class svm_model():
def train(self, X, ker):
self.model = OneClassSVM(kernel=ker, shrinking=True,random_state=1)
self.model.fit(X)
def predict(self, X):
return self.model.predict(X)
def main(): n = 1000 data = [] for i in range(n): data.append(np.array([np.random.randint(0, 5000) for i in range(np.random.randint(20, 150))])) data = np.array(data) # making all the data into 5 dimensions # howto : boxplot x = [] y = [] for i in data: sorted_i = sorted(i) x.append([max(sorted_i), np.percentile(sorted_i, 75), np.median(sorted_i), np.percentile(sorted_i, 25), min(sorted_i)]) y.append(0) x = np.array(x) ''' # making all the data into 5 dimensions # howto : distance start = time.time() data_i = 0 cnt = 1 x = np.zeros((n, n)) for i in data: data_j = data_i for j in data[cnt:]: dist = dtw(i, j, dist=lambda i, j: norm(i - j, ord=1))[0] x[data_i][data_j+1], x[data_j+1][data_i] = dist, dist data_j += 1 cnt += 1 data_i += 1 end = time.time() print(end - start) ''' # build model with x model = OneClassSVM() model.fit(x) # create test dataset test = [] for i in range(10): test.append(np.array([np.random.randint(0, 10000) for i in range(np.random.randint(20000, 30000))])) test = np.array(test) # transform test dataset x = [] y = [] for i in test: sorted_i = sorted(i) x.append([max(sorted_i), np.percentile(sorted_i, 75), np.median(sorted_i), np.percentile(sorted_i, 25), min(sorted_i)]) y.append(0) x = np.array(x) # predict test dataset pred = model.predict(x) '''
def fit(self, X, Y, W):
clf = OneClassSVM(kernel=self.kernel, degree=self.degree,
gamma=self.gamma, coef0=self.coef0, tol=self.tol,
nu=self.nu, shrinking=self.shrinking,
cache_size=self.cache_size, max_iter=self.max_iter)
if W is not None:
return OneClassSVMClassifier(clf.fit(X, W.reshape(-1)))
return OneClassSVMClassifier(clf.fit(X))
class Cluster(object):
def __init__(self, name):
self.name = name
self.raw_dataset = []
self.dataset = []
self.dataset_red = []
def get_featurevec(self, data):
'''Takes in data in the form of an array of EmoPackets, and outputs
a list of feature vectors.'''
# CHECKED, all good :)
num_bins = (len(data)/int(dsp.SAMPLE_RATE*dsp.STAGGER) -
int(dsp.BIN_SIZE / dsp.STAGGER) + 1)
size = int(dsp.BIN_SIZE*dsp.SAMPLE_RATE)
starts = int(dsp.SAMPLE_RATE*dsp.STAGGER)
points = []
for i in range(num_bins):
points.append(dsp.get_features(data[i*starts:i*starts+size]))
return points
def add_data(self, raw):
'''Allows the addition of new data. Will retrain upon addition.
Expects a list of EmoPackets.'''
self.dataset.extend(self.get_featurevec(raw))
def extract_features(self):
'''Does feature extraction for all of the datasets.'''
self.dataset = []
for sess in self.raw_dataset:
self.dataset.extend(self.get_featurevec(sess))
def reduce_dim(self, NDIM=5):
'''Reduces the dimension of the extracted feature vectors.'''
X = np.array(self.dataset)
self.pca = RandomizedPCA(n_components=NDIM).fit(X)
self.dataset_red = self.pca.transform(X)
def train(self):
'''Trains the classifier.'''
self.svm = OneClassSVM()
self.svm.fit(self.dataset_red)
def is_novel(self, pt):
'''Says whether or not the bin is novel. Expects an array of EmoPackets'''
X = self.pca.transform(np.array(self.get_featurevec(data)[0]))
ans = self.svm.predict(X)
self.dataset_red.append(X)
self.train()
return ans
def save(self):
'''Saves this classifier to a data directory.'''
this_dir, this_filename = os.path.split(__file__)
DATA_PATH = os.path.join(this_dir, "data", self.name+'.pkl')
dumpfile = open(DATA_PATH, "wb")
pickle.dump(self, dumpfile, pickle.HIGHEST_PROTOCOL)
dumpfile.close()
def determine_test_similarity(self, model):
clf_OCSVM = {}
model_OCSVM = {}
for i in range(len(model)):
clf = OneClassSVM(kernel='rbf', nu=0.1, gamma=.023)
clf_OCSVM[i] = clf
OCSVMmodel = clf.fit(model[i])
model_OCSVM[i] = OCSVMmodel
return clf_OCSVM, model_OCSVM
def runClassifier(self, _driverId, numComponents=0):
X = self.featuresHash.values()
self.ids = self.featuresHash.keys()
if self.runDimRed:
X = self.dimRed(X, numComponents)
clf = OCSVM(nu=self.nu, gamma=self.gamma)
clf.fit(X)
y_pred = clf.decision_function(X).ravel()
threshold = stats.scoreatpercentile(y_pred, 100 * self.outliers_fraction)
self.label = y_pred > threshold
self.label = map(int, self.label)
def select_best_support_vectors(data, nu=0.01, all_gammas=2 ** np.arange(-10, 10, 1)):
all_errors = []
for gamma in all_gammas:
clf = OneClassSVM(nu=nu, gamma=gamma)
clf.fit(data)
prediction = clf.predict(data)
out_of_class_count = np.sum(prediction == -1)
support_vectors_count = len(clf.support_vectors_)
error = (float(out_of_class_count) / len(data) - nu) ** 2
error += (float(support_vectors_count) / len(data) - nu) ** 2
all_errors.append(error)
index = np.argmin(all_errors)
return all_gammas[index], all_errors
def embed_dat_matrix_two_dimensions(low_dimension_data_matrix,
y=None,
labels=None,
density_colormap='Blues',
instance_colormap='YlOrRd'):
from sklearn.preprocessing import scale
low_dimension_data_matrix = scale(low_dimension_data_matrix)
# make mesh
x_min, x_max = low_dimension_data_matrix[:, 0].min(), low_dimension_data_matrix[:, 0].max()
y_min, y_max = low_dimension_data_matrix[:, 1].min(), low_dimension_data_matrix[:, 1].max()
step_num = 50
h = min((x_max - x_min) / step_num, (y_max - y_min) / step_num) # step size in the mesh
b = h * 10 # border size
x_min, x_max = low_dimension_data_matrix[:, 0].min() - b, low_dimension_data_matrix[:, 0].max() + b
y_min, y_max = low_dimension_data_matrix[:, 1].min() - b, low_dimension_data_matrix[:, 1].max() + b
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
# induce a one class model to estimate densities
from sklearn.svm import OneClassSVM
gamma = max(x_max - x_min, y_max - y_min)
clf = OneClassSVM(gamma=gamma, nu=0.1)
clf.fit(low_dimension_data_matrix)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, m_max] . [y_min, y_max].
