Python OneClassSVM.decision_function方法代码示例

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
    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)

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
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')

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
  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()

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
	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

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
 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

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
    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...')
    lof = LocalOutlierFactor(n_neighbors=20)
    lof.fit(X_train)
    s_X_lof = lof.decision_function(X_test)
    print('OneClassSVM processing...')
    ocsvm = OneClassSVM()
    ocsvm.fit(X_train[:min(ocsvm_max_train, n_samples_train - 1)])
    s_X_ocsvm = ocsvm.decision_function(X_test).reshape(1, -1)[0]
    s_unif_iforest = iforest.decision_function(unif)
    s_unif_lof = lof.decision_function(unif)
    s_unif_ocsvm = ocsvm.decision_function(unif).reshape(1, -1)[0]
    plt.subplot(121)
    auc_iforest, em_iforest, amax_iforest = em(t, t_max,
                                               volume_support,
                                               s_unif_iforest,
                                               s_X_iforest, n_generated)

    auc_lof, em_lof, amax_lof = em(t, t_max, volume_support,
                                   s_unif_lof, s_X_lof, n_generated)

    auc_ocsvm, em_ocsvm, amax_ocsvm = em(t, t_max, volume_support,
                                         s_unif_ocsvm, s_X_ocsvm,
                                         n_generated)

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
            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.

            precision_, recall_ = precision_recall_curve(y_test, scoring)[:2]

            # cluster: old version of scipy -> interpol1d needs sorted x_input
            arg_sorted = recall_.argsort()
            recall_ = recall_[arg_sorted]

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
 def decision_function(self, data):
     return -OneClassSVM.decision_function(self, data)

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
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)

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
def select_candidates(X, h, objective_function, verbose=False,
                      cov_computation_method=empirical_covariance):
    """Finds the best pure subset of observations to compute MCD from it.

    The purpose of this function is to find the best sets of h
    observations with respect to a minimization of their covariance
    matrix determinant. Equivalently, it removes n_samples-h
    observations to construct what we call a pure data set (i.e. not
    containing outliers). The list of the observations of the pure
    data set is referred to as the `support`.

    Starting from a support estimated with a Parzen density estimator,
    the pure data set is found by the c_step procedure introduced by
    Rousseeuw and Van Driessen in [1].

    Parameters
    ----------
    X: array-like, shape (n_samples, n_features)
      Data (sub)set in which we look for the h purest observations
    h: int, [(n + p + 1)/2] < h < n
      The number of samples the pure data set must contain.
    select: int, int > 0
      Number of best candidates results to return.

    See
    ---
    `c_step` function

    Returns
    -------
    best_locations: array-like, shape (select, n_features)
      The `select` location estimates computed from the `select` best
      supports found in the data set (`X`)
    best_covariances: array-like, shape (select, n_features, n_features)
      The `select` covariance estimates computed from the `select`
      best supports found in the data set (`X`)
    best_supports: array-like, shape (select, n_samples)
      The `select` best supports found in the data set (`X`)

    Notes
    -----
    References:
    [1] A Fast Algorithm for the Minimum Covariance Determinant Estimator,
        1999, American Statistical Association and the American Society
        for Quality, TECHNOMETRICS

    """
    n_samples, n_features = X.shape

    from sklearn.metrics.pairwise import euclidean_distances
    from sklearn.svm import OneClassSVM
    pairwise_distances = np.ravel(euclidean_distances(X))
    delta = sp.stats.scoreatpercentile(pairwise_distances, 10)
    gamma = 0.01 / delta
    clf = OneClassSVM(kernel='rbf', gamma=gamma)
    clf.fit(X)
    in_support = np.argsort(
        -np.ravel(clf.decision_function(X)))[-(n_samples / 2):]
    support = np.zeros(n_samples, dtype=bool)
    support[in_support] = True
    location = X[support].mean(0)
    covariance = cov_computation_method(X[support])
    initial_estimates = (location, covariance)
    best_location, best_covariance, _, best_support = c_step(
        X, h, objective_function, initial_estimates, verbose=verbose,
        cov_computation_method=cov_computation_method)

    return best_location, best_covariance, best_support

# 需要导入模块: from sklearn.svm import OneClassSVM [as 别名]
# 或者: from sklearn.svm.OneClassSVM import decision_function [as 别名]
import numpy as np
import pandas as pd
from sklearn.svm import OneClassSVM

df = pd.read_csv('kddcup_for_elki_100000.csv', header=None, index_col=False)
labelix = df.shape[1]-1

labels = df[labelix]
df = df.drop(labelix, axis=1)

svm = OneClassSVM(kernel='rbf', gamma=1.0/df.shape[0], tol=0.001, nu=0.5, shrinking=True, cache_size=80)
svm = svm.fit(df.values)

scores = svm.decision_function(df.values).flatten()
maxvalue = np.max(scores)
scores = maxvalue - scores

output = pd.DataFrame()

# perform reverse sort
sort_ix = np.argsort(scores)[::-1]

output['labels'] =  labels[sort_ix]
output['outlier_scores'] =  scores[sort_ix]

output.to_csv('outlier_scores.csv', header=None, index=None)