@ -1,36 +1,92 @@
from scipy . optimize import curve_fit
import llepe import llepe
import pandas as pd import pandas as pd
import numpy as np import numpy as np
import json
def linear ( x , a , b ) : def mod_lin_param_df ( lp_df , input_val , mini_species , mini_lin_param ) :
return a * x + b
new_lp_df = lp_df . copy ( )
index = new_lp_df . index [ new_lp_df [ ' species ' ] == mini_species ] . tolist ( ) [ 0 ]
new_lp_df . at [ index , mini_lin_param ] = input_val
return new_lp_df
species_list = ' Nd,Pr,Ce,La,Dy,Sm,Y ' . split ( ' , ' ) species_list = ' Nd,Pr,Ce,La,Dy,Sm,Y ' . split ( ' , ' )
pitzer_param_list = [ ' beta0 ' , ' beta1 ' , ' Cphi ' ] pitzer_param_list = [ ' beta0 ' , ' beta1 ' ]
lin_param_list = [ ' slope ' , ' intercept ' ]
meas_pitzer_param_df = pd . read_csv ( " ../../data/csvs/may_pitzer_params.csv " ) meas_pitzer_param_df = pd . read_csv ( " ../../data/csvs/may_pitzer_params.csv " )
pitzer_params_filename = " ../../data/jsons/min_h0_pitzer_params.txt "
with open ( pitzer_params_filename ) as file :
pitzer_params_dict = json . load ( file )
ext_h0_filename = " ../../data/jsons/min_h0_guess_ext_h0.txt "
with open ( ext_h0_filename ) as file :
ext_h0_dict = json . load ( file )
labeled_data = pd . read_csv ( " ../../data/csvs/ " labeled_data = pd . read_csv ( " ../../data/csvs/ "
" zeroes_removed_PC88A_HCL_NdPrCeLaDySmY.csv " )
" zeroes_removed_PC88A_HCL_NdPrCeLaDySmY.csv " )
exp_data = labeled_data . drop ( labeled_data . columns [ 0 ] , axis = 1 ) exp_data = labeled_data . drop ( labeled_data . columns [ 0 ] , axis = 1 )
xml_file = " PC88A_HCL_NdPrCeLaDySmY_w_pitzer.xml " xml_file = " PC88A_HCL_NdPrCeLaDySmY_w_pitzer.xml "
lin_param_df = pd . read_csv ( " ../../data/csvs "
" /zeroes_removed_min_h0_pitzer_lin_params.csv " )
estimator_params = { ' exp_data ' : exp_data ,
' phases_xml_filename ' : xml_file ,
' phase_names ' : [ ' HCl_electrolyte ' , ' PC88A_liquid ' ] ,
' aq_solvent_name ' : ' H2O(L) ' ,
' extractant_name ' : ' (HA)2(org) ' ,
' diluant_name ' : ' dodecane ' ,
' complex_names ' : [ ' {0} (H(A)2)3(org) ' . format ( species )
for species in species_list ] ,
' extracted_species_ion_names ' : [ ' {0} +++ ' . format ( species )
for species in
species_list ] ,
' aq_solvent_rho ' : 1000.0 ,
' extractant_rho ' : 960.0 ,
' diluant_rho ' : 750.0 ,
' temp_xml_file_path ' : ' outputs/temp.xml ' ,
' objective_function ' : llepe . lmse_perturbed_obj
}
estimator = llepe . LLEPE ( * * estimator_params )
def ext_to_complex ( h0 , custom_obj_dict , mini_species ) :
linear_params = custom_obj_dict [ ' lin_param_df ' ]
row = linear_params [ linear_params [ ' species ' ] == mini_species ]
return row [ ' slope ' ] . values [ 0 ] * h0 [ 0 ] + row [ ' intercept ' ] . values [ 0 ]
dependant_params_dict = { }
for species , complex_name in zip ( species_list ,
estimator_params [ ' complex_names ' ] ) :
inner_dict = { ' upper_element_name ' : ' species ' ,
' upper_attrib_name ' : ' name ' ,
' upper_attrib_value ' : complex_name ,
' lower_element_name ' : ' h0 ' ,
' lower_attrib_name ' : None ,
' lower_attrib_value ' : None ,
' input_format ' : ' {0} ' ,
' function ' : ext_to_complex ,
' kwargs ' : { " mini_species " : species } ,
' independent_params ' : ' (HA)2(org)_h0 ' }
dependant_params_dict [ ' {0} _h0 ' . format ( complex_name ) ] = inner_dict
estimator . update_xml ( pitzer_params_dict )
