def dorc(preprocessedData, random_state, outliers_fraction=0.1):
t0 = time.time()
clf = IForest(contamination=outliers_fraction,
random_state=random_state,
n_jobs=-1)
clf.fit(preprocessedData)
scores = clf.decision_function(preprocessedData)
# Apply IQR-based criteria to identify rare cells for further downstream analysis.
q3 = np.percentile(scores, 75)
iqr = stats.iqr(scores)
th = q3 + (1.5 * iqr)
# Select indexes that satisfy IQR-based thresholding criteria.
indIqr = np.where(scores >= th)[0]
print('shape of selected cells : {}'.format(indIqr.shape))
# Create a file with binary predictions
predictions = np.zeros(preprocessedData.shape[0])
predictions[indIqr] = 1 # Replace predictions for rare cells with '1'.
t1 = time.time()
duration = round(t1 - t0, ndigits=4)
print("Total running DoRC time is :" + str(duration) + " s")
return predictions, scores, duration
def anomaly_detection(data, label):
X = data[data.select_dtypes('number').columns.tolist()]
y = data[label]
y = y.values
X = X.drop([label], axis=1)
sc = StandardScaler()
X = pd.DataFrame(data=sc.fit_transform(X), columns=X.columns)
ifo = IForest(contamination=0.01,
behaviour='new',
n_estimators=1000,
max_samples=1024,
n_jobs=-1,
verbose=1)
ifo.fit(X)
ifo_pred = ifo.labels_
print('ROC score for Isolation forest: ', roc_auc_score(y, ifo_pred))
utilities.plot_outlier_scores(
y,
ifo.decision_scores_,
bw=0.1,
title='Fraud, Isolation forest. (n_estimators={})'.format(
ifo.n_estimators))
ae = AutoEncoder(hidden_neurons=[25, 20, 15, 20, 25],
hidden_activation='relu',
output_activation='sigmoid',
optimizer='adam',
epochs=20,
batch_size=128,
dropout_rate=0.2,
l2_regularizer=0.0,
validation_size=0.1,
preprocessing=False,
verbose=1,
random_state=1,
contamination=0.01)
ae.fit(X)
ae_pred = ae.labels_
print('ROC score for Autoencoder: ', roc_auc_score(y, ae_pred))
utilities.plot_outlier_scores(
y,
ae.decision_scores_,
bw=0.1,
title='Fraud, Autoencoder. (epochs={})'.format(ae.epochs))
# Too long to train, under-sample needed
lof = LOF(n_neighbors=int(y.sum() * 1.3), contamination=0.01, n_jobs=-1)
lof.fit(X)
lof_pred = lof.labels_
print('ROC score for LOF: ', roc_auc_score(y, lof_pred))
utilities.plot_outlier_scores(
y,
lof.decision_scores_,
bw=0.1,
title='Fraud, Local outliers factor. (n_neighbors={})'.format(
lof.n_neighbors))
return y, ifo_pred, ae_pred, lof_pred
class IForestSupervisedKNN(BaseDetector):
def __init__(self, get_top=0.8, if_params={}, knn_params={}):
super(IForestSupervisedKNN, self).__init__()
self.get_top = get_top
self.is_fitted = False
self.iforest = IForest(**if_params)
self.knn = KNN(**knn_params)
def fit(self, X, y=None):
X = check_array(X)
self._set_n_classes(y)
self.iforest.fit(X)
scores = self.iforest.predict_proba(X)[:, 1]
normal_instances = X[np.argsort(scores)[:int(len(X) * self.get_top)]]
self.knn.fit(normal_instances)
self.decision_scores_ = self.decision_function(X)
self._process_decision_scores()
self.is_fitted = True
return self
def decision_function(self, X):
check_is_fitted(self, ['is_fitted'])
return self.knn.decision_function(X)
def train():
# initiate the train
try:
# 1-. Take data and configuration
data = pd.read_csv(training_path, index_col=0)
# Read in any configuration stored
with open(param_path, 'r') as tc:
hyper_parameters = json.load(tc)
# 2-. Set up
# instantiate the Isolation Forest model
model = IForest(contamination=hyper_parameters['contamination'],
behaviour='new')
model.fit(data) # fit
# 3-. Save the model
model_name = 'great_model'
with open(os.path.join(model_path, '{}.pkl'.format(model_name)),
'wb') as out:
pickle.dump(model, out, protocol=0)
# consider that the train fails
except Exception as e:
# write the log
trc = traceback.format_exc()
with open(os.path.join(output_path, 'failure'), 'w') as s:
s.write('Exception during train: ' + str(e) + '\n' + trc)
sys.exit(255)
def densityBased(self):
'''
@brief Function that implements the dependency based component
@param self
@return It returns the vector with the scores of the instances
'''
# Initialize the scores
scores = np.array([0] * len(self.dataset)).astype(float)
for i in range(self.num_iter):
iforest = IForest(contamination=self.contamination,
behaviour="new")
# Number in the interval [50, 1000]
subsample_size = np.random.randint(50, 1001)
sample = []
if subsample_size >= len(self.dataset):
sample = list(range(len(self.dataset)))
else:
# Take the sample and train the model
sample = np.random.choice(len(self.dataset),
size=subsample_size,
replace=False)
iforest.fit(self.dataset[sample])
# Update the score to compute the mean
scores[sample] += iforest.decision_scores_
# Return the mean
scores = scores / self.num_iter
scores = scale(scores)
return scores
def iforest(X_train, X_test, Y_train, Y_test):
from pyod.models.iforest import IForest
model = IForest(random_state=0)
model.fit(X_train)
pred = model.predict(X_test)
acc = np.sum(pred == Y_test) / X_test.shape[0]
print(acc)
return (acc * 100)
def outlier_iforest(data, **kwargs):
import pandas as pd
from pyod.models.iforest import IForest
contamination = float(kwargs.pop('contamination'))
clf = IForest(contamination=contamination)
clf.fit(data)
pred = clf.labels_
df = pd.DataFrame(pred, columns=['is_outlier'])
ret = pd.concat([data, df], axis=1)
return ret
def remove_outliars(dft, target_col):