if hasattr(clf, "decision_function"):
score_matrix = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
else:
score_matrix = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
# Put the result into a color plot
levels = np.linspace(min(score_matrix), max(score_matrix), 40)
score_matrix = score_matrix.reshape(xx.shape)
if y is None:
y = 'white'
plt.contourf(xx, yy, score_matrix, cmap=plt.get_cmap(density_colormap), alpha=0.9, levels=levels)
plt.scatter(low_dimension_data_matrix[:, 0], low_dimension_data_matrix[:, 1],
alpha=.5,
s=70,
edgecolors='gray',
c=y,
cmap=plt.get_cmap(instance_colormap))
# labels
if labels is not None:
for id in range(low_dimension_data_matrix.shape[0]):
label = labels[id]
x = low_dimension_data_matrix[id, 0]
y = low_dimension_data_matrix[id, 1]
plt.annotate(label, xy=(x, y), xytext=(0, 0), textcoords='offset points')
def outlier_detect(data_frame):
#pandas to numpy - digestible by scikit
columns = ['blm_tag_count','protest_count','justice_count','riot_count','breathe_count']
features = data_frame[list(columns)].values
clf = OneClassSVM(nu=0.008, gamma=0.05)
clf.fit(features)
y_pred = clf.predict(features)
mask=[y_pred==-1]
oak_array = np.asarray(data_frame.hourly)
protest_predict = oak_array[mask]
protest_hours = list(protest_predict)
return protest_hours
def svm(data, fraction=0.05, kernel='poly', degree=3, gamma=0, coeff=0):
svm = OneClassSVM(kernel=kernel, degree=degree, gamma=gamma, nu=fraction, coeff0=coeff)
svm.fit(data)
score = svm.predict(data)
numeration = [[i] for i in xrange(1, len(data)+1, 1)]
numeration = np.array(numeration)
y = np.hstack((numeration, score))
anomalies = numeration
for num,s in y:
if (y == 1):
y = np.delete(anomalies, num-1, axis=0)
return anomalies
def select_best_outlier_fraction_cross_val(data, nu=0.05, all_gammas=2 ** np.arange(-10, 10, 50), folds_count=7):
all_errors = []
kf_iterator = KFold(len(data), n_folds=folds_count)
for gamma in all_gammas:
error = 0
for train, test in kf_iterator:
train_data = data[train,:]
test_data = data[test,:]
clf = OneClassSVM(nu=nu, gamma=gamma)
clf.fit(train_data)
prediction = clf.predict(test_data)
outlier_fraction = np.mean(prediction == -1)
error += (nu - outlier_fraction) ** 2 + (float(clf.support_vectors_.shape[0]) / len(data) - nu) ** 2
all_errors.append(error / folds_count)
best_index = np.argmin(error)
return int(best_index), all_errors
class OneClassSVMDetector(BaseOutlier):
@staticmethod
def get_attributes():
return {
"nu":0.1,
"kernel":['rbf','linear', 'poly', 'rbf', 'sigmoid', 'precomputed'],
"gamma":0.1,
}
def __init__(self,nu=0.1,kernel='rbf',gamma=0.1):
self.nu = nu
self.kernel = kernel
self.gamma = gamma
def fit(self,data=None):
self.data = data
self.check_finite(data)
if(self._is_using_pandas(data)==True):
self.data.interpolate(inplace=True)
# self.datareshap = data.reshape(-1,1)
self.clf = OneClassSVM(nu=self.nu, kernel=self.kernel, gamma=self.gamma)
self.clf.fit(data.reshape(-1,1))
# print "done"
return self
def predict(self, X_test):
y_pred_train = self.clf.predict(X_test.reshape(-1,1))
outlier_idx = np.where(y_pred_train == -1)
inlier_idx = np.where(y_pred_train == 1)
d = {
'timestamp': self.data.index[outlier_idx],
'anoms': self.data.iloc[outlier_idx]
}
anoms = pd.DataFrame(d)
self.anomaly_idx = anoms.index
self.anom_val = anoms['anoms']
return anoms
def fit_predict(self, data=None):
self.fit(data)
return self.predict(data)
def plot(self):
import matplotlib.pyplot as plt
f, ax = plt.subplots(1, 1)
ax.plot(self.data, 'b')
ax.plot(self.anomaly_idx, self.anom_val, 'ro')
ax.set_title('Detected Anomalies')
ax.set_ylabel('Count')
f.tight_layout()
return f
def cross_validate():
#for tinkering with the model
#read data
all_df = pd.read_csv('./data/train.csv',index_col = 'ID')
#split data
zeros_df = all_df[all_df.TARGET == 0]
ones_df = all_df[all_df.TARGET == 1]
num_ones = ones_df.shape[0]
msk = np.random.permutation(len(zeros_df)) < num_ones
zeros_train_df = zeros_df[~msk]
zeros_test_df = zeros_df[msk]
ones_test_df = ones_df
train_df = zeros_train_df
test_df = pd.concat([zeros_test_df,ones_test_df])
train_X = np.array(train_df.drop('TARGET', axis = 1))
train_Y = np.array(train_df.TARGET)
test_X = np.array(test_df.drop('TARGET',axis = 1))
test_Y = np.array(test_df.TARGET) #true target values
#init svm
print('training svm')
my_svm = OneClassSVM(verbose = True)
my_svm.fit(train_X)
#predict
print('predicting')
predictions = my_svm.predict(test_X)
conf_matrix = confusion_matrix(test_Y,predictions)
print('confusion matrix:')
print(pd.DataFrame(conf_matrix,columns = [0,1]))
print('accuracy:')
print(sum(test_Y.reshape(predictions.shape) == predictions)/len(test_Y))
def find_anomaly(label1, label2, winsize):
print("Find anomaly in channel", label1 + '-' + label2 + '...', file=sys.stderr)
print("-"*80)
print("Channel [" + label1 + '-' + label2 + ']')
print("-"*80)
# find difference
electrode1 = eeg.chan_lab.index(label1)
electrode2 = eeg.chan_lab.index(label2)
wave = eeg.X[electrode1] - eeg.X[electrode2]
# # import random
# wave = [random.uniform(-20,20) for _ in range(400*30)] + [random.uniform(-2000,2000) for _ in range(5*30)]
# wave = np.array(wave)
print("Splitting into windows...", file=sys.stderr)
wave_windows = np.array_split(wave, len(wave)/eeg.sample_rate/winsize)
# wave_windows = np.array_split(wave, len(wave)/winsize)
print("Extracting features...", file=sys.stderr)
def extract_features(wave_window):
max_val = max(wave_window)
min_val = min(wave_window)
stdev = np.std(wave_window)
sum_val = sum(wave_window)
sum_pos_val = sum([x for x in wave_window if x > 0])
sum_abs_val = sum([abs(x) for x in wave_window])
return [max_val, min_val, stdev, sum_val, sum_pos_val, sum_abs_val]
Examples = np.array(map(extract_features, wave_windows))
print("Training model, assuming no more than", CONTAMINATION, "anomaly...", file=sys.stderr)
od = OneClassSVM(nu=CONTAMINATION, kernel='poly', gamma=0.05, max_iter=100000)
od.fit(Examples)
decisions = od.decision_function(Examples)
# print decisions
# print max(decisions), min(decisions)
print("Most likely windows with anomaly:")
# find most likely windows, in desc order
largest_indices = np.argsort((-np.absolute(decisions)).ravel())[:20]
for large_index in largest_indices:
print(large_index*winsize/60, "min (score:", decisions[large_index][0], ")")
sys.stdout.flush()
def remove_outliers_SVM(self): ## Remove outliers using a OneClassSVM method print "Running SVM to remove outliers..." svm = OneClassSVM(kernel='rbf', nu=0.1, degree=3, verbose=1) fit = svm.fit(self.DataArray) decision = svm.decision_function(self.DataArray) _indices = [] # If a value is below the decision hyperplane, eliminate it for i in range(len(decision)): if decision[i] < 0: _indices.append(i) print self.DataArray.shape self.DataArray = np.delete(self.DataArray, _indices, axis=0) self.TargetArray = np.delete(self.TargetArray, _indices, axis=0) print self.DataArray.shape
def plot_scatter(X_dict, y_dict, col1, col2, max_error, max_filled_gap, insens,
f_colors = ['yellow', 'red', 'blue'], nu=0.98, high=0.95):
planes = sorted(X_dict.keys())
planes_with_failures = sorted([key for key in X_dict.keys() if y_dict[key].sum()>0])
ocsvm = OneClassSVM(kernel='linear', nu=0.98)
X_train = pd.concat(dict([(plane, X_dict[plane][[col1, col2]].dropna())
for plane in planes_with_failures]))
ocsvm.fit(X_train.values)
qb = QuantileBinarizer(low=0.0, high=0.95, each_side=False)
qb.fit(X_train)
mask_pref = pd.concat(dict(
[(plane, get_mask_pref(y_dict[plane], max_error)) for plane in planes]), axis=0)
mask_norm = pd.concat(dict(
[(plane, get_mask_norm(y_dict[plane], max_error, insens)) for plane in planes]), axis=0)
fig = plt.figure(figsize=(15,15), dpi=100)
# plt.xlabel('Norm of res. phase: %s, group: %s' % (col1[0], str(col_groups[col1[0]][int(col1[1][-1])])))
# plt.ylabel('Norm of res. phase: %s, group: %s' % (col2[0], str(col_groups[col2[0]][int(col2[1][-1])])))
plt.xlabel(col1)
plt.ylabel(col2)
plot_norm = plt.scatter(pd.concat(X_dict)[col1].loc[mask_norm],
pd.concat(X_dict)[col2].loc[mask_norm], c='lightgrey', zorder=1, s=6)
plot_pref = []
for i, plane in enumerate(planes_with_failures):
plot_pref.append(plt.scatter(X_dict[plane][col1].loc[get_mask_pref(y_dict[plane], max_error)],
X_dict[plane][col2].loc[get_mask_pref(y_dict[plane], max_error)],
c=f_colors[i], zorder=2, s=30))
x_min, x_max, y_min, y_max = plt.axis('tight')
plt.axvline(qb._thresholds[col1]['high'], c='green')
plt.axhline(qb._thresholds[col2]['high'], c='green')
plot_line = plt.plot([x_min, x_max],
[(ocsvm.intercept_ - ocsvm.coef_[0][0] * x_min) / ocsvm.coef_[0][1],
(ocsvm.intercept_ - ocsvm.coef_[0][0] * x_max) / ocsvm.coef_[0][1]],
c='red')
# # plt.legend((plot_norm, plot_pref), ('No-failure', 'Pre-failure'),
# # scatterpoints=1, loc='upper right', ncol=1)
# #plt.savefig('./scatter/pair_group_of_fours3.png')
def fit(self,data=None):
self.data = data
self.check_finite(data)
if(self._is_using_pandas(data)==True):
self.data.interpolate(inplace=True)
# self.datareshap = data.reshape(-1,1)
self.clf = OneClassSVM(nu=self.nu, kernel=self.kernel, gamma=self.gamma)
self.clf.fit(data.reshape(-1,1))
