import numpy as np
from scipy.stats import zscore

# 生成隨機(jī)數(shù)據(jù)
data = np.random.randn(100)

# 計(jì)算Z-Score
z_scores = zscore(data)

# 定義閾值，判斷是否為異常值
threshold = 2.5
outliers = np.where(np.abs(z_scores) > threshold)[0]

print("Z-Score Outliers:", outliers)

from sklearn.ensemble import IsolationForest

# 生成隨機(jī)數(shù)據(jù)
data = np.random.randn(100, 1)

# 創(chuàng)建Isolation Forest模型
model = IsolationForest(contamination=0.1)  # contamination參數(shù)表示異常值的比例

# 訓(xùn)練模型并預(yù)測(cè)異常值
outliers = model.fit_predict(data)

print("Isolation Forest Outliers:", np.where(outliers == -1)[0])

import matplotlib.pyplot as plt
import seaborn as sns

# 生成帶有異常值的隨機(jī)數(shù)據(jù)
data = np.concatenate([np.random.randn(80), np.random.randn(20) * 5 + 10])

# 繪制直方圖
plt.figure(figsize=(10, 6))
sns.histplot(data, kde=True)
plt.title("Histogram with Outliers")
plt.show()

# 繪制箱線圖
plt.figure(figsize=(10, 6))
sns.boxplot(x=data)
plt.title("Boxplot with Outliers")
plt.show()

# 假設(shè)我們將異常值替換為中位數(shù)
median_value = np.median(data)
data_no_outliers = np.where(np.abs(z_scores) > threshold, median_value, data)

# 繪制處理后的數(shù)據(jù)
plt.figure(figsize=(10, 6))
sns.histplot(data_no_outliers, kde=True)
plt.title("Histogram without Outliers")
plt.show()

from sklearn.cluster import DBSCAN
from sklearn.preprocessing import StandardScaler

# 生成帶有異常值的隨機(jī)數(shù)據(jù)
data = np.concatenate([np.random.randn(80), np.random.randn(20) * 5 + 10])

# 使用DBSCAN進(jìn)行聚類
data = data.reshape(-1, 1)  # DBSCAN要求輸入是二維數(shù)組
data_scaled = StandardScaler().fit_transform(data)
dbscan = DBSCAN(eps=0.5, min_samples=5)
clusters = dbscan.fit_predict(data_scaled)

# 找出標(biāo)簽為-1的異常點(diǎn)
outliers = np.where(clusters == -1)[0]

print("DBSCAN Outliers:", outliers)

import seaborn as sns

# 加載鳶尾花數(shù)據(jù)集
iris = sns.load_dataset("iris")

# 選擇一個(gè)特征進(jìn)行演示（這里選擇花萼長(zhǎng)度）
feature = "sepal_length"
data_iris = iris[feature]

# 計(jì)算Z-Score
z_scores_iris = zscore(data_iris)

# 定義閾值，判斷是否為異常值
threshold_iris = 2.5
outliers_iris = np.where(np.abs(z_scores_iris) > threshold_iris)[0]

print("Z-Score Outliers in Iris Dataset:", outliers_iris)

# 繪制箱線圖
plt.figure(figsize=(10, 6))
sns.boxplot(x=data_iris)
plt.title("Boxplot for Sepal Length in Iris Dataset")
plt.show()

# 假設(shè)我們將異常值替換為中位數(shù)
median_value_iris = np.median(data_iris)
data_iris_no_outliers = np.where(np.abs(z_scores_iris) > threshold_iris, median_value_iris, data_iris)

# 繪制處理后的數(shù)據(jù)
plt.figure(figsize=(10, 6))
sns.histplot(data_iris_no_outliers, kde=True)
plt.title("Histogram for Sepal Length without Outliers")
plt.show()