def remove_orphans(cc): ## cc - current clusters
initial_clusters = find_initial_clusters_and_their_info_from_table2()
current_clusters = cc #list os sets
import prog4
profile_freq = prog4.get_profile_freq()
profile_pair_freq = prog4.get_profile_pair_freq()
covered_clusters = []
for i_c in initial_clusters:
best_MI = -100
best_final_cluster = set()
for c in current_clusters:
MI = prog4.calc_MI_fast(
set(i_c.split(",")), c, profile_pair_freq, profile_freq
) # calculate MI between initial profile combination (i_c) and each of the current combinations (c)
if MI > best_MI:
best_MI = MI
best_final_cluster = c
best_final_cluster = sorted(list(best_final_cluster))
covered_clusters.append(best_final_cluster)
#now we have to remove duplicates and transform a list of lists into a list of sets
s = []
new_list = []
for i in covered_clusters:
if i not in s:
s.append(i)
new_list.append(set(i))
return new_list
input:
no input, but program prog4.py shoul be run first
output:
n/MI_matrix.csv - MI matrix of step n (before combining two clusters)
n/clusters.csv - current set of clusters of step n (before combining two clusters)
tree.csv - each line in this file corresponds to two clusters that are going to be combined and MI between them
"""
import os
import math
import prog4
import common
WORK_DIR = common.WORK_DIR
profile_freq = prog4.get_profile_freq()
profile_pair_freq = prog4.get_profile_pair_freq()
clusters = prog4.get_clusters()
def calc_MI_matrix():
matrix = {}
for i, c1 in enumerate(clusters):
for j, c2 in enumerate(clusters):
if j >= i: continue
matrix[(i, j)] = round(
prog4.calc_MI_fast(c1, c2, profile_pair_freq, profile_freq), 4)
return matrix
def create_MI_file_for_this_step():
if not os.path.exists(WORK_DIR + str(step)):