Python 离群点检测算法-OCSVM

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pyod.utils.data import generate_data
contamination = 0.05 # percentage of outliers
n_train = 500       # number of training points
n_test = 500        # number of testing points
n_features = 6      # number of features
X_train, X_test, y_train, y_test = generate_data(
    n_train=n_train, 
    n_test=n_test, 
    n_features= n_features, 
    cnotallow=contamination, 
    random_state=123)

X_train_pd = pd.DataFrame(X_train)
X_train_pd.head()

# Plot
plt.scatter(X_train_pd[0], X_train_pd[1], c=y_train, alpha=0.8)
plt.title('Scatter plot')
plt.xlabel('x0')
plt.ylabel('x1')
plt.show()

from pyod.models.ocsvm import OCSVM
ocsvm = OCSVM(cnotallow=0.05)  
ocsvm.fit(X_train)

# Training data
y_train_scores = ocsvm.decision_function(X_train)
y_train_pred = ocsvm.predict(X_train)

# Test data
y_test_scores = ocsvm.decision_function(X_test)
y_test_pred = ocsvm.predict(X_test) # outlier labels (0 or 1)

def count_stat(vector):
    # Because it is '0' and '1', we can run a count statistic. 
    unique, counts = np.unique(vector, return_counts=True)
    return dict(zip(unique, counts))

print("The training data:", count_stat(y_train_pred))
print("The training data:", count_stat(y_test_pred))
# Threshold for the defined comtanimation rate
print("The threshold for the defined comtanimation rate:" , ocsvm.threshold_)

The training data: {0: 475, 1: 25}
The training data: {0: 475, 1: 25}
The threshold for the defined comtanimation rate: 
29.680071121036956

ocsvm.get_params()

{'cache_size': 200,
 'coef0': 0.0,
 'contamination': 0.05,
 'degree': 3,
 'gamma': 'auto',
 'kernel': 'rbf',
 'max_iter': -1,
 'nu': 0.5,
 'shrinking': True,
 'tol': 0.001,
 'verbose': False}

import matplotlib.pyplot as plt
plt.hist(y_train_scores, bins='auto')  # arguments are passed to np.histogram
plt.title("Histogram with 'auto' bins")
plt.xlabel('One-class SVM outlier score')
plt.show()

threshold = ocsvm.threshold_ # Or other value from the above histogram

def descriptive_stat_threshold(df,pred_score, threshold):
    # Let's see how many '0's and '1's.
    df = pd.DataFrame(df)
    df['Anomaly_Score'] = pred_score
    df['Group'] = np.where(df['Anomaly_Score']< threshold, 'Normal', 'Outlier')

    # Now let's show the summary statistics:
    cnt = df.groupby('Group')['Anomaly_Score'].count().reset_index().rename(columns={'Anomaly_Score':'Count'})
    cnt['Count %'] = (cnt['Count'] / cnt['Count'].sum()) * 100 # The count and count %
    stat = df.groupby('Group').mean().round(2).reset_index() # The avg.
    stat = cnt.merge(stat, left_notallow='Group',right_notallow='Group') # Put the count and the avg. together
    return (stat)

descriptive_stat_threshold(X_train,y_train_scores, threshold)

Actual_pred = pd.DataFrame({'Actual': y_test, 'Anomaly_Score': y_test_scores})
Actual_pred['Pred'] = np.where(Actual_pred['Anomaly_Score']< threshold,0,1)
pd.crosstab(Actual_pred['Actual'],Actual_pred['Pred'])

from pyod.models.combination import aom, moa, average, maximization
from pyod.utils.utility import standardizer
from pyod.models.ocsvm import OCSVM

# Standardize data
X_train_norm, X_test_norm = standardizer(X_train, X_test)

# Test a range of nu
k_list = [0.01, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.99]
n_clf = len(k_list)
# Just prepare data frames so we can store the model results
train_scores = np.zeros([X_train.shape[0], n_clf])
test_scores = np.zeros([X_test.shape[0], n_clf])

# Modeling
for i in range(n_clf):
    k = k_list[i]
    ocsvm = OCSVM(nu=k,cnotallow=0.05)  
    ocsvm.fit(X_train_norm)
    # Store the results in each column:
    train_scores[:, i] = ocsvm.decision_function(X_train_norm) 
    test_scores[:, i] = ocsvm.decision_function(X_test_norm) 
# Decision scores have to be normalized before combination
train_scores_norm, test_scores_norm = standardizer(train_scores,test_scores)

# Combination by average
# The test_scores_norm is 500 x 10. The "average" function will take the average of the 10 columns. The result "y_by_average" is a single column: 
y_train_by_average = average(train_scores_norm)
y_test_by_average = average(test_scores_norm)
import matplotlib.pyplot as plt
plt.hist(y_train_by_average, bins='auto') # arguments are passed to np.histogram
plt.title("Combination by average")
plt.show()

descriptive_stat_threshold(
      X_train,y_train_by_average, 1.4)