"""
this is a description
"""
import numpy as np
import pandas as pd
from bgp.selection.corr import Corr
from mgetool.exports import Store
from mgetool.imports import Call
from mgetool.tool import name_to_name
# import seaborn as sns
if __name__ == "__main__":
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp\2.corr')
data = Call(r'C:\Users\Administrator\Desktop\band_gap_exp')
all_import = data.csv().all_import
name_init, abbr_init = data.pickle_pd().name_and_abbr
data_import = all_import
data225_import = data_import.iloc[np.where(
data_import['group_number'] == 225)[0]]
X_frame = data225_import.drop(['exp_gap', 'group_number'], axis=1)
y_frame = data225_import['exp_gap']
X = X_frame.values
y = y_frame.values
"""calculate corr"""
corr = Corr(threshold=0.90, muti_grade=2, muti_index=[2, len(X)])
corr.fit(X_frame)
cof_list = corr.count_cof()
# ],
# definate_variable=[
# [-3, [0]],
# [-2, [1]],
# [-1, [2]]],
# operate_linkage=[[-1, -2], ],
# # variable_linkage = None
# )
#
# result = mainPart(X, y, pset1, pop_n=500, random_seed=2, cxpb=0.8, mutpb=0.1, ngen=20,
# inter_add=True, iner_add=False, random_add=False, score=[explained_variance_score, r2_score])
# ret = result[2][1]
if __name__ == "__main__":
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp_last\4.symbollearning')
data_cluster = Call(r'C:\Users\Administrator\Desktop\band_gap_exp_last\1.generate_data',
r'C:\Users\Administrator\Desktop\band_gap_exp_last\3.MMGS')
all_import_structure = data_cluster.csv.all_import_structure
data_import = all_import_structure
select_gs = ['destiny', 'energy cohesive brewer', 'distance core electron(schubert)']
select_gs = ['destiny'] + [j + "_%i" % i for j in select_gs[1:] for i in range(2)]
data216_import = data_import.iloc[np.where(data_import['group_number'] == 216)[0]]
data225_import = data_import.iloc[np.where(data_import['group_number'] == 225)[0]]
data216_225_import = pd.concat((data216_import, data225_import))
X_frame = data225_import[select_gs]
y_frame = data225_import['exp_gap']
X = X_frame.values
import numpy as np
import pandas as pd
from bgp.selection.ugs import UGS
from mgetool.exports import Store
from mgetool.imports import Call
from mgetool.quickmethod import dict_method_reg
from mgetool.tool import name_to_name
from sklearn import preprocessing, utils
from sklearn.model_selection import GridSearchCV
warnings.filterwarnings("ignore")
if __name__ == '__main__':
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp\3.sum')
data = Call(r'C:\Users\Administrator\Desktop\band_gap_exp')
data_import = data.csv.all_import
name_init, abbr_init = data.csv.name_and_abbr
select = ['volume', 'destiny', 'lattice constants a', 'lattice constants c', 'radii covalent',
'radii ionic(shannon)',
'distance core electron(schubert)', 'latent heat of fusion', 'energy cohesive brewer', 'total energy',
'charge nuclear effective(slater)', 'valence electron number', 'electronegativity(martynov&batsanov)',
'volume atomic(villars,daams)']
select = ['volume', 'destiny'] + [j + "_%i" % i for j in select[2:] for i in range(2)]
data216_import = data_import.iloc[np.where(data_import['group_number'] == 216)[0]]
data225_import = data_import.iloc[np.where(data_import['group_number'] == 225)[0]]
data216_225_import = pd.concat((data216_import, data225_import))
# x2 = x[:, 2]
# x3 = x[:, 3]
#
# t = expr01
# func0 = sympy.utilities.lambdify(terminals, t)
# re = func0(*x.T)
# p = BasePlot(font=None)
# p.scatter(y, re, strx='Experimental $E_{gap}$', stry='Calculated $E_{gap}$')
# import matplotlib.pyplot as plt
#
# plt.show()
if __name__ == '__main__':
