python_异常值_EllipticEnvelope法和四分位差法

python_异常值_EllipticEnvelope法和四分位差法

# 加载库
import numpy as np
from sklearn.covariance import EllipticEnvelope
from sklearn.datasets import make_blobs
​
# 创建爱模拟数据
​
# sklearn 中 make_blobs模块使用
# sklearn.datasets.make_blobs(n_samples=100, n_features=2, centers=3, cluster_std=1.0, center_box=(-10.0, 10.0), shuffle=True, random_state=None)
​
# 属性含义：
​
# n_samples: int, optional (default=100) 
# The total number of points equally divided among clusters. 
# 待生成的样本的总数。 
# n_features: int, optional (default=2) 
# The number of features for each sample. 
# 每个样本的特征数。 
# centers: int or array of shape [n_centers, n_features], optional (default=3) 
# The number of centers to generate, or the fixed center locations. 
# 要生成的样本中心（类别）数，或者是确定的中心点。 
# cluster_std: float or sequence of floats, optional (default=1.0) 
# The standard deviation of the clusters. 
# 每个类别的方差，例如我们希望生成2类数据，其中一类比另一类具有更大的方差，可以将cluster_std设置为[1.0,3.0]。 
​
features, _ = make_blobs(n_samples = 10,
                         n_features = 2,
                         centers = 1,
                         random_state = 1)
features
​
array([[-1.83198811,  3.52863145],
       [-2.76017908,  5.55121358],
       [-1.61734616,  4.98930508],
       [-0.52579046,  3.3065986 ],
       [ 0.08525186,  3.64528297],
       [-0.79415228,  2.10495117],
       [-1.34052081,  4.15711949],
       [-1.98197711,  4.02243551],
       [-2.18773166,  3.33352125],
       [-0.19745197,  2.34634916]])
# # 将第一个值替换成异常值
features[0,0] = 10000
features[0,1] = 10000
features
# # contamination   污染指数  即清洁程度
outlier_detector = EllipticEnvelope(contamination=.1)
​
# # 拟合识别器
outlier_detector.fit(features)
​
# # 预测
outlier_detector.predict(features)
array([-1,  1,  1,  1,  1,  1,  1,  1,  1,  1])
# 创建一个函数返回异常值下标
feature = features[:,0]
feature


#四分位差法
# # 创建一个函数返回异常值下标
def indicies_of_outliers(x):
    q1, q3 = np.percentile(x, [25, 75])
    iqr = q3 - q1
    lower_bound = q1 - (iqr * 1.5)
    upper_bound = q3 + (iqr * 1.5)
    return np.where((x > upper_bound) | (x < lower_bound))
​
# 执行函数
indicies_of_outliers(feature)
# print(len(feature1))
(array([0], dtype=int64),)