Scott Warchal Swarchal

## 3k_plates.sh
ls | grep -E '*-(0[6-9]|1[1-5])$' > plates_06_to_15.txt

## find_correlation.py
import pandas as pd
import numpy as np

def find_correlation(data, threshold=0.9, remove_negative=False):
    """
    Given a numeric pd.DataFrame, this will find highly correlated features,
    and return a list of features to remove.
    Parameters
    -----------
    data : pandas DataFrame

## start_jupyter_server.sh
#!/bin/bash

# start a jupyter server running on a remote host
# and port-forward to local machine
remote_host=$1
terminal=x-terminal-emulator

# start remote jupyter session on port:8889
$terminal ssh $remote_host "ipython notebook --no-browser --port=8889"

## kmer.py
#!/usr/bin/env python3.6
# sensible solution
import re
import sys
import itertools

def get_seq(path):
    """return fasta sequence from file"""
    lines = open(path).readlines()
    seq = ""

## copy_dir_tree.sh
rsync -a -f"+ */" -f"- *" source/ destination/

## find_failed.py
#!/usr/bin/env python

"""re-rerun failed jobs
    >>> ./find_failed.py $results_dir $path_to_batchlist
"""

import os
from sys import argv

def has_failed(directory, expected):

## train_test_split.py
import random

def train_test_split(data, labels, test_prop=0.3):
    """roll your own train test split"""
    assert len(data) == len(labels)
    n_test = round(test_prop * len(data))
    n_train = len(data) - n_test
    combined = list(zip(data, labels))
    random.shuffle(combined)
    x_train, y_train = zip(*combined[:n_train])

## lexv_explanation.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Swarchal
                / lexv_explanation.ipynb
            
            
              Created
              December 15, 2016 16:32
            
              
                lexv_explanation
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## otsu.jl
using StatsBase

function otsu_threshold(img, bit_depth = 256)
    counts = fit(Histogram, img[:], nbins = bit_depth).weights
    const total = prod(size(img))
    current_max, threshold = 0, 0
    weightB, sumB = 0, 0
    sumT = sum([i * counts[i] for i in 1:bit_depth])
    for (i, count) in enumerate(counts)
        weightB += count

## qstatus.sh
# define some colours for pretty output
NC='\033[0m'
RED='\033[0;31m'
YELLOW='\033[0;33m'
GREEN='\033[0;32m'

alias=qstatus="echo -e '${NC}----------' ;\
               echo -e '${GREEN}running:' ;\
               qstat | grep ' r ' | wc -l ;\
               echo -e '${NC}----------' ;\
	import pandas as pd
	import numpy as np

	def find_correlation(data, threshold=0.9, remove_negative=False):
	"""
	Given a numeric pd.DataFrame, this will find highly correlated features,
	and return a list of features to remove.
	Parameters
	-----------
	data : pandas DataFrame
	#!/bin/bash

	# start a jupyter server running on a remote host
	# and port-forward to local machine
	remote_host=$1
	terminal=x-terminal-emulator

	# start remote jupyter session on port:8889
	$terminal ssh $remote_host "ipython notebook --no-browser --port=8889"
	#!/usr/bin/env python3.6
	# sensible solution
	import re
	import sys
	import itertools

	def get_seq(path):
	"""return fasta sequence from file"""
	lines = open(path).readlines()
	seq = ""
	#!/usr/bin/env python

	"""re-rerun failed jobs
	>>> ./find_failed.py $results_dir $path_to_batchlist
	"""

	import os
	from sys import argv

	def has_failed(directory, expected):
	import random

	def train_test_split(data, labels, test_prop=0.3):
	"""roll your own train test split"""
	assert len(data) == len(labels)
	n_test = round(test_prop * len(data))
	n_train = len(data) - n_test
	combined = list(zip(data, labels))
	random.shuffle(combined)
	x_train, y_train = zip(*combined[:n_train])
	using StatsBase

	function otsu_threshold(img, bit_depth = 256)
	counts = fit(Histogram, img[:], nbins = bit_depth).weights
	const total = prod(size(img))
	current_max, threshold = 0, 0
	weightB, sumB = 0, 0
	sumT = sum([i * counts[i] for i in 1:bit_depth])
	for (i, count) in enumerate(counts)
	weightB += count
	# define some colours for pretty output
	NC='\033[0m'
	RED='\033[0;31m'
	YELLOW='\033[0;33m'
	GREEN='\033[0;32m'

	alias=qstatus="echo -e '${NC}----------' ;\
	echo -e '${GREEN}running:' ;\
	qstat \| grep ' r ' \| wc -l ;\
	echo -e '${NC}----------' ;\