clf = Exhaustion(estimator,
n_select=n_select,
muti_grade=2,
muti_index=[2, X.shape[1]],
must_index=None,
n_jobs=1,
refit=True).fit(X, y)
name_ = name_to_name(X_frame.columns.values,
search=[i[0] for i in clf.score_ex[:10]],
search_which=0,
return_which=(1, ),
two_layer=True)
sc = np.array(clf.scatter)
for i in clf.score_ex[:]:
print(i[1])
for i in name_:
print(i)
t = clf.predict(X)
p = BasePlot()
p.scatter(y, t, strx='True $E_{gap}$', stry='Calculated $E_{gap}$')
plt.show()
p.scatter(sc[:, 0], sc[:, 1], strx='Number', stry='Score')
plt.show()
store.to_csv(sc, method_name + "".join([str(i) for i in n_select]))
store.to_pkl_pd(clf.score_ex,
method_name + "".join([str(i) for i in n_select]))
method_all = [
'SVR-set', "GPR-set", "RFR-em", "AdaBR-em", "DTR-em", "LASSO-L1", "BRR-L1"
]
methods = method_pack(method_all=method_all, me="reg", gd=True)
pre_y = []
ests = []
for name, methodi in zip(method_all, methods):
methodi.cv = 5
methodi.scoring = "neg_root_mean_squared_error"
gd = methodi.fit(X=x_, y=y_)
score = gd.best_score_
est = gd.best_estimator_
print(name, "neg_root_mean_squared_error", score)
score = cross_val_score(
est,
X=x_,
y=y_,
scoring="r2",
).mean()
print(name, "r2", score)
pre_yi = est.predict(x)
pre_y.append(pre_yi)
ests.append(est)
store.to_pkl_pd(est, name)
pre_y.append(y)
pre_y = np.array(pre_y).T
pre_y = pd.DataFrame(pre_y)
pre_y.columns = method_all + ["realy_y"]
store.to_csv(pre_y, "wrtem_result")
+ [np.array([0, 0, 0, 1, 0, 0, 0])] * 2 + [np.array([0, 0, 0, 0, 0, 0, 0])] + [
np.array([0, 3, 0, 0, 0, 0, 0])] \
+ [np.array([0, 0, 0, 0, 0, 0, 0])] + [np.array([0, 3, 0, 0, 0, -1, 0])] + [
np.array([1, -3, 0, 0, 0, 0, 0])] \
+ [np.array([1, -1, -2, 0, 0, 0, 0])]
dims.extend([np.array([0, 1, 0, 0, 0, 0, 0]), np.array([0, 2, 0, 0, 0, 0, 0]), np.array([0, 1, 0, 0, 0, 0, 0]),
np.array([0, 2, 0, 0, 0, 0, 0]),
np.array([1, -3, 0, 0, 0, 0, 0]), np.array([0, 3, 0, 0, 0, 0, 0]), np.array([0, 0, 0, 0, 0, 0, 0])
])
return dims
name_and_abbr = get_abbr()
dims = get_dim()
store.to_pkl_pd(dims, "dims")
store.to_pkl_pd(name_and_abbr, "name_and_abbr")
element_table = element_table.iloc[5:, 7:]
feature_select = [
'lattice constants a',
'lattice constants b',
'lattice constants c',
'radii atomic(empirical)',
'radii atomic(clementi)',
'radii ionic(pauling)',
'radii ionic(shannon)',
'radii covalent',
'radii covalent 2',
'radii metal(waber)',
'distance valence electron(schubert)',
estimator_all.append(GridSearchCV(me1, cv=cv1, scoring=scoring1, param_grid=param_grid1, n_jobs=1))
"""union"""
index_all = [tuple(index[0]) for _ in index_all for index in _[:10]]
index_all = list(set(index_all))
"""get x_name and abbr"""
index_all_name = name_to_name(X_frame.columns.values, search=[i for i in index_all],
search_which=0, return_which=(1,), two_layer=True)
index_all_name = [list(set([re.sub(r"_\d", "", j) for j in i])) for i in index_all_name]
[i.sort() for i in index_all_name]
index_all_abbr = name_to_name(name_init, abbr_init, search=index_all_name, search_which=1, return_which=2,
two_layer=True)
store.to_pkl_pd(index_all, "index_all")
store.to_csv(index_all_name, "index_all_name")
store.to_csv(index_all_abbr, "index_all_abbr")
ugs = UGS(estimator_all, index_all, estimator_n=[2, 3], n_jobs=3)
ugs.fit(X, y)
# re = gs.cv_score_all(index_all)
binary_distance = ugs.cal_binary_distance_all(index_all, estimator_i=3)
# slice_k = gs._cv_predict_all(estimator_i=3)
groups = ugs.cal_group(estimator_i=3, printing=True, print_noise=0.2, pre_binary_distance_all=binary_distance)
ugs.cluster_print(binary_distance, highlight=[1, 2, 3])
# groups = ugs.cal_t_group(printing=False, pre_group=None)
# ss=ugs.select_ugs(alpha=0.01)
# results = gs.select_gs(alpha=0.01)
# gs.cal_group(eps=0.10, estimator_i=1, printing=True, pre_binary_distance_all=slice_g, print_noise=0.1,