get_df_w_modules.py

import pandas as pd
import numpy as np
import os, sys
import shutil
from itertools import islice
from itertools import repeat
from addict import Dict
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import math
from collections import defaultdict
from mpl_toolkits.mplot3d import Axes3D
from chart_studio import plotly
from adjustText import adjust_text
# from chart_studio import pyplot as ply
# import plotly.plotly as py
import plotly.offline as pyoff
import re
import mplcursors
import mpldatacursor
import warnings
import time

from mpl_toolkits.mplot3d import Axes3D
from sklearn.cluster import KMeans

# pymatgen libraries
from pymatgen.core.structure import Structure
from pymatgen.transformations.standard_transformations import SupercellTransformation
from pymatgen.analysis.structure_matcher import StructureMatcher
from pymatgen.io.cif import CifWriter
from pymatgen.io.vasp.inputs import Poscar

# from get_weirdos_ver3_new_cleaned import Operation, Orientation, PreProcessingCONTCAR, ReadStructure, Mapping, Movement, Plot, CreateDataFrame
# splitall, copy_rename_single_file, copy_rename_files, check_folder_existance, weighing_movement
from positionism.functional import func_cartesian, func_directory, func_distance, func_kmeans, func_file
from positionism.preprocessing import create_dataframe, CONTCARorPOSCAR
from positionism.orientation import orient_propagate
from positionism.read import coordinate_and_el, metainfo
from positionism.mapper import analysis, flag_and_map, atom_indexing, labelling, output_CIF, output_weirdos
from positionism.plot import mapping_labelling, movement, structure_analysis
from positionism.pathway_classifier import path_by_tuple_cage

t = time.time()

direc = os.getcwd() # get current working directory

poscar_line_nr_start = 8        # index from 0
poscar_line_nr_end = 60
latticeconstantsmatrix_line_nr_start = 2
cif_line_nr_start = 26          # index from 0

amount_Li = 24
reference_Li_nr = 23    # moved Li is placed in nr 23
folder_name_init_system = "/Init_System"

file_new_system = "CONTCAR"
file_init_system = "POSCAR"

col_excel_geo = "geometry"
col_excel_path = "path"
col_excel_toten = "toten [eV]"

proceed_orientation="False"
proceed_XDATCAR = "True"
proceed_NEB = "True"

amount_P = 4
amount_S = 20
amount_Cl = 4

lattice_constant = 10.2794980000

# litype = 0
# file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_24g"

# litype = 2
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type1_area2" # "Li6PS5Cl_optitype1" # "Li6PS5Cl_type2" # same as: "Li6PS5Cl_type2_2iia_115_new"
# file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_optitype2" # "Li6PS5Cl_type2"
# file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_optitype1n2_strictr_a"

# litype = 3
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type3" # use this
# # # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type3_opti1"
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type3_init"
# file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_optitype1n2_strictr_a_type3_B_noweirdnr" # "Li6PS5Cl_optitype1n2_strictr_a_type3" # "Li6PS5Cl_optitype1n2_strictr_a_type3_A"

litype = 4
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type4_trial2"
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type4_DBSCAN_0_5_a_optitype2"
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type4_31" # "Li6PS5Cl_optitype1n2_strictr_a_type4_weirdo1_var2"
file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_optitype1n2_strictr_a_type4_weirdo1_var2_opti_zoomedin"

# litype = 5
# # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type5"           # better
# # # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type5_trial2_a"
# # # file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type5_trial2_b"
# file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type5_trial"

