Question

我构建了三个嵌套字典来分析我的大数据。我尝试对其中的值进行分析以绘制散点图，因此我创建了一个列表以将数据附加到它们上，然后通过matplotlib制作散点图。我的问题是尝试附加时出现错误！ TypeError：无法散列的类型：“列表”。所以我困惑于更改字典的结构，或者有可能通过我创建的字典来处理它。

我的字典结构分别是：

data_geo1：

'ENSG00000268358': {'Sample_19-leish_023_v2': 0, 'Sample_4-leish_012_v3': 0, 'Sample_25-leish027_v2': 0, 'Sample_6-leish_015_v3': 0, 'Sample_23-leish026_v2': 1, 'Sample_20-leish_023_v3': 0, 'Sample_18-leish_022_v3': 0, 'Sample_10-leish_017_v3': 0, 'Sample_13-leish_019_v2': 0, 'Sample_1-Leish_011_v2': 0, 'Sample_11-leish_018_v2': 0, 'Sample_3-leish_012_v2': 0, 'Sample_2-leish_011_v3': 0, 'Sample_29-leish032_v2': 0, 'Sample_8-leish_016_v3': 0, 'Sample_28-leish028_v3': 0, 'Sample_27-leish028_v2': 1, 'Sample_26-leish027_v3': 0, 'Sample_12-leish_018_v3': 0, 'Sample_5-leish_015_v2': 0, 'Sample_16-leish_021_v3': 0, 'Sample_21-leish_024_v2': 0, 'Sample_9-leish_017_v2': 0, 'Sample_24-leish026_v3': 1, 'Sample_22-leish_024_v3': 0, 'Sample_14-leish_019_v3': 0, 'Sample_30-leish032_v3': 0, 'Sample_7-leish_016_v2': 0, 'Sample_15-leish_021_v2': 0, 'Sample_17-leish_022_v2': 1}

data_ali：

{'ENSG00000268358': {'Sample_19-leish_023_v2': 0, 'Sample_16-leish_021_v3': 2, 'Sample_20': 0, 'Sample_24-leish026_v3': 1, 'Sample_6-leish_015_v3': 0, 'Sample_12-leish_018_v3': 0, 'Sample_22-leish_024_v3': 0, 'Sample_23-leish026_v2': 2, 'Sample_25-leish027_v2': 0, 'Sample_18-leish_022_v3': 1, 'Sample_14': 0, 'Sample_2-leish_011_v3': 0, 'Sample_13-leish_019_v2': 0, 'Sample_1-Leish_011_v2': 0, 'Sample_11-leish_018_v2': 0, 'Sample_20-leish_023_v3': 0, 'Sample_3-leish_012_v2': 0, 'Sample_10-leish_017_v3': 1, 'Sample_7': 0, 'Sample_29-leish032_v2': 1, 'Sample_8-leish_016_v3': 0, 'Sample_6': 0, 'Sample_7-leish_016_v2': 0, 'Sample_9': 0, 'Sample_8': 0, 'Sample_27-leish028_v2': 0, 'Sample_26-leish027_v3': 0, 'Sample_5': 1, 'Sample_4': 0, 'Sample_3': 0, 'Sample_19': 0, 'Sample_1': 0, 'Sample_2': 0, 'Sample_9-leish_017_v2': 0, 'Sample_5-leish_015_v2': 0, 'Sample_4-leish_012_v3': 0, 'Sample_21-leish_024_v2': 0, 'Sample_18': 0, 'Sample_13': 0, 'Sample_12': 0, 'Sample_11': 0, 'Sample_10': 1, 'Sample_17': 0, 'Sample_16': 0, 'Sample_15': 1, 'Sample_14-leish_019_v3': 0, 'Sample_30-leish032_v3': 0, 'Sample_28-leish028_v3': 1, 'Sample_15-leish_021_v2': 0, 'Sample_17-leish_022_v2': 0}

这是我从头开始的所有代码结构，正如您在最后一行看到的那样，我尝试创建列表并将我的值附加到列表中，但我无法成功。

import os
import numpy as np
import matplotlib.pyplot as plt

path = "/home/ali/Desktop/data/"
root = "/home/ali/Desktop/SAMPLES/"



data_geo1={}
with open(path+"GSE98212_H_DE_genes_count.txt","rt") as fin: #data for sample 1-30
    h = fin.readline()
    sample1 = h.split()
    sample_names = [s.strip('"') for s in sample1[1:31]]
    for l in fin.readlines():
        l = l.strip().split()
        if l:
            gene1= l[0].strip('"')
            data_geo1[gene1] = {}
            for i, x in enumerate(l[1:31]):
                data_geo1[gene1][sample_names[i]] = int(x)

#print(data_geo1)

data_geo2={}
with open (path+"GSE98212_L_DE_genes_count.txt","rt") as fin:
    h= fin.readline()
    sample2=h.split()
    sample_names=sample2[1:21]
    for l in fin.readlines():
        l = l.strip().split()
        if l:
            gene2= l[0].strip()
            data_geo2[gene2]={}
            for i,x in enumerate (l[1:21]):
                data_geo2[gene2][sample_names[i]]= int(x)
#print(data_geo2)

data_ali={}

for sample_name in os.listdir(root):
    with open(os.path.join(root, sample_name, "counts.txt"), "r") as fin:
        for line in fin.readlines():
            gene, reads = line.split()
            reads = int(reads)
            if gene.startswith('ENSG'):
                data_ali.setdefault(gene, {})[sample_name] = reads
        gene = l[0].strip()
#print(data_ali)

list_samples= data_ali[gene].keys()
#print(list_samples)
for sample in list_samples:
    reads_data_ali = []
    for gene in data_ali.keys():
        reads_data_ali.append(data_ali[gene][sample_name])

我希望输出如下：

[[0, 0], [0, 2], [11, 12], [4, 4], [18, 17], [2, 2], [381, 383], [1019, 1020], [198, 194], [66, 65], [2223, 2230], [30, 30], [0, 0], [33, 34], [0, 0], [411, 409], [804, 803], [11829, 7286], [137, 139], [277, 278], [3475, 3482], [5, 5], [2, 1], [70, 70], [48, 48], [234, 232], [121, 120], [928, 925], [220, 159], [165, 165], [702, 700], [1645, 1643], [79, 78], [1064, 1067], [971, 972], [0, 0]]

Answer 1

您可以通过在.append（...）之前检查字典中是否存在键来尝试避免键错误。尝试查看字典.get（）方法。对于防止此类错误很有用。

Answer 2

关于您的描述，我想您的使data_ali和data_geo1的字典获得正确输出的代码，因此问题可能出在创建列表的最后一个代码中。我发现两个问题： 1 for gene in data_ali.keys():，在以下循环reads_data_geo1.append(data_geo1[gene1][sample_names])中，这里是[gene1] 2 for sample in list_samples:，所以也许您应该使用reads_data_ali.append(data_ali[gene][sample]) 您可以修改这些变量的名称，然后查看其是否有效。

如何将嵌套字典中的键和值附加到列表

2 个答案: