-
-
Notifications
You must be signed in to change notification settings - Fork 107
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
148 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,5 @@ | ||
#!/usr/bin/env bash | ||
make clean | ||
make html | ||
cd .. | ||
cp examples/*.png /docs/figs/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,139 @@ | ||
# -*- coding: utf-8 -*- | ||
"""Compare all detection algorithms by plotting decision boundaries and | ||
the number of decision boundaries. | ||
""" | ||
# Author: Yue Zhao <zhaoy@cmu.edu> | ||
# License: BSD 2 clause | ||
|
||
from __future__ import division | ||
from __future__ import print_function | ||
|
||
import os | ||
import sys | ||
|
||
# temporary solution for relative imports in case pyod is not installed | ||
# if pyod is installed, no need to use the following line | ||
sys.path.append( | ||
os.path.abspath(os.path.join(os.path.dirname("__file__"), '..'))) | ||
|
||
# supress warnings for clean output | ||
import warnings | ||
|
||
warnings.filterwarnings("ignore") | ||
import numpy as np | ||
from numpy import percentile | ||
import matplotlib.pyplot as plt | ||
import matplotlib.font_manager | ||
|
||
# Import all models | ||
from sklearn.tree import DecisionTreeClassifier | ||
from sklearn.linear_model import LogisticRegression | ||
from sklearn.ensemble import AdaBoostClassifier | ||
from sklearn.ensemble import RandomForestClassifier | ||
from sklearn.naive_bayes import GaussianNB | ||
from sklearn.svm import SVC | ||
from sklearn.neighbors import KNeighborsClassifier | ||
|
||
from combo.models.classifier_comb import SimpleClassifierAggregator | ||
from combo.models.stacking import Stacking | ||
|
||
# Define the number of inliers and outliers | ||
n_samples = 300 | ||
outliers_fraction = 0.5 | ||
clusters_separation = [3] | ||
|
||
# Compare given detectors under given settings | ||
# Initialize the data | ||
xx, yy = np.meshgrid(np.linspace(-7, 7, 100), np.linspace(-7, 7, 100)) | ||
n_inliers = int((1. - outliers_fraction) * n_samples) | ||
n_outliers = int(outliers_fraction * n_samples) | ||
ground_truth = np.zeros(n_samples, dtype=int) | ||
ground_truth[-n_outliers:] = 1 | ||
|
||
# Show the statics of the data | ||
print('Number of inliers: %i' % n_inliers) | ||
print('Number of outliers: %i' % n_outliers) | ||
print( | ||
'Ground truth shape is {shape}. Outlier are 1 and inliers are 0.\n'.format( | ||
shape=ground_truth.shape)) | ||
print(ground_truth, '\n') | ||
|
||
random_state = np.random.RandomState(42) | ||
|
||
classifiers = [LogisticRegression(), GaussianNB(), SVC(probability=True), | ||
KNeighborsClassifier()] | ||
|
||
# Define nine outlier detection tools to be compared | ||
classifiers = { | ||
# 'Decision Tree': DecisionTreeClassifier(), | ||
'Logistic Regression': LogisticRegression(), | ||
# 'Ada': AdaBoostClassifier(random_state=random_state), | ||
# 'Random Forest': RandomForestClassifier(random_state=random_state), | ||
'Gaussian': GaussianNB(), | ||
'SVM': SVC(probability=True), | ||
'kNN': KNeighborsClassifier(), | ||
'Average': SimpleClassifierAggregator(base_estimators=classifiers, | ||
method='average'), | ||
'Max': SimpleClassifierAggregator(base_estimators=classifiers, | ||
method='maximization'), | ||
'Stacking': Stacking(base_clfs=classifiers, shuffle_data=True), | ||
'Stacking_RF': Stacking(base_clfs=classifiers, shuffle_data=True, | ||
meta_clf=RandomForestClassifier( | ||
random_state=random_state)) | ||
} | ||
|
||
# Show all detectors | ||
for i, clf in enumerate(classifiers.keys()): | ||
print('Model', i + 1, clf) | ||
|
||
# Fit the models with the generated data and | ||
# compare model performances | ||
for i, offset in enumerate(clusters_separation): | ||
np.random.seed(42) | ||
# Data generation | ||
X1 = 0.3 * np.random.randn(n_inliers // 2, 2) - offset | ||
X2 = 0.3 * np.random.randn(n_inliers // 2, 2) + offset | ||
X = np.r_[X1, X2] | ||
# Add outliers | ||
X = np.r_[X, np.random.uniform(low=-6, high=6, size=(n_outliers, 2))] | ||
|
||
# Fit the model | ||
plt.figure(figsize=(15, 8)) | ||
for i, (clf_name, clf) in enumerate(classifiers.items()): | ||
print() | ||
print(i + 1, 'fitting', clf_name) | ||
# fit the data and tag outliers | ||
|
||
clf.fit(X, ground_truth) | ||
scores_pred = clf.predict_proba(X)[:, 1] * -1 | ||
|
||
y_pred = clf.predict(X) | ||
threshold = percentile(scores_pred, 100 * outliers_fraction) | ||
n_errors = (y_pred != ground_truth).sum() | ||
# plot the levels lines and the points | ||
Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1] * -1 | ||
Z = Z.reshape(xx.shape) | ||
subplot = plt.subplot(2, 4, i + 1) | ||
subplot.contourf(xx, yy, Z, levels=np.linspace(Z.min(), threshold, 7), | ||
cmap=plt.cm.Blues_r) | ||
a = subplot.contour(xx, yy, Z, levels=[threshold], | ||
linewidths=2, colors='red') | ||
subplot.contourf(xx, yy, Z, levels=[threshold, Z.max()], | ||
colors='orange') | ||
b = subplot.scatter(X[:-n_outliers, 0], X[:-n_outliers, 1], c='white', | ||
s=20, edgecolor='k') | ||
c = subplot.scatter(X[-n_outliers:, 0], X[-n_outliers:, 1], c='black', | ||
s=20, edgecolor='k') | ||
subplot.axis('tight') | ||
subplot.legend( | ||
[a.collections[0], b, c], | ||
['learned boundary', 'class 0', 'class 1'], | ||
prop=matplotlib.font_manager.FontProperties(size=10), | ||
loc='lower right') | ||
subplot.set_xlabel("%d. %s (errors: %d)" % (i + 1, clf_name, n_errors)) | ||
subplot.set_xlim((-7, 7)) | ||
subplot.set_ylim((-7, 7)) | ||
plt.subplots_adjust(0.04, 0.1, 0.96, 0.94, 0.1, 0.26) | ||
plt.suptitle("Model Combination") | ||
plt.savefig('ALL.png', dpi=300) | ||
plt.show() |