# litype = 6
# file_perfect_poscar_48n24_wo_cif = "Li6PS5Cl_type5_C_type6_b_type2"

file_perfect_poscar_48n24 = f"{file_perfect_poscar_48n24_wo_cif}.cif"

activate_radius = 1 # [1: r1 for 24g 48htype1 48htype2, 2: r2 for 48htype1 48htype2, 3: r3 for 48htype2]
max_mapping_radius = 0.051 # 0.051 # 0.051 # 0.043 ### 0.018 # 0.015 # 0.043
max_mapping_radius_48htype2 = 0.066 # 0.076 ### 0.075 # 0.051 # 0.076
max_mapping_radius_48htype1_48htype2 = (max_mapping_radius + max_mapping_radius_48htype2) / 2
file_perfect_poscar_24 = "Li6PS5Cl_24_mod_2p27291.cif"

file_name_toten = "toten_final.ods"

if activate_radius == 3:
    folder_name_destination_restructure = f"/restructure_{max_mapping_radius}_{max_mapping_radius_48htype2}_{max_mapping_radius_48htype1_48htype2}_{file_perfect_poscar_48n24_wo_cif}/"
elif activate_radius == 2:
    folder_name_destination_restructure = f"/restructure_{max_mapping_radius}_{max_mapping_radius_48htype2}_{file_perfect_poscar_48n24_wo_cif}/"
elif activate_radius == 1:
    folder_name_destination_restructure = f"/restructure_{max_mapping_radius}_{file_perfect_poscar_48n24_wo_cif}/"
else:
    print("activate_radius is not correct")

# # # # # folder_name_destination_lattice_coeff_input = "/lattice_coeff_input/"
folder_name_perfect_poscar = "/_reference_cif/"
file_restructure = "CONTCAR"
file_restructure_positive = "CONTCAR_positive"
element_restructure = "P"

cif_columns = ['species', 'idx_species', 'unkownvar_1', 'coord_x', 'coord_y', 'coord_z', 'unkownvar_2']
poscar_columns_type2 = ['coord_x', 'coord_y', 'coord_z', 'species']
contcar_columns_type2 = ['coord_x', 'coord_y', 'coord_z']

direc_init_system = direc+str(folder_name_init_system)
# # direc_perfect_system = direc+os.sep+str(file_perfect_poscar_24)
direc_restructure_destination = direc+str(folder_name_destination_restructure)
# # # # # direc_lattice_coeff_input = direc+str(folder_name_destination_lattice_coeff_input)
direc_perfect_poscar = direc+str(folder_name_perfect_poscar)

path_perfect_poscar_24 = os.path.join(direc_perfect_poscar, file_perfect_poscar_24)
path_perfect_poscar_48n24 = os.path.join(direc_perfect_poscar, file_perfect_poscar_48n24)
# path_perfect_poscar_P = os.path.join(direc_perfect_poscar, file_perfect_poscar_P)

dtype = {col_excel_geo: float, col_excel_path: float}

data_toten = pd.read_excel(file_name_toten, dtype=dtype, engine="odf")
data_toten_ori = data_toten
data_toten = data_toten.sort_values(by=["geometry","path"],ignore_index=True,ascending=False)

file_loc = create_dataframe.base(data_toten, file_new_system)

# just refreshing folder
func_directory.check_folder_existance(direc_restructure_destination, empty_folder=True)

# just copy reference file
func_directory.copy_rename_single_file(direc_restructure_destination, direc_perfect_poscar, file_perfect_poscar_24, prefix=None)
func_directory.copy_rename_single_file(direc_restructure_destination, direc_perfect_poscar, file_perfect_poscar_48n24, prefix=None)

# file_loc_important_cols = file_loc.copy()
func_directory.copy_rename_files(file_loc, direc_restructure_destination, file_restructure, prefix=None, savedir = False)

### ADJUSTMENT HERE !!!
if proceed_NEB == "True":
    CONTCARorPOSCAR.edit_to_normal_elements(file_loc, direc_restructure_destination, file_restructure, prefix = None)
else:
    pass

CONTCARorPOSCAR.positive_lessthan1(file_loc, direc_restructure_destination, poscar_line_nr_start, poscar_line_nr_end, contcar_columns_type2, file_type = "CONTCAR", var_name_in = None, var_name_out = "positive", n_decimal=16)

file_loc_mask_1, file_loc_important_cols = orient_propagate.calculate(file_loc, direc_restructure_destination, file_restructure_positive, 
                                                                       path_perfect_poscar_24
                                                                       , proceed_orientation)

ref_structure_48n24 = Structure.from_file(path_perfect_poscar_48n24)
cif_structure = Structure(ref_structure_48n24.lattice, ref_structure_48n24.species, ref_structure_48n24.frac_coords)
cif = CifWriter(cif_structure)
cif.write_file(f"{direc_restructure_destination}{file_perfect_poscar_48n24_wo_cif}_expanded.cif")

