continue
r2 = np.zeros(len(im_sampling_plot_agc_gdf_dict))
feat_corr = OrderedDict()
for feat_i, feat_key in enumerate(feats_of_interest):
ref_feat = ref_im_sampling_plot_agc_gdf['feats'][feat_key]
feat = im_calib_plot_gdf['feats'][feat_key]
(slope, intercept, r2, p, stde) = stats.linregress(ref_feat, feat)
feat_corr[feat_key] = r2
# print(f'slope: {slope}, intercept: {intercept}')
if False:
pyplot.figure(feat_i)
pyplot.subplot(2, 2, image_i)
xlabel = f'WV3 Oct 2017 - {feat_key}'
ylabel = f'{image_key} - {feat_key}'
vis.scatter_ds(
pd.DataFrame(data=np.array([ref_feat, feat]).transpose(),
columns=[xlabel, ylabel]))
image_feat_corr[f'+{image_key}'] = feat_corr
image_feat_corr_df = pd.DataFrame.from_dict(image_feat_corr)
logger.info('Correlation of features between WV3 Oct 2017 and...')
logger.info('\n' + image_feat_corr_df.to_string())
logger.info('Average correlation of features over images')
logger.info('\n' + image_feat_corr_df.mean(axis=1).to_string())
logger.info('Average correlation of features over images')
logger.info('\n' + image_feat_corr_df.mean(axis=1).to_string())
## run the temporal calibration accuracy test with univariate model and log(mean(R/pan) feature
calib_feat_keys = ['log(mean(R/pan))']
model_data_dict = {}
for image_key, im_sampling_plot_agc_gdf in im_sampling_plot_agc_gdf_dict.items(
## write per-plant and per-plot ABC/AGC etc files
agc_plot_est.write_abc_plant_file(out_file_name=plant_abc_file_name)
agc_plot_est.write_agc_plot_file(out_file_name=plot_agc_file_name)
## write out surrogate map
with open(surrogate_file_name, 'w', newline='') as outfile:
writer = DictWriter(outfile, list(agc_plot_est.abc_aggregator.master_surrogate_dict.values())[100].keys())
writer.writeheader()
writer.writerows(list(agc_plot_est.abc_aggregator.master_surrogate_dict.values()))
## plot relationships between plant volume and C stocks
f1 = pyplot.figure('Relation between plant vol. and C stocks')
f1.set_size_inches(10, 4, forward=True)
ax = pyplot.subplot(1, 2, 1, aspect='equal')
vis.scatter_ds(agc_plot_est.plot_summary_agc_df, x_col='VolHa', y_col='AbcHa', xfn=lambda x: x / 1000., yfn=lambda y: y / 1000.,
x_label='Biomass volume ($10^3$ m$^{3}$ ha$^{-1}$)', y_label='ABC (t C ha$^{-1}$)')
ax.set_title('(a)')
ax = pyplot.subplot(1, 2, 2, aspect='equal')
vis.scatter_ds(agc_plot_est.plot_summary_agc_df, x_col='VolHa', y_col='AgcHa', xfn=lambda x: x / 1000., yfn=lambda y: y / 1000.,
x_label='Biomass volume ($10^3$ m$^{3}$ ha$^{-1}$)', y_label='AGC (t C ha$^{-1}$)')
ax.set_title('(b)')
f1.tight_layout()
pyplot.pause(0.2)
f1.savefig(root_path.joinpath('data/outputs/plots/vol_vs_agc_scatter.png'), dpi=300)
f2 = pyplot.figure('Relation between Litter C and ABC')
f2.set_size_inches(5, 4, forward=True)
vis.scatter_ds(agc_plot_est.plot_summary_agc_df, x_col='LitterCHa', y_col='AbcHa', xfn=lambda x: x / 1000., yfn=lambda y: y / 1000.,
x_label='Litter C (t C ha$^{-1}$)', y_label='ABC (t C ha$^{-1}$)')
f2.tight_layout()
orient='index')
for key in ['AbcHa2', 'AgcHa2']: # append to im_plot_data_gdf
im_plot_agc_gdf[('data', key)] = carbon_polynorm_df[key]
# fix stratum labels
im_plot_agc_gdf.loc[im_plot_agc_gdf['data']['Stratum'] == 'Degraded',
('data', 'Stratum')] = 'Severe'
im_plot_agc_gdf.loc[im_plot_agc_gdf['data']['Stratum'] == 'Intact',
('data', 'Stratum')] = 'Pristine'
# make an example scatter plot of feature vs AGC/ABC
pyplot.figure()
vis.scatter_ds(im_plot_agc_gdf,
x_col=('feats', '(mean(pan/R))'),
y_col=('data', 'AgcHa'),
class_col=('data', 'Stratum'),
xfn=lambda x: np.log10(x),
do_regress=True)
## select and analyse best features for predicting AGC with linear regression
# TODO - experiment with cv vals in fs and eval below - has a big effect on what is selected and how it is scored.
y = im_plot_agc_gdf['data']['AgcHa']
selected_feats_df, selected_scores = fs.forward_selection(
im_plot_agc_gdf['feats'], y, max_num_feats=25, cv=5, score_fn=None)
# calculate scores of selected features with LOOCV
selected_loocv_scores = []
num_feats = range(0, len(selected_scores))
for i in num_feats:
scores, predicted = fs.score_model(selected_feats_df.to_numpy()[:, :i + 1],
y,
im_plot_agc_gdf.loc[im_plot_agc_gdf['data']['Stratum'] == 'Degraded',
('data', 'Stratum')] = 'Severe'
im_plot_agc_gdf.loc[im_plot_agc_gdf['data']['Stratum'] == 'Intact',
('data', 'Stratum')] = 'Pristine'
# make an example scatter plot of feature vs AGC/ABC
pyplot.rcParams["font.family"] = "arial"
pyplot.rcParams["font.size"] = "12"
pyplot.rcParams["font.style"] = "normal"
pyplot.rcParams['legend.fontsize'] = 'medium'
pyplot.rcParams['figure.titlesize'] = 'medium'
pyplot.figure()
vis.scatter_ds(im_plot_agc_gdf,
x_col=('feats', 'log(mean(pan/R))'),
y_col=('data', 'AgcHa'),
class_col=('data', 'Stratum'),
xfn=lambda x: x,
do_regress=True)
## select and analyse best features for predicting AGC with linear regression
# TODO - experiment with cv vals in fs and eval below - has a big effect on what is selected and how it is scored.
# eg, cv=10, selects ~45 features and gets R2~.93, cv=5 selects ~10 features with R2~.88
y = im_plot_agc_gdf['data']['AgcHa']
# selected_feats_df, selected_scores = fs.fcr(im_plot_agc_gdf['feats'], y, max_num_feats=None, dist_fn=None, score_fn=None)
cv = 5
selected_feats_df, selected_scores = fs.forward_selection(
im_plot_agc_gdf['feats'], y, max_num_feats=25, cv=cv, score_fn=None)
# calculate scores of selected features with LOOCV
selected_loocv_scores = []
num_feats = range(1, len(selected_scores) + 1)