machine-learning - ML 分类中的 SMOTE

Question

我正在 Jupyter 中使用 sklearn 运行分类算法。我想使用 SMOTE，因为我的一组只有其他 2 组的 35%。所以我想对该组(组 1)进行过采样，但我不知道如何整合它。 (编辑:我了解 SMOTE 脚本，但我想知道它适合下面我的脚本的位置)。帮忙？

from sklearn.model_selection import train_test_split
    X_train, X_test, y_train, y_test = train_test_split (X, y, test_size = 0.1) 
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform (X_test)
from sklearn.svm import SVC
clf = SVC(kernel = 'linear')
clf.fit (X_train, y_train.ravel())
y_pred = clf.predict(X_test)
from sklearn.metrics import confusion_matrix
cm = confusion_matrix (y_test, y_pred)
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score (estimator = clf, X = X_train, y = y_train, cv = 10)
accuracies.mean()
accuracies.std()
from sklearn.model_selection import GridSearchCV
parameters = [{'C':[1, 10, 100], 'kernel':['linear']}, 
              {'C':[1, 10, 100], 
               'kernel':['rbf'], 
               'gamma': [0.05, 0.001,　0.005]}]
grid_search = GridSearchCV (estimator = clf, param_grid = parameters, scoring = 'accuracy', cv = 10)
grid_search = grid_search.fit (X_train,y_train)
best_accuracy =  grid_search.best_score_ 
print (best_accuracy)
best_parameters = grid_search.best_params_
print (best_parameters)

Answer 1

您必须对数据集进行 SMOTE 并使用生成的平衡数据集来训练您的模型。

因此，您必须像在问题中未显示的代码中一样加载数据，并对其应用 SMOTE。

就代码而言，可以这样完成

X = # train data
y = # train labels

# applying SMOTE

from imblearn.over_sampling import SMOTE

sm = SMOTE(random_state=42)
X_balanced, y_balanced = sm.fit_sample(X, y)

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split (X_balanced, y_balanced, test_size = 0.1) 
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform (X_test)
from sklearn.svm import SVC
clf = SVC(kernel = 'linear')
clf.fit (X_train, y_train.ravel())
y_pred = clf.predict(X_test)
from sklearn.metrics import confusion_matrix
cm = confusion_matrix (y_test, y_pred)
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score (estimator = clf, X = X_train, y = y_train, cv = 10)
accuracies.mean()
accuracies.std()
from sklearn.model_selection import GridSearchCV
parameters = [{'C':[1, 10, 100], 'kernel':['linear']}, 
              {'C':[1, 10, 100], 
               'kernel':['rbf'], 
               'gamma': [0.05, 0.001,　0.005]}]
grid_search = GridSearchCV (estimator = clf, param_grid = parameters, scoring = 'accuracy', cv = 10)
grid_search = grid_search.fit (X_train,y_train)
best_accuracy =  grid_search.best_score_ 
print (best_accuracy)
best_parameters = grid_search.best_params_
print (best_parameters)