python类Birch()的实例源码

def __init__(self, edges, branching_factor=50, threshold=0.1):
        # Make features list.
        features = []
        for i in range(len(edges)):
            edge = edges[i]
            features.append([edge['perimeter'], edge['area'],
                             edge['shape_factor'], edge['radius_deviation']])
        features = np.array(features)

        # Normalize features
        normed_features = features.copy()
        for i in range(features.shape[1]):
            avg = np.median(features[::, i])
            std = np.std(features[::, i])

            normed_features[::, i] -= avg
            normed_features[::, i] /= avg

        self.features = features
        self.normed_features = normed_features
        self.branching_factor = branching_factor
        self.threshold = threshold
        #self.run(Birch, branching_factor=50, threshold=0.1, n_clusters=2)
        self.run(KMeans, n_clusters=2)
        #self.run(AgglomerativeClustering, n_clusters=2)

def birch_cluster_partitioning(X, points_per_expert):
    """Return a list of lists each containing a partition of the indices of the
    data to be fit that is generated by splitting along clusters found via
    Birch clustering approach."""
    sample_sets = []
    num_samples = X.shape[0]
    indices = np.arange(num_samples)

    num_clusters = int(
            float(num_samples) / points_per_expert)
    birch = Birch(n_clusters=num_clusters, threshold=0.2)
    labels = birch.fit_predict(X)
    unique_labels = np.unique(labels)

    # Fill each inner list i with indices matching its label i
    for label in unique_labels:
        sample_sets.append([i for i in indices if labels[i] == label])
    return sample_sets

def GetItemPixels(self, I):
        '''
        Locates items that should be picked up on the screen
        '''
        ws = [8, 14]
        D1 = np.abs(I - np.array([10.8721,  12.8995,  13.9932])).sum(axis = 2) < 15
        D2 = np.abs(I - np.array([118.1302, 116.0938, 106.9063])).sum(axis = 2) < 76
        R1 = view_as_windows(D1, ws, ws).sum(axis = (2, 3))
        R2 = view_as_windows(D2, ws, ws).sum(axis = (2, 3))
        FR = ((R1 + R2 / np.prod(ws)) >= 1.0) & (R1 > 10) & (R2 > 10)
        PL = np.transpose(np.nonzero(FR)) * np.array(ws)
        if len(PL) <= 0:
            return []
        bc = Birch(threshold = 50, n_clusters = None)
        bc.fit(PL)
        return bc.subcluster_centers_

def cluster_kmeans(X_train, model_args=None, gridsearch=True):
    from sklearn.cluster import KMeans
    print('KMeans')

    if gridsearch is True:
        param_grid = {
            'n_clusters': np.arange(1, 20, 2),
            'max_iter': [50, 100, 300],
            'tol': [1e-5, 1e-4, 1e-3]
        }
        prune(param_grid, model_args)
    else:
        if 'n_clusters' not in model_args:
            raise KeyError('Need to define n_clusters for Birch')
        param_grid = None

    return ModelWrapper(KMeans, X=X_train, model_args=model_args, param_grid=param_grid, unsupervised=True)

def cluster_birch(X_train, model_args=None, gridsearch=True):
    from sklearn.cluster import Birch
    print('Birch')

    if gridsearch is True:
        ## TODO:
        # add hyperparamter searching. No scoring method available for this model, 
        # so we can't easily use gridsearching.

        raise NotImplementedError('No hyperparameter optimization available yet for this model. Set gridsearch to False')
        # prune(param_grid, model_args)
    else:
        if 'n_clusters' not in model_args:
            raise KeyError('Need to define n_clusters for Birch')
        param_grid = None

    return ModelWrapper(Birch, X=X_train, model_args=model_args, param_grid=param_grid, unsupervised=True)

def clusteringReminMost(window):
    brc = Birch(branching_factor=50, n_clusters=3, threshold=0.5,compute_labels=True)
    brc.fit(window)
    Class = brc.predict(window)
    #???????????????????????????????????
    num0 = 0
    num1 = 0
    num2 = 0

    for i in Class :
        if i == 0:
            num0 += 1
        elif i ==1:
            num1 +=1
        else:
            num2 +=1
    lable = chooseMax(num0, num1, num2)
    newwindow = []
    for i in range(1,len(Class)):
        if Class[i] == lable:#????????????
            newwindow.append(window[i])
    return newwindow

