Python covariance.EllipticEnvelope類代碼示例

    def filter_remove_outlayers(self, flat, minimum_value=0):
        """
        Remove outlayers using ellicptic envelope from scikits learn
        :param flat:
        :param minimum_value:
        :return:
        """
        from sklearn.covariance import EllipticEnvelope
        flat0 = flat.copy()
        flat0[np.isnan(flat)] = 0
        x,y = np.nonzero(flat0)
        # print np.prod(flat.shape)
        # print len(y)

        z = flat[(x,y)]

        data = np.asarray([x,y,z]).T

        clf = EllipticEnvelope(contamination=.1)
        clf.fit(data)
        y_pred = clf.decision_function(data)


        out_inds = y_pred < minimum_value
        flat[(x[out_inds], y[out_inds])] = np.NaN
        return flat

    def clean_series(self, token, discard=5):

        """
        Remove outliers from the ratio series for a token.

        Args:
            discard (int): Drop the most outlying X% of the data.

        Returns: OrderedDict{year: wpm}
        """

        series = self.ratios[token]

        X = np.array(list(series.values()))[:, np.newaxis]

        env = EllipticEnvelope()
        env.fit(X)

        # Score each data point.
        y_pred = env.decision_function(X).ravel()

        # Get the discard threshold.
        threshold = stats.scoreatpercentile(y_pred, discard)

        return OrderedDict([
            (year, ratio)
            for (year, ratio), pred in zip(series.items(), y_pred)
            if pred > threshold
        ])

def outlier_removal2(features, samples, cv_predict):

    outliers_fraction = 0.1

    print cv_predict.shape
    print samples.shape
    test = np.column_stack((cv_predict, samples))
    #clf = EllipticEnvelope(contamination=.1)
    clf = EllipticEnvelope(contamination=.1)
    #clf = svm.OneClassSVM(nu=0.95 * outliers_fraction + 0.05,
    #                                 kernel="rbf", gamma=0.1)
    clf.fit(test)
    y_pred = clf.decision_function(test).ravel()
    threshold = stats.scoreatpercentile(y_pred,
                                        100 * outliers_fraction)

    y_pred_new = y_pred > threshold
    print y_pred_new
    #print samples[y_pred_new]
    print samples.shape
    print samples[y_pred_new].shape
    print features.shape
    print features[y_pred_new].shape

    return features[y_pred_new], samples[y_pred_new]

    def calc(self,outliers_fraction):
        

        data, dqs, raw = self.get_data()
        clf = EllipticEnvelope(contamination=outliers_fraction)
        X = zip(data['Tbandwidth'],data['Tlatency'],data['Tframerate'])
        clf.fit(X)
        #data['y_pred'] = clf.decision_function(X).ravel()
        #data['y_pred'] = clf.decision_function(X).ravel()
        
        #threshold = np.percentile(data['y_pred'],100 * outliers_fraction)
        data['MDist']=clf.mahalanobis(X)
        
        #picking "bad" outliers, not good ones
        outliers = chi2_outliers(data, [.8,.9,.95], 3)
        #print outliers
        outliers = [i[i['Tbandwidth']<i['Tlatency']] for i in outliers]
        
        #outliers = data[data['y_pred']<threshold]
        #data['y_pred'] = data['y_pred'] > threshold
        #outliers = [x[['ticketid','MDist']].merge(raw, how='inner').drop_duplicates() for x in outliers]
        #print raw
        #outliers = [raw[raw['ticketid'].isin(j['ticketid'])] for j in outliers]
        outliers = [k[k['Tframerate']<(k['Tframerate'].mean()+k['Tframerate'].std())] for k in outliers] #making sure we don't remove aberrantly good framrates
        outliers = [t.sort_values(by='MDist', ascending=False).drop_duplicates().drop(['Tbandwidth','Tlatency','Tframerate'],axis=1) for t in outliers]
        