## # Reverse file_loc_important_cols for NEB

if proceed_NEB == "True":
    file_loc_important_cols = file_loc_important_cols[::-1].reset_index()
    file_loc_important_cols = file_loc_important_cols.drop('index', axis=1)

coor_ref_structure_48n24 = coordinate_and_el.single_structure(ref_structure_48n24)
coor_ref_structure_48n24_expanded = coordinate_and_el.single_structure(Structure.from_file(f"{direc_restructure_destination}{file_perfect_poscar_48n24_wo_cif}_expanded.cif"))


coordinate_and_el.structures(file_loc_important_cols, mapping = "False")

if activate_radius == 3:
    flag_and_map.all_atoms_of_el(file_loc_important_cols, coor_ref_structure_48n24, "Li", max_mapping_radius)
    flag_and_map.li_48htype1_48htype2(file_loc_important_cols, coor_ref_structure_48n24, "Li", max_mapping_radius_48htype1_48htype2)
    flag_and_map.li_48htypesmerged_level1(file_loc_important_cols, "Li")
    flag_and_map.li_48htype2(file_loc_important_cols, coor_ref_structure_48n24, "Li", max_mapping_radius_48htype2, activate_radius)
    flag_and_map.li_48htypesmerged(file_loc_important_cols, "Li", activate_radius)
elif activate_radius == 2:
    flag_and_map.all_atoms_of_el(file_loc_important_cols, coor_ref_structure_48n24, "Li", max_mapping_radius)
    flag_and_map.li_48htype2(file_loc_important_cols, coor_ref_structure_48n24, "Li", max_mapping_radius_48htype2, activate_radius)
    flag_and_map.li_48htypesmerged(file_loc_important_cols, "Li", activate_radius)
elif activate_radius == 1:
    flag_and_map.all_atoms_of_el(file_loc_important_cols, coor_ref_structure_48n24, "Li", max_mapping_radius)

# flag_and_map.all_atoms_of_el(file_loc_important_cols, coor_ref_structure_48n24, "P", max_mapping_radius)
# flag_and_map.all_atoms_of_el(file_loc_important_cols, coor_ref_structure_48n24, "S", max_mapping_radius)
# flag_and_map.all_atoms_of_el(file_loc_important_cols, coor_ref_structure_48n24, "Cl", max_mapping_radius)
    
atom_indexing.weirdos_el(file_loc_important_cols, "Li", activate_radius)

atom_indexing.correct_idx_and_order_mapped_el(file_loc_important_cols, 
                                                 "Li", activate_radius)
# output_CIF.write_merged_structure(file_loc_important_cols, direc_restructure_destination, 
#                                     amount_Li, amount_P, amount_S, 
#                                     var_savefilename = "mapLi")

labelling.weirdos_to_top_n_closestcoorref_el(file_loc_important_cols, 
                                             coor_ref_structure_48n24, 
                                             "Li", litype)

output_CIF.write_merged_structure(file_loc_important_cols, direc_restructure_destination, 
                                    amount_Li, amount_P, amount_S, activate_radius, 
                                    var_savefilename = "mapLi")

output_CIF.correct_Li_idx(file_loc_important_cols, direc_restructure_destination, 
                                        amount_Li, amount_P, amount_S, amount_Cl, 
                                        var_savefilename_init = "mapLi", 
                                        var_savefilename_new = "mapLi_reindexed")

output_CIF.Edit.format_spacing_cif(file_loc_important_cols, direc_restructure_destination, 
                                   var_savefilename_init = "mapLi_reindexed", 
                                   var_savefilename_new = "mapLi_reindexed")
# # # # Operation.File.delete_files(file_loc_important_cols, direc_restructure_destination, file_name_w_format = "mapLi_reindexed.cif")