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp\4.symbol')
data = Call(r'C:\Users\Administrator\Desktop\c', index_col=None)
data_import = data.xlsx().sr
X = data_import["delt_x"].values
input_x = data_import[["delt_x", "G"]].values
Pexp = data_import["Pexp"].values
Pmix = data_import["Pmix"].values
G = data_import["G"].values
y = data_import["PG_y"].values
y = y * G
testfunc = input_x[:, 0] * input_x[:, 1]
t = np.corrcoef(y, input_x[:, 0] * input_x[:, 1])
dim1 = Dim([0, 0, 0, 0, 0, 0, 0])
from featurebox.selection.corr import Corr
from mgetool.exports import Store
from mgetool.imports import Call
from mgetool.show import corr_plot
from mgetool.tool import name_to_name
# import seaborn as sns
if __name__ == "__main__":
import os
os.chdir(r'band_gap')
store = Store()
data = Call()
all_import = data.csv().all_import
name_and_abbr = data.csv().name_and_abbr
data_import = all_import
data225_import = data_import
X_frame = data225_import.drop(['exp_gap'], axis=1)
y_frame = data225_import['exp_gap']
X = X_frame.values
y = y_frame.values
#
# """calculate corr"""
corr = Corr(threshold=0.90, muti_grade=2, muti_index=[2, len(X)])
corr.fit(X_frame)
cof_list = corr.count_cof()
#
import warnings
import matplotlib.pyplot as plt
import numpy as np
import sklearn
from bgp.selection.backforward import BackForward
from mgetool.exports import Store
from mgetool.imports import Call
from sklearn import svm
from sklearn.model_selection import GridSearchCV, LeaveOneOut
warnings.filterwarnings("ignore")
# 数据导入
store = Store(r'/data/home/wangchangxin/data/zlj/')
data = Call(r'/data/home/wangchangxin/data/zlj/', index_col=None)
all_import = data.xlsx().data
x_name = all_import.index.values
y = all_import["y"].values
x_frame = all_import.drop("y", axis=1)
x = x_frame.values
# # 预处理
# minmax = MinMaxScaler()
# x = minmax.fit_transform(x)
# 数据划分
xtrain, xtest = x[3:], x[:3]
ytrain, ytest = y[3:], y[:3]
xtrain, ytrain = sklearn.utils.shuffle(xtrain, ytrain, random_state=3)
from bgp.selection.quickmethod import dict_method_reg
from bgp.selection.sum import SUM
from mgetool.exports import Store
from mgetool.imports import Call
from mgetool.tool import name_to_name
from sklearn import utils
from sklearn.model_selection import GridSearchCV
warnings.filterwarnings("ignore")
"""
this is a description
"""
if __name__ == "__main__":
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp\3.sum\sub')
data = Call(
r'C:\Users\Administrator\Desktop\band_gap_exp',
r'C:\Users\Administrator\Desktop\band_gap_exp\3.sum\method',
)
data_import = data.csv().all_import
name_init, abbr_init = data.pickle_pd().name_and_abbr
select = [
'cell volume', 'electron density', 'lattice constants a',
'lattice constants c', 'radii covalent', 'radii ionic(shannon)',
'distance core electron(schubert)', 'latent heat of fusion',
'energy cohesive brewer', 'total energy',
'charge nuclear effective(slater)', 'valence electron number',
'electronegativity(martynov&batsanov)', 'volume atomic(villars,daams)'
]
select = ['cell volume', 'electron density'
] + [j + "_%i" % i for j in select[2:] for i in range(2)]
