- 博客(21)
- 收藏
- 关注
RSS订阅原创 for和panda 的连用
```pythonimport pandas as pdimport numpy as npdf = pd.read_excel('D://test/ppp.xlsx',sheet_name="Phylum")# print(df)# df1=df.groupby(by='Phylum')## df# df1.to_excel("D://test//PP_Des.xlsx")# df['X.mean'] = df['SUM'].mean()#df.groupby(by='Phy.
2021-12-15 13:56:00
1245
原创 pandas 对数据进行对数转换。
import pandas as pdimport numpy as npdf = pd.read_excel('e://xionghuan/test.xlsx')#选取有值得列名columns = df.columns[5::]for i in columns : df[i+'_log'] = df[i].map(lambda x : np.log(x)) # 进行对数转换 以 e 为底 想以其他为底可以变换如 np.log10(x) df2 = df.loc[:,df.co
2021-03-11 21:18:02
3500
原创 Biopython根据ko号访问KEGG数据库并找到通路LEVEL1和LEVE2
import pandas as pdfrom Bio.KEGG import RESTdf = pd.read_excel(r'E:\XY\hhly1\clean\unchime-dn-out\picrust2/kegg.xlsx')pwid = df['pathway']my_dict={}for id in pwid: print(id) pathway = REST.kegg_get(id).read() for i in pathway.rstrip().spl
2021-02-18 09:58:09
2647
原创 Linux 子系统搭建以及16S rRNA conda环境设置
Linux 子系统搭建以及conda环境设置文章目录Linux 子系统搭建以及conda环境设置一、Linux子系统二、Conda 安装三、QIIME2环境的创建下载一、Linux子系统1.widonws10下先打开，开发者选项2.在应用与程序中找到 window功能，打开 勾选linux 的子系统（家庭版直接搜索windows功能）其他版本不一样可以百度去Microsoft store 中搜索 linux下载安装然后设置名字和密码二、Conda 安装（1）.bash ./
2021-02-15 13:24:43
363
原创 seaborn多子图绘制(箱线图+点图）.附有表格格式
import pandas as pdimport seaborn as snsimport matplotlib.pyplot as pl导入数据df = pd.read_excel(r'E:\XY\hhly1\clean\hhly1\Alphy/alphy.xlsx')设置风格sns.set_theme(style='ticks',font='Times New Roman')绘制多子图g=sns.FacetGrid(df,col='index',col_wrap=2,sharey=No
2021-02-13 21:34:27
6309
原创 python绘制微生物物种层次聚类热图
import matplotlib.pyplot as pltimport pandas as pdimport seaborn as sns#设置绘图风格以及字体格式sns.set_theme(style='ticks',font='Times New Roman')#读取excel表df = pd.read_excel('e://xh/zm/Genus.xlsx')#数据整理df2=df.pivot_table(columns = 'Genus')#绘制物种热图sns.cluster
2021-02-13 21:26:56
2046
1
原创 python 按指定字符删除数据
"""数据清洗"""import pandas as pdimport numpy as npdef wu(x,y,z): df=pd.read_excel(x) df2=df.groupby(by=y,as_index=False).sum() #数据分组求和 df2[y]=df2[y].map(lambda x:str(x)[3:]) #除去某列前面前三个字符 df2[y][df2[y].str.contains('unclassified')]='Unkno
2021-01-30 20:32:00
340
1
原创 ggoplot2绘制 柱状图
# Title : TODO# Objective : TODO# Created by: Administrator# Created on: 2021/1/30#导入包library('tidyverse')library('reshape2')#定义向量l <-c('Phylum','Order','Genus','Species')h <- 'f://'#定义函数f<-function (h,m){ data <-readxl::read_x
2021-01-30 20:25:36
229
原创 arcpy 按掩膜提取
#按掩膜提取数据import arcpyfrom arcpy import envfrom arcpy.sa import *import osimport os.pathimport sysrootdir = 'D:\\clime21'filenames = os.listdir(rootdir)for filename in filenames: if os.path.splitext(filename)[1] == '.tif': inRaster = roo
2021-01-06 21:08:16
490
原创 arcpy
"""、取多波段的值 转ASC多值到点"""在这里插入代码片# coding:utf-8import os.pathimport shutilimport arcpyfrom arcpy import envfrom arcpy.conversion import RasterToASCIIfrom shutil import copyfilefrom arcpy.sa import ExtractMultiValuesToPointsarcpy.CheckOutExtens