# print "done"
return self
def predict_header_features(self, pkt_featurizer):
group_id = pkt_featurizer.pkt_type
features = pkt_featurizer.features
arrival_time = pkt_featurizer.arrival_time
try:
vectorizer = DictVectorizer()
vectorizer.fit(self.training_data[group_id])
training_data_vectorized = vectorizer.transform(self.training_data[group_id])
features_vectorized = vectorizer.transform(features)
scaler = preprocessing.StandardScaler(with_mean=False)
training_data_vectorized = scaler.fit_transform(training_data_vectorized)
features_vectorized = scaler.transform(features_vectorized)
classifier = OneClassSVM()
classifier.fit(training_data_vectorized)
result = classifier.predict(features_vectorized)
distance = classifier.decision_function(features_vectorized)
except KeyError:
result = 0
distance = 0
return result, distance
class TwoStage(object):
def __init__(self, *args, **kwargs):
super(TwoStage, self).__init__(*args, **kwargs)
self._oneCls = OneClassSVM(nu=NU, gamma=GAMMA)
self._clf = RandomForestClassifier(n_estimators=30)
self._scaler = StandardScaler()
def fit(self, data, labels):
sdata = self._scaler.fit_transform(data)
self._oneCls.fit(sdata)
self._clf.fit(sdata, labels)
return self
def predict(self, data):
sdata = self._scaler.transform(data)
is_known_cls = self._oneCls.predict(sdata)
cls = self._clf.predict(sdata)
cls[is_known_cls == -1] = "zother"
classes = list(self._clf.classes_) + ["zother"]
return cls, classes
class NoveltySeparator(BaseEstimator):
def get_params(self, deep=True):
return {}
def fit(self, X, y):
# lets treat users spending something in the rest of the month as outliers
inliers = y - X[:, 0]
inliers = np.where(inliers < 0.1, True, False)
self.detector = OneClassSVM(nu=0.05, cache_size=2000, verbose=True)
# training only on inliers
print("Training detector")
self.detector.fit(X[inliers])
results = self.detector.predict(X).reshape(X.shape[0])
# predicted
inliers = results == 1
outliers = results == -1
print("Training estimators")
self.est_inliers = Ridge(alpha=0.05)
self.est_outliers = Ridge(alpha=0.05)
self.est_inliers.fit(X[inliers], y[inliers])
self.est_inliers.fit(X[outliers], y[outliers])
def predict(self, X):
y = np.zeros(X.shape[0])
labels = self.detector.predict(X).reshape(X.shape[0])
inliers = lables == 1
outliers = lables == -1
y[inliers] = self.est_inliers.predict(X[inliers])
y[outliers] = self.est_outliers.predict(X[outliers])
return y
def predict_pkt_length_features(self, pkt_featurizer):
group_id = pkt_featurizer.pkt_type
try:
dbscan = DBSCAN()
pkt_lengths = np.array(list(self.pkt_lengths[group_id])+[pkt_featurizer.len_bytes]).reshape(-1,1)
labels = dbscan.fit_predict(pkt_lengths)
dbscan_prediction = labels[-1] == -1
if self.plot:
self.plot_1d_dbscan(pkt_lengths, labels, range(len(pkt_lengths)), self.pkt_lengths_fig_dbscan,
"", "Pkt Length", "Pkt Length DBSCAN Clustering - Anomalous Pkts in Black")
one_class_svm = OneClassSVM()
scaler = preprocessing.StandardScaler()
pkt_lengths_scaled = scaler.fit_transform(np.array(self.pkt_lengths[group_id]).reshape(-1,1))
features_scaled = scaler.transform(np.array(pkt_featurizer.len_bytes).reshape(1,-1))
one_class_svm.fit(pkt_lengths_scaled)
svm_prediction = one_class_svm.predict(features_scaled)
if self.plot and len(pkt_lengths_scaled) > 2:
self.plot_1d_svm(self.pkt_lengths[group_id], one_class_svm, range(len(self.pkt_lengths[group_id])), scaler, self.pkt_lengths_fig_svm,
"Pkt", "Pkt Length", "Pkt Length One Class SVM Classification")
except (KeyError, IndexError) as e:
print e
dbscan_prediction = 0
return dbscan_prediction
def check_authors_vocabulary(category):
"""Use 80% of the authors as training set and the rest as test set. A good score validates the
assumption that there is a defined vocabulary for a given category.
"""
print category
with open('%s_tweets.json' % category, 'r') as f:
tweets = json.load(f)
tweets_by_author = defaultdict(list)
for tweet in tweets['tweets']:
tweets_by_author[tweet['author_name']].append(tweet)
authors = tweets_by_author.keys()
training_set_count = len(authors) * 80 / 100
training_authors = random.sample(authors, training_set_count)
test_authors = list(set(authors) - set(training_authors))
train_set = []
test_set = []
for author, tweets in tweets_by_author.items():
if author in training_authors:
train_set.extend([prepare_tweet(t['text']) for t in tweets])
else:
test_set.extend([prepare_tweet(t['text']) for t in tweets])
vectorizer = CountVectorizer(
max_features=10000,
#stop_words='english',
max_df=0.7)
classifier = OneClassSVM()
text_clf = Pipeline([('vect', vectorizer),
('tfidf',
TfidfTransformer(sublinear_tf=True, norm='l2')),
('clf', classifier)])
text_clf = text_clf.fit(train_set)
predicted = text_clf.predict(test_set)
print np.mean(predicted == 1)
print classification_report([1 for _ in range(len(test_set))], predicted)
def __init__(self,
embedder,
detector,
G2V_nhid=128,
G2V_wl_iter=2,
FGSD_hist_bins=200,
IF_n_trees=200,
IF_sample_ratio=0.5,
LOF_n_neighbors=20,
LOF_n_leaf=30,
normalize_embedding=False,
**kwargs):
embedders = {
'Graph2Vec':
Graph2Vec(wl_iterations=G2V_wl_iter,
dimensions=G2V_nhid,
attributed=True,
epochs=50),
'FGSD':
FGSD(hist_bins=FGSD_hist_bins, hist_range=20)
}
detectors = {
'IF':
IsolationForest(n_estimators=IF_n_trees,
max_samples=IF_sample_ratio,
contamination=0.1),
'LOF':
LocalOutlierFactor(n_neighbors=LOF_n_neighbors,
leaf_size=LOF_n_leaf,
contamination=0.1),
'OCSVM':
OneClassSVM(gamma='scale', nu=0.1)
}
assert embedder in embedders.keys()
assert detector in detectors.keys()
self.embedder = embedders[embedder]
self.detector = detectors[detector]
self.embedder_name = embedder
self.detector_name = detector
self.normalize_embedding = normalize_embedding
def thread_monitoring_pre_train(self):
########################################################
## Normalize and apply PCA to the training data
result = self.pca.fit_transform(
self.scaler.fit_transform(self.anomaly_data))
## First element of the Tuple is True or False either if it is a neighbourhood-based method or not
self.anomaly_algorithms[0][2] = EllipticEnvelope(
support_fraction=1, contamination=self.contamination)
self.anomaly_algorithms[1][2] = DBSCAN(eps=self.avg_dist(
result[:, 0], result[:, 1]),
metric='euclidean',
min_samples=2)
self.anomaly_algorithms[2][2] = OneClassSVM(kernel='rbf',
nu=self.contamination,
gamma=0.05)
########################################################
## Predict outliers - use DBSCAN (unsupervised technique) for first fitering of outliers
## get predictions for all training data
DBSCAN_index = 1
predictions_temp = self.anomaly_algorithms[DBSCAN_index][
2].fit_predict(result)
#########################################################
## Filter data - for each element of the training data
filtered_anomaly = np.array([])
for temp_i in np.arange(len(self.anomaly_data)):
## If sample is not outlier
if predictions_temp[temp_i] != -1:
if len(filtered_anomaly) == 0:
filtered_anomaly = self.anomaly_data[temp_i]
else:
filtered_anomaly = np.vstack(
(filtered_anomaly, self.anomaly_data[temp_i]))
##########################################################
## Update data
self.anomaly_data = filtered_anomaly
## Train algorithms
self.thread_monitoring_train()
def test():
np.random.seed(42)
dataset = datasets.load_iris()
test_indices = np.random.choice(150, 10)
test_set = dataset.data[test_indices, :]
test_set = np.vstack((test_set, np.array([[0.0, 0.0, 0.0, 0.0]])))
test_set = np.vstack((test_set, np.array([[10.0, 10.0, 10.0, 10.0]])))
print "GMM"
gmm = GMM(n_components=3, covariance_type='diag')
bc_gmm = BackgroundCheck(estimator=gmm, mu=0.0, m=1.0)
bc_gmm.fit(dataset.data)
print bc_gmm.predict_proba(test_set)
print "OneClassSVM"
sv = OneClassSVM()
bc_sv = BackgroundCheck(estimator=sv, mu=0.0, m=1.0)
bc_sv.fit(dataset.data)
print bc_sv.predict_proba(test_set)
def fit(self, X, y):
# lets treat users spending something in the rest of the month as outliers
inliers = y - X[:, 0]
inliers = np.where(inliers < 0.1, True, False)
self.detector = OneClassSVM(nu=0.05, cache_size=2000, verbose=True)
# training only on inliers
print("Training detector")
self.detector.fit(X[inliers])
results = self.detector.predict(X).reshape(X.shape[0])
# predicted
inliers = results == 1
outliers = results == -1
print("Training estimators")
self.est_inliers = Ridge(alpha=0.05)
self.est_outliers = Ridge(alpha=0.05)
self.est_inliers.fit(X[inliers], y[inliers])
self.est_inliers.fit(X[outliers], y[outliers])
def COSVM(training_data, testing_data, nu_list, kernel_list):
# Build SVM model
clf = OneClassSVM(nu=nu_list, kernel=kernel_list, gamma=0.1)
clf.fit(training_data)
y_pred_test = clf.predict(testing_data)
n_error_test = y_pred_test[y_pred_test == -1].size
testing_accuracy = 1 - 1.0 * n_error_test / testing_data.shape[0]
#
# print(n_error_test)
# print('final accuracy on testing data: ', testing_accuracy, '\n')
test_score = clf.decision_function(testing_data)
test_score = test_score.reshape(-1)
return test_score
def model(self,
nu = [0.001, 0.01, 0.001],
contamination = [0.001, 0.001, 0.001]):
if self.verbose: print(datetime.now(), 'the model is being created ...')