exps1 = exps1.subs(subbb1) exps1 = exps1.subs(subbb2) # exps1 = sympy.simplify(exps1) exps2 = exps2.subs(subbb1) exps2 = exps2.subs(subbb2) # exps2 = sympy.simplify(exps2) exps3 = exps3.subs(subbb1) exps3 = exps3.subs(subbb2) # exps3 = sympy.simplify(exps3) from mgetool.imports import Call data = Call(r'C:\Users\Administrator\Desktop\cl', index_col=None) values_data = data.xlsx().values_data E_values = values_data["E"].values Rct_values = values_data["Rct"].values Rp_values = values_data["Rp"] taup_values = (values_data["Rp"] * values_data["Cp"]).values R0_values = -(Rct_values**2 + Rct_values * Rp_values) / Rp_values F_values = 96485 T_values = 298 R_values = 8.314 q_values = 8 * 10e-5 beta_values = 0.5 std_Rct = np.std(Rct_values) std_taup = np.std(taup_values)
import pandas as pd
from bgp.featurizers.compositionfeaturizer import WeightedAverage
from bgp.selection.corr import Corr
from mgetool.exports import Store
from mgetool.imports import Call
from pymatgen import Composition
from sklearn.ensemble import RandomForestRegressor, AdaBoostRegressor
from sklearn.feature_selection import RFECV
from sklearn.linear_model import BayesianRidge
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import MinMaxScaler
from sklearn.tree import DecisionTreeRegressor
# 数据导入
store = Store(r'C:\Users\Administrator\Desktop\skk')
data = Call(r'C:\Users\Administrator\Desktop\skk')
all_import = data.csv().skk
# """for element site"""
element_table = pd.read_excel(
r'C:\Users\Administrator\Desktop\band_gap_exp\element_table.xlsx',
header=4,
skiprows=0,
index_col=0)
element_table = element_table.iloc[5:, 7:]
# 其他数据获取
feature_select = [
'lattice constants a',
'lattice constants b',
'lattice constants c',
import numpy as np
from mgetool.exports import Store
from mgetool.imports import Call
from mgetool.tool import tt
from bgp.base import SymbolSet
from bgp.skflow import SymbolLearning
if __name__ == "__main__":
import os
os.chdir(r'band_gap')
data = Call()
name_and_abbr = data.csv().name_and_abbr
SL_data = data.SL_data
si_transformer = data.si_transformer
store = Store()
x, x_dim, y, y_dim, c, c_dim, X, Y = SL_data
x_g = np.arange(x.shape[1])
x_g = list(x_g[1:])
x_g = x_g.reshape(-1, 2)
pset0 = SymbolSet()
pset0.add_features(x, y, x_dim=x_dim, y_dim=y_dim, x_group=x_g)
pset0.add_constants(c, c_dim=c_dim, c_prob=0.05)
pset0.add_operations(power_categories=(2, 3, 0.5, 1 / 3, 4, 1 / 4),
# categories=("Mul",),
categories=("Add", "Mul", "Sub", "Div", "exp", "ln"),
"""
import numpy as np
import pandas as pd
import sympy
from bgp.combination.symbolbase import calculateExpr, getName
from mgetool.exports import Store
from mgetool.imports import Call
if __name__ == "__main__":
store = Store(
r'C:\Users\Administrator\Desktop\band_gap_exp_last\4.symbollearning')
data = Call(
r'C:\Users\Administrator\Desktop\band_gap_exp_last\1.generate_data',
r'C:\Users\Administrator\Desktop\band_gap_exp_last\3.MMGS',
r'C:\Users\Administrator\Desktop\band_gap_exp_last\2.correction_analysis'
)
all_import_structure = data.csv.all_import_structure
data_import = all_import_structure
data216_import = data_import.iloc[np.where(
data_import['group_number'] == 216)[0]]
data225_import = data_import.iloc[np.where(
data_import['group_number'] == 225)[0]]
data221_import = data_import.iloc[np.where(
data_import['group_number'] == 221)[0]]
data216_225_221import = pd.concat(
(data216_import, data225_import, data221_import))
list_name = data.csv.list_name
toolbox,
cxpb=cxpb,
mutpb=mutpb,
ngen=ngen,
stats=stats,
halloffame=hof,
pset=pset,
store=store)
return hof
if __name__ == '__main__':
# 输入
store = Store(r'D:\sy')
data = Call(r'D:\sy')
data_import = data.xlsx().featuredata
name_abbr = data_import.columns.values