estimator . set_custom_objects_dict ( { ' lin_param_df ' : lin_param_df } )
estimator . set_dependant_params_dict ( dependant_params_dict )
estimator . update_xml ( ext_h0_dict ,
dependant_params_dict = dependant_params_dict )
eps = 1e-4 eps = 1e-4
mini_eps = 1e-8 mini_eps = 1e-8
x_guesses = [ [ - 5178500.0 , - 1459500.0 ] , pitzer_guess_dict = { ' species ' : [ ] ,
[ - 5178342.857142857 , - 1460300.0 ] ,
' beta0 ' : [ ] ,
[ - 5178342.857142857 , - 1459500.0 ] ,
' beta1 ' : [ ] }
[ - 5178342.857142857 , - 1458300.0 ] ,
for species in species_list :
[ - 5178185.714285715 , - 1459900.0 ] ,
pitzer_guess_dict [ ' species ' ] . append ( species )
[ - 5178185.714285715 , - 1459500.0 ] ,
for param in pitzer_param_list :
[ - 5178185.714285715 , - 1459100.0 ] ,
mini_dict = pitzer_params_dict [ ' {0} _ {1} ' . format ( species , param ) ]
[ - 5178185.714285715 , - 1458300.0 ] ,
value = mini_dict [ ' input_value ' ]
[ - 5178028.571428572 , - 1459900.0 ] ,
pitzer_guess_dict [ param ] . append ( value )
[ - 5178028.571428572 , - 1459100.0 ] ,
pitzer_guess_df = pd . DataFrame ( pitzer_guess_dict )
[ - 5178028.571428572 , - 1458300.0 ] ,
ext_h0_guess = ext_h0_dict [ ' (HA)2(org)_h0 ' ] [ ' input_value ' ]
[ - 5177557.142857143 , - 1459900.0 ] ,
lin_guess_df = lin_param_df . copy ( )
[ - 5177400.0 , - 1460300.0 ] ]
pitzer_guess_df = meas_pitzer_param_df . copy ( )
ignore_list = [ ] ignore_list = [ ]
optimizer = ' scipy_minimize ' optimizer = ' scipy_minimize '
output_dict = { ' iter ' : [ 0 ] , output_dict = { ' iter ' : [ 0 ] ,
@ -49,17 +105,8 @@ while rel_diff > 1e-4:
best_obj = 1e20
best_obj = 1e20
output_dict [ ' iter ' ] . append ( i )
output_dict [ ' iter ' ] . append ( i )
for species in species_list :
for species in species_list :
print ( species )
lower_species = species . lower ( )
lower_species = species . lower ( )
opt_values = {
' (HA)2(org)_h0 ' : [ ] ,
' {0} (H(A)2)3(org)_h0 ' . format ( species ) : [ ] ,
' beta0 ' : [ ] ,
' beta1 ' : [ ] ,
' Cphi ' : [ ] ,
' obj_value ' : [ ] ,
' guess ' : [ ] }
for ind1 , x_guess in enumerate ( x_guesses ) :
print ( ind1 )
info_dict = { ' (HA)2(org)_h0 ' : { ' upper_element_name ' : ' species ' ,
info_dict = { ' (HA)2(org)_h0 ' : { ' upper_element_name ' : ' species ' ,
' upper_attrib_name ' : ' name ' ,
' upper_attrib_name ' : ' name ' ,
' upper_attrib_value ' : ' (HA)2(org) ' ,
' upper_attrib_value ' : ' (HA)2(org) ' ,
@ -67,18 +114,8 @@ while rel_diff > 1e-4:
' lower_attrib_name ' : None ,
' lower_attrib_name ' : None ,
' lower_attrib_value ' : None ,
' lower_attrib_value ' : None ,
' input_format ' : ' {0} ' ,
' input_format ' : ' {0} ' ,
' input_value ' : x_guess [ 1 ] } ,
' input_value ' : ext_h0_guess } }
' {0} (H(A)2)3(org)_h0 ' . format ( species ) : {
' upper_element_name ' : ' species ' ,
' upper_attrib_name ' : ' name ' ,
' upper_attrib_value ' : ' {0} (H(A)2)3(org) ' . format (
species ) ,
' lower_element_name ' : ' h0 ' ,
' lower_attrib_name ' : None ,
' lower_attrib_value ' : None ,
' input_format ' : ' {0} ' ,
' input_value ' : x_guess [ 0 ] } ,
}
for pitzer_param in pitzer_param_list :
for pitzer_param in pitzer_param_list :
if ' {0} _ {1} ' . format ( species , pitzer_param ) not in ignore_list :
if ' {0} _ {1} ' . format ( species , pitzer_param ) not in ignore_list :
pitzer_row = pitzer_guess_df [
pitzer_row = pitzer_guess_df [