self.ocsvm_rbf = OneClassSVM(gamma = 'scale', kernel = 'rbf', nu = nu[0])
self.ocsvm_sigmoid = OneClassSVM(gamma = 'auto', kernel = 'sigmoid', nu = nu[1])
self.ocsvm_linear = OneClassSVM(kernel = 'linear', nu = nu[2])
self.ifo = IsolationForest(contamination = contamination[0])
self.lof = LocalOutlierFactor(contamination = contamination[1], novelty = True)
self.ee = EllipticEnvelope(contamination = contamination[2])
if self.verbose: print(datetime.now(), 'the model is ready.')
def data_learn(name="song_data"):
"""GET endpoint for training model
Arguments:
name -- the name of file to get the data from, default song_data
"""
# load data
df = pd.read_pickle("./" + url_prefix + "data/" + name + ".pkl").drop(
columns=['analysis_url', 'track_href', 'type', 'uri'])
# drop "useless" columns
df = df.drop(columns=['duration_ms', 'key', 'mode', 'time_signature'])
# split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(
df.drop(columns=['name', 'id']), df['id'], test_size=0.30)
# fit estimator
#clf = IsolationForest(n_estimators = 500, contamination = 0.11)
clf = make_pipeline(StandardScaler(), OneClassSVM(nu=0.11, gamma=0.04))
clf.fit(X_train, y_train)
# Predict off test data and create array of outliers
predictions = clf.predict(X_test)
outliers = [id for id, predict in zip(y_test, predictions) if predict < 0]
count = len(outliers)
with open("./" + url_prefix + "model/" + "clf.pkl", 'wb') as fid:
pickle.dump(clf, fid, 2)
return jsonify({
'success':
True,
"test_outliers":
json.loads(df.loc[df['id'].isin(outliers)].to_json(orient='index')),
"test_outliers_count":
count,
"test_outliers_%":
count / len(y_test) * 100
})
def oneclass(c: Config):
normal_traffic_array, traffic_scenario = load_normal_traffic_array(c)
bridge_scenarios = [HealthyScenario()] + each_pier_scenarios(c)
response_type = ResponseType.YTranslation
points = [
Point(x=x, y=0, z=z)
for x, z in itertools.product(
np.linspace(c.bridge.x_min, c.bridge.x_max / 2, 20),
np.linspace(c.bridge.z_min, c.bridge.z_max / 2, 3),
)
]
results = []
for b, bridge_scenario in enumerate(bridge_scenarios):
print_i(f"One class: bridge scenario {bridge_scenario.name}")
responses = responses_to_traffic_array(
c=c,
traffic_array=normal_traffic_array,
response_type=response_type,
bridge_scenario=bridge_scenario,
points=points,
fem_runner=OSRunner(c),
).T
print(len(normal_traffic_array))
print(responses.shape)
# Fit on the healthy scenario.
if b == 0:
assert len(responses) == len(points)
clfs = []
for r, rs in enumerate(responses):
print_i(f"Training classifier {r} / {len(responses)}")
clfs.append(OneClassSVM().fit(rs.reshape(-1, 1)))
scenario_results = []
for p, _ in enumerate(points):
print_i(f"Predicting points {p} / {len(points)}")
prediction = clfs[p].predict(responses[p].reshape(-1, 1))
print(prediction)
print(len(prediction[prediction < 0]))
print(len(prediction[prediction > 0]))
def Estimators(num_extimators=100,
max_samples=0.25,
contamination=0.2,
eps=0.2):
ifsf = IsolationForest(max_samples=max_samples,
random_state=0,
contamination=contamination,
n_estimators=num_extimators,
n_jobs=-1)
lofsf = LocalOutlierFactor(n_neighbors=15,
metric='euclidean',
algorithm='auto',
contamination=contamination,
n_jobs=-1)
ocsvm = OneClassSVM(nu=contamination, kernel="rbf", gamma=0.1)
dbscan = DBSCAN(eps=eps,
min_samples=10,
metric='euclidean',
algorithm='auto',
n_jobs=-1)
return {"if": ifsf, "lof": lofsf, "dbs": dbscan, "svm": ocsvm}
def tau_to_npy(a, domain='xs'):
tau_a = np.array([])
for i in range(a.shape[1]):
# print(i)
temp1 = a[:, i].reshape(-1, 1)
y_pred = OneClassSVM(nu=0.1).fit(temp1).predict(temp1)
index = np.where(y_pred == 1)[0].tolist()
length = len(index)
average = np.sum(temp1[index]) / length
tau_a = np.append(tau_a, average)
tau_a = tau_a.reshape(1, -1)
if domain == 'xs':
np.save("Xs.npy", tau_a)
elif domain == 'xt':
np.save("Xt.npy", tau_a)
elif domain == 'xs_add':
np.save("Xs_add.npy", tau_a)
elif domain == 'xt_add':
np.save("Xt_add.npy", tau_a)
else:
print("data save error")
def main():
print('------------01')
iris = load_iris()
pca = PCA(n_components=2)
data = pca.fit_transform(iris.data)
print(type(data))
print(data)
# nuで異常値の割合を指定。predictすると正常値=1,異常値=-1。
ocsvm = OneClassSVM(nu=0.1, gamma="auto")
ocsvm.fit(data)
preds = ocsvm.predict(data)
print(preds)
plt.scatter(data[:, 0], data[:, 1], c=preds, cmap=plt.cm.RdBu)
plt.show()
print('------------02A')
x = np.linspace(-5, 5, 500)
y = np.linspace(-1.5, 1.5, 250)
X, Y = np.meshgrid(x, y)
print('X.ravel():')
print(X.ravel())
print(X.shape)
print(Y.shape)
z1 = np.array([X.ravel(), Y.ravel()])
print(z1.shape)
z2 = ocsvm.decision_function(np.array([X.ravel(), Y.ravel()]).T)
print(z2.shape)
# (250, 500)
# (250, 500)
# (2, 125000)
# (125000,)
# (250, 500)
print(z2.reshape(X.shape).shape)
df = ocsvm.decision_function(np.array([X.ravel(),
Y.ravel()]).T).reshape(X.shape)
plt.scatter(data[:, 0], data[:, 1], c=preds, cmap=plt.cm.RdBu, alpha=0.8)
r = max([abs(df.min()), abs(df.max())])
print('------------02B')
print(df.min())
print(max([abs(df.min()), abs(df.max())]))
print(df)
plt.contourf(X, Y, df, 10, vmin=-r, vmax=r, cmap=plt.cm.RdBu, alpha=.5)
plt.show()
def get_best_params(self, param_grid, n_iter=5):
"""
This function compute a GridSearchCV for different training sets
inputs:
n_iter: number of iterations of the GridSearchCV in different training sets
param_grid: dictionary with the name and values of the parameter to change.
ex: {"nu": [.2, .5, .7]}
return:
"""
self.train_score, self.test_score = pd.DataFrame(), pd.DataFrame()
self.train_score["best_nu"] = np.zeros(len(param_grid["nu"]))
self.test_score["best_nu"] = np.zeros(len(param_grid["nu"]))
#set index
self.train_score = self.train_score.set_index(param_grid["nu"])
self.test_score = self.test_score.set_index(param_grid["nu"])
count_cv = 0
for i in range(n_iter):
#self.X = self.X.sample(self.X.shape[0]) #shuffle pandas dataframe is very slow
np.random.shuffle(self.X)
self.ocsvm = OneClassSVM(kernel="rbf", gamma="auto")
self.gsCV = GridSearchCV(self.ocsvm,
param_grid=param_grid,
cv=self.k_folds,
scoring=self.ocsvm_score,
return_train_score=True,
n_jobs=3) #idd=False
self.gsCV.fit(self.X, self.y)
#self.cv_results["iter_"+str(i)] = self.gsCV.cv_results_
for cv in range(self.k_folds):
self.train_score["score_cv_" +
str(count_cv)] = self.gsCV.cv_results_[
"split" + str(cv) + "_train_score"]
self.test_score["score_cv_" +
str(count_cv)] = self.gsCV.cv_results_[
"split" + str(cv) + "_test_score"]
count_cv += 1
self.train_score.loc[self.gsCV.best_params_["nu"], "best_nu"] += 1
self.test_score.loc[self.gsCV.best_params_["nu"], "best_nu"] += 1
return self.train_score, self.test_score
def update_event(self, input_called=-1):
if input_called == 0:
clf = OneClassSVM()
if self.input(1) != None:
clf.set_params(**self.input(1))
try:
X = self.input(2)
clf.fit(X)
except:
pass
self.set_output_val(1, clf)
self.exec_output(0)
def __init__(self):
rospy.init_node('svm_imu_test')
self.is_training = True
rospy.Subscriber('/base_state',
BaseState,
self.base_state_CB,
queue_size=1)
self.pub = list()
self.clf = list()
for i in range(4):
self.clf.append(OneClassSVM(nu=0.4, kernel="poly", gamma=0.4))
self.pub.append(
rospy.Publisher('/observer_' + str(i),
sensorFusionMsg,
queue_size=1))
rospy.loginfo("Training period starting")
rospy.Timer(rospy.Duration(30), self.timer_cb, oneshot=True)
rospy.spin()
def outlier_rejection(X=None,
y=None,
method='IsolationForest',
contamination=0.1):
"""This will be our function used to resample our dataset.
