In [3]:

    

%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style("white")
sns.set(style="ticks")
from matplotlib import rc
rc('text', usetex=True)
from scipy.stats import norm
from scipy import stats
import statsmodels.api as sm
# sns.despine()
import csv
import ast
import random
import numpy as np


    

In [63]:

    

# import itertools

# motiflist = []

# for key in itertools.product(range(2),repeat = 5):
#     mod_key = str(key).strip(" ,(),','").replace(", ", "")
#     if len(motiflist) > 0:
#         if len(mod_key) == len(motiflist[-1]):
#             for keys_so_far in range(len(motiflist)):
#                 if len(mod_key) == len(motiflist[keys_so_far]):
#                     if mod_key.count('1') < motiflist[keys_so_far].count('1'):
#                         motiflist.insert(keys_so_far,mod_key)
#                         break
#             else:
#                 motiflist.append(mod_key)
#         else:
#             motiflist.append(mod_key)
#     else:
#         motiflist.append(mod_key)

motiflist = ['10000','00001']


    

In [2]:

    

# biaslist = [0.0,0.05,0.1,0.15,0.2,0.25,0.3,0.35,0.4,0.45,0.5,0.55,0.6,0.65,0.7,0.75,0.8,0.85,0.9,0.95,1.0]
# biaslist = [0.5,0.55,0.6,0.65,0.7,0.75,0.8,0.85,0.9,0.95,1.0]
# biaslist = [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]

# biaslist = [0.5,0.8,0.9,1.0]
biaslist = [0.9]

# numSamples = 50
# numSamples = 150
equil_start = 1000
numTrials = 2
numRounds = 40000


    

In [202]:

    

import csv
import ast
import random
import numpy as np
datalist = []
parameterlist = []
motif_mean = []
motif_ci = []
cells_mean = []
cells_ci = []
word_list = []

for motif in range(len(motiflist)):
    datalist.append([])
    parameterlist.append([])
    motif_mean.append([])
    motif_ci.append([])
    cells_mean.append([])
    cells_ci.append([])
    word_list.append([])
    for bias in range(len(biaslist)):
        datalist[motif].append([])
        parameterlist[motif].append([])
        motif_mean[motif].append([])
        motif_ci[motif].append([])
        cells_mean[motif].append([])
        cells_ci[motif].append([])
        word_list[motif].append([])
        if biaslist[bias]<0.5:
            temp_file = "EquilibriumDataFinder_sampler_validitycheck_start1000_samples"+str(numSamples)+"_MotifSimulation_NewLeaf_Test1_MotifData_motif"+motiflist[motif]+"_len7_bias"+str(biaslist[bias])+"_elong0.05_50trials_numRound7000.csv"
        else:      
            temp_file = "EquilibriumDataFinder_sampler_validitycheck_start1000_samples"+str(numSamples)+"_MotifSimulation_NewLeaf_Test1_MotifData_motif"+motiflist[motif]+"_len7_bias"+str(biaslist[bias])+"_elong0.05_50trials_numRound7000.csv"
        csvFile = []
        with open(temp_file) as f:
            handle = csv.reader(f)
            line_counter = 0
            for line in handle:     
                words = []
                for word in line:
                    words.append(ast.literal_eval(word))
                if line_counter == 0:
                    parameterlist[motif][bias] = words
                    print words
                elif line_counter == 2:
                    if motif == 5:
                        print words
                    motif_mean[motif][bias].append(words[0])
                    motif_ci[motif][bias].append(1.96*words[3])
                elif line_counter == 4:
                    cells_mean[motif][bias].append(words[0])
                    cells_ci[motif][bias].append(1.96*words[3])
                word_list[motif][bias].append(words)
                line_counter += 1
        f.close()


    

    




[50, 100, 7, 100, 7000, 10000, 0.05, 0.5]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.55]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.6]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.65]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.7]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.75]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.8]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.85]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.9]
[50, 100, 7, 100, 7000, 10000, 0.05, 0.95]
[50, 100, 7, 100, 7000, 10000, 0.05, 1.0]
[50, 100, 7, 100, 7000, 1, 0.05, 0.5]
[50, 100, 7, 100, 7000, 1, 0.05, 0.55]
[50, 100, 7, 100, 7000, 1, 0.05, 0.6]
[50, 100, 7, 100, 7000, 1, 0.05, 0.65]
[50, 100, 7, 100, 7000, 1, 0.05, 0.7]
[50, 100, 7, 100, 7000, 1, 0.05, 0.75]
[50, 100, 7, 100, 7000, 1, 0.05, 0.8]
[50, 100, 7, 100, 7000, 1, 0.05, 0.85]
[50, 100, 7, 100, 7000, 1, 0.05, 0.9]
[50, 100, 7, 100, 7000, 1, 0.05, 0.95]
[50, 100, 7, 100, 7000, 1, 0.05, 1.0]

In [3]:

