-
-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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
1 changed file
with
143 additions
and
9 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,9 +1,143 @@ | ||
import pandas as pd | ||
from pyod.models.sos import SOS | ||
iris = pd.read_csv("http://bit.ly/iris-csv") | ||
X = iris.drop("Name", axis=1).values | ||
detector = SOS() | ||
detector.fit(X) | ||
iris["score"] = detector.decision_scores_ | ||
|
||
print(iris.sort_values("score", ascending=False).head(10)) | ||
# 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__"), '..'))) | ||
|
||
from sklearn.utils import check_X_y | ||
import numpy as np | ||
from sklearn.model_selection import train_test_split | ||
from xgboost.sklearn import XGBClassifier | ||
from scipy.io import loadmat | ||
|
||
from pyod.models.knn import KNN | ||
from pyod.models.lof import LOF | ||
from pyod.models.iforest import IForest | ||
from pyod.models.hbos import HBOS | ||
from pyod.models.ocsvm import OCSVM | ||
from pyod.utils.data import generate_data | ||
from pyod.utils.data import get_color_codes | ||
from pyod.utils.data import evaluate_print | ||
from pyod.utils.utility import standardizer | ||
|
||
|
||
if __name__ == "__main__": | ||
|
||
# Define data file and read X and y | ||
# Generate some data if the source data is missing | ||
mat_file = 'cardio.mat' | ||
try: | ||
mat = loadmat(os.path.join('data', mat_file)) | ||
|
||
except TypeError: | ||
print('{data_file} does not exist. Use generated data'.format( | ||
data_file=mat_file)) | ||
X, y = generate_data(train_only=True) # load data | ||
except IOError: | ||
print('{data_file} does not exist. Use generated data'.format( | ||
data_file=mat_file)) | ||
X, y = generate_data(train_only=True) # load data | ||
else: | ||
X = mat['X'] | ||
y = mat['y'].ravel() | ||
|
||
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4) | ||
# X_train_norm, X_test_norm = X_train, X_test | ||
X_train_norm, X_test_norm = standardizer(X_train, X_test) | ||
|
||
estimator_list = [] | ||
# predefined range of k | ||
k_range = [1, 2, 3, 4, 5, 10, 15, 20, 30, 40, 50, 60, 70, 80, 90, 100, 150, | ||
200, 250] | ||
# validate the value of k | ||
k_range = [k for k in k_range if k < X.shape[0]] | ||
|
||
for k in k_range: | ||
estimator_list.append(KNN(n_neighbors=k)) | ||
estimator_list.append(LOF(n_neighbors=k)) | ||
|
||
n_bins_range = [3, 5, 7, 9, 12, 15, 20, 25, 30, 50] | ||
for n_bins in n_bins_range: | ||
estimator_list.append(HBOS(n_bins=n_bins)) | ||
|
||
# predefined range of nu for one-class svm | ||
nu_range = [0.01, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.99] | ||
|
||
# predefined range for number of estimators in isolation forests | ||
n_range = [10, 20, 50, 70, 100, 150, 200, 250] | ||
|
||
for nu in nu_range: | ||
estimator_list.append(OCSVM(nu=nu)) | ||
|
||
# estimator_list = [KNN(n_neighbors=10), | ||
# KNN(n_neighbors=30), | ||
# KNN(n_neighbors=50), | ||
# KNN(n_neighbors=70), | ||
# KNN(n_neighbors=90), | ||
# LOF(n_neighbors=20), | ||
# LOF(n_neighbors=40), | ||
# LOF(n_neighbors=60), | ||
# LOF(n_neighbors=80), | ||
# LOF(n_neighbors=100), | ||
# IForest(n_estimators=30), | ||
# IForest(n_estimators=50), | ||
# IForest(n_estimators=70), | ||
# IForest(n_estimators=90), | ||
# IForest(n_estimators=100), | ||
# HBOS(n_bins=10), | ||
# HBOS(n_bins=20), | ||
# HBOS(n_bins=30), | ||
# HBOS(n_bins=40), | ||
# HBOS(n_bins=50), | ||
# ] | ||
|
||
X_train_add = np.zeros([X_train.shape[0], len(estimator_list)]) | ||
X_test_add = np.zeros([X_test.shape[0], len(estimator_list)]) | ||
|
||
# fit the model | ||
for index, estimator in enumerate(estimator_list): | ||
estimator.fit(X_train_norm) | ||
X_train_add[:, index] = estimator.decision_scores_ | ||
X_test_add[:, index] = estimator.decision_function(X_test_norm) | ||
|
||
# prepare the new feature space | ||
|
||
X_train_new = np.concatenate((X_train, X_train_add), axis=1) | ||
X_test_new = np.concatenate((X_test, X_test_add), axis=1) | ||
|
||
clf = XGBClassifier() | ||
clf.fit(X_train_new, y_train) | ||
y_test_scores = clf.predict_proba(X_test_new) # outlier scores | ||
|
||
evaluate_print('XGBOD', y_test, y_test_scores[:, 1]) | ||
|
||
|
||
clf = XGBClassifier() | ||
clf.fit(X_train, y_train) | ||
y_test_scores_orig = clf.predict_proba(X_test) # outlier scores | ||
|
||
evaluate_print('XGBOD', y_test, y_test_scores_orig[:, 1]) | ||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|