python交并补_交并补操作.py

import pandas as pd

import numpy as np

from matplotlib import pyplot as plt

from matplotlib_venn import venn2

&＃39;&＃39;&＃39;tt &＃61; pd.read_excel("E:/111.xlsx")

print(tt.isnull())

bb &＃61; tt.dropna()

print(bb)&＃39;&＃39;&＃39;

&＃39;&＃39;&＃39;a &＃61; pd.read_table("C:/Users/hasee/Desktop/生物信息/final/EP/0.txt")

b &＃61; a.loc[:, ["gene_name"]]

c &＃61; pd.read_table("C:/Users/hasee/Desktop/生物信息/final/EP/2.txt")

d &＃61; c.loc[:, ["gene_name"]]

result_inner &＃61; pd.merge(b,d,how&＃61;&＃39;inner&＃39;) #交集 is

result_outer &＃61; pd.merge(b,d,how&＃61;&＃39;outer&＃39;)

cs1 &＃61; b.append(d)

bsc &＃61; cs1.drop_duplicates()

cs2 &＃61; d.append(b)

dsc &＃61; cs2.drop_duplicates()

print(bsc)

print(dsc)

bsc.to_excel("C:/Users/hasee/Desktop/生物信息/final/work.xlsx",sheet_name&＃61; "1",index&＃61;False)&＃39;&＃39;&＃39;

for i in range(0,16):

a &＃61; pd.read_table("C:/Users/hasee/Desktop/生物信息/final/EP/"&＃43;str(i)&＃43;".txt")

b &＃61; a.loc[:, ["gene_name"]]

lista &＃61; b["gene_name"].values.tolist()

for t in range(0,16):

ts &＃61; "%t"

c &＃61; pd.read_table("C:/Users/hasee/Desktop/生物信息/final/ME/" &＃43; str(t) &＃43; ".txt")

d &＃61; c.loc[:, ["gene_name"]]

listd&＃61; d["gene_name"].values.tolist()

writer &＃61; pd.ExcelWriter("C://Users//hasee//Desktop//生物信息//final//work"&＃43;str(i)&＃43;str(t)&＃43;".xlsx")

intsec &＃61; pd.merge(b, d, how&＃61;&＃39;inner&＃39;) # intersection

intsec.to_excel(writer, sheet_name&＃61;"intsec(EP"&＃43;str(t)&＃43;"ME"&＃43;str(t), index&＃61;False)

us &＃61; pd.merge(b, d, how&＃61;&＃39;outer&＃39;)#union set

fa &＃61; us.append(d)

print(fa)

fa &＃61; fa.drop_duplicates(subset &＃61;["gene_name"],keep&＃61;False) # a supplementary set drop_duplicates(subset&＃61;[&＃39;name&＃39;, &＃39;age&＃39;, &＃39;sex&＃39;],keep&＃61;False

fb &＃61; us.append(b)

fb &＃61; fb.drop_duplicates(subset&＃61;["gene_name"], keep&＃61;False) # b supplementary set

fa.to_excel(writer, sheet_name&＃61;"supleEP("&＃43;str(t)&＃43;"ME"&＃43;str(t)&＃43;")", index&＃61;False)

fb.to_excel(writer, sheet_name&＃61;"supleME("&＃43;str(t)&＃43;"ME"&＃43;str(t)&＃43;")", index&＃61;False)

venn2(subsets &＃61; [set(lista),set(listd)],set_labels &＃61; ("EP","ME"),set_colors&＃61;("r","g"))

plt.savefig("C:/Users/hasee/Desktop/生物信息/final/"&＃43;str(i)&＃43;"&"&＃43;str(t)&＃43;".png")

plt.close()

writer.save()

writer.close()

print(i)

&＃39;&＃39;&＃39;for t in range(0,16):

c &＃61; pd.read_table("C:/Users/hasee/Desktop/生物信息/final/ME/" &＃43; t &＃43; ".txt")

d &＃61; c.loc[:, ["gene_name"]]

intsec &＃61; pd.merge(b, d, how&＃61;&＃39;inner&＃39;) # intersection

intsec.to_excel("C:/Users/hasee/Desktop/生物信息/final/work.xlsx", sheet_name&＃61;"1", index&＃61;1)

cs1 &＃61; b.append(d)

cs2 &＃61; d.append(b)

bsc &＃61; cs1.drop_duplicates() # a supplementary set

dsc &＃61; cs2.drop_duplicates() # b supplementary set

bsc.to_excel("C:/Users/hasee/Desktop/生物信息/final/work.xlsx", sheet_name&＃61;"1", index&＃61;2)

dsc.to_excel("C:/Users/hasee/Desktop/生物信息/final/work.xlsx", sheet_name&＃61;"1", index&＃61;1)

#数组里面&＃xff0c;要取出一个东西&＃xff0c;index,[]

#print()&＃39;&＃39;&＃39;

&＃39;&＃39;&＃39;df1 &＃61; pd.DataFrame([[&＃39;a&＃39;, 10, &＃39;男&＃39;],

[&＃39;b&＃39;, 11, &＃39;男&＃39;],

[&＃39;c&＃39;, 11, &＃39;女&＃39;],

[&＃39;a&＃39;, 10, &＃39;女&＃39;],

[&＃39;c&＃39;, 11, &＃39;男&＃39;]],

columns&＃61;[&＃39;name&＃39;, &＃39;age&＃39;, &＃39;sex&＃39;])

df2 &＃61; pd.DataFrame([[&＃39;a&＃39;, 10, &＃39;男&＃39;],

[&＃39;b&＃39;, 11, &＃39;男&＃39;]],

columns&＃61;[&＃39;name&＃39;, &＃39;age&＃39;, &＃39;sex&＃39;])

result_inner &＃61; pd.merge(df1,df2,how&＃61;&＃39;inner&＃39;,keep &＃61; ["age"])

result_outer &＃61; pd.merge(df1,df2,how&＃61;&＃39;outer&＃39;)

df3 &＃61; df1.append(df2)

df3 &＃61; df3.drop_duplicates(subset&＃61;[&＃39;name&＃39;, &＃39;age&＃39;, &＃39;sex&＃39;],keep&＃61;False)

print(result_inner)

print(result_outer)

print(df3)&＃39;&＃39;&＃39;

一键复制

编辑

Web IDE

原始数据

按行查看

历史