x_name = name_abbr[:-1]
# data_import = data_import.iloc[np.where(data_import['f1'] <= 1)[0]]
X_frame = data_import[x_name]
y_frame = data_import['y']
X = X_frame.values
y = y_frame.values
# 处理
# scal = preprocessing.MinMaxScaler()
# X = scal.fit_transform(X)
import pandas as pd
from bgp.selection.quickmethod import dict_method_reg
from bgp.selection.sum import SUM
from mgetool.exports import Store
from mgetool.imports import Call
from mgetool.tool import name_to_name
from sklearn import preprocessing, utils
from sklearn.model_selection import GridSearchCV
warnings.filterwarnings("ignore")
if __name__ == '__main__':
store = Store(
r'C:\Users\Administrator\Desktop\band_gap_exp\3.sum\10times100')
data = Call(
r'C:\Users\Administrator\Desktop\band_gap_exp\3.sum\method',
r"C:\Users\Administrator\Desktop\band_gap_exp\3.sum\10times100",
r'C:\Users\Administrator\Desktop\band_gap_exp')
data_import = data.csv().all_import
name_init, abbr_init = data.pickle_pd().name_and_abbr
select = [
'volume', 'destiny', 'lattice constants a', 'lattice constants c',
'radii covalent', 'radii ionic(shannon)',
'distance core electron(schubert)', 'latent heat of fusion',
'energy cohesive brewer', 'total energy',
'charge nuclear effective(slater)', 'valence electron number',
'electronegativity(martynov&batsanov)', 'volume atomic(villars,daams)'
]
select = ['volume', 'destiny'
] + [j + "_%i" % i for j in select[2:] for i in range(2)]
# @Project : feature_toolbox
# @FileName: 1.1add_compound_features.py
# @Software: PyCharm
import pandas as pd
import pymatgen as mg
from bgp.featurizers.voronoifeature import count_voronoinn
from mgetool.exports import Store
from mgetool.imports import Call
"""
this is a description
"""
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp_last\1.generate_data')
data = Call(r'C:\Users\Administrator\Desktop\band_gap_exp_last\1.generate_data')
com_data = pd.read_excel(r'C:\Users\Administrator\Desktop\band_gap_exp_last\init_band_data.xlsx',
sheet_name='binary_4_structure', header=0, skiprows=None, index_col=0, names=None)
composition = pd.Series(map(eval, com_data['composition']))
composition_mp = pd.Series(map(mg.Composition, composition))
"""for element site"""
com_mp = pd.Series([i.to_reduced_dict for i in composition_mp])
# com_mp = composition_mp
all_import = data.csv.all_import
id_structures = data.id_structures
structures = id_structures
vor_area = count_voronoinn(structures, mess="area")
vor_dis = count_voronoinn(structures, mess="face_dist")
vor = pd.DataFrame()
vor.insert(0, 'vor_area0', vor_area[:, 0])
#
# ],
# definate_variable=[[-5, [0]],
# [-4, [1]],
# [-3, [2]],
# [-2, [3]],
# [-1, [4]]],
# operate_linkage=[[-1, -2], [-3, -4]],
# variable_linkage=None)
# result = mainPart(X, y, pset, pop_n=500, random_seed=1, cxpb=0.8, mutpb=0.6, ngen=20, tournsize=3, max_value=10,
# double=False, score=[r2_score, custom_loss_func], target_dim=target_dim)
# 5
if __name__ == '__main__':
store = Store(r'C:\Users\Administrator\Desktop\band_gap_exp\4.symbol')
data = Call(r'C:\Users\Administrator\Desktop\band_gap_exp')
data_import = data.csv().all_import
name_init, abbr_init = data.name_and_abbr
select = ['latent heat of fusion', 'valence electron number']
X_frame_abbr = name_to_name(name_init,
abbr_init,
search=select,
search_which=1,
return_which=2,
two_layer=False)
select = [j + "_%i" % i for j in select[:] for i in range(2)]
select_abbr = [j + "_%i" % i for j in X_frame_abbr[:] for i in range(2)]