# 生成不平衡分類數據集
from collections import Counter
from sklearn.datasets import make_classification
X, y = make_classification(n_samples=3000, n_features=2, n_informative=2,
              n_redundant=0, n_repeated=0, n_classes=3,
              n_clusters_per_class=1,
              weights=[0.1, 0.05, 0.85],
              class_sep=0.8, random_state=2018)
Counter(y)
# Counter({2: 2532, 1: 163, 0: 305})

# 使用RandomOverSampler從少數類的樣本中進行隨機采樣來增加新的樣本使各個分類均衡
from imblearn.over_sampling import RandomOverSampler
 
ros = RandomOverSampler(random_state=0)
X_resampled, y_resampled = ros.fit_sample(X, y)
sorted(Counter(y_resampled).items())
# [(0, 2532), (1, 2532), (2, 2532)]

# SMOTE: 對于少數類樣本a, 隨機選擇一個最近鄰的樣本b, 然后從a與b的連線上隨機選取一個點c作為新的少數類樣本
from imblearn.over_sampling import SMOTE
 
X_resampled_smote, y_resampled_smote = SMOTE().fit_sample(X, y)
 
sorted(Counter(y_resampled_smote).items())
# [(0, 2532), (1, 2532), (2, 2532)]

# ADASYN: 關注的是在那些基于K最近鄰分類器被錯誤分類的原始樣本附近生成新的少數類樣本
from imblearn.over_sampling import ADASYN

X_resampled_adasyn, y_resampled_adasyn = ADASYN().fit_sample(X, y)
 
sorted(Counter(y_resampled_adasyn).items())
# [(0, 2522), (1, 2520), (2, 2532)]

# RandomUnderSampler函數是一種快速并十分簡單的方式來平衡各個類別的數據: 隨機選取數據的子集.
from imblearn.under_sampling import RandomUnderSampler
rus = RandomUnderSampler(random_state=0)
X_resampled, y_resampled = rus.fit_sample(X, y)
 
sorted(Counter(y_resampled).items())
# [(0, 163), (1, 163), (2, 163)]

# 在之前的SMOTE方法中, 當由邊界的樣本與其他樣本進行過采樣差值時, 很容易生成一些噪音數據. 因此, 在過采樣之后需要對樣本進行清洗. 
# 這樣TomekLink 與 EditedNearestNeighbours方法就能實現上述的要求.
from imblearn.combine import SMOTEENN
smote_enn = SMOTEENN(random_state=0)
X_resampled, y_resampled = smote_enn.fit_sample(X, y)
 
sorted(Counter(y_resampled).items())
# [(0, 2111), (1, 2099), (2, 1893)]

from imblearn.combine import SMOTETomek
smote_tomek = SMOTETomek(random_state=0)
X_resampled, y_resampled = smote_tomek.fit_sample(X, y)
 
sorted(Counter(y_resampled).items())
# [(0, 2412), (1, 2414), (2, 2396)]

# 使用SVM的權重調節(jié)處理不均衡樣本 權重為balanced 意味著權重為各分類數據量的反比
from sklearn.svm import SVC 
svm_model = SVC(class_weight='balanced')
svm_model.fit(X, y)

# # EasyEnsemble 通過對原始的數據集進行隨機下采樣實現對數據集進行集成.
# EasyEnsemble 有兩個很重要的參數: (i) n_subsets 控制的是子集的個數 and (ii) replacement 決定是有放回還是無放回的隨機采樣.
from imblearn.ensemble import EasyEnsemble
ee = EasyEnsemble(random_state=0, n_subsets=10)
X_resampled, y_resampled = ee.fit_sample(X, y)
sorted(Counter(y_resampled[0]).items())
# [(0, 163), (1, 163), (2, 163)]

# BalanceCascade(級聯平衡)的方法通過使用分類器(estimator參數)來確保那些被錯分類的樣本在下一次進行子集選取的時候也能被采樣到. 同樣, n_max_subset 參數控制子集的個數, 以及可以通過設置bootstrap=True來使用bootstraping(自助法).
from imblearn.ensemble import BalanceCascade
from sklearn.linear_model import LogisticRegression
bc = BalanceCascade(random_state=0,
          estimator=LogisticRegression(random_state=0),
          n_max_subset=4)
X_resampled, y_resampled = bc.fit_sample(X, y)
 
sorted(Counter(y_resampled[0]).items())
# [(0, 163), (1, 163), (2, 163)]

# BalancedBaggingClassifier 允許在訓練每個基學習器之前對每個子集進行重抽樣. 簡而言之, 該方法結合了EasyEnsemble采樣器與分類器(如BaggingClassifier)的結果.
from sklearn.tree import DecisionTreeClassifier
from imblearn.ensemble import BalancedBaggingClassifier
bbc = BalancedBaggingClassifier(base_estimator=DecisionTreeClassifier(),
                ratio='auto',
                replacement=False,
                random_state=0)
bbc.fit(X, y)