import config as c
import numpy as np
from pathlib import Path
import matplotlib.pyplot as plt
import data.data_helpers as data_helpers
import data.prepare_data as prepare_data
import evaluate
from evaluate import compute_calibration,sample_posterior
import time
import torch
#compute_calibration = evaluate.compute_calibration
#sample_posterior = evaluate.sample_posterior
x_all, y_all, ana_all = data_helpers.concatenate_test_set(c.evaluation_samples)
def show_error_correlations(x=x_all,y=y_all,load=False):
#plot error co2 against: xco2, "albedo_o2","albedo_sco2","albedo_wco2", "tcwv" 4
#and: "year","xco2_apriori","altitude","psurf","t700","longitude","latitude" 7
#"snr_wco2","snr_sco2","snr_o2a","aod_bc","aod_dust","aod_ice","aod_oc","aod_seasalt","aod_sulfate","aod_total","aod_water"
params=prepare_data.x_to_params(x)
spectra=prepare_data.y_to_spectra(y)
post = sample_posterior(y)
diff = torch.mean(torch.FloatTensor(post), dim = 1)-x
#post_params =prepare_data.x_to_params(post)
_,_,uncert_intervals,_, post_params = compute_calibration(x,y,load=load)
uncert_error_co2=uncert_intervals[68,:,c.co2_pos]/2
diff = np.mean(post_params, axis = 1) - params
diff_co2 = diff [:, 0]
1000) #concatenate_test_set(1000)#400)#20)#400)
print(torch.max(y_all), torch.min(y_all))
print(torch.max(y_all[:, -params_in_spectrum:], dim=0),
torch.min(y_all[:, -params_in_spectrum:], dim=0))
print(torch.max(y_all[:, :prepare_data.spec_length]),
torch.min(y_all[:, :prepare_data.spec_length]))
print(
torch.max(y_all[:, prepare_data.spec_length:2 * prepare_data.spec_length]),
torch.min(y_all[:, prepare_data.spec_length:2 * prepare_data.spec_length]))
print(
torch.max(y_all[:, 2 * prepare_data.spec_length:3 *
prepare_data.spec_length]),
torch.min(y_all[:, 2 * prepare_data.spec_length:3 *
prepare_data.spec_length]))
x_all, y_all, ana_all = data_helpers.concatenate_test_set(
1000) #concatenate_test_set(1000)#400)#20)#400)
print(torch.max(y_all), torch.min(y_all))
#assert 0
#x=prepare_data.x
#params=prepare_data.params
#spectra = prepare_data.spectra
#params_in_spectrum = prepare_data.number_external_params #5 or 18
#params_names = prepare_data.params_names#list(prepare_data.namedict.keys())
#spec_length = prepare_data.spec_length
def show_param_hists(parameters,
n_parameters=n_parameters,
offset=0,
name="",