问如何使用xgboost获得低选择功能的最高精度？

EN

thresholds = sort(model.feature_importances_)
for thresh in thresholds:
    # select features using threshold
    selection = SelectFromModel(model, threshold=thresh, prefit=True)
    select_X_train = selection.transform(X_train)
    # train model
    selection_model = XGBClassifier()
    selection_model.fit(select_X_train, y_train)
    # eval model
    select_X_test = selection.transform(X_test)
    predictions = selection_model.predict(select_X_test)
    accuracy = accuracy_score(y_test, predictions)
    print("Thresh=%.3f, n=%d, Accuracy: %.2f%%" % (thresh, select_X_train.shape[1], accuracy*100.0))

selection = SelectFromModel(model, threshold=threshold[5], prefit=True)
select_X_train = selection.transform(X_train)
selection_model = XGBClassifier()
selection_model.fit(select_X_train, y_train)
select_X_test = selection.transform(X_test)
predictions = selection_model.predict(select_X_test)
accuracy = accuracy_score(y_test, predictions)
print("Thresh=%.3f, n=%d, Accuracy: %.2f%%" % (threshold[5], select_X_train.shape[1], accuracy*100.0))

n_min = *your maximum number of used features*
acc_max = 0
thresholds = sort(model.feature_importances_)
obj_thresh = thresholds[0]
for thresh in thresholds:
    selection = SelectFromModel(model, threshold=thresh, prefit=True)
    select_X_train = selection.transform(X_train)
    selection_model = XGBClassifier()
    selection_model.fit(select_X_train, y_train)
    select_X_test = selection.transform(X_test)
    predictions = selection_model.predict(select_X_test)
    accuracy = accuracy_score(y_test, predictions)
    if(select_X_train.shape[1] < n_min) and (accuracy > acc_max):
        n_min = select_X_train.shape[1]
        acc_max = accuracy
        obj_thresh = thresh

selection = SelectFromModel(model, threshold=obj_thresh, prefit=True)
select_X_train = selection.transform(X_train)
selection_model = XGBClassifier()
selection_model.fit(select_X_train, y_train)
select_X_test = selection.transform(X_test)
predictions = selection_model.predict(select_X_test)
accuracy = accuracy_score(y_test, predictions)
print("Thresh=%.3f, n=%d, Accuracy: %.2f%%" % (obj_thresh, select_X_train.shape[1], accuracy*100.0))

# Fit the model:
f_max = 8
f_min = 2
acc_max = accuracy
thresholds = np.sort(model_FS.feature_importances_)
obj_thresh = thresholds[0]
accuracy_list = []
for thresh in thresholds:
    # select features using threshold:
    selection = SelectFromModel(model_FS, threshold=thresh, prefit=True)
    select_X_train = selection.transform(X_train)
    # train model:
    selection_model = xgb.XGBClassifier()
    selection_model.fit(select_X_train, y_train)
    # eval model:
    select_X_test = selection.transform(X_test)
    selection_model_pred = selection_model.predict(select_X_test)
    selection_predictions = [round(value) for value in selection_model_pred]
    accuracy = accuracy_score(y_true=y_test, y_pred=selection_predictions)
    accuracy = accuracy * 100
    print('Thresh= %.3f, n= %d, Accuracy: %.2f%%' % (thresh, select_X_train.shape[1], accuracy))
    accuracy_list.append(accuracy)
    if(select_X_train.shape[1] < f_max) and (select_X_train.shape[1] >= f_min) and (accuracy >= acc_max):
        n_min = select_X_train.shape[1]
        acc_max = accuracy
        obj_thresh = thresh
# select features using threshold:
selection = SelectFromModel(model_FS, threshold=obj_thresh, prefit=True)
select_X_train = selection.transform(X_train)
# train model:
selection_model = xgb.XGBClassifier()
selection_model.fit(select_X_train, y_train)
# eval model:
select_X_test = selection.transform(X_test)
selection_model_pred = selection_model.predict(select_X_test)
accuracy = accuracy_score(y_test, predictions)
selection_predictions = [round(value) for value in selection_model_pred]
accuracy = accuracy_score(y_true=y_test, y_pred=selection_predictions)
print("Selected: Thresh=%.3f, n=%d, Accuracy: %.2f%%" % (obj_thresh, select_X_train.shape[1], accuracy*100.0))
key_list = list(range(X_train.shape[1], 0, -1))
accuracy_dict = dict(zip(key_list, accuracy_list))
optimum_num_feat = n_min
print(optimum_num_feat)

# Printing out the features:
X_train = X_train.iloc[:, optimum_number_features]
X_test = X_test.iloc[:, optimum_number_features]

print('X Train FI: ')
print(X_train)
print('X Test FI: ')
print(X_test)

# Calculate feature importances
importances = model_FS.feature_importances_
print((model_FS.feature_importances_) * 100)

# Organising the feature importance in dictionary:
## The key value depends on your maximum number of features:
key_list = range(0, 11, 1)
feature_importance_dict = dict(zip(key_list, importances))
sort_feature_importance_dict = dict(sorted(feature_importance_dict.items(), key=lambda x: x[1], reverse=True))
print('Feature Importnace Dictionary (Sorted): ', sort_feature_importance_dict)

# Removing the features that have value zero in feature importance:
filtered_feature_importance_dict = {x:y for x,y in sort_feature_importance_dict.items() if y!=0}
print('Filtered Feature Importnace Dictionary: ', filtered_feature_importance_dict)
f_indices = list(filtered_feature_importance_dict.keys())
f_indices = np.asarray(f_indices)
print(f_indices)

X_train = X_train.loc[:, f_indices]
X_test = X_test.loc[:, f_indices]

print('X Train FI: ')
print(X_train)
print('X Test FI: ')
print(X_test)