Python svm.OneClassSVM类代码示例

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 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 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 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 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 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 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 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')