CImageProcessor/generate_number_dictionary.py at master · chiellini/CImageProcessor · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
'''
This llibrary defines all structures that will be used in the shape analysis
'''

import os
import glob
import pandas as pd
from treelib import Tree

from utils.data_structure import read_cd_file

def add_number_dict(nucleus_file, max_time):
    '''
    Construct cell tree structure with cell names
    :param nucleus_file:  the name list file to the tree initilization
    :param max_time: the maximum time point to be considered
    :return cell_tree: cell tree structure where each time corresponds to one cell (with specific name)
    '''

    ##  Construct cell
    #  Add unregulized naming
    cell_tree = Tree()
    cell_tree.create_node('P0', 'P0')
    cell_tree.create_node('AB', 'AB', parent='P0')
    cell_tree.create_node('P1', 'P1', parent='P0')
    cell_tree.create_node('EMS', 'EMS', parent='P1')
    cell_tree.create_node('P2', 'P2', parent='P1')
    cell_tree.create_node('P3', 'P3', parent='P2')
    cell_tree.create_node('C', 'C', parent='P2')
    cell_tree.create_node('P4', 'P4', parent='P3')
    cell_tree.create_node('D', 'D', parent='P3')
    cell_tree.create_node('Z2', 'Z2', parent='P4')
    cell_tree.create_node('Z3', 'Z3', parent='P4')

    # EMS
    cell_tree.create_node('E', 'E', parent='EMS')
    cell_tree.create_node('MS', 'MS', parent='EMS')

    # Read the name excel and construct the tree with complete segCell
    df_time = read_cd_file(nuc_file)

    # read and combine all names from different acetrees
    ## Get cell number
    try:
        label_name_dict = pd.read_csv(r'necessary_files/name_dictionary_cmap.csv', index_col=0).to_dict()['0']
        name_label_dict = {value: key for key, value in label_name_dict.items()}

    except:
        name_label_dict = {}

    # =====================================
    # dynamic update the name dictionary
    # =====================================
    cell_in_dictionary = list(name_label_dict.keys())

    ace_pd = read_cd_file(os.path.join(nucleus_file))

    ace_pd = ace_pd[ace_pd.time <= max_time]
    cell_list = list(ace_pd.cell.unique())
    print(len(cell_in_dictionary) , len(cell_list))
    add_cell_list = list(set(cell_list) - set(cell_in_dictionary))
    add_cell_list.sort()
    print(add_cell_list)

    if len(add_cell_list) > 0:
        print("Name dictionary updated !!!")
        add_number_dictionary = dict(zip(add_cell_list, range(len(cell_in_dictionary) + 1, len(cell_in_dictionary) + len(add_cell_list) + 1)))
        # --------save name_label_dict csv-------------
        name_label_dict.update(add_number_dictionary)
        pd_number_dictionary = pd.DataFrame.from_dict(name_label_dict, orient="index")
        print(pd_number_dictionary)
        pd_number_dictionary.to_csv('./necessary_files/number_dictionary.csv')

        # -----------save label_name_dict csv
        label_name_dict_saving={value: key for key, value in name_label_dict.items()}
        pd_name_dictionary = pd.DataFrame.from_dict(label_name_dict_saving, orient="index")
        print(pd_name_dictionary)
        pd_name_dictionary.to_csv('./necessary_files/name_dictionary.csv')


class cell_node(object):
    # Node Data in cell tree
    def __init__(self):
        self.number = 0
        self.time = 0

    def set_number(self, number):
        self.number = number

    def get_number(self):

        return self.number

    def set_time(self, time):
        self.time = time

    def get_time(self):

        return self.time


if __name__ == "__main__":

    CD_folder = r"./necessary_files/CD_files"
    nuc_files = sorted(glob.glob(os.path.join(CD_folder, "*.csv")))

    for idx, nuc_file in enumerate(nuc_files):
        add_number_dict(nuc_file, max_time=1000)