def write_distance_matrix_to_csv(): postgres_handle = PostgresHandle(smarttypes.connection_string) network = load_network_from_the_db(postgres_handle, 5) landmarks = get_landmarks(network) similarity_matrix = mk_similarity_matrix(network, landmarks) distance_matrix = dist_euclidean(similarity_matrix) write_similarity_matrix_to_csv(distance_matrix)
def test_metaNMDS(self):
"""l19 data should give stress below .13"""
ptmtx = array(
[
[7, 1, 0, 0, 0, 0, 0, 0, 0],
[4, 2, 0, 0, 0, 1, 0, 0, 0],
[2, 4, 0, 0, 0, 1, 0, 0, 0],
[1, 7, 0, 0, 0, 0, 0, 0, 0],
[0, 8, 0, 0, 0, 0, 0, 0, 0],
[0, 7, 1, 0, 0, 0, 0, 0, 0], #idx 5
[0, 4, 2, 0, 0, 0, 2, 0, 0],
[0, 2, 4, 0, 0, 0, 1, 0, 0],
[0, 1, 7, 0, 0, 0, 0, 0, 0],
[0, 0, 8, 0, 0, 0, 0, 0, 0],
[0, 0, 7, 1, 0, 0, 0, 0, 0], #idx 10
[0, 0, 4, 2, 0, 0, 0, 3, 0],
[0, 0, 2, 4, 0, 0, 0, 1, 0],
[0, 0, 1, 7, 0, 0, 0, 0, 0],
[0, 0, 0, 8, 0, 0, 0, 0, 0],
[0, 0, 0, 7, 1, 0, 0, 0, 0], #idx 15
[0, 0, 0, 4, 2, 0, 0, 0, 4],
[0, 0, 0, 2, 4, 0, 0, 0, 1],
[0, 0, 0, 1, 7, 0, 0, 0, 0]
],
'float')
distmtx = dist_euclidean(ptmtx)
nm = metaNMDS(1, distmtx, verbosity=0)
self.assertLessThan(nm.getStress(), .13)
def write_distance_matrix_to_csv():
postgres_handle = PostgresHandle(smarttypes.connection_string)
network = load_network_from_the_db(postgres_handle, 5)
landmarks = get_landmarks(network)
similarity_matrix = mk_similarity_matrix(network, landmarks)
distance_matrix = dist_euclidean(similarity_matrix)
write_similarity_matrix_to_csv(distance_matrix)
def test_metaNMDS(self):
"""l19 data should give stress below .13"""
ptmtx = array(
[[7,1,0,0,0,0,0,0,0],
[4,2,0,0,0,1,0,0,0],
[2,4,0,0,0,1,0,0,0],
[1,7,0,0,0,0,0,0,0],
[0,8,0,0,0,0,0,0,0],
[0,7,1,0,0,0,0,0,0],#idx 5
[0,4,2,0,0,0,2,0,0],
[0,2,4,0,0,0,1,0,0],
[0,1,7,0,0,0,0,0,0],
[0,0,8,0,0,0,0,0,0],
[0,0,7,1,0,0,0,0,0],#idx 10
[0,0,4,2,0,0,0,3,0],
[0,0,2,4,0,0,0,1,0],
[0,0,1,7,0,0,0,0,0],
[0,0,0,8,0,0,0,0,0],
[0,0,0,7,1,0,0,0,0],#idx 15
[0,0,0,4,2,0,0,0,4],
[0,0,0,2,4,0,0,0,1],
[0,0,0,1,7,0,0,0,0]], 'float')
distmtx = dist_euclidean(ptmtx)
nm = metaNMDS(1, distmtx, verbosity=0)
self.assertLessThan(nm.getStress(), .13)
def test_3(self):
"""l19 data should give stress below .13 in multi-D"""
ptmtx = array(
[[7,1,0,0,0,0,0,0,0],
[4,2,0,0,0,1,0,0,0],
[2,4,0,0,0,1,0,0,0],
[1,7,0,0,0,0,0,0,0],
[0,8,0,0,0,0,0,0,0],
[0,7,1,0,0,0,0,0,0],#idx 5
[0,4,2,0,0,0,2,0,0],
[0,2,4,0,0,0,1,0,0],
[0,1,7,0,0,0,0,0,0],
[0,0,8,0,0,0,0,0,0],
[0,0,7,1,0,0,0,0,0],#idx 10
[0,0,4,2,0,0,0,3,0],
[0,0,2,4,0,0,0,1,0],
[0,0,1,7,0,0,0,0,0],
[0,0,0,8,0,0,0,0,0],
[0,0,0,7,1,0,0,0,0],#idx 15
[0,0,0,4,2,0,0,0,4],
[0,0,0,2,4,0,0,0,1],
[0,0,0,1,7,0,0,0,0]], 'float')
distmtx = dist_euclidean(ptmtx)
for dim in range(3,18):
nm = NMDS(distmtx, verbosity=0, dimension=dim)
self.assertLessThan(nm.getStress(), .13)
def test_3(self):
"""l19 data should give stress below .13 in multi-D"""
ptmtx = array(
[
[7, 1, 0, 0, 0, 0, 0, 0, 0],
[4, 2, 0, 0, 0, 1, 0, 0, 0],
[2, 4, 0, 0, 0, 1, 0, 0, 0],
[1, 7, 0, 0, 0, 0, 0, 0, 0],
[0, 8, 0, 0, 0, 0, 0, 0, 0],
[0, 7, 1, 0, 0, 0, 0, 0, 0], #idx 5
[0, 4, 2, 0, 0, 0, 2, 0, 0],
[0, 2, 4, 0, 0, 0, 1, 0, 0],
[0, 1, 7, 0, 0, 0, 0, 0, 0],
[0, 0, 8, 0, 0, 0, 0, 0, 0],
[0, 0, 7, 1, 0, 0, 0, 0, 0], #idx 10
[0, 0, 4, 2, 0, 0, 0, 3, 0],