@ -96,27 +133,20 @@ while rel_diff > 1e-4:
}
}
info_dict [ ' {0} _ {1} ' . format (
info_dict [ ' {0} _ {1} ' . format (
species , pitzer_param ) ] = inner_dict
species , pitzer_param ) ] = inner_dict
llepe_params = {
for lin_param in lin_param_list :
' exp_data ' : exp_data ,
if ' {0} _ {1} ' . format ( species , lin_param ) not in ignore_list :
' phases_xml_filename ' : xml_file ,
lin_row = lin_guess_df [ lin_guess_df [ ' species ' ] == species ]
' opt_dict ' : info_dict ,
inner_dict = { ' custom_object_name ' : ' lin_param_df ' ,
' phase_names ' : [ ' HCl_electrolyte ' , ' PC88A_liquid ' ] ,
' function ' : mod_lin_param_df ,
' aq_solvent_name ' : ' H2O(L) ' ,
' kwargs ' : { ' mini_species ' : species ,
' extractant_name ' : ' (HA)2(org) ' ,
' mini_lin_param ' : lin_param } ,
' diluant_name ' : ' dodecane ' ,
' input_value ' : lin_row [ lin_param ] . values [ 0 ]
' complex_names ' : [ ' {0} (H(A)2)3(org) ' . format ( species )
for species in species_list ] ,
' extracted_species_ion_names ' : [ ' {0} +++ ' . format ( species )
for species in species_list ] ,
' aq_solvent_rho ' : 1000.0 ,
' extractant_rho ' : 960.0 ,
' diluant_rho ' : 750.0 ,
' objective_function ' : llepe . lmse_perturbed_obj ,
' optimizer ' : optimizer ,
' temp_xml_file_path ' : ' outputs/temp.xml '
}
}
estimator = llepe . LLEPE ( * * llepe_params )
info_dict [ ' {0} _ {1} ' . format (
estimator . update_xml ( llepe_params [ ' opt_dict ' ] )
species , lin_param ) ] = inner_dict
estimator . set_opt_dict ( info_dict )
estimator . update_custom_objects_dict ( info_dict )
estimator . update_xml ( info_dict )
obj_kwargs = { ' species_list ' : [ species ] , ' epsilon ' : 1e-100 }
obj_kwargs = { ' species_list ' : [ species ] , ' epsilon ' : 1e-100 }
bounds = [ ( 1e-1 , 1e1 ) ] * len ( info_dict )
bounds = [ ( 1e-1 , 1e1 ) ] * len ( info_dict )
optimizer_kwargs = { " method " : ' l-bfgs-b ' ,
optimizer_kwargs = { " method " : ' l-bfgs-b ' ,
@ -127,49 +157,26 @@ while rel_diff > 1e-4:
if obj_value < best_obj :
if obj_value < best_obj :
best_obj = obj_value
best_obj = obj_value
keys = list ( opt_dict . keys ( ) )
keys = list ( opt_dict . keys ( ) )
info1 = [ opt_dict [ key ] [ ' input_value ' ] for key in keys ]
for lin_param in lin_param_list :
info1 . append ( obj_value )
mini_dict = opt_dict [ ' {0} _ {1} ' . format ( species , lin_param ) ]
info1 . append ( x_guess )
value = mini_dict [ ' input_value ' ]
opt_values_keys = opt_values . keys ( )
output_dict [ ' {0} _ {1} ' . format ( species , lin_param ) ] . append ( value )
for ind , key in enumerate ( opt_values_keys ) :
opt_values [ key ] . append ( info1 [ ind ] )
opt_value_df = pd . DataFrame ( opt_values )
p_opt , p_cov = curve_fit ( linear ,
opt_value_df [ ' (HA)2(org)_h0 ' ] . values ,
opt_value_df [ ' {0} (H(A)2)3(org)_h0 ' . format (
species ) ] . values )
slope , intercept = p_opt
output_dict [ ' {0} _slope ' . format ( species ) ] . append ( slope )
output_dict [ ' {0} _intercept ' . format ( species ) ] . append ( intercept )
min_h0_df = opt_value_df [
opt_value_df [ ' (HA)2(org)_h0 ' ]
== opt_value_df [ ' (HA)2(org)_h0 ' ] . min ( ) ]
update_pitzer_dict = { }
for pitzer_param in pitzer_param_list :
for pitzer_param in pitzer_param_list :
key_name = ' {0} _ {1} ' . format ( species , pitzer_param )
mini_dict = opt_dict [ ' {0} _ {1} ' . format ( species , pitzer_param ) ]