    

motiflist = ['10000']
# biaslist = [0.5,0.8,0.9,1.0]
biaslist = [0.9]


    

In [14]:

    

single_set_10000motif = []
single_set_01111motif = []
single_set_cell = []
single_set_strands = []
for s in range(3):
    if s == 0:
        temp_file = "MotifCompeteSimulation_NewLeaf_Compete_Test1_MotifData_motif'10000'|'01111'_len7_bias0.9|0.1_elong0.05_50trials_numRound15000_verificationcopy.csv"
        with open(temp_file) as f:
            handle = csv.reader(f)
            line_counter = 0
            for line in handle:
                if line_counter in range(1,2*5+1,5):
                    words = []
                    for word in line:
                        words.append(ast.literal_eval(word))
                    single_set_10000motif.append(words)
                elif line_counter in range(2,2*5+2,5):
                    words = []
                    for word in line:
                        words.append(ast.literal_eval(word))
                    single_set_01111motif.append(words)
                line_counter += 1
    elif s == 1:
        temp_file = "MotifCompeteSimulation_RobustIC_halfeach_MotifData_motif'10000'|'01111'_len7_bias0.9|0.1_elong0.05_2trials_numRound1500.csv"
        with open(temp_file) as f:
            handle = csv.reader(f)
            line_counter = 0
            for line in handle:
                if line_counter in range(1,2*5+1,5):
                    words = []
                    for word in line:
                        words.append(ast.literal_eval(word))
                    single_set_10000motif.append(words)
                elif line_counter in range(2,2*5+2,5):
                    words = []
                    for word in line:
                        words.append(ast.literal_eval(word))
                    single_set_01111motif.append(words)
                line_counter += 1
    elif s == 2:
        temp_file = "MotifCompeteSimulation_RobustIC_all01111_MotifData_motif'10000'|'01111'_len7_bias0.9|0.1_elong0.05_2trials_numRound1500.csv"
        with open(temp_file) as f:
            handle = csv.reader(f)
            line_counter = 0
            for line in handle:
                if line_counter in range(1,2*5+1,5):
                    words = []
                    for word in line:
                        words.append(ast.literal_eval(word))
                    single_set_10000motif.append(words)
                elif line_counter in range(2,2*5+2,5):
                    words = []
                    for word in line:
                        words.append(ast.literal_eval(word))
                    single_set_01111motif.append(words)
                line_counter += 1


    

In [15]:

    

len(single_set_10000motif)
len(single_set_01111motif)


    

    
Out[15]:





6

In [134]:

    

window_lengths = []
for i in range(1,7000-1000+1):
    if (7000-1000) % i == 0:
        window_lengths.append(i)
    
means = []
print window_lengths
for window_length in range(len(window_lengths)):
    means.append([])
    possible_windows = range(1000,7000+1,window_lengths[window_length])
    for window in possible_windows:
        print window, window_length
        means[window_length].append(np.mean(single_set_motif[0][window:window+window_lengths[window_length]]))


    

    




[1, 2, 3, 4, 5, 6, 8, 10, 12, 15, 16, 20, 24, 25, 30, 40, 48, 50, 60, 75, 80, 100, 120, 125, 150, 200, 240, 250, 300, 375, 400, 500, 600, 750, 1000, 1200, 1500, 2000, 3000, 6000]

In [138]:

    

reoriented_means = []
reoriented_lengths = []
for window_length in range(len(window_lengths)):
    for item in means[window_length]:
        reoriented_means.append(item)
        reoriented_lengths.append(window_lengths[window_length])


    

In [14]:

    

import math


    

In [17]:

    

means = []
# stderr = []
for trial in range(6):
    means.append(np.mean(single_set_motif[0][0][trial][1000:]))
stderr = 1.96*math.sqrt(np.var(means)/len(means))


    

In [19]:

    

print stderr
print np.mean(means)


    

    




0.000428738568405
0.0905182063952

In [90]:

    

plt.figure()
for trial in range(14):
    plt.plot(single_set_motif[0][0][trial][1000:1200])


    

In [17]:

    

start = 0
add = 1500
plt.figure()
plt.plot(single_set_10000motif[0][start:start+add],'r',label='Empty')
plt.plot(single_set_01111motif[0][start:start+add],'r',label='Empty')
plt.plot(single_set_10000motif[1][start:start+add],'r',label='Empty')
plt.plot(single_set_01111motif[1][start:start+add],'r',label='Empty')
plt.plot(single_set_10000motif[2][start:start+add],'b',label='HalfEach')
plt.plot(single_set_01111motif[2][start:start+add],'b',label='HalfEach')
plt.plot(single_set_10000motif[3][start:start+add],'b',label='HalfEach')
plt.plot(single_set_01111motif[3][start:start+add],'b',label='HalfEach')
plt.plot(single_set_10000motif[4][start:start+add],'g',label='All01111')
plt.plot(single_set_01111motif[4][start:start+add],'g',label='All01111')
plt.plot(single_set_10000motif[5][start:start+add],'g',label='All01111')
plt.plot(single_set_01111motif[5][start:start+add],'g',label='All01111')
plt.legend(loc='upper right')