ol_model = IForest() #### can be used as a hyperparameter
ol_model.fit(dft.drop(columns=target_col))
dft['is_outliar'] = ol_model.labels_
dft = dft[dft['is_outliar'] != 1]
dft = dft.drop(columns='is_outliar')
print("Completed Outliar Detection - ", datetime.datetime.now())
return dft
def S2(self):
self.S1()
water_data = self.water_data
result = self.result
# 数据预处理及模型训练
clean_data = water_data[water_data['S1'] == 0]
Y = pd.DataFrame(index=clean_data.index, columns=['S2'])
X_train = np.array(clean_data.iloc[:, 1:12])
name = list(clean_data.iloc[:, 1:12].columns.values)
scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)
clf1 = IForest(contamination=0.05, max_features=11, bootstrap=True)
clf2 = KNN(contamination=0.05, n_neighbors=100)
clf3 = HBOS(contamination=0.05, n_bins=10)
clf4 = PCA(contamination=0.05)
clf1.fit(X_train)
clf2.fit(X_train)
clf3.fit(X_train)
clf4.fit(X_train)
Y['S2'] = clf1.labels_ * clf2.labels_ * clf3.labels_ * clf4.labels_
water_data = pd.concat([water_data, Y], axis=1)
# water_data.loc[water_data['S2'].isna(),['S2']]=0，将S1中异常的，在S2中标注为0；
result['统计异常'] = water_data['S2'].values
# 寻找异常维度
from sklearn.neighbors import KernelDensity
clean_data = water_data[water_data['S1'] == 0]
dens = pd.DataFrame(index=clean_data.index,
columns=[
'temperature', 'pH', 'EC', 'ORP', 'DO',
'turbidity', 'transparency', 'COD', 'P',
'NH3N', 'flux'
])
for i in dens.columns:
kde = KernelDensity(kernel='gaussian', bandwidth=0.5).fit(
clean_data[i].values.reshape(-1, 1))
dens[i] = np.exp(
kde.score_samples(clean_data[i].values.reshape(-1, 1)))
dens = dens.iloc[:, 0:11].rank()
dens['S2_names'] = dens.idxmin(axis=1)
water_data = pd.concat([water_data, dens['S2_names']], axis=1)
self.water_data = water_data
result['统计异常维度'] = water_data['S2_names'].values
# 存储模型
joblib.dump(scaler, "./water_model/S2_scaler")
joblib.dump(clf1, "./water_model/S2_Iforest")
def outlier_detection(x_raw, y_raw):
"""
Filter all ourlier points
:param x_raw: feature in ndarray
:param y_raw: label in ndarray
:return x_clean, y_clean: cleaned feature and label in ndarray
"""
# TODO Filter the outliers.
print()
print("Detecting outliers...")
print("Before outlier detection: {}".format(x_raw.shape))
outliers_fraction = 0.04
random_state = np.random.RandomState(42)
# all outlier detection method candidate list as follows
classifiers = {
'Angle-based Outlier Detector (ABOD)':
ABOD(contamination=outliers_fraction),
'Cluster-based Local Outlier Factor':
CBLOF(contamination=outliers_fraction,
check_estimator=False,
random_state=random_state),
'Feature Bagging':
FeatureBagging(contamination=outliers_fraction,
random_state=random_state),
'Histogram-base Outlier Detection (HBOS)':
HBOS(contamination=outliers_fraction),
'Isolation Forest':
IForest(contamination=outliers_fraction, random_state=random_state),
'K Nearest Neighbors (KNN)':
KNN(contamination=outliers_fraction),
'Local Outlier Factor (LOF)':
LOF(contamination=outliers_fraction),
'Minimum Covariance Determinant (MCD)':
MCD(contamination=outliers_fraction, random_state=random_state),
'One-class SVM (OCSVM)':
OCSVM(contamination=outliers_fraction),
'Principal Component Analysis (PCA)':
PCA(contamination=outliers_fraction, random_state=random_state),
'Improving Supervised Outlier Detection with Unsupervised Representation Learning':
XGBOD(contamination=outliers_fraction),
}
clf_name = 'Isolation Forest'
clf = IForest(contamination=outliers_fraction, random_state=random_state)
# clf_name = 'Angle-based Outlier Detector (ABOD)'
# clf = ABOD(contamination=outliers_fraction, method='default')
clf.fit(x_raw)
y_pred = clf.predict(x_raw)
# for pyod, 1 means outliers and 0 means inliers
# for sklearn, -1 means outliers and 1 means inliers
idx_y_pred = [i for i in range(0, 1212) if y_pred[i] == 1]
x_clean = del_rowsorcolumns(x_raw, idx_y_pred, axis=0)
y_clean = del_rowsorcolumns(y_raw, idx_y_pred, axis=0)
print("After outlier detection: {}".format(x_clean.shape))
assert (x_clean.shape[0] == y_clean.shape[0])
return x_clean, y_clean
def getOutlierIForest(dataset):
'''
@brief Function that executes IForest algorithm on the dataset and obtains the
labels of the dataset indicating which instance is an inlier (0) or outlier (1)
@param dataset Dataset on which to try the algorithm
@return It returns a list of labels 0 means inlier, 1 means outlier
'''
# Initializating the model without verbose
ifor = IForest(verbose=0)
# Fits the data and obtains labels
ifor.fit(dataset)
# Return labels
return ifor.labels_
class IForestPyOD(BaseAlgorithm):
name = "iForest_pyod"
def __init__(self, t=100, psi=256):
self.iforest = IForest(max_samples=psi, n_estimators=t, behaviour="new", contamination=0.1)
def fit(self, X):
self.iforest.fit(X)
def predict(self, X):
return self.iforest.decision_function(X)
def detect(self, X, y=None):
"""
:param X: Dataframe
:param y: np.array
:return: outlier scores
"""
rng = np.random.RandomState(42)
# 构造训练样本
n_estimators = 200 # 森林中树的棵数
outliers_fraction = 0.5 # 异常样本比例
clf = IForest(max_samples='auto', random_state=rng, contamination=outliers_fraction, n_estimators=n_estimators)
clf.fit(X)
scores = clf.decision_function(X)
return scores
def detect_outliers(stocks: list, all_stocks_cip: pd.DataFrame, rules=None):
"""
Returns a dataframe describing those outliers present in stocks based on the provided rules.