[0, 0, 2, 4, 0, 0, 0, 1, 0],
[0, 0, 1, 7, 0, 0, 0, 0, 0],
[0, 0, 0, 8, 0, 0, 0, 0, 0],
[0, 0, 0, 7, 1, 0, 0, 0, 0], #idx 15
[0, 0, 0, 4, 2, 0, 0, 0, 4],
[0, 0, 0, 2, 4, 0, 0, 0, 1],
[0, 0, 0, 1, 7, 0, 0, 0, 0]
],
'float')
distmtx = dist_euclidean(ptmtx)
for dim in range(3, 18):
nm = NMDS(distmtx, verbosity=0, dimension=dim)
self.assertLessThan(nm.getStress(), .13)
def distance(args):
json_data = open(args.matrix_file)
data = json.load(json_data)
json_data.close()
datasets = []
for i in data['columns']:
#print i['id']
datasets.append(i['id'])
z = np.array(data['data'])
dm = np.transpose(z)
if args.metric == 'bray_curtis':
distance_matrix = dt.dist_bray_curtis(dm)
elif args.metric == 'morisita_horn':
distance_matrix = dt.dist_morisita_horn(dm)
elif args.metric == 'canberra':
distance_matrix = dt.dist_canberra(dm)
elif args.metric == 'chisq':
distance_matrix = dt.dist_chisq(dm)
elif args.metric == 'chord':
distance_matrix = dt.dist_chord(dm)
elif args.metric == 'euclidean':
distance_matrix = dt.dist_euclidean(dm)
elif args.metric == 'gower':
distance_matrix = dt.dist_gower(dm)
elif args.metric == 'hellinger':
distance_matrix = dt.dist_hellinger(dm)
elif args.metric == 'kulczynski':
distance_matrix = dt.dist_kulczynski(dm)
elif args.metric == 'manhattan':
distance_matrix = dt.dist_manhattan(dm)
elif args.metric == 'abund_jaccard':
distance_matrix = dt.dist_abund_jaccard(dm)
elif args.metric == 'binary_jaccard':
distance_matrix = dt.binary_dist_jaccard(dm)
elif args.metric == 'pearson':
distance_matrix = dt.dist_pearson(dm)
elif args.metric == 'soergel':
distance_matrix = dt.dist_soergel(dm)
elif args.metric == 'spearman':
distance_matrix = dt.dist_spearman_approx(dm)
else: # default
distance_matrix = dt.dist_bray_curtis(dm)
dist = {}
for i,x in enumerate(distance_matrix):
for n,d in enumerate(distance_matrix[i]):
if i < n: # only needs one copy
dist[ (datasets[i],datasets[n]) ] = d
#np.savetxt(os.path.join(args.output_dir, args.file_prefix+'_distance.mtx'), distance_matrix)
if args.to_output == 'distance':
print(distance_matrix)
return dist
def distance(args):
json_data = open(args.matrix_file)
data = json.load(json_data)
json_data.close()
datasets = []
for i in data['columns']:
#print i['id']
datasets.append(i['id'])
z = np.array(data['data'])
dm = np.transpose(z)
if args.metric == 'bray_curtis':
distance_matrix = dt.dist_bray_curtis(dm)
elif args.metric == 'morisita_horn':
distance_matrix = dt.dist_morisita_horn(dm)
elif args.metric == 'canberra':
distance_matrix = dt.dist_canberra(dm)
elif args.metric == 'chisq':
distance_matrix = dt.dist_chisq(dm)
elif args.metric == 'chord':
distance_matrix = dt.dist_chord(dm)
elif args.metric == 'euclidean':
distance_matrix = dt.dist_euclidean(dm)
elif args.metric == 'gower':
distance_matrix = dt.dist_gower(dm)
elif args.metric == 'hellinger':
distance_matrix = dt.dist_hellinger(dm)
elif args.metric == 'kulczynski':
distance_matrix = dt.dist_kulczynski(dm)
elif args.metric == 'manhattan':
distance_matrix = dt.dist_manhattan(dm)
elif args.metric == 'abund_jaccard':
distance_matrix = dt.dist_abund_jaccard(dm)
elif args.metric == 'binary_jaccard':
distance_matrix = dt.binary_dist_jaccard(dm)
elif args.metric == 'pearson':
distance_matrix = dt.dist_pearson(dm)
