flashton2003

{
 "metadata": {
  "name": "",
  "signature": "sha256:b5d9c057e15441865c84a9422297988c0e93d5961f3da2e00ebd3be695766282"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

flashton2003

{
 "metadata": {
  "name": "",
  "signature": "sha256:dd3f380620371d7def93011e81b190a7a8f796fba0551a284b06626a6757a641"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

flashton2003

{
 "metadata": {
  "name": "",
  "signature": "sha256:dd3f380620371d7def93011e81b190a7a8f796fba0551a284b06626a6757a641"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

flashton2003

1995 1
1996 3
1999 4
1998 1
2002 13
2003 10
2000 31
2001 2
2006 21

flashton2003

1996	2
1999	1
2001	1
2002	4
2003	13
2004	3
2005	2
2006	9
2007	59
2008	37

flashton2003

install.packages('ggplot2')
library(ggplot2)

## simple histogram

data <- read.delim("path/to/data")
ggplot(data, aes(x = data$V1)) + geom_histogram(binwidth = 30000)

## more complex - with axis labels and custom scaling - more info http://www.cookbook-r.com/Graphs/Plotting_distributions_(ggplot2)/

flashton2003

def plot_heat_tree(heatmap_file, tree_file, output_file=None):
    '''
    Plot heatmap next to a tree. The order of the heatmap **MUST** be the same,
    as order of the leafs on the tree. The tree must be in the Newick format. If
    *output_file* is specified, then heat-tree will be rendered as a PNG, 
    otherwise interactive browser will pop-up with your heat-tree.
    
    Parameters
    ----------
    heatmap_file: str

flashton2003

library(ggplot2)
library(RPostgreSQL)

drv <- dbDriver("PostgreSQL")
con = dbConnect(drv, dbname = 'dbname', host = 'postgres', user = 'user', password = 'password')

query <- 'select * from your_table'
res <- dbSendQuery(con, query)
data_from_db <- fetch(res, n = -1) # n = -1 means all results will be returned

flashton2003

library(reshape)
library(ape)

# read in the data
f <- read.delim("~/Dropbox/mash_project/2015.09.23.all_vs_all.txt", header=F)
# use reshape's cast function to change to matrix
m <- cast(f, V1 ~ V2)
# set the row names
rownames(m) <- m[,1]
# get rid of a couple of rows

flashton2003

import ftplib

# ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR038/ERR038787/ERR038787_1.fastq.gz
todo_list = ['ERR024633'] # ERR accessions
target_dir = '/where/you/want/the/data'

def download_from_ena(todo_list, target_dir):
	ftp = ftplib.FTP('ftp.sra.ebi.ac.uk')
	ftp.login()
	ftp.cwd('vol1')