"""
if rules is None:
rules = default_point_score_rules()
str_rules = { str(r):r for r in rules }
rows = []
stocks_by_sector_df = stocks_by_sector() # NB: ETFs in watchlist will have no sector
stocks_by_sector_df.index = stocks_by_sector_df['asx_code']
for stock in stocks:
#print("Processing stock: ", stock)
try:
sector = stocks_by_sector_df.at[stock, 'sector_name']
sector_companies = list(stocks_by_sector_df.loc[stocks_by_sector_df['sector_name'] == sector].asx_code)
# day_low_high() may raise KeyError when data is currently being fetched, so it appears here...
day_low_high_df = day_low_high(stock, all_stocks_cip.columns)
except KeyError:
warning(None, "Unable to locate watchlist entry: {} - continuing without it".format(stock))
continue
state = {
'day_low_high_df': day_low_high_df, # never changes each day, so we init it here
'all_stocks_change_in_percent_df': all_stocks_cip,
'stock': stock,
'daily_range_threshold': 0.20, # 20% at either end of the daily range gets a point
}
points_by_rule = defaultdict(int)
for date in all_stocks_cip.columns:
market_avg = all_stocks_cip[date].mean()
sector_avg = all_stocks_cip[date].filter(items=sector_companies).mean()
stock_move = all_stocks_cip.at[stock, date]
state.update({ 'market_avg': market_avg, 'sector_avg': sector_avg,
'stock_move': stock_move, 'date': date })
for rule_name, rule in str_rules.items():
points_by_rule[rule_name] += rule(state)
d = { 'stock': stock }
d.update(points_by_rule)
rows.append(d)
df = pd.DataFrame.from_records(rows)
df = df.set_index('stock')
print(df)
from pyod.models.iforest import IForest
clf = IForest()
clf.fit(df)
scores = clf.predict(df)
results = [row[0] for row, value in zip(df.iterrows(), scores) if value > 0]
#print(results)
print("Found {} outlier stocks".format(len(results)))
return results
def add_other_class(num, size, pad):
res = pd.read_csv("data/train.txt", header=None).values
tif_data = []
for r in tqdm(range(res.shape[0])):
img = get_cell(res[r][1], res[r][2], size)
if img is None:
print("img NOT Exist.", res[r])
continue
img = img.reshape(-1).tolist()
tif_data.append([labels_key[res[r][0]]] + img)
tif_data = np.array(tif_data)
print(tif_data.shape)
np.random.shuffle(tif_data)
clf = IForest()
clf.fit(tif_data[:, 1:])
i = 0
pos = []
false_num = 0
while True:
ix = np.random.randint(pad, dataset.RasterXSize - pad)
iy = np.random.randint(pad, dataset.RasterYSize - pad)
t = get_cell(ix, iy, size)
if t is None:
continue
t = t.reshape(1, -1)
y_test_pred = clf.predict(t)[0] # outlier labels (0 or 1)
if y_test_pred == 1:
i += 1
pos.append(["其他"] + [ix, iy])
print("{}/{} added.".format(i, num))
else:
false_num += 1
print("{}/{} is not include {}.{}. false_num: {}".format(
i, num, ix, iy, false_num))
if i == num:
break
pos = np.concatenate((res, np.array(pos)), axis=0)
print(Counter(pos[:, 0]))
pd.DataFrame(pos).to_csv("data/train_enhance.txt", index=None, header=None)
pos[:, 2] = -1 * (pos[:, 2].astype(np.int))
pd.DataFrame(pos).to_csv("data/train_enhance_view.txt",
index=None,
header=None)
def transform(self, df2: pd.DataFrame) -> pd.DataFrame:
"""Apply the transforms to the dataframe."""