"""
outlier_model = (
IsolationForest(contamination=contamination),
LocalOutlierFactor(contamination=contamination),
OneClassSVM(nu=contamination),
EllipticEnvelope(contamination=contamination),
)
outlier_model = {i.__class__.__name__: i for i in outlier_model}
if X is None:
return outlier_model.keys()
model = outlier_model.get(method)
if model is None:
raise ValueError("method '{}' is invalid".format(method))
y_pred = model.fit_predict(X)
return X[y_pred == 1], y[y_pred == 1]
def runOCSVMGridSearch(data_folder, cfg):
#Gather the dataset
#train_x[:len(train_x)/2] = (training) 70% of reg samples
#train_x[len(train_x)/2:] = (training) 70% of facet samples
#test_x[:len(test_x)/2] = (testing) 30% of reg samples
#test_x[len(test_x)/2:] = (testing) 30% of facet samples
train_x, train_y, test_x, test_y = gatherHoldoutData(data_folder, cfg)
# PreProcess data
train_x, test_x = preprocessData(train_x, test_x, "soft_scaling")
parameters = {'nu': np.linspace(0.01, 1, 100)}
# fit the model
#clf = OneClassSVM(nu=0.95 * 0.5 + 0.05, kernel="rbf")
clf = GridSearchCV(OneClassSVM(kernel="rbf"),
parameters,
cv=5,
scoring='recall')
clf.fit(train_x, train_y[:len(train_y) / 2]) #fit to normal samples only
print("Best parameters set found on development set:")
print(clf.best_params_)
print("Grid scores on training set:")
means = clf.cv_results_['mean_test_score']
stds = clf.cv_results_['std_test_score']
for mean, std, params in zip(means, stds, clf.cv_results_['params']):
print("%0.3f (+/-%0.03f) for %r" % (mean, std * 2, params))
print("Classification results on test set:")
y_true, y_pred = test_y, clf.predict(test_x)
print y_true
print y_pred
print(classification_report(y_true, y_pred))
print accuracy_score(y_true, y_pred)
print("accuracy: ", accuracy_score(y_true, y_pred))
print("precision: ", precision_score(y_true, y_pred))
print("recall: ", recall_score(y_true, y_pred))
print("area under curve (auc): ", roc_auc_score(y_true, y_pred))
def train_CSD_SVM(args):
'''
Train a SVM outlier detector using real images
:param real_img_dir: A directory contains real images
:param svm_model_path: A path for saving trained model
:return:
'''
train_paths = list(
map(lambda x: args.real_img_dir + x, os.listdir(args.real_img_dir)))
logging.info("Training file paths: {}".format(len(train_paths)))
train_feat = get_color_feat(train_paths)
train_feat = np.squeeze(train_feat, axis=1)
y_true = [1] * np.shape(train_feat)[0]
# train SVM
parameters = {'gamma': [0.001, 0.0001, 1 / 588, 0.01, 0.1]}
svm_model = OneClassSVM(nu=0.1, kernel="rbf")
clf = GridSearchCV(svm_model, parameters, cv=5, scoring='accuracy')
clf.fit(train_feat, y_true)
logging.info(clf.best_estimator_.get_params())
# save the model
joblib.dump(clf.best_estimator_, args.svm_model_path)
logging.info('model saved')
def detect_outlier(data,
classifier="Robust Covariance",
outlier_fraction=0.005):
classifiers = {
"Empirical Covariance":
EllipticEnvelope(support_fraction=1., contamination=outlier_fraction),
"Robust Covariance":
EllipticEnvelope(contamination=outlier_fraction),
"OCSVM":
OneClassSVM(nu=outlier_fraction, gamma=0.05)
}
# colors = ['m', 'g', 'b']
legend = {}
# Learn a frontier for outlier detection with several classifiers
xx1, yy1 = np.meshgrid(np.linspace(5, 10, 500), np.linspace(10, 15, 500))
plt.figure(1)
clf = classifiers[classifier]
clf.fit(data)
scores = clf.decision_function(np.c_[xx1.ravel(),
yy1.ravel()]).reshape(xx1.shape)
legend[classifier] = plt.contour(xx1,
yy1,
scores,
levels=[0],
linewidths=2,
colors='m',
linestyles='dashed')
legend_key = list(legend.keys())
# Plot the results (= shape of the data points cloud)
plt.figure(1) # two clusters
plt.title("Identify potential outliers")
plt.xlabel('log: Above grade (ground) living area square feet')
plt.ylabel('log: Sales Price')
plt.scatter(data.iloc[:, 0], data.iloc[:, 1], color='black')
plt.xlim((xx1.min(), xx1.max()))
plt.ylim((yy1.min(), yy1.max()))
plt.legend([legend_key[0]]).legendHandles[0].set_color('m')
plt.show()
def __init__(self,
kernel,
detector,
labeled=True,
WL_iter=5,
PK_bin_width=1,
LOF_n_neighbors=20,
LOF_n_leaf=30,
**kwargs):
kernels = {
'WL':
WeisfeilerLehman(n_iter=WL_iter,
normalize=True,
base_graph_kernel=VertexHistogram),
'PK':
Propagation(t_max=WL_iter, w=PK_bin_width, normalize=True)
if labeled else PropagationAttr(
t_max=WL_iter, w=PK_bin_width, normalize=True),
}
detectors = {
'OCSVM':
OneClassSVM(kernel='precomputed', nu=0.1),
'LOF':
LocalOutlierFactor(n_neighbors=LOF_n_neighbors,
leaf_size=LOF_n_leaf,
metric='precomputed',
contamination=0.1),
# 'IF': current similarity forest also has problem
}
assert kernel in kernels.keys()
assert detector in detectors.keys()
self.kernel = kernels[kernel]
self.detector = detectors[detector]
self.kernel_name = kernel
self.detector_name = detector
self.labeled = labeled
def trainLocalModel(r, key, datas):
r_list = datas
requests = pipeline.group_requests(
r_list, lambda r: '{} {}'.format(r.method, r.url))
for i, (k, v_list) in enumerate(sorted(requests.items())):
d2 = pipeline.group_requests(v_list, lambda r: r.label_type)
normal_request = d2.get('normal', [])
anormal_request = d2.get('anormal', [])
anormal_size = int(0.01 * len(normal_request))
train_list, _ = train_test_split(normal_request +
anormal_request[-anormal_size:-1],
random_state=RANDOM_STATE,
train_size=TRAIN_SIZE)
clf_svm = make_pipeline(
make_union(*[class_() for class_ in TF_LIST]),
OneClassSVM(kernel='sigmoid', nu=NU, gamma='auto'))
clf_isolation = make_pipeline(
make_union(*[class_() for class_ in TF_LIST]),
IsolationForest(n_estimators=128,
max_samples=400,
max_features=0.7,
random_state=rng))
#clf_lof = make_pipeline(
# make_union(*[class_() for class_ in TF_LIST]),
# LocalOutlierFactor(n_neighbors=20))
models = [clf_svm.fit(train_list),
clf_isolation.fit(train_list)] #, clf_lof.fit(train_list)]
return models
def fit_selected_classifier(X_data):
""" Fits the selected classifier
Parameters:
X_data (np.ndarray) - input dataset
Returns:
None
"""
global classifier
if sel_classifier == Classifier.OCSVM:
#classifier = OneClassSVM(kernel='sigmoid', gamma='scale', nu=0.1).fit(X_data)
classifier = OneClassSVM(gamma='scale', verbose=True).fit(X_data)
if sel_classifier == Classifier.IFOREST:
classifier = IsolationForest(random_state=0, contamination=0.1).fit(X_data)
if sel_classifier == Classifier.EllipticEnvelope:
classifier = EllipticEnvelope(random_state=0, contamination=0.1).fit(X_data)
if sel_classifier == Classifier.LocalOutlierFactor:
classifier = LocalOutlierFactor(contamination=0.1, novelty=True).fit(X_data)
def fit(self, params):
if len(self.data) <= 1:
self.DEBUG_INFO = "No samples are there!"
self.changed("alert_generated")
return
X = np.asarray(self.data)[:,0:2]
y = np.asarray(self.data)[:,2]
if np.unique(y).size == 1:
# only one-class
self.clf = OneClassSVM(nu=params['nu'],
gamma=params['gamma'],
degree=params['degree'],
coef0=params['coef0'],
kernel=params['kernel'])
self.clf.fit(X)
else:
self.clf = SVC(C=params['C'],
gamma=params['gamma'],
degree=params['degree'],
coef0=params['coef0'],
kernel=params['kernel'])
self.clf.fit(X, y)
self.is_fitted = True
self.changed("model_fitted")
def __init__(
self,
trainable_invertible_ica,
predictor_model,
novelty_detector=OneClassSVM(nu=0.1, gamma="auto"),
aug_max_iter: Optional[int] = None,
augmentation_size: Optional[int] = None,
):
"""Build CausalMechanismTransfer object.
Parameters
----------
trainable_invertible_ica : object
Trainable invertible ICA model for estimating the mechanism function.