        #dqs = raw[raw['ticketid'].isin(dqs['ticketid'])]
        #data = data.sort_values('MDist', ascending=False).drop_duplicates()
        
        return outliers, dqs, data.sort_values(by='MDist', ascending=False).drop_duplicates().drop(['Tbandwidth','Tlatency','Tframerate'],axis=1)

 def model_2_determine_test_data_similarity(self,model):
     clf_EE={}
     model_EE={}
     for i in range(len(model)):
         clf=EllipticEnvelope(contamination=0.01,support_fraction=1)
         clf_EE[i]=clf
         EEmodel=clf.fit(model[i])
         model_EE[i]=EEmodel
     return clf_EE,model_EE

def plot(X, y):
    proj = TSNE().fit_transform(X)
    e = EllipticEnvelope(assume_centered=True, contamination=.25) # Outlier detection
    e.fit(X)

    good = np.where(e.predict(X) == 1)
    X = X[good]
    y = y[good]

    scatter(proj, y)

def filterOut(x):
    x = np.array(x)
    outliers_fraction=0.05
    #clf = svm.OneClassSVM(nu=0.95 * outliers_fraction + 0.05,  kernel="rbf", gamma=0.1) 
    clf = EllipticEnvelope(contamination=outliers_fraction)
    clf.fit(x)
    y_pred = clf.decision_function(x).ravel()
    threshold = stats.scoreatpercentile(y_pred,
                                        100 * outliers_fraction)
    y_pred = y_pred > threshold
    return y_pred

    def module4(self):
        '''
            入力された一次元配列からanomaly detectionを用いて外れ値を検出する
        '''

        # get data
        img = cv2.imread('../saliency_detection/image/pearl.png')
        b,g,r = cv2.split(img) 
        B,G,R = map(lambda x,y,z: x*1. - (y*1. + z*1.)/2., [b,g,r],[r,r,g],[g,b,b])

        Y = (r*1. + g*1.)/2. - np.abs(r*1. - g*1.)/2. - b*1.
        # 負の部分は0にする
        R[R<0] = 0
        G[G<0] = 0
        B[B<0] = 0
        Y[Y<0] = 0
        rg = cv2.absdiff(R,G)
        by = cv2.absdiff(B,Y)
        img1 = rg
        img2 = by

        rg, by = map(lambda x:x.reshape((len(b[0])*len(b[:,0]),1)),[rg,by])
        data = np.hstack((rg,by))
        data = data.astype(np.float64)
        data = np.delete(data, range( 0,len(data[:,0]),2),0)

        # grid
        xx1, yy1 = np.meshgrid(np.linspace(-10, 300, 500), np.linspace(-10, 300, 500))
        
        # 學習して境界を求める # contamination大きくすると円は小さく
        clf = EllipticEnvelope(support_fraction=1, contamination=0.01)
        print 'data.shape =>',data.shape
        print 'learning...'
        clf.fit(data) #學習 # 0があるとだめっぽいかも
        print 'complete learning!'

        # 學習した分類器に基づいてデータを分類して楕円を描畫
        z1 = clf.decision_function(np.c_[xx1.ravel(), yy1.ravel()])
        z1 = z1.reshape(xx1.shape)
        plt.contour(xx1,yy1,z1,levels=[0],linewidths=2,colors='r')

        # plot
        plt.scatter(data[:,0],data[:,1],color= 'black')
        plt.title("Outlier detection")
        plt.xlim((xx1.min(), xx1.max()))
        plt.ylim((yy1.min(), yy1.max()))
        plt.pause(.001)
        # plt.show()
        
        cv2.imshow('rg',img1/np.amax(img1))
        cv2.imshow('by',img2/np.amax(img2))

def find_outlier_test_homes(df,all_homes,  appliance, outlier_features, outliers_fraction=0.1):
    from scipy import stats

    from sklearn import svm
    from sklearn.covariance import EllipticEnvelope
    clf = EllipticEnvelope(contamination=.1)
    try:
        X = df.ix[all_homes[appliance]][outlier_features].values
        clf.fit(X)
    except:
        try:
            X = df.ix[all_homes[appliance]][outlier_features[:-1]].values
            clf.fit(X)
        except:
            try:
                X = df.ix[all_homes[appliance]][outlier_features[:-2]].values
                clf.fit(X)
            except:
                print "outlier cannot be found"
                return df.ix[all_homes[appliance]].index.tolist()