def clusteringReminMost(window):
    brc = Birch(branching_factor=50, n_clusters=3, threshold=0.5,compute_labels=True)
    brc.fit(window)
    Class = brc.predict(window)
    #???????????????????????????????????
    num0 = 0
    num1 = 0
    num2 = 0

    for i in Class :
        if i == 0:
            num0 += 1
        elif i ==1:
            num1 +=1
        else:
            num2 +=1
    lable = chooseMax(num0, num1, num2)
    newwindow = window[0:1]
    for i in range(1,len(Class)):
        if Class[i] == lable:#????????????
            newwindow = newwindow.append(window[i-1:i])#??pandas????
    return newwindow

def clusteringReminMost(window):
    brc = Birch(branching_factor=50, n_clusters=3, threshold=0.5,compute_labels=True)
    brc.fit(window)
    Class = brc.predict(window)
    #???????????????????????????????????
    num0 = 0
    num1 = 0
    num2 = 0

    for i in Class :
        if i == 0:
            num0 += 1
        elif i ==1:
            num1 +=1
        else:
            num2 +=1
    lable = chooseMax(num0, num1, num2)
    newwindow = window[0:1]
    for i in range(1,len(Class)):
        if Class[i] == lable:#????????????
            newwindow = newwindow.append(window[i-1:i])
    return newwindow

def clusteringReminMost(window):
    brc = Birch(branching_factor=50, n_clusters=3, threshold=0.5,compute_labels=True)
    brc.fit(window)
    Class = brc.predict(window)
    #???????????????????????????????????
    num0 = 0
    num1 = 0
    num2 = 0

    for i in Class :
        if i == 0:
            num0 += 1
        elif i ==1:
            num1 +=1
        else:
            num2 +=1
    lable = chooseMax(num0, num1, num2)
    newwindow = window[0:1]
    for i in range(1,len(Class)):
        if Class[i] == lable:#????????????
            newwindow = newwindow.append(window[i-1:i])#??pandas????
    return newwindow

def make_birch_clustering(self, short_filenames, input_texts):

        output_dir = self.output_dir + 'birch/'
        if not os.path.exists(output_dir):
            os.makedirs(output_dir)

        if self.need_tf_idf:
            self.signals.PrintInfo.emit("?????? TF-IDF...")
            idf_filename = output_dir + 'tf_idf.csv'
            msg = self.calculate_and_write_tf_idf(idf_filename, input_texts)
            self.signals.PrintInfo.emit(msg)

        vectorizer = CountVectorizer()
        X = vectorizer.fit_transform(input_texts)

        svd = TruncatedSVD(2)
        normalizer = Normalizer(copy=False)
        lsa = make_pipeline(svd, normalizer)
        X = lsa.fit_transform(X)

        birch = Birch(threshold=self.birch_threshold,
                      branching_factor=self.birch_branching_factor,
                      n_clusters=self.birch_clusters_count)

        predict_result = birch.fit_predict(X)
        self.signals.PrintInfo.emit('\n??????? ?? ??????????:\n')

        clasters_output = ''
        for claster_index in range(max(predict_result) + 1):
            clasters_output += ('??????? ' + str(claster_index) + ':\n')
            for predict, document in zip(predict_result, short_filenames):
                if predict == claster_index:
                    clasters_output += ('  ' + str(document) + '\n')
            clasters_output += '\n'
        self.signals.PrintInfo.emit(clasters_output)
        self.signals.PrintInfo.emit('????????? ?:' + str(output_dir + 'clusters.txt'))
        writeStringToFile(clasters_output, output_dir + 'clusters.txt')

        self.draw_clusters_plot(X, predict_result, short_filenames)

def birchclustering(datalist):
    brc = Birch(branching_factor=50, n_clusters=None, threshold=0.17,compute_labels=True)
    brc.fit(datalist)
    return brc
    #print brc.predict(datalist)

def get_subtrees_sklearn(d, bin_chr, bin_position, method="ward", nchrom=1000, distfrac=0.4):

    names = get_names(bin_chr, bin_position)
    #ap = Birch(n_clusters=15)#damping=0.5, max_iter=200, convergence_iter=15, affinity='euclidean') #euclidean precomputed
    ap = KMeans(n_clusters=10)
    assignements = ap.fit_predict(d)#; print assignements[:10]
    c = Counter(assignements); print c.most_common(5)
    subtrees = [[] for i in range(max(assignements)+1)]; print len(subtrees), max(assignements)
    for chrom, i in zip(names, assignements):
        subtrees[i].append(chrom)
    return subtrees