dela3499

module Penrose where
import List exposing (foldr, map)
import Graphics.Collage exposing (..)
import Graphics.Element exposing (..)
import Color exposing (..)
goldenRatio = (1 + sqrt 5) / 2

type alias Point = (Float, Float)
type Triangle
  =  Kite (Point, Point, Point)

dela3499

# type PrerankedProfile = Series(Index = Integer, Probe_ID = String, Rank = Integer)

# DataFrame -> List PrerankedProfile
def cmap2sortedseries(df):
    return [series.order(ascending = True).reset_index() for series in df2series(df)]

# PrerankedProfile -> List a -> Float
def gsea_preranked(sorted_series, tag_list):
    """ Apply KS test.
        ex: scores = map(lambda profile: gsea_preranked(profile, up_probes), profiles)

dela3499

# Wikipedia: https://en.wikipedia.org/wiki/Kolmogorov%E2%80%93Smirnov_test#Two-sample_Kolmogorov.E2.80.93Smirnov_test
# Scipy source: https://github.com/scipy/scipy/blob/v0.15.1/scipy/stats/stats.py#L3966 

def ks_2samp(data1, data2):
    data1, data2 = map(asarray, (data1, data2)) 
    n1 = data1.shape[0] # n1 and n2 reassigned below, and can be removed here. 
    n2 = data2.shape[0] # maybe this is used for error message, in case inputs aren't lists. But len provides a good error message. 
    n1 = len(data1) # Avoid repetition with list comprehension or map
    n2 = len(data2)
    data1 = np.sort(data1) # Avoid repetition with list comprehension or map

dela3499

from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd

# String -> [String]
def parse_abstracts(filename):
    """ Given a text file containing PubMed abstracts, 
        return these abstracts as a list of strings. """
    f = open(filename).read()
    lines = f.split("\n")
    docs = [[]]

dela3499

# source("http://bioconductor.org/biocLite.R")
library("affy")
library("frma")
library("hgu133plus2frmavecs")
library("parallel")

# String -> String
change.file.extension <- function(filename, extension){
  # Strip file extensions from filename, 
  #  and replace with given extension

dela3499

import numpy as np

mag = np.linalg.norm
r = np.random.random

def cosdist(x,y):
    return sum(x * y) / (mag(x) * mag(y))

def repeat(f,n):
    return [f() for _ in range(n)]

dela3499

import pandas as pd
from pandas import DataFrame as DF
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
from IPython.display import display
import IPython.html.widgets as widgets
from scipy.cluster.hierarchy import \
    linkage,\
    leaves_list,\

dela3499

# Download or retrieve dataset in SOFT format
soft_filepath = "./GSE11882.soft.gz"
gse = GEOparse.get_GEO(filepath = soft_filepath)


# Parse metadata for individual samples

# [String] -> Dict (individual_id, brain_region, gender, age)
def parse_characteristics(c):

dela3499

import Graphics.Element exposing (..)
import Graphics.Collage exposing (..)
import Window
import Signal
import Color exposing (..)


main = 
  Signal.map (view x) Window.dimensions

dela3499

import Graphics.Element exposing (..)
import Graphics.Collage exposing (..)
import Window
import Signal
import Color exposing (..)


main = 
  Signal.map (view x) Window.dimensions