le = LabelEncoder()
df2['mm'] = df2['make'] + ' ' + df2['model']
g_mm_count = df2.groupby(['mm']).count().reset_index()
mm_more_than_100 = g_mm_count[g_mm_count['make'] > 100]['mm']
df2 = df2[df2['mm'].isin(mm_more_than_100)]
dfn3 = df2.copy()
g1 = dfn3.groupby('mm')
clf1 = IForest(contamination=0.01)
flag = [1]
if 1 in flag:
dff1 = pd.DataFrame(columns=[
'idv_id', 'kms_run', 'owners', 'age', 'Popularity Index',
'quoted_price', 'outlier', 'dep_percentage'
])
for idv_id, idv_id_df in g1:
idv_id_df1 = idv_id_df[[
'kms_run', 'owners', 'age', 'quoted_price',
'dep_percentage'
]]
clf1.fit(idv_id_df1)
y_pred = clf1.predict(idv_id_df1)
idv_id_df['outlier'] = y_pred.tolist()
dff1 = pd.concat([dff1, idv_id_df])
outlier_idv_if_dff1 = set(dff1[dff1['outlier'] == 1].index)
df2 = df2.drop(outlier_idv_if_dff1)
df = df2.copy()
X = df[[
'make', 'model', 'city', 'variant', 'owners', 'kms_run', 'age',
'Popularity Index', 'ex_showroom_price', 'fuel_type',
'transmission', 'color'
]]
categorical_feature_mask = X.dtypes == object
categorical_cols = X.columns[categorical_feature_mask].tolist()
self.dic = {}
for i in categorical_cols:
X[i] = le.fit_transform(X[i])
self.dic[i] = dict(zip(le.classes_, le.transform(le.classes_)))
y = df[['dep_percentage']]
aa = pd.concat([X, y], axis=1)
return aa
class IForestWrapper:
def __init__(self, **kwargs):
self._model = IForest(**kwargs)
def fit(self, X, T):
# unsupervised learning Targets not used
self._model.fit(X)
return self
def predict(self, X):
Y = self._model.predict(X)
return Y
def predict_proba(self, X):
probs = self._model.predict_proba(X)
return probs
def main():
dataset, label = pre_data()
from numpy import nan as NA
from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=NA, strategy="mean")
dataset = imputer.fit_transform(dataset)
x_train, x_test, y_train, y_label = train_test_split(dataset,
label,
test_size=0.3,
random_state=44)
# x_train, x_test, y_train, y_label =[], [], [], []
# for i in range(1000):
# x_train.append(dataset[i])
# y_train.append(label[i])
# for i in range(6000,10000):
# x_train.append(dataset[i])
# y_train.append(label[i])
# x_test = dataset[1000:6000]
# y_label = label[1000:6000]
for i in range(3):
clf_name = 'IForest'
clf = IForest()
clf.fit(x_train)
# get the prediction label and outlier scores of the training data
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
print(accuracy_score(y_train, y_train_pred))
print(precision_score(y_train, y_train_pred))
print(recall_score(y_train, y_train_pred))
# get the prediction on the test data
y_test_pred = clf.predict(x_test) # outlier labels (0 or 1)
y_test_scores = clf.decision_function(x_test) # outlier scores
# evaluate and print the results
print("\nOn Training Data:")
evaluate_print(clf_name, y_train, y_train_scores)
print(accuracy_score(y_label, y_test_pred))
print(precision_score(y_train, y_train_pred))
print(recall_score(y_train, y_train_pred))
print("\nOn Test Data:")
evaluate_print(clf_name, y_label, y_test_scores)
def test_pyod_isolation_forest():
import shap
import numpy as np
from pyod.models.iforest import IForest
from sklearn.ensemble.iforest import _average_path_length
X, _ = shap.datasets.boston()
for max_features in [1.0, 0.75]:
iso = IForest(max_features=max_features)
iso.fit(X)
explainer = shap.TreeExplainer(iso)
shap_values = explainer.shap_values(X)
score_from_shap = -2**(
-(np.sum(shap_values, axis=1) + explainer.expected_value) /
_average_path_length(np.array([iso.max_samples_]))[0])
assert np.allclose(iso.detector_.score_samples(X),
score_from_shap,
atol=1e-7)
def get_IF_scores(dataframe,
cols,
outliers_fraction=0.01,
standardize=True):
'''Takes df, a list selected column nmaes, outliers_fraction = 0.01 default
Returns:
df with Isolation Forest (IF) scores added
'''
if standardize:
#standardize selected variables
minmax = MinMaxScaler(feature_range=(0, 1))
dataframe[cols] = minmax.fit_transform(dataframe[cols])
#Convert dataframe to a numpy array in order to incorprate our algorithm
arrays = []
for row in cols:
row = dataframe[row].values.reshape(-1, 1)
arrays.append(row)
X = np.concatenate((arrays), axis=1)
#fit
clf = IForest(contamination=outliers_fraction, random_state=0)
clf.fit(X)
# predict raw anomaly score
scores_pred = clf.decision_function(X) * -1
# prediction of a datapoint category outlier or inlier
y_pred = clf.predict(X)
n_inliers = len(y_pred) - np.count_nonzero(y_pred)
n_outliers = np.count_nonzero(y_pred == 1)
CheckOutliers.df3 = dataframe
CheckOutliers.df3['outlier'] = y_pred.tolist()
print('OUTLIERS:', n_outliers, 'INLIERS:', n_inliers,
'found with HBOS')
Created on Tue Dec 24 15:54:36 2019
@author: zixing.mei
"""
from pyod.models.iforest import IForest
clf = IForest(behaviour='new',
bootstrap=False,
contamination=0.1,
max_features=1.0,
max_samples='auto',
n_estimators=500,
n_jobs=-1,
random_state=None,
verbose=0)
clf.fit(x)
