kaspermunch

from scipy.stats import fisher_exact
import pandas as pd
from IPython.display import display, Markdown

def read_google_sheet():
    SHEET_ID = '1JSjSLuto3jqdEnnG7JqzeC_1pUZw76n7XueVAYrUOpk'
    SHEET_NAME = 'Sheet1'
    url = f'https://docs.google.com/spreadsheets/d/{SHEET_ID}/gviz/tq?tqx=out:csv&sheet={SHEET_NAME}'
    df = pd.read_csv(url, header=1, dtype='str')
    return df.loc[:, [not x.startswith('Unnamed') for x in df.columns]]

kaspermunch

import matplotlib.pyplot as plt
import matplotlib.colors as clr
import numpy as np

some_matrix = np.random.rand(10, 10)
cmap = clr.LinearSegmentedColormap.from_list('custom colormap',
                                            ['white', 'gold', 'red', 'magenta', 'blue', 'black'],
                                            N=256)
sns.heatmap(some_matrix, cmap=cmap)

kaspermunch

# set dark plots if theme is dark
user_settings = '~/.jupyter/lab/user-settings/@jupyterlab/apputils-extension/themes.jupyterlab-settings'
if 'JupyterLab Dark' in open(os.path.expanduser(user_settings)).read():
    style = {'axes.facecolor': '#111111',
     'axes.edgecolor': '.99',
     'axes.labelcolor': '.99',
     'figure.facecolor': '#111111',
     'grid.color': '.0',
     'text.color': '.99',
     'xtick.color': '.99',

kaspermunch

kaspermunch

def read_google_sheet():
    SHEET_ID = '1JSjSLuto3jqdEnnG7JqzeC_1pUZw76n7XueVAYrUOpk'
    SHEET_NAME = 'Sheet1'
    url = f'https://docs.google.com/spreadsheets/d/{SHEET_ID}/gviz/tq?tqx=out:csv&sheet={SHEET_NAME}'
    df = pd.read_csv(url, header=1)
    return df.loc[:, [not x.startswith('Unnamed') for x in df.columns]]
    
def gene_list_names():
    df = read_google_sheet()
    return sorted(df.columns.tolist())

kaspermunch

class left:
    def __rlshift__(self, df):
        "Left align columns of data frame: df << left()"
        left_aligned_df = df.style.set_properties(**{'text-align': 'left'})
        left_aligned_df = left_aligned_df.set_table_styles(
        [dict(selector = 'th', props=[('text-align', 'left')])])
        display(left_aligned_df)
        
# df.head << left()

kaspermunch

from math import sqrt
from itertools import zip_longest

def list_genes(words, ncols=None):
    n = len(words)
    col_width = max(map(len, words)) + 1
    if ncols is None:
        ncols = max(100//col_width, 1+sqrt(n/col_width))
    nrows = int(n/ncols) + 1
    rows = []

kaspermunch

for file in `find codeml/steps/codeml -name '*.txt'`; do
  echo mv -- "$file" "$(dirname "$file")/$(basename -- "$file" .txt)_site.txt"
done

kaspermunch

def felsenstein(tree, states):
  # Initialize a dictionary to store the probabilities at each node
  probabilities = {}

  # Traverse the tree in postorder (i.e. children first, parent last)
  for node in postorder_traverse(tree):
    # If the node is a leaf, its probability is 1
    if is_leaf(node):
      probabilities[node] = 1
    else:

kaspermunch

def burrows_wheeler_transform(text):
  # Create a list of all rotations of the input text
  rotations = [text[i:] + text[:i] for i in range(len(text))]

  # Sort the list of rotations in lexicographic order
  rotations.sort()

  # Return the last characters of each rotated string, which is the
  # Burrows-Wheeler transform of the input text
  return “”.join([rot[-1] for rot in rotations])