    y_pred = clf.decision_function(X).ravel()
    threshold = stats.scoreatpercentile(y_pred,
                                        100 * outliers_fraction)
    y_pred = y_pred > threshold
    return df.ix[all_homes[appliance]][~y_pred].index.tolist()

def ellipticenvelope(data, fraction = 0.02):
    elenv = EllipticEnvelope(contamination=fraction)
    elenv.fit(data)
    score = elenv.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 elliptic_envelope(df, modelDir, norm_confidence=0.95):
	from sklearn.covariance import EllipticEnvelope
	from scipy.stats import normaltest

	if "ds" in df.columns:
		del df["ds"]
	model = EllipticEnvelope()
	test_stats, p_vals = normaltest(df.values, axis=0)
	normal_cols = p_vals >= (1 - norm_confidence)
	df = df.loc[:, normal_cols]
	if df.shape[1] == 0:
		return None
	df.outlier = model.fit_predict(df.values)
	df.outlier = df.outlier < 0  # 1 if inlier, -1 if outlier
	return df

def labelValidSkeletons(skel_file, valid_index, trajectories_data, fit_contamination = 0.05):
    #calculate valid widths if they were not used
    calculate_widths(skel_file)
    
    #calculate classifier for the outliers    
    X4fit = nodes2Array(skel_file, valid_index)        
    clf = EllipticEnvelope(contamination = fit_contamination)
    clf.fit(X4fit)
    
    #calculate outliers using the fitted classifier
    X = nodes2Array(skel_file) #use all the indexes
    y_pred = clf.decision_function(X).ravel() #less than zero would be an outlier

    #labeled rows of valid individual skeletons as GOOD_SKE
    trajectories_data['auto_label'] = ((y_pred>0).astype(np.int))*wlab['GOOD_SKE'] #+ wlab['BAD']*np.isnan(y_prev)
    saveLabelData(skel_file, trajectories_data)

def test_score_samples():
    X_train = [[1, 1], [1, 2], [2, 1]]
    clf1 = EllipticEnvelope(contamination=0.2).fit(X_train)
    clf2 = EllipticEnvelope().fit(X_train)
    assert_array_equal(clf1.score_samples([[2., 2.]]),
                       clf1.decision_function([[2., 2.]]) + clf1.offset_)
    assert_array_equal(clf2.score_samples([[2., 2.]]),
                       clf2.decision_function([[2., 2.]]) + clf2.offset_)
    assert_array_equal(clf1.score_samples([[2., 2.]]),
                       clf2.score_samples([[2., 2.]]))

def labelValidSkeletons(skel_file):
    calculate_widths(skel_file)
    
    #get valid rows using the trajectory displacement and the skeletonization success
    valid_index, trajectories_data = getValidIndexes(skel_file)
    
    #calculate classifier for the outliers    
    X4fit = nodes2Array(skel_file, valid_index)        
    clf = EllipticEnvelope(contamination=.1)
    clf.fit(X4fit)
    
    #calculate outliers using the fitted classifier
    X = nodes2Array(skel_file)
    y_pred = clf.decision_function(X).ravel() #less than zero would be an outlier

    #labeled rows of valid individual skeletons as GOOD_SKE
    trajectories_data['auto_label'] = ((y_pred>0).astype(np.int))*wlab['GOOD_SKE'] #+ wlab['BAD']*np.isnan(y_prev)
    saveLabelData(skel_file, trajectories_data)

def test_outlier_detection():
    rnd = np.random.RandomState(0)
    X = rnd.randn(100, 10)
    clf = EllipticEnvelope(contamination=0.1)
    assert_raises(NotFittedError, clf.predict, X)
    assert_raises(NotFittedError, clf.decision_function, X)
    clf.fit(X)
    y_pred = clf.predict(X)
    decision = clf.decision_function(X, raw_values=True)
    decision_transformed = clf.decision_function(X, raw_values=False)

    assert_array_almost_equal(decision, clf.mahalanobis(X))
    assert_array_almost_equal(clf.mahalanobis(X), clf.dist_)
    assert_almost_equal(clf.score(X, np.ones(100)), (100 - y_pred[y_pred == -1].size) / 100.0)
    assert sum(y_pred == -1) == sum(decision_transformed < 0)