out_pred = clf.predict_proba(x, method='linear')[:, 1]
train['out_pred'] = out_pred
train['for_pred'] = np.where(train.out_pred > 0.7, '负样本占比', '正样本占比')
dic = dict(train.groupby(train.for_pred).bad_ind.agg(np.sum)/ \
train.bad_ind.groupby(train.for_pred).count())
pd.DataFrame(dic, index=[0])
clf = IForest(behaviour='new',
bootstrap=False,
contamination=0.1,
max_features=1.0,
max_samples='auto',
n_estimators=500,
n_jobs=-1,
random_state=None,
class TestIForest(unittest.TestCase):
def setUp(self):
self.n_train = 100
self.n_test = 50
self.contamination = 0.1
self.roc_floor = 0.6
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train, n_test=self.n_test,
contamination=self.contamination, random_state=42)
self.clf = IForest(contamination=self.contamination, random_state=42)
self.clf.fit(self.X_train)
def test_sklearn_estimator(self):
check_estimator(self.clf)
def test_parameters(self):
assert_true(hasattr(self.clf, 'decision_scores_') and
self.clf.decision_scores_ is not None)
assert_true(hasattr(self.clf, 'labels_') and
self.clf.labels_ is not None)
assert_true(hasattr(self.clf, 'threshold_') and
self.clf.threshold_ is not None)
assert_true(hasattr(self.clf, '_mu') and
self.clf._mu is not None)
assert_true(hasattr(self.clf, '_sigma') and
self.clf._sigma is not None)
assert_true(hasattr(self.clf, 'estimators_') and
self.clf.estimators_ is not None)
assert_true(hasattr(self.clf, 'estimators_samples_') and
self.clf.estimators_samples_ is not None)
assert_true(hasattr(self.clf, 'max_samples_') and
self.clf.max_samples_ is not None)
def test_train_scores(self):
assert_equal(len(self.clf.decision_scores_), self.X_train.shape[0])
def test_prediction_scores(self):
pred_scores = self.clf.decision_function(self.X_test)
# check score shapes
assert_equal(pred_scores.shape[0], self.X_test.shape[0])
# check performance
assert_greater(roc_auc_score(self.y_test, pred_scores), self.roc_floor)
def test_prediction_labels(self):
pred_labels = self.clf.predict(self.X_test)
assert_equal(pred_labels.shape, self.y_test.shape)
def test_prediction_proba(self):
pred_proba = self.clf.predict_proba(self.X_test)
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_fit_predict(self):
pred_labels = self.clf.fit_predict(self.X_train)
assert_equal(pred_labels.shape, self.y_train.shape)
def test_fit_predict_score(self):
self.clf.fit_predict_score(self.X_test, self.y_test)
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='roc_auc_score')
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='prc_n_score')
with assert_raises(NotImplementedError):
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='something')
def test_predict_rank(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3)
assert_array_less(pred_ranks, self.X_train.shape[0] + 1)
assert_array_less(-0.1, pred_ranks)
def test_predict_rank_normalized(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test, normalized=True)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
def tearDown(self):
pass
#Extracting y-labels for the validation data and dropping in X data. Y labels will be the same for all feature sets ofcourse
Y_valid1 = X_valid1['Label_<lambda>']
X_valid1.drop(['Label_<lambda>'], inplace=True, axis=1)
# Reading original test data to extract the malicious flow data after prediction
orig_test_data = pd.read_csv("test_data.csv", header=None)
orig_test_data.columns = ['Date_Flow_Start', 'Duration','Protocol','Src_IP','Src_Port','Direction','Dst_IP','Dst_Port','State','Source_Service','Dest_Service','Total_Packets','BiDirection_Bytes','SrcToDst_Bytes']
"""TRAINING on Feature Set 1
IFOREST on Default Parameters
"""
#Training
clf1 = IForest(random_state = 42) # Default contamination = 0.1
clf1.fit(X_train1)
#Setting threshold using the contamination parameter
dec_scores = clf1.decision_scores_
dec_scores_sorted=sorted(dec_scores, reverse=True)
a = round(len(X_train1) * clf1.contamination)
print(a)
anomalies=dec_scores_sorted[:a]
threshold = anomalies[-1]
# Validation data is scored
y_valid_scores = clf1.decision_function(X_valid1)
y_valid_scores = pd.Series(y_valid_scores)
valid_SrcIP = np.load('preprocessing1_valid_srcIP.npy',allow_pickle=True)
class IF(IForest):
def __init__(self,
n_estimators=100,
max_samples='auto',
contamination=0.1,
random_state=42,
verbose=1):
"""Isolation Forest (IF)
Parameters
----------
n_estimators : int, optional (default=100)
The number of base estimators in the ensemble.
max_samples : int or float, optional (default="auto")
The number of samples to draw from X to train each base estimator.
contamination : float in (0., 0.5), optional (default=0.1)
The amount of contamination of the data set, i.e., the proportion of outliers in the data set.
Used when fitting to define the threshold on the decision function.
verbose: int (default is 1)
A print level is to control what information should be printed according to the given value.
