def main(name_label_list, feature_file, image_name):
print('Ploting dendroheatmap...')
# read in names and labels
names = [i[0] for i in parse_listfile(name_label_list, [1, 2])]
labels = [i[1] for i in parse_listfile(name_label_list, [1, 2])]
# read in features
data = np.load(feature_file)
# cluster the rows
row_dist = ssd.squareform(ssd.pdist(data, 'cosine'))
row_Z = sch.linkage(row_dist)
row_idxing = sch.leaves_list(row_Z)
row_labels = ['%s.%s' % (labels[i], names[i]) for i in row_idxing]
# cluster the columns
col_dist = ssd.squareform(ssd.pdist(data.T, 'cosine'))
col_Z = sch.linkage(col_dist)
col_idxing = sch.leaves_list(col_Z)
# make the dendrogram
data = data[:, col_idxing][row_idxing, :]
#heatmap = pdh.DendroHeatMap(heat_map_data=data, left_dendrogram=row_Z, top_dendrogram=col_Z)
heatmap = pdh.DendroHeatMap(heat_map_data=data, left_dendrogram=row_Z)
heatmap.row_labels = row_labels
heatmap.title = 'Feature dendroheatmap'
heatmap.export(image_name)
def plot(self, s_imgfile, colormap=None, row_labels_size=0, col_labels_size=14, l_pdf=False, l_normalize_for_color=True, l_legend_pvalue=False):
import pydendroheatmap as pdh
heatmap=pdh.DendroHeatMap(heat_map_data=self.data, row_labels=self.S_description, col_labels=self.S_col, left_dendrogram=self.Zr, top_dendrogram=self.Zc, row_labels_size=row_labels_size, col_labels_size=col_labels_size, l_normalize_for_color=l_normalize_for_color, l_legend_pvalue=l_legend_pvalue)
if colormap is None:
heatmap.colormap=heatmap.color_brewer(brewer_name='Oranges', map_type='sequential', number=3, reverse=False)
else:
heatmap.colormap=colormap
heatmap.export(s_imgfile, l_pdf)
def run():
counts = 'phage_kmer_count_k4_c0_s2255.csv'
headers = 'phage_kmer_headers_k4_c0_s2255.txt'
data = normalize_rows(np.loadtxt(counts, delimiter=','))
row_labels = np.array([header.split('|')[3] for header in open(headers, 'r').readlines()[1:]])
col_labels = np.array(kmers(4))
N = 50
data = data[:N,:N]
row_labels = row_labels[:N]
col_labels = col_labels[:N]
# cluster the rows
row_dist = ssd.squareform(ssd.pdist(data))
row_Z = sch.linkage(row_dist)
row_idxing = sch.leaves_list(row_Z)
#cluster the columns
col_dist = ssd.squareform(ssd.pdist(data.T))
col_Z = sch.linkage(col_dist)
col_idxing = sch.leaves_list(col_Z)
#make the dendrogram
data = data[:,col_idxing][row_idxing,:]
row_labels = list(row_labels[np.array(row_idxing)])
col_labels = list(col_labels[np.array(col_idxing)])
heatmap = pdh.DendroHeatMap(heat_map_data=data, left_dendrogram=row_Z, top_dendrogram=col_Z)
heatmap.colormap = heatmap.redBlackBlue
heatmap.row_labels = row_labels
heatmap.col_labels = col_labels
heatmap.title = 'Bacteirophage 4-mer hierarchical clustering'
heatmap.export('phage_heatmap.png')
heatmap.show()
## clustering genes (rows) diss_genes = diss_genes(M,-1) z_genes = create_linkage(diss_genes,'single') idx_genes = create_leaves_list(z_genes) ## sorting matrix and labels M = M[idx_genes,:] M = M[:,idx_cells] hclust_cells = [labels_cells[int(i)] for i in idx_cells] hclust_genes = [labels_genes[int(i)] for i in idx_genes] ## plotting heatmap #bash command: pip install pydendroheatmap import pydendroheatmap as pdh heatmap = pdh.DendroHeatMap(heat_map_data=M.toarray(), left_dendrogram=z_genes, top_dendrogram=z_cells) heatmap.colormap = heatmap.yellowBlackBlue heatmap.row_labels = hclust_genes heatmap.show() ## Matlab can plot large heatmaps better than any other program. ## I strongly advise to load the clustered matrix in Matlab ## and use imagesc() to visualize the results. Students can download ## Matlab for free from the access.caltech.edu website. save_matrix(M,'clustered.mtx')
def HC(domain, para):
if para in Metric:
if para == 'TF':
if domain == 'DietItem':
X = dataGen4DietAct.genDietItemTFArray()
elif domain == 'ActItem':
X = dataGen4DietAct.genActItemTFArray()
elif domain == 'DietType':
X = dataGen4DietAct.genDietTypeTFArray()
elif domain == 'ActType':
X = dataGen4DietAct.genActTypeTFArray()
elif para == 'TFIDF':
if domain == 'DietItem':
X = dataGen4DietAct.DietItemTfidfArray()
elif domain == 'ActItem':
X = dataGen4DietAct.ActItemTfidfArray()
elif domain == 'DietType':
X = dataGen4DietAct.DietTypeTfidfArray()
elif domain == 'ActType':
X = dataGen4DietAct.ActTypeTfidfArray()
X = utilise.normArray(X)
if para in Sim:
Similarity_dict = {}
if domain == 'DietItem':
Similarity_dict = utilise.SimilarityDict(domain, para)
elif domain == 'ActItem':
Similarity_dict = utilise.SimilarityDict(domain, para)
elif domain == 'DietType':
Similarity_dict = utilise.SimilarityDict(domain, para)
elif domain == 'ActType':
Similarity_dict = utilise.SimilarityDict(domain, para)
X = visSimilarityMat.similarityDict2array(Similarity_dict, 0)
# method can be ward, complete, average
method = 'ward'
row_method = method
row_metric = 'euclidean'
column_method = method
column_metric = 'euclidean'
# http://docs.scipy.org/doc/scipy-0.16.0/reference/generated/scipy.spatial.distance.pdist.html
# d1 = ssd.pdist(X,'cosine')
d1 = ssd.pdist(X)
# http://docs.scipy.org/doc/scipy-0.16.0/reference/generated/scipy.spatial.distance.squareform.html#scipy.spatial.distance.squareform
D1 = ssd.squareform(d1) # full matrix
# http://docs.scipy.org/doc/scipy/reference/generated/scipy.cluster.hierarchy.linkage.html#scipy.cluster.hierarchy.linkage
Y1 = sch.linkage(D1, method=row_method, metric=row_metric)
row_idxing = sch.leaves_list(Y1)
# http://docs.scipy.org/doc/scipy-0.16.0/reference/generated/scipy.spatial.distance.pdist.html
d2 = ssd.pdist(X.T)
# http://docs.scipy.org/doc/scipy-0.16.0/reference/generated/scipy.spatial.distance.squareform.html#scipy.spatial.distance.squareform
D2 = ssd.squareform(d2)
# http://docs.scipy.org/doc/scipy/reference/generated/scipy.cluster.hierarchy.linkage.html#scipy.cluster.hierarchy.linkage
Y2 = sch.linkage(D2, method=column_method, metric=column_metric)
col_idxing = sch.leaves_list(Y2)
heatmap_array = X[:, col_idxing][
row_idxing, :] #a numpy.ndarray or numpy.matrix, for this example, let's say mxn array
top_dendrogram = Y2 #a (n-1) x 4 array
side_dendrogram = Y1 #a (m-1) x 4 array
row_labels = range(X.shape[0])
if para in Sim:
col_labels = range(X.shape[1])
if para in Metric:
if domain == 'DietItem':
col_labels = utilise.itemDict2list(
dataGen4DietAct.genDietItemDict())
elif domain == 'ActItem':
col_labels = utilise.itemDict2list(
dataGen4DietAct.genActItemDict())
elif domain == 'DietType':
col_labels = utilise.itemDict2list(
dataGen4DietAct.genDietTypeDict())
elif domain == 'ActType':
col_labels = utilise.itemDict2list(
dataGen4DietAct.genActTypeDict())
col_idxing = list(col_idxing)
row_idxing = list(row_idxing)
print col_idxing
new_row_labels = []
new_col_labels = []
for i in range(len(row_idxing)):
new_row_labels.append(str(row_labels[row_idxing[i]]))
for j in range(len(col_idxing)):
new_col_labels.append(str(col_labels[col_idxing[j]]))
heatmap = pdh.DendroHeatMap(heat_map_data=heatmap_array,
left_dendrogram=side_dendrogram,
top_dendrogram=top_dendrogram)
heatmap.title = 'HC_' + domain + '_' + para + '_' + method
heatmap.row_labels = new_row_labels
heatmap.col_labels = new_col_labels
# heatmap.show()
heatmap.export('VisClustering' + domain + 'Pattern/Hierarchy_' + para +
'_' + method + '.png')
def run():
print('Here is the source for this example: ')
print("""
import numpy as np
import pyDendroHeatMap as pdh
import scipy.cluster.hierarchy as sch
import scipy.spatial.distance as ssd
#make up some data
data = np.random.normal(scale = 50,size=(50,50))
data[0:25,0:25] += 75
data[25:,25:] = np.random.poisson(lam=50,size=data[25:,25:].shape)
#cluster the rows
row_dist = ssd.squareform(ssd.pdist(data))
row_Z = sch.linkage(row_dist)
row_idxing = sch.leaves_list(row_Z)
row_labels = 50 * ['blah']
#cluster the columns
col_dist = ssd.squareform(ssd.pdist(data.T))
col_Z = sch.linkage(col_dist)
col_idxing = sch.leaves_list(col_Z)
#make the dendrogram
col_labels = 50 * ['blah']
data = data[:,col_idxing][row_idxing,:]
heatmap = pdh.DendroHeatMap(heat_map_data=data, left_dendrogram=row_Z, top_dendrogram=col_Z)
heatmap.row_labels = row_labels
heatmap.col_labels = col_labels
heatmap.title = 'An example heatmap'
heatmap.show()
""")
#make up some data
data = np.random.normal(scale=50, size=(50, 50))
data[0:25, 0:25] += 75
data[25:, 25:] = np.random.poisson(lam=50, size=data[25:, 25:].shape)
#cluster the rows
row_dist = ssd.squareform(ssd.pdist(data))
row_Z = sch.linkage(row_dist)
row_idxing = sch.leaves_list(row_Z)
row_labels = 50 * ['blah']
#cluster the columns
col_dist = ssd.squareform(ssd.pdist(data.T))
col_Z = sch.linkage(col_dist)
col_idxing = sch.leaves_list(col_Z)
#make the dendrogram
col_labels = 50 * ['blah']
data = data[:, col_idxing][row_idxing, :]
heatmap = pdh.DendroHeatMap(heat_map_data=data,
left_dendrogram=row_Z,
top_dendrogram=col_Z)
heatmap.row_labels = row_labels
heatmap.col_labels = col_labels
heatmap.title = 'An example heatmap'
heatmap.show()