Required to implement ``train()`` and ``inv()``.
predictor_model : object
Trainable predictor model to be trained on the augmented data. Needs to implement ``fit()`` and ``predict()``.
aug_max_iter : int or None
The maximum number of iterations for performing the augmentation.
augmentation_size : int or None
The size of the augmentation. Fully augmented if ``None``.
Returns
----------
None : None
"""
self.trainable_invertible_ica = trainable_invertible_ica
self.augmenter = ICATransferAugmenter(
self.trainable_invertible_ica.get_invertible_ica_model(),
novelty_detector=novelty_detector,
max_iter=aug_max_iter)
self.predictor_model = predictor_model
self.augmentation_size = augmentation_size
def single_eval_one_class(X_train, X_test, y_test, species_train, args,
class_list):
if args.classifier == 'GaussianMixed':
# define the gaussian mixed model, fit to training data and make predictions
clf = GaussianMixed(class_list,
threshold=args.threshold,
mixmodel=True,
epsilon=1e-6)
clf.fit(X_train, species_train)
y_preds, y_score = clf.predict(X_test)
else:
# define the one class svm, and fit it to the training data
clf = OneClassSVM(kernel=args.classifier, gamma='auto')
clf.fit(X_train)
#make predictions and calculate the roc curve
y_preds = clf.predict(X_test)
y_score = clf.decision_function(X_test)
# calculate the false and true positive rate, followed by the AUROC
fpr, tpr, _ = roc_curve(y_test, y_score)
roc_auc = auc(fpr, tpr)
return y_preds, roc_auc, fpr, tpr
def _load_detection_models(self):
self._detection_models = {}
for ds_url in data_sets.DS_URL_LIST[TEST_CONFIG['DS_URL_SLICE']]:
try:
normal_list = self._get_from_data_server(ds_url, 'n')
except ValueError as err:
self.log_debug(
'_load_detection_models',
'could not get req_list "{}": {}'.format(ds_url, err))
return
train_list, _ = train_test_split(normal_list,
random_state=RANDOM_STATE,
train_size=TRAIN_SIZE)
clf = make_pipeline(
make_union(*[class_() for class_ in TF_LIST]),
OneClassSVM(random_state=0, nu=NU, gamma=GAMMA))
clf.fit(train_list)
key = str(normal_list[0])
self._detection_models[key] = clf
self.log_debug('_load_detection_models', 'loaded "{}"'.format(key))
def fit_sklearn_model(embeddings, model_name, output_filename, n_neighbors=4):
logger.info('final size of the collected embeddings: {}'.format(
len(embeddings)))
embedding_array = np.concatenate(embeddings)
if model_name == 'local_outlier_factor':
logger.info('using local outlier factor with n_neighbour {}'.format(
n_neighbors))
clf = LocalOutlierFactor(n_neighbors=n_neighbors,
novelty=True,
contamination=0.1)
elif model_name == 'isolation_forest':
clf = IsolationForest(contamination=0.1)
elif model_name == 'svm':
clf = OneClassSVM(kernel='linear')
else:
raise ValueError('model {} not supported'.format(model_name))
clf.fit(embedding_array)
logger.info('Saving OOD model to {}'.format(output_filename))
with open(output_filename, "wb") as out_stream:
pickle.dump(clf, out_stream)
return clf
def __generate_probas(self, samples, resolution, affinity_matrix, number_of_questions):
print(
f"📞 Looks like there's a probability distribution ({self.name}) that wants to phone in an expert (that's "
f"you)\n"
)
clf = OneClassSVM(kernel='precomputed')
samples_and_weights = {0: 0.5}
for nq in range(number_of_questions):
indices = list(samples_and_weights.keys())
if nq == 0:
idx = np.random.choice(range(1, len(samples)))
else:
preds = clf.decision_function(affinity_matrix[:, indices])
idx = [i for i, _ in sorted(enumerate(preds), key=lambda x: x[1]) if i not in samples_and_weights][
0]
sample = samples[idx]
print('Score the sample below with a number between 0 and 1 (higher is better)\n')
if hasattr(sample, '_repr_html_'):
print(sample)
else:
print(sample)
weight = float(input('Score: '))
assert 0 <= weight <= 1
samples_and_weights[idx] = weight
indices = list(samples_and_weights.keys())
clf.fit(
affinity_matrix[indices, :][:, indices],
sample_weight=list(samples_and_weights.values())
)
indices = list(samples_and_weights.keys())
preds = clf.decision_function(affinity_matrix[:, indices])
scores = KernelDiscretizedMethod.discretized_scores(
resolution,
samples,
affinity_matrix,
lambda mask, _idx: preds[mask].mean())
Z = logsumexp([s for s in scores.values()])
return {idx: s - Z for idx, s in scores.items()}
def main():
print "loading data"
train = read_data(0)
print train.shape
label = np.ones(train.shape[0], )
print label.shape
# train = train.tolist()
# label = label.tolist()
print "training the one-class SVM"
model = OneClassSVM(kernel='rbf',
nu=0.2,
degree=3,
gamma=0.009,
shrinking=1)
model.fit(train)
print "predicting the test data"
label_test = np.ones(200, )
test = read_data(1)
pred1 = model.predict(train)
print pred1[np.where(pred1 > 0)].sum() / pred1.shape[0]
pred2 = model.predict(test)
print pred2[np.where(pred2 > 0)].sum() / pred2.shape[0]
# pred = np.zeros(200,)
pred = []
for i in range(200):
#print 'the iteration:', i, p_label[i]
if pred2[i] == 1:
pred.append('healthy')
elif pred2[i] == -1:
pred.append('dzs_1r+dzs_1l')
print len(pred)
np.save('corrcoef_predict_9.npy', pred)
def outlier_detection_SVM():
df_X, df_y = load_confirmed()
df_X = remove_not_numeric(df_X)
index = df_X[df_y == 1].index
X = df_X.drop(index)
y = df_y.drop(index)
print(X)
print(len(index), index)
div = int(len(X) * 0.7)
X_train = X[:div]
X_test = X[div:]
X_outliers = df_X.ix[index]
print(X_outliers)
pipe = Pipeline([("imputer", Imputer()), ("scaler", MinMaxScaler()),
("decomposition", PCA(n_components=100))])
X_train = pipe.fit_transform(X_train)
clf = OneClassSVM(gamma=(1 / len(X_train)), nu=0.37)
clf.fit(X_train)
X_test = pipe.transform(X_test)
X_outliers = pipe.transform(X_outliers)
print(X_outliers)
y_pred_train = clf.predict(X_train)
y_pred_test = clf.predict(X_test)
print("********** " + str(len(X_test)) + " " + str(len(y_pred_test)))
y_pred_outliers = clf.predict(X_outliers)
n_error_train = y_pred_train[y_pred_train == -1].size
n_error_test = y_pred_test[y_pred_test == -1].size
n_error_outliers = y_pred_outliers[y_pred_outliers == 1].size
print("train error:", n_error_train / len(y_pred_train))
print("test error:", n_error_test / len(y_pred_test))
print("outliers error:", n_error_outliers / len(y_pred_outliers))
return y_pred_train, y_pred_test, y_pred_outliers, y[div:]
def slice_probability_space_selection(data, nu=0.05, all_gammas=2 ** np.linspace(-10, 10, 50),
rho=0.05, outlier_distribution = np.random.rand, folds_count=7):
kf_iterator = KFold(len(data), n_folds=folds_count)
all_errors = []
for gamma in all_gammas:
error = 0.0
clf = OneClassSVM(nu=nu, gamma=gamma)
for train, test in kf_iterator:
train_data = data[train,:]
test_data = data[test,:]
clf = OneClassSVM(nu=nu, gamma=gamma)
clf.fit(train_data)
prediction = clf.predict(test_data)
inlier_metric_part = np.mean(prediction == -1)
inlier_metric_part = inlier_metric_part / (1 + rho) / len(data)
outliers = outlier_distribution(*data.shape) - 0.5
outliers *= 8 * np.std(data)
outlier_metric_part = np.mean(clf.predict(outliers) == 1) * rho / (1 + rho) / len(outliers)
error += inlier_metric_part + outlier_metric_part
all_errors.append(error / folds_count)
index = np.argmin(all_errors)
#best_index = pd.Series(all_errors).pct_change().argmax() - 1
return int(index), all_errors
def base_experiment(pct_noise=0.15, noverlap_bits=0, exp_name='1-1',
ntrials=10, verbose=True, seed=123456789):
"""
Run a single experiment, locally.
@param pct_noise: The percentage of noise to add to the dataset.
@param noverlap_bits: The number of bits the base class should overlap
with the novelty class.
@param exp_name: The name of the experiment.
@param ntrials: The number of times to repeat the experiment.
@param verbose: If True print the results.
@param seed: The random seed to use.
@return: A tuple containing the percentage errors for the SP's training
and testing results and the SVM's training and testing results,
respectively.
