)) - N)) dist_for_model = {'ssnt_0': isd_ssnt_0, 'ssnt_1': isd_ssnt_1, 'asne': isd_asne, 'agsne': isd_agsne} dist = dist_for_model[model] pred_obs = wk.import_obs_pred_data(out_dir + dat_name + '_obs_pred_isd_' + model + '.csv') pred = pred_obs[pred_obs['site'] == site]['pred'] obs = pred_obs[pred_obs['site'] == site]['obs'] out_list_rsquare = [dat_name, site, str(mtools.obs_pred_rsquare(np.log10(obs), np.log10(pred)))] wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_rsquare.txt', ",".join(str(x) for x in out_list_rsquare), new_line = False) emp_cdf = mtools.get_emp_cdf(obs) out_list_ks = [dat_name, site, str(max(abs(emp_cdf - np.array([dist.cdf(x) for x in obs]))))] wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', ",".join(str(x) for x in out_list_ks), new_line = False) num_pools = 8 # Assuming that 8 pools are to be created for i in xrange(Niter): obs_boot = [] cdf_boot = [] while len(obs_boot) < N: pool = multiprocessing.Pool(num_pools) out_sample = pool.map(wk.generate_isd_sample, [dist for j in xrange(num_pools)]) for combo in out_sample: cdf_sublist, sample_sublist = combo obs_boot.extend(sample_sublist) cdf_boot.extend(cdf_sublist) pool.close() pool.join() if model in ['asne', 'agsne']: obs_boot = np.sort(obs_boot[:N]) ** 0.5 # Convert to diameter else: obs_boot = np.sort(obs_boot[:N]) sample_rsquare = mtools.obs_pred_rsquare(np.log10(obs_boot), np.log10(pred)) sample_ks = max(abs(emp_cdf - np.sort(cdf_boot[:N]))) wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_rsquare.txt', "".join([',', str(sample_rsquare)]), new_line = False) wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', "".join([',', str(sample_ks)]), new_line = False) wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_rsquare.txt', '\t') wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', '\t') wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', ",".join(str(x) for x in out_list_ks))
def bootstrap_ISD(name_site_combo, model, in_dir='./data/', out_dir='./out_files/', Niter=200): """A general function of bootstrapping for ISD applying to all four models. Inputs: name_site_combo: a list with dat_name and site model - takes one of four values 'ssnt_0', 'ssnt_1', 'asne', or 'agsne' in_dir - directory of raw data out_dir - directory used both in input (obs_pred.csv file) and output Niter - number of bootstrap samples Output: Writes to disk, with one file for R^2 and one for KS statistic. """ dat_name, site = name_site_combo dat = wk.import_raw_data(in_dir + dat_name + '.csv') dat_site = dat[dat['site'] == site] dat_clean = clean_data_agsne(dat_site) G, S, N, E = get_GSNE(dat_clean) lambda1, beta, lambda3 = agsne.get_agsne_lambdas(G, S, N, E) isd_agsne = mete_distributions.psi_agsne([G, S, N, E], [ lambda1, beta, lambda3, agsne.agsne_lambda3_z(lambda1, beta, S) / lambda3 ]) isd_asne = mete_distributions.psi_epsilon_approx(S, N, E) dbh_scaled = np.array(dat_clean['dbh'] / min(dat_clean['dbh'])) isd_ssnt_0 = ssnt_isd_bounded(1, N / (sum(dbh_scaled**1) - N)) isd_ssnt_1 = ssnt_isd_bounded(2 / 3, N / (sum(dbh_scaled**(2 / 3)) - N)) dist_for_model = { 'ssnt_0': isd_ssnt_0, 'ssnt_1': isd_ssnt_1, 'asne': isd_asne, 'agsne': isd_agsne } dist = dist_for_model[model] pred_obs = wk.import_obs_pred_data(out_dir + dat_name + '_obs_pred_isd_' + model + '.csv') pred = pred_obs[pred_obs['site'] == site]['pred'] obs = pred_obs[pred_obs['site'] == site]['obs'] out_list_rsquare = [ dat_name, site, str(mtools.obs_pred_rsquare(np.log10(obs), np.log10(pred))) ] wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_rsquare.txt', ",".join(str(x) for