def find_best_random_forest(data, target, cv):
clf = RandomForestClassifier(random_state=0)
n_estimators = [10, 20, 35, 50, 80, 100, 120, 150, 200]
param_grid = [{'n_estimators': n_estimators}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = '随机森林'
return grid_search
def find_best_logistic(data, target, cv):
clf = LogisticRegression(penalty='l2')
C = [0.1, 0.5, 1, 5, 10]
param_grid = [{'C': C}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = '逻辑回归'
return grid_search
def find_best_random_forest(data, target, cv):
clf = RandomForestClassifier(random_state=0)
n_estimators = [10, 20, 35, 50, 80, 100, 120, 150, 200]
param_grid = [{'n_estimators': n_estimators}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = '随机森林'
return grid_search
def find_best_logistic(data, target, cv):
clf = LogisticRegression(penalty='l2')
C = [0.1, 0.5, 1, 5, 10]
param_grid = [{'C': C}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = '逻辑回归'
return grid_search
def find_best_svm(data, target, cv):
clf = SVC()
C = [0.1, 0.5, 1, 5, 10]
kernel = ['linear', 'poly', 'rbf']
param_grid = [{'C': C, 'kernel':kernel}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = 'SVM'
return grid_search
def find_best_knn(data,target,cv):
clf = KNeighborsClassifier()
n_neighbors = [1,2,3,5,8,10,15,20,25,30,35,40]
weights = ['uniform','distance']
param_grid = [{'n_neighbors': n_neighbors, 'weights': weights}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = 'KNN'
return grid_search
def find_best_svm(data, target, cv):
clf = SVC()
C = [0.1, 0.5, 1, 5, 10]
kernel = ['linear', 'poly', 'rbf']
param_grid = [{'C': C, 'kernel': kernel}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = 'SVM'
return grid_search
def find_best_knn(data, target, cv):
clf = KNeighborsClassifier()
n_neighbors = [1, 2, 3, 5, 8, 10, 15, 20, 25, 30, 35, 40]
weights = ['uniform', 'distance']
param_grid = [{'n_neighbors': n_neighbors, 'weights': weights}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = 'KNN'
return grid_search
def find_best_decisiontree(data, target, cv):
clf = DecisionTreeClassifier()
criterion = ['gini','entropy']
max_depth = [10, 15, 20, 30, None]
min_samples_split = [2, 3, 5, 8, 10]
min_samples_leaf = [1, 2, 3, 5, 8]
param_grid = [{'criterion': criterion, 'max_depth':max_depth, 'min_samples_split':min_samples_split, 'min_samples_leaf':min_samples_leaf}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = '决策树'
return grid_search
def find_best_decisiontree(data, target, cv):
clf = DecisionTreeClassifier()
criterion = ['gini', 'entropy']
max_depth = [10, 15, 20, 30, None]
min_samples_split = [2, 3, 5, 8, 10]
min_samples_leaf = [1, 2, 3, 5, 8]
param_grid = [{
'criterion': criterion,
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'min_samples_leaf': min_samples_leaf
}]
grid_search = GridSearchCV(clf, param_grid=param_grid, cv=cv)
grid_search.fit(data, target)
grid_search.cls_name = '决策树'
return grid_search