"""
# Base parameters
ntrain, ntest = 800, 200
nsamples, nbits, pct_active = ntest + ntrain, 100, 0.4
clf_th = 0.5
log_dir = os.path.join(os.path.expanduser('~'), 'scratch',
'novelty_experiments', exp_name)
# Configure the SP
config = {
'ninputs': 100,
'trim': 1e-4,
'disable_boost': True,
'seed': seed,
'pct_active': None,
'random_permanence': True,
'pwindow': 0.5,
'global_inhibition': True,
'ncolumns': 200,
'nactive': 50,
'nsynapses': 75,
'seg_th': 15,
'syn_th': 0.5,
'pinc': 0.001,
'pdec': 0.001,
'nepochs': 10,
'log_dir': log_dir
}
# Seed numpy
np.random.seed(seed)
# Create the base dataset
x_ds = SPDataset(nsamples, nbits, pct_active, pct_noise, seed=seed)
x_tr, x_te = x_ds.data[:ntrain], x_ds.data[ntrain:]
# Create the outlier dataset
base_indexes = set(np.where(x_ds.base_class == 1)[0])
choices = [x for x in xrange(nbits) if x not in base_indexes]
outlier_base = np.zeros(nbits, dtype='bool')
outlier_base[np.random.choice(choices, x_ds.nactive - noverlap_bits,
False)] = 1
outlier_base[np.random.permutation(list(base_indexes))[:noverlap_bits]] = 1
y_ds = SPDataset(ntest, nbits, pct_active, pct_noise, outlier_base, seed)
y_te = y_ds.data
if verbose:
print "\nBase class' test noise: {0:2.2f}".format(1 - (np.mean(x_te, 0)
* x_ds.base_class.astype('i')).sum() / 40.)
print "Outlier's class noise: {0:2.2f}".format(1 - (np.mean(y_te, 0) *
outlier_base.astype('i')).sum() / 40.)
print 'Overlap between two classes: {0}'.format(np.dot(
x_ds.base_class.astype('i'), outlier_base.astype('i')))
# Metrics
metrics = SPMetrics()
# Get the metrics for the datasets
u_x_tr = metrics.compute_uniqueness(x_tr)
o_x_tr = metrics.compute_overlap(x_tr)
c_x_tr = 1 - metrics.compute_distance(x_tr)
u_x_te = metrics.compute_uniqueness(x_te)
o_x_te = metrics.compute_overlap(x_te)
c_x_te = 1 - metrics.compute_distance(x_te)
u_y_te = metrics.compute_uniqueness(y_te)
o_y_te = metrics.compute_overlap(y_te)
c_y_te = 1 - metrics.compute_distance(y_te)
# Initialize the overall results
sp_x_results = np.zeros(ntrials)
sp_y_results = np.zeros(ntrials)
svm_x_results = np.zeros(ntrials)
svm_y_results = np.zeros(ntrials)
# Iterate across the trials:
for i in xrange(ntrials):
# Make a new seed
seed2 = np.random.randint(1000000)
config['seed'] = seed2
config['log_dir'] = '{0}-{1}'.format(log_dir, i + 1)
# Create the SP
sp = SPRegion(**config)
# Fit the SP
sp.fit(x_tr)
# Get the SP's output
sp_x_tr = sp.predict(x_tr)
sp_x_te = sp.predict(x_te)
sp_y_te = sp.predict(y_te)
# Get the metrics for the SP's results
u_sp_x_tr = metrics.compute_uniqueness(sp_x_tr)
o_sp_x_tr = metrics.compute_overlap(sp_x_tr)
c_sp_x_tr = 1 - metrics.compute_distance(sp_x_tr)
u_sp_x_te = metrics.compute_uniqueness(sp_x_te)
o_sp_x_te = metrics.compute_overlap(sp_x_te)
c_sp_x_te = 1 - metrics.compute_distance(sp_x_te)
u_sp_y_te = metrics.compute_uniqueness(sp_y_te)
o_sp_y_te = metrics.compute_overlap(sp_y_te)
c_sp_y_te = 1 - metrics.compute_distance(sp_y_te)
# Log all of the metrics
sp._log_stats('Input Base Class Train Uniqueness', u_x_tr)
sp._log_stats('Input Base Class Train Overlap', o_x_tr)
sp._log_stats('Input Base Class Train Correlation', c_x_tr)
sp._log_stats('Input Base Class Test Uniqueness', u_x_te)
sp._log_stats('Input Base Class Test Overlap', o_x_te)
sp._log_stats('Input Base Class Test Correlation', c_x_te)
sp._log_stats('Input Novelty Class Test Uniqueness', u_y_te)
sp._log_stats('Input Novelty Class Test Overlap', o_y_te)
sp._log_stats('Input Novelty Class Test Correlation', c_y_te)
sp._log_stats('SP Base Class Train Uniqueness', u_sp_x_tr)
sp._log_stats('SP Base Class Train Overlap', o_sp_x_tr)
sp._log_stats('SP Base Class Train Correlation', c_sp_x_tr)
sp._log_stats('SP Base Class Test Uniqueness', u_sp_x_te)
sp._log_stats('SP Base Class Test Overlap', o_sp_x_te)
sp._log_stats('SP Base Class Test Correlation', c_sp_x_te)
sp._log_stats('SP Novelty Class Test Uniqueness', u_sp_y_te)
sp._log_stats('SP Novelty Class Test Overlap', o_sp_y_te)
sp._log_stats('SP Novelty Class Test Correlation', c_sp_y_te)
# Print the results
fmt_s = '{0}:\t{1:2.4f}\t{2:2.4f}\t{3:2.4f}\t{4:2.4f}\t{5:2.4f}\t{5:2.4f}'
if verbose:
print '\nDescription\tx_tr\tx_te\ty_te\tsp_x_tr\tsp_x_te\tsp_y_te'
print fmt_s.format('Uniqueness', u_x_tr, u_x_te, u_y_te, u_sp_x_tr,
u_sp_x_te, u_sp_y_te)
print fmt_s.format('Overlap', o_x_tr, o_x_te, o_y_te, o_sp_x_tr, o_sp_x_te,
o_sp_y_te)
print fmt_s.format('Correlation', c_x_tr, c_x_te, c_y_te, c_sp_x_tr,
c_sp_x_te, c_sp_y_te)
# Get average representation of the base class
sp_base_result = np.mean(sp_x_tr, 0)
sp_base_result[sp_base_result >= 0.5] = 1
sp_base_result[sp_base_result < 1] = 0
# Averaged results for each metric type
u_sp_base_to_x_te = 0.
o_sp_base_to_x_te = 0.
c_sp_base_to_x_te = 0.
u_sp_base_to_y_te = 0.
o_sp_base_to_y_te = 0.
c_sp_base_to_y_te = 0.
for x, y in zip(sp_x_te, sp_y_te):
# Refactor
xt = np.vstack((sp_base_result, x))
yt = np.vstack((sp_base_result, y))
# Compute the sums
u_sp_base_to_x_te += metrics.compute_uniqueness(xt)
o_sp_base_to_x_te += metrics.compute_overlap(xt)
c_sp_base_to_x_te += 1 - metrics.compute_distance(xt)
u_sp_base_to_y_te += metrics.compute_uniqueness(yt)
o_sp_base_to_y_te += metrics.compute_overlap(yt)
c_sp_base_to_y_te += 1 - metrics.compute_distance(yt)
u_sp_base_to_x_te /= ntest
o_sp_base_to_x_te /= ntest
c_sp_base_to_x_te /= ntest
u_sp_base_to_y_te /= ntest
o_sp_base_to_y_te /= ntest
c_sp_base_to_y_te /= ntest
# Log the results
sp._log_stats('Base Train to Base Test Uniqueness',
u_sp_base_to_x_te)
sp._log_stats('Base Train to Base Test Overlap', o_sp_base_to_x_te)
sp._log_stats('Base Train to Base Test Correlation', c_sp_base_to_x_te)
sp._log_stats('Base Train to Novelty Test Uniqueness',
u_sp_base_to_y_te)
sp._log_stats('Base Train to Novelty Test Overlap', o_sp_base_to_y_te)
sp._log_stats('Base Train to Novelty Test Correlation',
c_sp_base_to_y_te)
# Print the results
if verbose:
print '\nDescription\tx_tr->x_te\tx_tr->y_te'
print 'Uniqueness:\t{0:2.4f}\t{1:2.4f}'.format(u_sp_base_to_x_te,
u_sp_base_to_y_te)
print 'Overlap:\t{0:2.4f}\t{1:2.4f}'.format(o_sp_base_to_x_te,
o_sp_base_to_y_te)
print 'Correlation:\t{0:2.4f}\t{1:2.4f}'.format(c_sp_base_to_x_te,
c_sp_base_to_y_te)
# Create an SVM
clf = OneClassSVM(kernel='linear', nu=0.1, random_state=seed2)
# Evaluate the SVM's performance
clf.fit(x_tr)
svm_x_te = len(np.where(clf.predict(x_te) == 1)[0]) / float(ntest) * \
100
svm_y_te = len(np.where(clf.predict(y_te) == -1)[0]) / float(ntest) * \
100
# Perform classification using overlap as the feature
# -- The overlap must be above 50%
clf_x_te = 0.
clf_y_te = 0.