The higher the value is, the more info is printed.
random_state: int (default is 42)
"""
self.n_estimators = n_estimators
self.max_samples = max_samples
self.contamination = contamination
self.verbose = verbose
self.random_state = random_state
def fit(self, X_train, y_train=None):
"""Fit the model. y is ignored in unsupervised methods.
Parameters
----------
X_train : numpy array of shape (n_samples, n_features)
The input samples.
y_train : Ignored
Not used, present for API consistency by convention.
Returns
-------
self : object
The fitted estimator.
"""
self.model_ = IForest(
n_estimators=self.n_estimators,
max_samples=self.max_samples,
contamination=self.contamination,
max_features=1.,
bootstrap=False,
n_jobs=-1,
behaviour='deprecated', # no use any more in sklean 0.24.
random_state=self.random_state,
verbose=self.verbose)
self.model_.fit(X=X_train)
return self
def decision_function(self, X):
"""Predict raw anomaly score of X using the fitted detector.
The anomaly score of an input sample is computed based on different
detector algorithms. For consistency, outliers are assigned with
larger anomaly scores.
Parameters
----------
X : numpy array of shape (n_samples, n_features)
The training input samples. Sparse matrices are accepted only
if they are supported by the base estimator.
Returns
-------
anomaly_scores : numpy array of shape (n_samples,)
The anomaly score of the input samples.
"""
return self.model_.decision_function(X)
def predict_proba(self, X):
raise NotImplementedError
def evaluation_od_train(x,
y,
data_name,
model_name="iforest",
chosen_subspace=None):
"""
using anomaly detector to yield anomaly score for each subspace,
generate two files: the subspaces with the highest anomaly score & lof score for each subspace
:param x: data matrix
:param y: class information
:param data_name: the data set name, using for naming the ground truth file
:param model_name: anomaly detector name, default: lof
:param chosen_subspace: use this to only evaluate a subset of the power set of full feature space
:return: df: a ground-truth map using anomaly idx as key and ground truth feature subspace as value.
"""
global chosen_model
dim = x.shape[1]
ano_idx = np.where(y == 1)[0]
n_ano = len(ano_idx)
# get all the possible feature subset or just use given subset list
f_subsets = utils.get_subset_candidate(dim, chosen_subspace)
# score anomalies in each subspace, generate the score matrix
n_subsets = len(f_subsets)
score_matrix = np.zeros([n_ano, n_subsets])
for i in tqdm(range(n_subsets)):
subset = f_subsets[i]
x_subset = x[:, subset]
if model_name == "iforest":
clf = IForest()
clf.fit(x_subset)
od_score = clf.decision_scores_
elif model_name == "copod":
clf = COPOD()
clf.fit(x_subset)
od_score = clf.decision_scores_
elif model_name == "hbos":
clf = HBOS()
clf.fit(x_subset)
od_score = clf.decision_scores_
else:
raise ValueError("unsupported od model")
od_score = utils.min_max_norm(od_score)
score_matrix[:, i] = od_score[ano_idx]
if not os.path.exists(eva_root + "data_od_evaluation/"):
os.makedirs(eva_root + "data_od_evaluation/")
# score matrix to df
anomaly_score_df = pd.DataFrame(data=score_matrix,
columns=[str(s) for s in f_subsets])
col_name = anomaly_score_df.columns.tolist()
col_name.insert(0, 'ano_idx')
anomaly_score_df["ano_idx"] = ano_idx
anomaly_score_df = anomaly_score_df.reindex(columns=col_name)
path1 = eva_root + "data_od_evaluation/" + data_name + "_score_" + model_name + ".csv"
anomaly_score_df.to_csv(path1, index=False)
# get the ground truth (one subspace for each anomaly that the anomaly can obtain the highest anomaly score)
g_truth_df = pd.DataFrame(columns=["ano_idx", "exp_subspace"])
exp_subspaces = []
for ii, ano_score in enumerate(score_matrix):
max_score_idx = int(np.argmax(ano_score))
exp_subset = str(f_subsets[max_score_idx])
exp_subspaces.append(exp_subset)
g_truth_df["ano_idx"] = ano_idx
g_truth_df["exp_subspace"] = exp_subspaces
g_truth_df.astype({"exp_subspace": "object"})
path2 = eva_root + "data_od_evaluation/" + data_name + "_gt_" + model_name + ".csv"
g_truth_df.to_csv(path2, index=False)
return anomaly_score_df, g_truth_df
contamination = 0.1 # percentage of outliers
n_train = 200 # number of training points
n_test = 100 # number of testing points
# Generate sample data
X_train, y_train, X_test, y_test = \
generate_data(n_train=n_train,
n_test=n_test,
n_features=2,
contamination=contamination,
random_state=42)
# train IForest detector
clf_name = 'IForest'
clf = IForest()
clf.fit(X_train)
# get the prediction labels and outlier scores of the training data
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores
# get the prediction on the test data
y_test_pred = clf.predict(X_test) # outlier labels (0 or 1)
y_test_scores = clf.decision_function(X_test) # outlier scores
# evaluate and print the results
print("\nOn Training Data:")
evaluate_print(clf_name, y_train, y_train_scores)
print("\nOn Test Data:")
evaluate_print(clf_name, y_test, y_test_scores)
def detect_outliers(stocks: list, all_stocks_cip: pd.DataFrame, rules=None):
"""
Returns a dataframe describing those outliers present in stocks based on the provided rules.
