JohannesBuchner

import numpy
from numpy import log, log10, sin, cos, tan, arctan, arccos, arcsin, abs, any, pi
import sys
import matplotlib.pyplot as plt

data = numpy.loadtxt(sys.argv[1], 
	dtype=[(colname, 'f') for colname in 'x', 'x_err', 'y', 'y_err', 'cor'],
	skiprows=1)

plt.figure(figsize=(7,7))

JohannesBuchner

# "x" "x_err" "y" "y_err" "cor"
10.191 0.125 20.128 0.125 0.731
9.808 0.050 20.286 0.050 0.662
9.700 0.039 20.437 0.039 0.580
9.831 0.065 20.058 0.065 0.720
9.912 0.058 20.194 0.058 0.502
9.861 0.083 19.989 0.083 0.769
9.971 0.060 20.229 0.060 0.563
9.859 0.060 20.164 0.060 0.752
9.720 0.044 20.318 0.044 0.646

JohannesBuchner

import numpy
import matplotlib.pyplot as plt

def prob(M):
	# for M people, compute the probability of having more than 4 with same birthday
	hits = 0
	# number of simulation instances
	N = 1000
	I = numpy.arange(365).reshape((1,-1))
	for j in range(N):

JohannesBuchner

def generateTuple():
   if numpy.random.uniform() > 0.05:
      # generate from normal data set, e.g. normal distribution around some values -- here, a line
      k = 1.16
      d = 8.9
      x = numpy.random.uniform(6, 12)
      y = k * (x - 11) + d
      return numpy.random.norm(x, 1), numpy.random.norm(y, 3)
   else:
      # generate from outlier distribution, e.g. uniform distribution over full parameter space

JohannesBuchner

import numpy
from numpy import cos, sin, exp, log, pi, tan, arccos, arcsin, arctan
import matplotlib.pyplot as plt

# make a quadratic figure
plt.figure(figsize=(6, 6))

# generate 400 points between 0 and 1
t = numpy.linspace(0, 1, 40)
print 't = ', t

JohannesBuchner

"""
Memoizes a given function, given its code dependencies (loaded modules and 
additional data files)

Example::

  import douglasadams
  def costlyfunction():
  	# compute answer to the universe and everything
  	return douglasadams.compute_answer() == 42

JohannesBuchner

import numpy
import matplotlib.pyplot as plt
import scipy.stats

# two gaussian uncertainties with width sigma
# at distance delta
# what is the probability that they actually have the same value?

def compute_bayes(delta, border=5):
	a = scipy.stats.norm()

JohannesBuchner

import matplotlib.pyplot as plt
import numpy
import scipy.stats

# http://www.medpagetoday.com/Blogs/TheMethodsMan/52171

def calc_reliability(p, power=0.8, frac_true=0.1):
	"""
	Given this p-value, power of the test and fraction of hypotheses that 
	are actually true.

JohannesBuchner

"""
SYNOPSIS: ./myprog | python console-progress.py

example for myprog: 

#!/bin/bash
echo 100
for i in $(seq 1 100)
do
   sleep 1

JohannesBuchner

ArXiV minimal statistics checklist

This checklist help you identify and fix common errors/misinterpretation in your analysis, or of a paper you are refereeing.

1. If you use p-values (from a KS test, Pearson correlation, etc.).

1. What do you think a low p-value says?

1. You have absolutely disproved the null hypothesis (e.g. "no correlation" is ruled out, the data are not sampled from this model, there is no difference between the population means).