for x, y in zip(sp_x_te, sp_y_te):
# Refactor
xt = np.vstack((sp_base_result, x))
yt = np.vstack((sp_base_result, y))
# Compute the accuracy
xo = metrics.compute_overlap(xt)
yo = metrics.compute_overlap(yt)
if xo >= clf_th: clf_x_te += 1
if yo < clf_th: clf_y_te += 1
clf_x_te = (clf_x_te / ntest) * 100
clf_y_te = (clf_y_te / ntest) * 100
# Store the results as errors
sp_x_results[i] = 100 - clf_x_te
sp_y_results[i] = 100 - clf_y_te
svm_x_results[i] = 100 - svm_x_te
svm_y_results[i] = 100 - svm_y_te
# Log the results
sp._log_stats('SP % Correct Base Class', clf_x_te)
sp._log_stats('SP % Correct Novelty Class', clf_y_te)
sp._log_stats('SVM % Correct Base Class', svm_x_te)
sp._log_stats('SVM % Correct Novelty Class', svm_y_te)
# Print the results
if verbose:
print '\nSP Base Class Detection : {0:2.2f}%'.format(clf_x_te)
print 'SP Novelty Class Detection : {0:2.2f}%'.format(clf_y_te)
print 'SVM Base Class Detection : {0:2.2f}%'.format(svm_x_te)
print 'SVM Novelty Class Detection : {0:2.2f}%'.format(svm_y_te)
return sp_x_results, sp_y_results, svm_x_results, svm_y_results
def main():
usage="refine2d using simmx information "
parser = EMArgumentParser(usage=usage,version=EMANVERSION)
parser.add_argument("--ptcls", type=str,help="particle file", default=None)
parser.add_argument("--simmx", type=str,help="simmx", default=None)
parser.add_argument("--npca", type=int,help="number of pca factors", default=10)
parser.add_argument("--niter", type=int,help="number of iterations", default=5)
parser.add_argument("--outlier", type=float,help="outlier fraction", default=0.1)
parser.add_argument("--ncls", type=int,help="number of centers", default=128)
parser.add_argument("--nref", type=int,help="number of references", default=32)
(options, args) = parser.parse_args()
logid=E2init(sys.argv)
simmxfile=options.simmx
for itr in range(options.niter):
### start from the simmx
print "Pre-processing simmx"
e=EMData(simmxfile)
pts=e.numpy().T.copy()
for i in range(len(pts)):
pts[i]-=np.mean(pts[i])
pts[i]/=np.std(pts[i])
pts=pts.astype(np.float).copy();
#e=from_numpy(pts.T.copy())
#e.write_image("simmx_tmp.hdf")
#exit()
print "Doing PCA"
(nptcl, ncls) = pts.shape;
#nfac=options.npca
pca=PCA(options.npca)
pts_pca=pca.fit_transform(pts)
bs=pts_pca
bs/=np.std(bs)
print bs.shape,pts.shape
np.savetxt("test_pca_{:02d}".format(itr),pts_pca)
print "Removing outliers"
outliers_fraction=options.outlier
svm=OneClassSVM(nu=0.95 * outliers_fraction + 0.05,kernel="rbf", gamma=0.1)
svm.fit(bs)
y_pred = svm.decision_function(bs).ravel()
nkeep=int(len(bs)*(1-outliers_fraction))
st=np.argsort(y_pred)[::-1]
st=st[:nkeep]
print "Clustering"
ncnt=options.ncls
centroids,_ = kmeans(bs[st],ncnt)
l,_ = vq(bs[st],centroids)
labels=np.zeros(len(bs))-1
labels[st]=l
print "Class averaging"
e=EMData(1,len(labels))
for i in range(len(labels)):
e.set_value_at(0,i,labels[i])
clsmxfile="clsmx_{:02d}.hdf".format(itr)
e.write_image(clsmxfile)
clsout="classes_{:02d}.hdf".format(itr)
run("e2classaverage.py --input={} --classmx={} --output={} --force --center xform.center --iter=5 --align=rotate_translate_flip:maxshift=32 --averager=mean --keep=.6 --cmp=ccc --aligncmp=ccc --normproc=normalize --parallel=thread:12".format(options.ptcls,clsmxfile,clsout))
simmxfile="simmx_{:02d}.hdf".format(itr)
run("e2simmx.py {} {} {} --align rotate_translate_flip --aligncmp ccc --cmp ccc --saveali --parallel thread:12".format(options.ptcls, clsout, simmxfile))
E2end(logid)
def decision_function(self, data):
return -OneClassSVM.decision_function(self, data)
# indices = np.arange(X.shape[0])
# np.random.shuffle(indices) # shuffle the dataset
# X = X[indices]
# y = y[indices]
X_train = X[:n_samples_train, :]
X_test = X[n_samples_train:, :]
y_train = y[:n_samples_train]
y_test = y[n_samples_train:]
# # training only on normal data:
# X_train = X_train[y_train == 0]
# y_train = y_train[y_train == 0]
print('OneClassSVM processing...')
model = OneClassSVM(cache_size=500)
tstart = time()
model.fit(X_train)
fit_time += time() - tstart
tstart = time()
scoring = -model.decision_function(X_test) # the lower,the more normal
predict_time += time() - tstart
fpr_, tpr_, thresholds_ = roc_curve(y_test, scoring)
if fit_time + predict_time > max_time:
raise TimeoutError
f = interp1d(fpr_, tpr_)
tpr += f(x_axis)
tpr[0] = 0.
X_train = X[:n_samples_train, :]
X_test = X[n_samples_train:, :]
y_train = y[:n_samples_train]
y_test = y[n_samples_train:]
# training and testing only on normal data:
X_train = X_train[y_train == 0]
y_train = y_train[y_train == 0]
X_test = X_test[y_test == 0]
y_test = y_test[y_test == 0]
# define models:
iforest = IsolationForest()
lof = LocalOutlierFactor(n_neighbors=20)
ocsvm = OneClassSVM()
lim_inf = X.min(axis=0)
lim_sup = X.max(axis=0)
volume_support = (lim_sup - lim_inf).prod()
t = np.arange(0, 100 / volume_support, 0.01 / volume_support)
axis_alpha = np.arange(alpha_min, alpha_max, 0.0001)
unif = np.random.uniform(lim_inf, lim_sup,
size=(n_generated, n_features))
# fit:
print('IsolationForest processing...')
iforest = IsolationForest()
iforest.fit(X_train)
s_X_iforest = iforest.decision_function(X_test)
print('LocalOutlierFactor processing...')
ax.set_xlabel( 'Ratio' ) ax.set_ylabel( 'Margin' ) ax.set_zlabel( 'Similarity of Neighboring Districts' ) ax.set_zlim( [ 0., 1. ] ) ax.set_xlim( [ 0., 500. ] ) ax.set_ylim( [ 0., 1. ] ) fig.show() angles = np.linspace(0,360,41)[:-1] # Take 20 angles between 0 and 360 rotanimate(ax, angles,'movie.gif',delay=20, width = 6., height = 5.) # do outlier search using one-class SVM data[ 0, : ] = preprocessing.scale( data[ 0, : ] ) model = OneClassSVM( gamma = .001, nu = .1 ) fit = model.fit( data ) preds = model.predict( data ) inlier = np.where( preds == 1. )[ 0 ] outlier = np.where( preds == -1. )[ 0 ] fig = plt.figure() ax = fig.add_subplot( 111, projection = '3d' ) ax.scatter( data[ inlier, 0 ], data[ inlier, 1 ], data[ inlier, 2 ], c = 'b' ) ax.scatter( data[ outlier, 0 ], data[ outlier, 1 ], data[ outlier, 2 ], c = 'k' ) ax.set_xlabel( '$P^2/A$' ) ax.set_ylabel( 'Margin' ) ax.set_zlabel( 'Similarity of Neighboring Districts' ) ax.set_ylim( [0., 1 ] )
def classifier(data):
from sklearn.covariance import EllipticEnvelope
from sklearn.svm import OneClassSVM
from sklearn.datasets import load_boston
from sklearn import preprocessing
# Get data
# Define "classifiers" to be used
legend1 = {}
legend2 = {}
evaluation = [[val["coverage"], val["num_exons"], val["distance_to_next"]] for val in data]
X = [[val["coverage"], val["num_exons"], val["distance_to_next"]] for val in data]
X = preprocessing.scale(X)
evaluation = preprocessing.scale(evaluation)
# Learn a frontier for outlier detection with several classifiers
sample = random.sample(X, 20000)
clf = OneClassSVM(nu=.1, kernel='rbf')
test = random.sample(evaluation, 2000)
print >> sys.stderr, "fitting data"
clf.fit(sample)
print >> sys.stderr, "predicting data"
Y = clf.predict(test)
print >> sys.stderr, "plotting data"
fig, axes = subplots()
for i in range(len(test)):
if Y[i] == 1:
color = 'blue'
else:
color = 'red'
axes.scatter(test[i][2], test[i][1], c=color)
#ylim([50,2000]) #num exons
ylabel("distance")
#xlim([3,10])
xlabel("coverage")
savefig("DistanceVCoverage.pdf")
fig, axes = subplots()
"""
for i in range(len(test)):
if Y[i] == 1:
color = 'blue'
else:
color = 'red'
axes.scatter(test[i][1], test[i][0], c=color)
#xlim([0,10]) #num exons
xlabel("number of exons")
#ylim([3,15])
ylabel("coverage")
savefig("ExonsvsCoverage.pdf")
"""
full_test = clf.predict(evaluation)
novel, regular = [],[]
for i in range(len(full_test)):
result = full_test[i]
if result == -1:
print data[i]["id"]
novel.append(data[i]["num_exons"])
else:
regular.append(data[i]["num_exons"])
multi_exon_novel = [val for val in novel if val > 1]
multi_exon_regular = [val for val in regular if val > 1]
print >> sys.stderr, "novel, regular"
print >> sys.stderr, len(novel), len(regular)
print >> sys.stderr, mean(multi_exon_novel), mean(multi_exon_regular), len(multi_exon_novel), len(multi_exon_regular)