x in out_list_rsquare), new_line=False) emp_cdf = mtools.get_emp_cdf(obs) out_list_ks = [ dat_name, site, str(max(abs(emp_cdf - np.array([dist.cdf(x) for x in obs])))) ] wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', ",".join(str(x) for x in out_list_ks), new_line=False) num_pools = 8 # Assuming that 8 pools are to be created for i in xrange(Niter): obs_boot = [] cdf_boot = [] while len(obs_boot) < N: pool = multiprocessing.Pool(num_pools) out_sample = pool.map(wk.generate_isd_sample, [dist for j in xrange(num_pools)]) for combo in out_sample: cdf_sublist, sample_sublist = combo obs_boot.extend(sample_sublist) cdf_boot.extend(cdf_sublist) pool.close() pool.join() if model in ['asne', 'agsne']: obs_boot = np.sort(obs_boot[:N])**0.5 # Convert to diameter else: obs_boot = np.sort(obs_boot[:N]) sample_rsquare = mtools.obs_pred_rsquare(np.log10(obs_boot), np.log10(pred)) sample_ks = max(abs(emp_cdf - np.sort(cdf_boot[:N]))) wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_rsquare.txt', "".join([',', str(sample_rsquare)]), new_line=False) wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', "".join([',', str(sample_ks)]), new_line=False) wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_rsquare.txt', '\t') wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', '\t') wk.write_to_file(out_dir + 'ISD_bootstrap_' + model + '_ks.txt', ",".join(str(x) for x in out_list_ks))
def bootstrap_SAD(name_site_combo, model, in_dir='./data/', out_dir='./out_files/', Niter=200): """A general function of bootstrapping for SAD applying to all four models. Inputs: name_site_combo: a list with dat_name and site model - takes one of four values 'ssnt_0', 'ssnt_1', 'asne', or 'agsne' in_dir - directory of raw data out_dir - directory used both in input (obs_pred.csv file) and output Niter - number of bootstrap samples Output: Writes to disk, with one file for R^2 and one for KS statistic. """ dat_name, site = name_site_combo dat = wk.import_raw_data(in_dir + dat_name + '.csv') dat_site = dat[dat['site'] == site] dat_clean = clean_data_agsne(dat_site) G, S, N, E = get_GSNE(dat_clean) beta_ssnt = mete.get_beta(S, N, version='untruncated') beta_asne = mete.get_beta(S, N) lambda1, beta, lambda3 = agsne.get_agsne_lambdas(G, S, N, E) sad_agsne = mete_distributions.sad_agsne([G, S, N, E], [ lambda1, beta, lambda3, agsne.agsne_lambda3_z(lambda1, beta, S) / lambda3 ]) dist_for_model = { 'ssnt_0': stats.logser(np.exp(-beta_ssnt)), 'ssnt_1': stats.logser(np.exp(-beta_ssnt)), 'asne': md.trunc_logser(np.exp(-beta_asne), N), 'agsne': sad_agsne } dist = dist_for_model[model] pred_obs = wk.import_obs_pred_data(out_dir + dat_name + '_obs_pred_rad_' + model + '.csv') pred = pred_obs[pred_obs['site'] == site]['pred'][::-1] obs = pred_obs[pred_obs['site'] == site]['obs'][::-1] out_list_rsquare = [ dat_name, site, str(mtools.obs_pred_rsquare(np.log10(obs), np.log10(pred))) ] emp_cdf = mtools.get_emp_cdf(obs) out_list_ks = [ dat_name, site, str(max(abs(emp_cdf - np.array([dist.cdf(x) for x in obs])))) ] for i in range(Niter): obs_boot = np.array(sorted(dist.rvs(S))) cdf_boot = np.array([dist.cdf(x) for x in obs_boot]) emp_cdf_boot = mtools.get_emp_cdf(obs_boot) out_list_rsquare.append( str(mtools.obs_pred_rsquare(np.log10(obs_boot), np.log10(pred)))) out_list_ks.append(str(max(abs(emp_cdf_boot - np.array(cdf_boot))))) wk.write_to_file(out_dir + 'SAD_bootstrap_' + model + '_rsquare.txt', ",".join(str(x) for x in out_list_rsquare)) wk.write_to_file(out_dir + 'SAD_bootstrap_' + model + '_ks.txt', ",".join(str(x) for x in out_list_ks))