All_stocks_cip is the "change in percent" for at least the stocks present in the specified list
"""
if rules is None:
rules = default_point_score_rules()
str_rules = {str(r): r for r in rules}
rows = []
stocks_by_sector_df = (stocks_by_sector()
) # NB: ETFs in watchlist will have no sector
stocks_by_sector_df.index = stocks_by_sector_df["asx_code"]
for stock in stocks:
# print("Processing stock: ", stock)
try:
sector = stocks_by_sector_df.at[stock, "sector_name"]
sector_companies = list(stocks_by_sector_df.loc[
stocks_by_sector_df["sector_name"] == sector].asx_code)
# day_low_high() may raise KeyError when data is currently being fetched, so it appears here...
day_low_high_df = day_low_high(stock, all_stocks_cip.columns)
except KeyError:
warning(
None,
"Unable to locate watchlist entry: {} - continuing without it".
format(stock),
)
continue
state = {
"day_low_high_df":
day_low_high_df, # never changes each day, so we init it here
"all_stocks_change_in_percent_df": all_stocks_cip,
"stock": stock,
"daily_range_threshold":
0.20, # 20% at either end of the daily range gets a point
}
points_by_rule = defaultdict(int)
for date in all_stocks_cip.columns:
market_avg = all_stocks_cip[date].mean()
sector_avg = all_stocks_cip[date].filter(
items=sector_companies).mean()
stock_move = all_stocks_cip.at[stock, date]
state.update({
"market_avg": market_avg,
"sector_avg": sector_avg,
"stock_move": stock_move,
"date": date,
})
for rule_name, rule in str_rules.items():
try:
points_by_rule[rule_name] += rule(state)
except TypeError: # handle nan's in dataset safely
pass
d = {"stock": stock}
d.update(points_by_rule)
rows.append(d)
df = pd.DataFrame.from_records(rows)
df = df.set_index("stock")
# print(df)
clf = IForest()
clf.fit(df)
scores = clf.predict(df)
results = [
row[0] for row, value in zip(df.iterrows(), scores) if value > 0
]
# print(results)
print("Found {} outlier stocks".format(len(results)))
return results
def anomaly_rate(model, validation_df, freq, plot=False):
if freq[:-1].isnumeric() and (freq[-1] == 'S' or freq[-1] == 'D'):
last_history = (model.start + model.t_scale).round(freq)
else:
raise ValueError(
"Unsupported frequency format. "
"Provide any valid frequency for pd.date_range, as multiple of 'D' or 'S'."
)
first_validation = validation_df['ds'].iloc[0]
last_validation = validation_df['ds'].iloc[-1]
if last_validation > last_history:
if first_validation <= last_history:
validation_df = validation_df.loc[
validation_df['ds'] > last_history].dropna()[['ds', 'y']]
start_timer = time.time()
future = validation_df['ds'].to_frame(name='ds')
prediction_data = model.predict(future)[['ds', 'yhat']] # TOO SLOW!
print("--- Prediction: %s seconds ---" % (time.time() - start_timer))
df = pd.DataFrame({
'y': validation_df['y'].values,
'yhat': prediction_data['yhat'].values
})
scaler = MinMaxScaler(feature_range=(0, 1))
df[['y', 'yhat']] = scaler.fit_transform(df[['y', 'yhat']])
clf_name = 'iForest'
clf = IForest()
clf.fit(df)
# get the prediction labels and outlier scores of the training data
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores
if plot:
# fig = plt.figure(facecolor='w', figsize=(10, 6))
# ax = fig.add_subplot(111)
# ax.plot(prediction_data['ds'].dt.to_pydatetime(), deviation, 'k.')
# ax.plot(prediction_data['ds'][y_train_pred == 1].dt.to_pydatetime(), deviation[y_train_pred == 1], 'r.')
# fig.show()
fig1 = plt.figure(facecolor='w', figsize=(10, 6))
ax = fig1.add_subplot(111)
ax.plot(prediction_data['ds'].dt.to_pydatetime(), y_train_scores)
ax.plot(
prediction_data['ds'][y_train_pred == 1].dt.to_pydatetime(),
y_train_scores[y_train_pred == 1], 'r.')
