In [1]:

    

import json

with open('data1.json', 'r') as g: 
    data1 = json.load(g)
with open('data2.json', 'r') as g: 
    data2 = json.load(g)


    

In [2]:

    

cd code


    

    




/home/2011190707/0531project/code

In [3]:

    

from __future__ import print_function, division

import nsfg
import nsfg2
import first

import thinkstats2
import thinkplot

import copy
import random
import numpy as np
import matplotlib.pyplot as pyplot


    

In [4]:

    

class DiffMeansPermute(thinkstats2.HypothesisTest):
    """Tests a difference in means by permutation."""

    def TestStatistic(self, data):
        """Computes the test statistic.

        data: data in whatever form is relevant        
        """
        group1, group2 = data
        test_stat = abs(group1.mean() - group2.mean())
        return test_stat

    def MakeModel(self):
        """Build a model of the null hypothesis.
        """
        group1, group2 = self.data
        self.n, self.m = len(group1), len(group2)
        self.pool = np.hstack((group1, group2))

    def RunModel(self):
        """Run the model of the null hypothesis.

        returns: simulated data
        """
        np.random.shuffle(self.pool)
        data = self.pool[:self.n], self.pool[self.n:]
        return data


    

In [5]:

    

class DiffMeansOneSided(DiffMeansPermute):
    """Tests a one-sided difference in means by permutation."""

    def TestStatistic(self, data):
        """Computes the test statistic.

        data: data in whatever form is relevant        
        """
        group1, group2 = data
        test_stat = group1.mean() - group2.mean()
        return test_stat


    

In [6]:

    

class DiffStdPermute(DiffMeansPermute):
    """Tests a one-sided difference in standard deviation by permutation."""

    def TestStatistic(self, data):
        """Computes the test statistic.

        data: data in whatever form is relevant        
        """
        group1, group2 = data
        test_stat = group1.std() - group2.std()
        return test_stat


    

In [7]:

    

def PrintTest(p_value, ht):
    """Prints results from a hypothesis test.

    p_value: float
    ht: HypothesisTest
    """
    print('p-value =', p_value)
    print('actual =', ht.actual)
    print('ts max =', ht.MaxTestStat())


    

In [8]:

    

%matplotlib inline


    

In [9]:

    

def RunTests(data, iters=1000):
    """Runs several tests on the given data.

    data: pair of sequences
    iters: number of iterations to run
    """

    # test the difference in means
    ht = DiffMeansPermute(data)
    p_value = ht.PValue(iters=iters)
    print('\nmeans permute two-sided')
    PrintTest(p_value, ht)

    ht.PlotCdf()
    thinkplot.Save(root='hypothesis1',
                   title='Permutation test',
                   xlabel='difference in means (books per library)',
                   ylabel='CDF',
                   legend=False) 
    
    
    # test the difference in means one-sided
    ht = DiffMeansOneSided(data)
    p_value = ht.PValue(iters=iters)
    print('\nmeans permute one-sided')
    PrintTest(p_value, ht)

    # test the difference in std
    ht = DiffStdPermute(data)
    p_value = ht.PValue(iters=iters)
    print('\nstd permute one-sided')
    PrintTest(p_value, ht)


    

In [10]:

    

data_1 = np.array(data1)
data_2 = np.array(data2)
data = data_1, data_2


    

In [11]:

    

book = DiffMeansPermute(data)
RunTests(data)


    

    




means permute two-sided
p-value = 0.078
actual = 8178.77821346
ts max = 14647.2754674
Writing hypothesis1.pdf
Writing hypothesis1.eps

means permute one-sided
p-value = 0.045
actual = 8178.77821346
ts max = 15506.2988752

std permute one-sided
p-value = 0.426
actual = -4896.90338984
ts max = 30695.7353029






    






<matplotlib.figure.Figure at 0x7f9de5cb6438>