2021-01-06 21:06:26
340
原创 python 圈图
import osimport pandas as pdimport numpy as npimport matplotlib.pyplot as pltfrom itertools import chainfrom pandas import Series,DataFramefrom pylab import mpl%matplotlib inlineplt.rc('font',family='Times New Roman') mpl.rcParams['font.size']=12
2020-11-25 20:54:25
284
原创 python横向柱状图
import pandas as pd import matplotlib.pyplot as pltfrom pandas import Series,DataFrameimport numpy as npfrom pylab import mpl# df = pd.read_excel('f://Research/2020/Xionjianli/Data/季节差异显著_genus1.xls',sheet_name)#修改字体大小及其格式plt.rc('font',family='Time
2020-11-25 20:46:33
5230
原创 python 柱状图
#导入相应包import pandas as pd import matplotlib.pyplot as pltfrom pandas import Series,DataFramefrom pylab import mpl导入数据df = pd.read_excel('f://Research/2020/Xionjianli/Data/DiversityIdex.xlsx',sheet_name='Sheet6')#定义字体格式大小plt.rc('font',family='Times
2020-11-25 10:31:00
290
原创 python横向多组柱状图
#导入包import pandas as pd import matplotlib.pyplot as pltfrom pandas import Series,DataFrameimport numpy as npfrom pylab import mpl#定义图像字体和字体大小plt.rc('font',family='Times New Roman') mpl.rcParams['font.size']=16#读取文件df = pd.read_excel('F://Research
2020-11-25 10:27:42
2496
原创 python指定列索引筛选数据
#导入包import pandas as pdimport numpy as npfrom pandas import Series,DataFrame# from numpy import mean, ptp, var, std#读取数据df_season = pd.read_excel('e://xionghuan//20201123/pathway_1_2.xlsx',sheet_name='Pathway_2')df_site = pd.read_excel('e://xiongh
2020-11-25 10:22:53
2125
原创 python折线图
#导入包import xlrdimport osimport matplotlib.pyplot as plt%matplotlib inline#打开exceldate=xlrd.open_workbook('F:\\study\\python\\AREA.xlsx')#筛选数据table=date.sheets()[2]x=(1,2,3,4,5,6)y=table.row_values(0)z=table.row_values(1)a=table.row_values(2)b=
2020-11-25 10:19:48
236
原创 python多子图
# '斑块间欧氏距离平均值Timport pandas as pdimport matplotlib.pyplot as pltimport os %matplotlib inlineplt.rc('font',family='Times New Roman') os.chdir('F://熊欢//3.9图像')su=pd.read_excel('制图（熊欢）.xlsx',sheet_name=1)x=['mid-Holocene','Current','2070(RCP26)','
2020-11-25 10:15:23
635
原创 python绘制多子图
#导入包import pandas as pdimport matplotlib.pyplot as pltimport os%matplotlib inline#定义路径os.chdir('e:\\students\\Xiongh')#打开excel文件df=pd.read_excel('Mean_std.xls',sheetname='Sheet3')#筛选数据y1=df['Mean'].loc[0:5]y2=df['Mean'].loc[6:11]y3=df['Mean'].l
2020-11-25 10:09:51
721
原创 python筛选fasta中特定位置的基因
from Bio import SeqIOfasta=input('请输入你的fasta文件：')for seq_record in SeqIO.parse(fasta, "fasta"): name = input('输入你的基因名字（>xxx格式）：') star = eval(input('请输入起始位置（注意软件索引从0开始，且是半开区间）:')) end = eval(input('请输入终止位置（注意软件索引从0开始，且是半开区间）:')) print(
2020-11-25 10:05:20
671
原创 2020-02-16
import requestsimport re def getHTMLText(url) tyr: r=requests,get(url,timeout=30) r.raise_for_status() r.encoding='utf-8' return r.text except: return " " d...
2020-02-19 20:38:44
108
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人