python数据可视化火山图

import numpy as np
import pandas as pd

data=pd.read_csv(r'E:\ZYH\R.project\rna-seq\lianxi1\exon_level\df.csv')

data.head()

# 3.尝试写循环筛选上下调基因分类赋值给 "up" 和 "down" 和 "nosig" 加入pvalue条件
###loc函数：通过行索引 "Index" 中的具体值来取行数据（如取"Index"为"A"的行）
data.loc[(data.log2FoldChange>1)&(data.padj<0.05),'type']='up'
data.loc[(data.log2FoldChange<-1)&(data.padj<0.05),'type']='down'
data.loc[(abs(data.log2FoldChange)<=1)|(data.padj>=0.05),'type']='nosig'

data.head()

data.type.value_counts()
up      123
down    103
Name: type, dtype: int64

import seaborn as sns
import math
import matplotlib.pyplot as plt
import matplotlib as mpl
%matplotlib inline
# 对padj取个-log10对数
data['-logpadj']=-data.padj.apply(math.log10)
# 查看
data[['log2FoldChange','padj','type','-logpadj']].head()

# 先设置一下自己的颜色
colors = ["#01c5c4","#ff414d", "#686d76"]
sns.set_palette(sns.color_palette(colors))
# 绘图
ax=sns.scatterplot(x='log2FoldChange', y='-logpadj',data=data,
                hue='type',#颜色映射
                edgecolor = None,#点边界颜色
                s=8,#点大小
                )
# 标签
ax.set_title("vocalno")
ax.set_xlabel("log2FC")
ax.set_ylabel("-log10(padj)")
#移动图例位置
ax.legend(loc='center right', bbox_to_anchor=(0.95,0.76), ncol=1)

fig = ax.get_figure()
fig.savefig('./python_vocalno.pdf')