elif args.metric == 'soergel':
distance_matrix = dt.dist_soergel(dm)
elif args.metric == 'spearman':
distance_matrix = dt.dist_spearman_approx(dm)
else: # default
distance_matrix = dt.dist_bray_curtis(dm)
dist = {}
for i, x in enumerate(distance_matrix):
for n, d in enumerate(distance_matrix[i]):
if i < n: # only needs one copy
dist[(datasets[i], datasets[n])] = d
#np.savetxt(os.path.join(args.output_dir, args.file_prefix+'_distance.mtx'), distance_matrix)
if args.to_output == 'distance':
print(distance_matrix)
return dist
def calculate_distance(args):
if args.file_format == 'json':
try:
json_data = open('./tmp/'+args.in_file)
except IOError:
json_data = open(args.in_file)
except:
print("NO FILE FOUND ERROR")
sys.exit()
data = json.load(json_data)
json_data.close()
else: # csv file
# this doesn't work now
with open('./tmp/'+args.in_file, 'rb') as csvfile:
csv_data = csv.reader(csvfile, delimiter=',', quotechar='"')
for row in csv_data:
pass
datasets = []
for i in data['columns']:
datasets.append(i['name'])
z = np.array(data['data'])
dm = np.transpose(z)
if args.metric == 'bray_curtis':
dist = dt.dist_bray_curtis(dm)
elif args.metric == 'morisita_horn':
dist = dt.dist_morisita_horn(dm)
elif args.metric == 'canberra':
dist = dt.dist_canberra(dm)
elif args.metric == 'chisq':
dist = dt.dist_chisq(dm)
elif args.metric == 'chord':
dist = dt.dist_chord(dm)
elif args.metric == 'euclidean':
dist = dt.dist_euclidean(dm)
elif args.metric == 'gower':
dist = dt.dist_gower(dm)
elif args.metric == 'hellinger':
dist = dt.dist_hellinger(dm)
elif args.metric == 'kulczynski':
dist = dt.dist_kulczynski(dm)
elif args.metric == 'manhattan':
dist = dt.dist_manhattan(dm)
elif args.metric == 'abund_jaccard':
dist = dt.dist_abund_jaccard(dm)
elif args.metric == 'binary_jaccard':
dist = dt.binary_dist_jaccard(dm)
elif args.metric == 'pearson':
dist = dt.dist_pearson(dm)
elif args.metric == 'soergel':
dist = dt.dist_soergel(dm)
elif args.metric == 'spearman':
dist = dt.dist_spearman_approx(dm)
else: # default
dist = dt.dist_bray_curtis(dm)
distance_matrix1 = {}
distance_matrix2 = {}
mat = []
out_fp = open(args.out_file,'w')
file_header_line = ','.join([x['name'] for x in data['columns']]) + '\n'
out_fp.write(file_header_line)
for row,line in enumerate(data['columns']):
name = line['name']
distance_matrix1[name] = {}
file_data_line = name+','
for col,d in enumerate(dist[row]):
file_data_line += str(dist[row][col])+','
distance_matrix1[name][data['columns'][col]['name']] = dist[row][col]
distance_matrix2[(name, data['columns'][col]['name'])] = dist[row][col]
file_data_line = file_data_line[:-1]+'\n'
out_fp.write(file_data_line)
out_fp.close()
#if args.function == 'distance' or args.function == 'heatmap':
print(json.dumps(distance_matrix1))
arr = []
for ds1 in distance_matrix1:
print(ds1)
tmp = []
for ds2 in distance_matrix1[ds1]:
val = distance_matrix1[ds1][ds2]
tmp.append(val)
arr.append(tmp)
#np.array(arr)
linkage_matrix = linkage(arr, "single")
dendrogram(linkage_matrix, color_threshold=1, show_leaf_counts=True)
#image_file = '/Users/avoorhis/node_projects/vamps-node.js/public/tmp_images/'+args.prefix+'.png'
image_file = 'public/tmp_images/'+args.prefix+'.png'
plt.savefig(image_file)
