def remove_by_y(self, y_):
corr = self.cov_y(self.data, y_)
corr = self.feature_fold(corr)
lcount = self.list_count
fea_all = []
score = name_to_name(corr,
search=lcount,
search_which=0,
return_which=(1, ),
two_layer=True)
for score_i, list_i in zip(score, lcount):
indexs = np.argmax(score_i)
feature_index = list_i[int(indexs)]
fea_all.append(feature_index)
fea_all = sorted(list(set(fea_all)))
return fea_all
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()
"""get x_name and abbr"""
X_frame_name = corr.transform(X_frame.columns.values)
X_frame_name = [i.replace("_0", "") for i in X_frame_name]
X_frame_abbr = name_to_name(name_init,
abbr_init,
search=X_frame_name,
search_which=1,
return_which=2,
two_layer=False)
"""rename"""
# cov = pd.DataFrame(corr.cov_shrink)
# cov = cov.set_axis(X_frame_abbr, axis='index', inplace=False)
# cov = cov.set_axis(X_frame_abbr, axis='columns', inplace=False)
#
# # fig = plt.figure()
# # fig.add_subplot(111)
# # sns.heatmap(cov, vmin=-1, vmax=1, cmap="bwr", linewidths=0.3, xticklabels=True, yticklabels=True, square=True,
# # annot=True, annot_kws={'size': 3})
# # plt.show()
#
# corr_plot(corr.cov_shrink, X_frame_abbr,title="", left_down="fill", right_top="pie", threshold_right=0, front_raito=0.4)
#
"""base_method"""
method_name = ['GPR-set', 'SVR-set', 'KRR-set', 'KNR-set']
index_all = [data.pickle_pd.GPR_set23, data.pickle_pd.SVR_set23, data.pickle_pd.KR_set23, data.pickle_pd.KNR_set23]
estimator_all = []
for i in method_name:
me1, cv1, scoring1, param_grid1 = dict_method_reg()[i]
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)
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()
#
"""get x_name and abbr"""
X_frame_name = corr.transform(X_frame.columns.values)
X_frame_name = [i.replace("_0", "") for i in X_frame_name]
X_frame_abbr = name_to_name(name_and_abbr.columns.values,
list(name_and_abbr.iloc[0, :]),
search=X_frame_name,
search_which=1,
return_which=[
2,
],
two_layer=False)
"""rename"""
# cov = pd.DataFrame(corr.cov_shrink)
# cov = cov.set_axis(X_frame_abbr, axis='index', inplace=False)
# cov = cov.set_axis(X_frame_abbr, axis='columns', inplace=False)
#
# fig = plt.figure()
# fig.add_subplot(111)
# sns.heatmap(cov, vmin=-1, vmax=1, cmap="bwr", linewidths=0.3, xticklabels=True, yticklabels=True, square=True,
# annot=True, annot_kws={'size': 3})
# plt.show()
#
plt0 = corr_plot(corr.cov_shrink,
scoring=scoring1,
param_grid=param_grid1,
n_jobs=1)
# n_select = [1,]
n_select = (2, 3)
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()