output_CIF.correct_Li_idx_weirdos_appended(file_loc_important_cols, direc_restructure_destination, 
                                                         amount_Li, amount_P, amount_S, amount_Cl, 
                                                         activate_radius,var_savefilename_init = "mapLi", 
                                                         var_savefilename_new = "mapLi_reindexed_weirdos_appended")

output_CIF.Edit.format_spacing_cif(file_loc_important_cols, direc_restructure_destination, 
                                   var_savefilename_init = "mapLi_reindexed_weirdos_appended", 
                                   var_savefilename_new = "mapLi_reindexed_weirdos_appended")
# # # Operation.File.delete_files(file_loc_important_cols, direc_restructure_destination, file_name_w_format = "mapLi_reindexed_weirdos_appended.cif")

output_CIF.ascending_Li(file_loc_important_cols, direc_restructure_destination, 
                        var_filename_init = "mapLi_reindexed_weirdos_appended", 
                        var_savefilename_new = "mapLi_reindexed_weirdos_appended_reordered")
# # # Mapping.OutputCIF.format_spacing_cif(file_loc_important_cols, direc_restructure_destination, var_savefilename_init = "mapLi_reindexed_weirdos_appended_reordered", var_savefilename_new = "mapLi_reindexed_weirdos_appended_reordered")

atom_indexing.get_idx_coor_limapped_weirdos_dict(file_loc_important_cols, coor_ref_structure_48n24, 
                                                 activate_radius, litype, el="Li")

labelling.get_label_mapping(file_loc_important_cols, coor_ref_structure_48n24, 
                            "Li", activate_radius, litype)

coor_weirdos_Li = output_weirdos.as_array(file_loc_important_cols, activate_radius)

output_weirdos.create_POSCAR(coor_weirdos_Li, direc_restructure_destination, 
                                     lattice_constant, 
                                     filename = "POSCAR_weirdos")

CONTCARorPOSCAR.convert_to_cif_pymatgen(file_loc_important_cols, direc_restructure_destination, 
                                        file_restructure = "CONTCAR_positive", 
                                        var_name = "CONTCAR_positive_pymatgen")

CONTCARorPOSCAR.get_latticeconstant_dict(file_loc_important_cols, direc_restructure_destination, 
                                         proceed_XDATCAR, 
                                         var_filename = "CONTCAR")

# # # structure_analysis.energy_vs_latticeconstant(file_loc_important_cols, 
# # #                                              var_filename = "CONTCAR")    # commented out

# # # structure_analysis.weirdos_directcoor(file_loc_important_cols, activate_radius)


tuple_metainfo = metainfo.tuple(coor_ref_structure_48n24_expanded, litype, el = "Li")
coor_48htype1_metainfo = metainfo.coor_48htype2(coor_ref_structure_48n24_expanded, el = 'Li')

file_loc_important_cols_sorted = file_loc_important_cols.sort_values("toten [eV]", ascending=True).reset_index()

idx_coor_cage_order = {0: np.array([0.97111, 0.25   , 0.25   ]), 3: np.array([0.02889, 0.75   , 0.25   ]),
                       1: np.array([0.02889, 0.25   , 0.75   ]), 2: np.array([0.97111, 0.75   , 0.75   ])}

coor_24g_array = np.array([item['coor'] for sublist in tuple_metainfo.values() for item in sublist if item['type'] == '24g'])
centroids, labels = func_kmeans.kmeans_cluster_atoms(coor_24g_array, amount_clusters = 4)
func_kmeans.create_POSCAR_atoms_centroids_appended(coor_24g_array, centroids, direc_restructure_destination, lattice_constant, filename = "POSCAR_24g_centroids4")

idx_cage_coor_24g = metainfo.idx_cage_coor_24g(coor_24g_array, labels, idx_coor_cage_order, amount_clusters = 4)
tuple_cage_metainfo = metainfo.tuple_cage(tuple_metainfo, idx_cage_coor_24g)