fig1.show()
fig2 = plt.figure(facecolor='w', figsize=(10, 6))
ax = fig2.add_subplot(111)
ax.plot(validation_df['ds'].dt.to_pydatetime(),
validation_df['y'].values)
ax.plot(prediction_data['ds'].dt.to_pydatetime(),
prediction_data['yhat'].values)
ax.vlines(
prediction_data['ds'][y_train_pred == 1].dt.to_pydatetime(),
min(validation_df['y'].values), max(validation_df['y'].values),
'r')
fig2.show()
return sum(y_train_pred) / len(y_train_pred)
else:
raise ValueError(
"Validation dataset has no data point after last member of time-series of historical data that",
"the model was trained on. Please use validation dataset with last member of the time series",
"after %s." % last_history)
# In[19]: from sklearn.manifold import TSNE tsne = TSNE(n_components=2) # Reduce the redunant data X14 = tsne.fit_transform(unique4) plt.figure(figsize=(20, 20)) plt.scatter(X14[:, 0], X14[:, 1], c=pca4.labels_) plt.show() # In[17]: from pyod.models.iforest import IForest iforest2 = IForest() iforest2.fit(unique2) # In[15]: from sklearn.manifold import TSNE tsne = TSNE(n_components=2) # Reduce the redunant data X22 = tsne.fit_transform(unique2) plt.figure(figsize=(20, 20)) plt.scatter(X22[:, 0], X22[:, 1], c=iforest2.labels_) plt.show() # In[22]: iforest3 = IForest()
class TestIForest(unittest.TestCase):
def setUp(self):
self.n_train = 200
self.n_test = 100
self.contamination = 0.1
self.roc_floor = 0.8
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train, n_test=self.n_test,
contamination=self.contamination, random_state=42)
self.clf = IForest(contamination=self.contamination, random_state=42)
self.clf.fit(self.X_train)
def test_parameters(self):
assert (hasattr(self.clf, 'decision_scores_') and
self.clf.decision_scores_ is not None)
assert (hasattr(self.clf, 'labels_') and
self.clf.labels_ is not None)
assert (hasattr(self.clf, 'threshold_') and
self.clf.threshold_ is not None)
assert (hasattr(self.clf, '_mu') and
self.clf._mu is not None)
assert (hasattr(self.clf, '_sigma') and
self.clf._sigma is not None)
assert (hasattr(self.clf, 'estimators_') and
self.clf.estimators_ is not None)
assert (hasattr(self.clf, 'estimators_samples_') and
self.clf.estimators_samples_ is not None)
assert (hasattr(self.clf, 'max_samples_') and
self.clf.max_samples_ is not None)
def test_train_scores(self):
assert_equal(len(self.clf.decision_scores_), self.X_train.shape[0])
def test_prediction_scores(self):
pred_scores = self.clf.decision_function(self.X_test)
# check score shapes
assert_equal(pred_scores.shape[0], self.X_test.shape[0])
# check performance
assert (roc_auc_score(self.y_test, pred_scores) >= self.roc_floor)
def test_prediction_labels(self):
pred_labels = self.clf.predict(self.X_test)
assert_equal(pred_labels.shape, self.y_test.shape)
def test_prediction_proba(self):
pred_proba = self.clf.predict_proba(self.X_test)
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert (pred_proba.min() >= 0)
assert (pred_proba.max() <= 1)
def test_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_fit_predict(self):
pred_labels = self.clf.fit_predict(self.X_train)
assert_equal(pred_labels.shape, self.y_train.shape)
def test_fit_predict_score(self):
self.clf.fit_predict_score(self.X_test, self.y_test)
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='roc_auc_score')
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='prc_n_score')
with assert_raises(NotImplementedError):
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='something')
def test_predict_rank(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3)
assert_array_less(pred_ranks, self.X_train.shape[0] + 1)
assert_array_less(-0.1, pred_ranks)
def test_predict_rank_normalized(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test, normalized=True)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
def test_model_clone(self):
clone_clf = clone(self.clf)
def tearDown(self):
pass
from pyod.utils.data import generate_data
from pyod.utils.data import evaluate_print
from pyod.utils.data import visualize
if __name__ == "__main__":
contamination = 0.1 # percentage of outliers
n_train = 200 # number of training points
n_test = 100 # number of testing points
X_train, y_train, X_test, y_test = generate_data(
n_train=n_train, n_test=n_test, contamination=contamination)
# train IForest detector
clf_name = 'IForest'
clf = IForest()
clf.fit(X_train)
# get the prediction label and decision_scores_ on the training data
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores
# get the prediction on the test data
y_test_pred = clf.predict(X_test) # outlier labels (0 or 1)
y_test_scores = clf.decision_function(X_test) # outlier scores
# evaluate and print the results
print("\nOn Training Data:")
evaluate_print(clf_name, y_train, y_train_scores)
print("\nOn Test Data:")
evaluate_print(clf_name, y_test, y_test_scores)
class Remove_Outliers(BaseEstimator, TransformerMixin):
def __init__(self,
target,
contamination=.20,
random_state=42,
methods=['knn', 'iso', 'mcd']):
self.target = target
self.contamination = contamination
self.random_state = random_state
self.methods = methods
def fit(self, data, y=None):
return (None)
def transform(self, data, y=None):
return (data)
def fit_transform(self, dataset, y=None):
data = dataset.copy()
if 'iso' in self.methods:
self.iso_forest = IForest(contamination=self.contamination,
random_state=self.random_state,
behaviour='new')
self.iso_forest.fit(data.drop(self.target, axis=1))
iso_predict = self.iso_forest.predict(
data.drop(self.target, axis=1))
data['iso'] = iso_predict
if 'knn' in self.methods:
self.knn_out = KNN(contamination=self.contamination)
self.knn_out.fit(data.drop(self.target, axis=1))
knn_predict = self.knn_out.predict(data.drop(self.target, axis=1))
data['knn'] = knn_predict
if 'pca' in self.methods:
self.out_pca = PCA_RO(contamination=self.contamination,
random_state=self.random_state)
self.out_pca.fit(data.drop(self.target, axis=1))
pca_predict = self.out_pca.predict(data.drop(self.target, axis=1))
data['pca'] = pca_predict
# use for those features which are gaussian distributed
if 'mcd' in self.methods:
self.mcd = EllipticEnvelope(contamination=0.01)
self.mcd.fit(data.drop(self.target, axis=1))
mcd_predict = self.mcd.predict(data.drop(self.target, axis=1))
data['mcd'] = mcd_predict
data['vote_outlier'] = 0
for i in self.methods:
data['vote_outlier'] = data['vote_outlier'] + data[i]
self.outliers = data[data['vote_outlier'] == len(self.methods)]
return dataset[[
True if i not in self.outliers.index else False
for i in dataset.index
]]
