python：一组元素在多个列表中的有无情况

安装依赖模块：pands

python3 -m pip install pandas

计算思路：
1 读取"一组元素"，读取"多个列表"的名字
2 构造"元素数*列表数"的数据框，分别取行名、列名
3 for循环readlines"多个列表"作为库，for读取各个元素判断"有/无"给表格赋值
4 to_csv保存表格到文本

df.iloc数字定位，df.loc文本定位

python3 代码：

import re,sys,os
import pandas as pd
import numpy as np
# 读取文件，去除换行符给新列表
with open("total/cgr2.total.uniq2uhgg", 'r') as list_genes:
    list_genes = list_genes.readlines()
    list_genes_enter = []
    for each in list_genes:
        list_genes_enter.append(each.strip())

with open("genome_cgr2.list", 'r') as list_genomes:
    list_genomes = list_genomes.readlines()
    list_genomes_enter = []
    for each in list_genomes:
        list_genomes_enter.append(each.strip())

# 重复命名不规范 
# TypeError: expected str, bytes or os.PathLike object, not list

# 构造数据框
num_row = len(list_genes_enter)
num_col = len(list_genomes_enter)
num_total = num_row * num_col
df = pd.DataFrame(np.arange(num_total).reshape((num_row, num_col)),
                  columns = list_genomes_enter,
                  index = list_genes_enter)

# 遍历所有基因集，遍历所有行名(基因)是否存在于各基因集(CGR2)，重新给表格赋值
for each_genome in list_genomes_enter:
    target_file = "Prokka/{}/{}.gene".format(each_genome, each_genome)
    # 读取基因集
    with open(target_file, 'r') as target:
        target_db = target.readlines()
        for each_gene in list_genes_enter:
            # 判断行名基因是否在基因集，并给表格元素赋值
            # loc: 字符定位表格元素
            # iloc: 数字定位
            if "{}\n".format(each_gene) in target_db:
                df.loc[each_gene, each_genome] = "yes"
            else:
                df.loc[each_gene, each_genome] = "no"
            print("\033[32m _____ {} DONE!\033[0m".format(each_gene))
    print("\033[32m {} DONE!\033[0m".format(each_genome))

# 表格保存
df.to_csv('cgr2_uniq_freq.txt', sep='\t', index = True)

把表格中的yes/no替换成1/0

绘制热图：

data = read.table("data.txt", header=T, row.names=1, sep="\t", check.names=F, na.string="", stringsAsFactors=F, quote="", comment.char="")

library(pheatmap)
pheatmap(data, cellheight=0.2, cellwidth=2, fontfamily="serif",
         colorRampPalette(c("snow", "red"))(2), 
         fontsize_row = 0.2, 
         fontsize_col=2, fontsize=2, legend=F,
         filename="out.pdf"
        )

pheatmap(tmp, filename="strain_number_star.png", cluster_row=F, cluster_col=F, cellheight=3, cellwidth=20, fontfamily="serif", annotation_row=group, colorRampPalette(c("snow", "red"))(50), display_numbers = mark, annotation_colors = colors, labels_row="142 Genera", fontsize_row=15, fontsize_col=15, fontsize=12, fontsize_number=4)