category_labels_occupancy = {
    '2': '2',
    '1': '1',
    '0': '0',
    '48htype1': '48htype2',
    'weirdo': 'weirdo'
    # ... add more as needed
}

analysis.get_occupancy(file_loc_important_cols, coor_ref_structure_48n24_expanded, tuple_cage_metainfo, el = "Li")
df_occupancy = movement.get_df_occupancy(file_loc_important_cols)
# # # movement.plot_occupancy(df_occupancy, category_labels_occupancy)  # commented out
df_occupancy.to_pickle(f'df_occupancy.pkl') 

path_by_tuple_cage.get_complete_closest_tuple_cage(file_loc_important_cols, tuple_cage_metainfo, coor_48htype1_metainfo)


category_labels = {
    '48htype1': '48htype2',
    '48htype2': '48htype1',
    '48htype3': '48htype3',
    '48htype4': '48htype4',
    '24g': '24g',
    'weirdo': 'weirdo'
    # ... add more as needed
}

if proceed_NEB == "True": # commented out
    df_type = path_by_tuple_cage.get_df_movement(file_loc_important_cols, to_plot = 'type', activate_closest_tuple = False)
    df_idx_tuple = path_by_tuple_cage.get_df_movement(file_loc_important_cols, to_plot = 'idx_tuple', activate_closest_tuple = False)
    df_idx_cage = path_by_tuple_cage.get_df_movement(file_loc_important_cols, to_plot = 'idx_cage', activate_closest_tuple = False)
    df_type.to_pickle(f'df_type.pkl') 
    df_idx_tuple.to_pickle(f'df_idx_tuple.pkl') 
    df_idx_cage.to_pickle(f'df_idx_cage.pkl') 

    # category_labels_activate_s_i = {
    #     '48htype1': '48htype2',
    #     '48htype2': '48htype1',
    #     '48htype3': '48htype3',
    #     '48htype4': '48htype4',
    #     '24g': '24g',
    #     'weirdo': 'weirdo'
    #     # ... add more as needed
    # }

    # # # # # Plot.Movement.Distance.plot_distance(df_idx_cage, max_mapping_radius, Li_idxs="all")
    # # # movement.plot_cage_tuple_label(df_idx_cage, df_type, df_idx_tuple, max_mapping_radius, litype, category_labels, activate_diameter_line=False, activate_relabel_s_i = True, Li_idxs="all")   # commented out


if proceed_NEB == "True":
    df_movement = path_by_tuple_cage.get_df_movement_category(file_loc_important_cols, activate_closest_tuple=False)
    # # # movement.plot_distance(df_movement, max_mapping_radius, activate_shifting_x = True, activate_diameter_line = False, Li_idxs = 'all')  # commented out
    df_movement.to_pickle(f'df_movement.pkl') 

labelling.get_amount_type(file_loc_important_cols, litype, el = "Li")

el = "Li"
style = "bar"
df_amount_type = mapping_labelling.get_df_amount_type(file_loc_important_cols, litype, el)
# # # mapping_labelling.plot_amount_type(df_amount_type, style, category_labels) # commented out
df_amount_type.to_pickle(f'df_amount_type.pkl') 

if proceed_NEB == "True": # commented out
    df_amount_movement = path_by_tuple_cage.get_df_movement_category_counted(df_movement)
    # # # move_by_tuple_cage.plot_movement_category_counted(df_amount_movement)  # commented out
    df_amount_movement.to_pickle(f'df_amount_movement.pkl') 

# file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_weirdos_Li","sum_weirdos_48htype2_Li","dist_weirdos_atom"dist_weirdos_48htype2_atom72_Li","idx1_weirdos_Li","#weirdos_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
# file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_weirdos_Li","sum_weirdos_48htype2_Li","dist_weirdos_atom"dist_weirdos_48htype2_atom72_Li","idx1_weirdos_Li","#weirdos_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
if activate_radius == 3:
    file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","sum_weirdos_Li","sum_mapped_48htype1_48htype2_Li_closestduplicate","sum_weirdos_48htype1_48htype2_Li","sum_mapped_48htype2_Li_closestduplicate","#weirdos_Li","sum_mapped_48htypesmerged_Li","sum_sanitycheck_48htypesmerged_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
    file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","sum_weirdos_Li","sum_mapped_48htype1_48htype2_Li_closestduplicate","sum_weirdos_48htype1_48htype2_Li","sum_mapped_48htype2_Li_closestduplicate","#weirdos_Li","sum_mapped_48htypesmerged_Li","sum_sanitycheck_48htypesmerged_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","toten [eV]"]]
    
    sum_weirdos_Li = float(file_loc_important_cols_sorted_toten["#weirdos_Li"].sum())

    var_excel_file = f"map2type2_{sum_weirdos_Li}_{max_mapping_radius}_{max_mapping_radius_48htype2}_{max_mapping_radius_48htype1_48htype2}_{file_perfect_poscar_48n24_wo_cif}"

elif activate_radius == 2:
    if litype == 2:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 3:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 4:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 5:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 6:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_24g_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_24g_Li","toten [eV]"]] 
    elif litype == 7:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_24g_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_24g_Li","toten [eV]"]] 
    elif litype == 8:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_48htype8_Li","#closest_24g_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_48htype8_Li","#closest_24g_Li","toten [eV]"]]   

    sum_weirdos_Li = float(file_loc_important_cols_sorted_toten["#weirdos_Li"].sum())

    var_excel_file = f"map2type2_{sum_weirdos_Li}_{max_mapping_radius}_{max_mapping_radius_48htype2}_{file_perfect_poscar_48n24_wo_cif}"

elif activate_radius == 1:
    if litype == 2:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 3:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 4:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 5:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_24g_Li","atom_mapping_Li_w_dist_label","toten [eV]"]]
    elif litype == 6:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_24g_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_24g_Li","toten [eV]"]] 
    elif litype == 7:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_24g_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_24g_Li","toten [eV]"]] 
    elif litype == 8:
        file_loc_important_cols_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_48htype8_Li","#closest_24g_Li","toten [eV]"]].sort_values("toten [eV]", ascending=True)
        file_loc_important_cols_not_sorted_toten = file_loc_important_cols[["geometry","path","sum_mapped_Li_closestduplicate","#weirdos_Li","idx0_weirdos_Li","top3_sorted_idxweirdo_dist_Li","top3_sorted_idxweirdo_label_Li","#closest_48htype1_Li","#closest_48htype2_Li","#closest_48htype3_Li","#closest_48htype4_Li","#closest_48htype5_Li","#closest_48htype6_Li","#closest_48htype7_Li","#closest_48htype8_Li","#closest_24g_Li","toten [eV]"]]   

    sum_weirdos_Li = float(file_loc_important_cols_sorted_toten["#weirdos_Li"].sum())

    var_excel_file = f"map2type2_{sum_weirdos_Li}_{max_mapping_radius}_{file_perfect_poscar_48n24_wo_cif}"

file_loc_important_cols_not_sorted_toten.to_excel(f'04_important_outputs_{var_excel_file}.xlsx', index=False)

if activate_radius == 1:
    file_loc_important_cols.to_pickle(f'file_loc_important_cols_{max_mapping_radius}_{file_perfect_poscar_48n24_wo_cif}.pkl') 
elif activate_radius == 2:
    file_loc_important_cols.to_pickle(f'file_loc_important_cols_{max_mapping_radius}_{max_mapping_radius_48htype2}_{file_perfect_poscar_48n24_wo_cif}.pkl')
elif activate_radius == 3:
    file_loc_important_cols.to_pickle(f'file_loc_important_cols_{max_mapping_radius}_{max_mapping_radius_48htype2}_{max_mapping_radius_48htype1_48htype2}_{file_perfect_poscar_48n24_wo_cif}.pkl')

print("Amount occupancy:")
print(df_occupancy.sum())
print()
print()

print("Amount type:")
print(df_amount_type.sum())
print()
print()

print("Amount movement:")
print(df_amount_movement.sum())
print()
print()

elapsed_time = time.time() - t
print(f"elapsed_time: {elapsed_time}")