from data_reader import DataReader
from co_graph import CoGraph
import numpy as np
import cluster_merge as cm
from log import output
import matplotlib.pyplot as plt
import scipy
from scipy.linalg import logm, expm
rd = DataReader()
rd.pre_process_cell(threshold=1850, original=True)
rd.pre_process_gene(threshold=2600, original=False)
genes = rd.get_gene_data()
collect = dict()
for x in range(len(genes)):
for y in range(x + 1, len(genes)):
X = genes[x]
Y = genes[y]
# matrix dimension
N = 15
matrix = [[0 for _ in range(N)] for _ in range(N)]
for k in range(len(X)):
xcord = X[k]
ycord = Y[k]
if xcord >= N or ycord >= N: continue
matrix[int(xcord)][int(ycord)] += 1
# for i in range(len(matrix[0])):
from data_reader import DataReader
from co_graph import CoGraph
import numpy as np
import cluster_merge as cm
from log import output
from scipy.stats import entropy
# preprocess data, tune threshold parameter to adjust data size
rd = DataReader()
rd.pre_process_cell(threshold=1850, original=True)
rd.pre_process_gene(threshold=2600, original=False)
# build graph by using hypergeometry test. then use jaccard to filter the
# graph. pass parameter to adjust graph.
g = CoGraph(rd.get_gene_data())
output('data shape after preprocessing ', g.data.shape)
g.build_graph(threshold=0.001, jaccard=True, jaccard_threshold=0.5)
# find community by louvain algorithm
g.find_partition()
# get gene clusters and merge gene in same clusters
cm = cm.Cluster(g.data, g.parts)
cm.merge()
# cell type clustering. build graph by using euclidean distance measurement
g2 = CoGraph(cm.parts)
output('data shape after gene clustering ', g2.data.shape)
g2.build_graph(threshold=1.0,
jaccard=True,
jaccard_threshold=0.8,