output_dict [ key_name ] . append ( min_h0_df [ pitzer_param ] . values [ 0 ] )
value = mini_dict [ ' input_value ' ]
output_dict [ ' {0} _ {1} ' . format ( species , pitzer_param ) ] . append ( value )
inner_dict = { ' upper_element_name ' : ' binarySaltParameters ' ,
estimator . update_custom_objects_dict ( info_dict )
' upper_attrib_name ' : ' cation ' ,
estimator . update_xml ( opt_dict )
' upper_attrib_value ' :
' {0} +++ ' . format ( species ) ,
' lower_element_name ' : pitzer_param ,
' lower_attrib_name ' : None ,
' lower_attrib_value ' : None ,
' input_format ' : ' {0} , 0.0, 0.0, 0.0, 0.0 ' ,
' input_value ' :
min_h0_df [ pitzer_param ] . values [ 0 ]
}
update_pitzer_dict [ ' {0} _ {1} ' . format (
species , pitzer_param ) ] = inner_dict
estimator . update_xml ( update_pitzer_dict )
pitzer_guess_dict = { ' species ' : [ ] ,
pitzer_guess_dict = { ' species ' : [ ] ,
' beta0 ' : [ ] ,
' beta0 ' : [ ] ,
' beta1 ' : [ ] ,
' beta1 ' : [ ] ,
' Cphi ' : [ ] }
}
lin_guess_dict = { ' species ' : [ ] ,
' slope ' : [ ] ,
' intercept: ' : [ ] }
for species in species_list :
for species in species_list :
pitzer_guess_dict [ ' species ' ] . append ( species )
pitzer_guess_dict [ ' species ' ] . append ( species )
lin_guess_dict [ ' species ' ] . append ( species )
for pitzer_param in pitzer_param_list :
for pitzer_param in pitzer_param_list :
value_list = output_dict [ ' {0} _ {1} ' . format ( species , pitzer_param ) ]
value_list = output_dict [ ' {0} _ {1} ' . format ( species , pitzer_param ) ]
value = value_list [ - 1 ]
value = value_list [ - 1 ]
@ -182,7 +189,20 @@ while rel_diff > 1e-4:
np . abs ( value_list [ - 3 ] ) )
np . abs ( value_list [ - 3 ] ) )
if mini_rel_diff1 < mini_eps and mini_rel_diff2 < mini_eps :
if mini_rel_diff1 < mini_eps and mini_rel_diff2 < mini_eps :
ignore_list . append ( ' {0} _ {1} ' . format ( species , pitzer_param ) )
ignore_list . append ( ' {0} _ {1} ' . format ( species , pitzer_param ) )
for lin_param in lin_param_list :
value_list = output_dict [ ' {0} _ {1} ' . format ( species , lin_param ) ]
value = value_list [ - 1 ]
lin_guess_dict [ lin_param ] . append ( value )
if i > 2 :
mini_rel_diff1 = np . abs ( value_list [ - 1 ]
- value_list [ - 2 ] ) / (
np . abs ( value_list [ - 2 ] ) )
mini_rel_diff2 = np . abs ( value_list [ - 2 ] - value_list [ - 3 ] ) / (
np . abs ( value_list [ - 3 ] ) )
if mini_rel_diff1 < mini_eps and mini_rel_diff2 < mini_eps :
ignore_list . append ( ' {0} _ {1} ' . format ( species , lin_param ) )
pitzer_guess_df = pd . DataFrame ( pitzer_guess_dict )
pitzer_guess_df = pd . DataFrame ( pitzer_guess_dict )
lin_guess_df = pd . DataFrame ( lin_guess_dict )
output_dict [ ' best_obj ' ] . append ( best_obj )
output_dict [ ' best_obj ' ] . append ( best_obj )
output_df = pd . DataFrame ( output_dict )
output_df = pd . DataFrame ( output_dict )
@ -191,4 +211,4 @@ while rel_diff > 1e-4:
rel_diff = np . sum ( np . abs ( new_row - old_row ) / np . abs ( old_row ) )
rel_diff = np . sum ( np . abs ( new_row - old_row ) / np . abs ( old_row ) )
output_dict [ ' rel_diff ' ] . append ( rel_diff )
output_dict [ ' rel_diff ' ] . append ( rel_diff )
output_df = pd . DataFrame ( output_dict )
output_df = pd . DataFrame ( output_dict )
output_df . to_csv ( ' outputs/iterative_fitter_output _df .csv' )
output_df . to_csv ( ' outputs/iterative_fitter_output .csv' )
titusquah
5 years ago