    

    
Out[17]:





<matplotlib.legend.Legend at 0x11037dfd0>






    

In [101]:

    

start = 0
add = 1000
plt.figure()
# plt.plot(single_set_motif[0][0][0][start:start+add],'r',label='Empty')
# plt.plot(single_set_motif[0][0][1][start:start+add],'r')
# plt.plot(single_set_motif[0][0][2][start:start+add],'b',label='All 1')
# plt.plot(single_set_motif[0][0][3][start:start+add],'b')
# plt.plot(single_set_motif[0][0][4][start:start+add],'g',label ='Random w/ Bin(100,0.1) empty')
# plt.plot(single_set_motif[0][0][5][start:start+add],'g')
# plt.plot(single_set_motif[0][0][6][start:start+add],'y',label ='Random w/ Bin(100,0.5) empty')
# plt.plot(single_set_motif[0][0][7][start:start+add],'y')
# plt.plot(single_set_motif[0][0][8][start:start+add],'c',label ='Random w/ Bin(100,0.9) empty')
# plt.plot(single_set_motif[0][0][9][start:start+add],'c')
# plt.plot(single_set_motif[0][0][10][start:start+add],'m',label ='All Motif')
# plt.plot(single_set_motif[0][0][11][start:start+add],'m')
# plt.plot(single_set_motif[0][0][12][start:start+add],color='orange',label ='Half Motif, Half Empty')
# plt.plot(single_set_motif[0][0][13][start:start+add],color='orange')

plt.plot(single_set_motif[0][0][2][start:start+add],color='#e41a1c',label='All 1')
plt.plot(single_set_motif[0][0][3][start:start+add],color='#e41a1c')
plt.plot(single_set_motif[0][0][4][start:start+add],color='#ffff33',label ='Random w/ Bin(100,0.1) empty')
plt.plot(single_set_motif[0][0][5][start:start+add],color='#ffff33')
plt.plot(single_set_motif[0][0][6][start:start+add],color='#a65628',label ='Random w/ Bin(100,0.5) empty')
plt.plot(single_set_motif[0][0][7][start:start+add],color='#a65628')
plt.plot(single_set_motif[0][0][8][start:start+add],color='#ff7f00',label ='Random w/ Bin(100,0.9) empty')
plt.plot(single_set_motif[0][0][9][start:start+add],color='#ff7f00')
plt.plot(single_set_motif[0][0][10][start:start+add],color='#4daf4a',label ='All Motif')
plt.plot(single_set_motif[0][0][11][start:start+add],color='#4daf4a')
plt.plot(single_set_motif[0][0][12][start:start+add],color='#984ea3',label ='Half Motif, Half Empty')
plt.plot(single_set_motif[0][0][13][start:start+add],color='#984ea3')
plt.plot(single_set_motif[0][0][14][start:start+add],color='#f781bf',label ='Half Motif, Half Random')
plt.plot(single_set_motif[0][0][15][start:start+add],color='#f781bf')
plt.plot(single_set_motif[0][0][0][start:start+add],color='#377eb8',label='Empty')
plt.plot(single_set_motif[0][0][1][start:start+add],color='#377eb8')
#e41a1c
#377eb8
#4daf4a
#984ea3
#ff7f00
#ffff33
#a65628
#f781bf
plt.legend(loc='upper right',ncol=2,fontsize=12)
plt.xlabel('Time')
plt.ylabel('Motif Frequency')


    

    
Out[101]:





<matplotlib.text.Text at 0x119d98210>






    

In [111]:

    

start = 0
add = 1000
plt.figure()
# plt.plot(single_set_motif[0][0][0][start:start+add],'r',label='Empty')
# plt.plot(single_set_motif[0][0][1][start:start+add],'r')
# plt.plot(single_set_motif[0][0][2][start:start+add],'b',label='All 1')
# plt.plot(single_set_motif[0][0][3][start:start+add],'b')
# plt.plot(single_set_motif[0][0][4][start:start+add],'g',label ='Random w/ Bin(100,0.1) empty')
# plt.plot(single_set_motif[0][0][5][start:start+add],'g')
# plt.plot(single_set_motif[0][0][6][start:start+add],'y',label ='Random w/ Bin(100,0.5) empty')
# plt.plot(single_set_motif[0][0][7][start:start+add],'y')
# plt.plot(single_set_motif[0][0][8][start:start+add],'c',label ='Random w/ Bin(100,0.9) empty')
# plt.plot(single_set_motif[0][0][9][start:start+add],'c')
# plt.plot(single_set_motif[0][0][10][start:start+add],'m',label ='All Motif')
# plt.plot(single_set_motif[0][0][11][start:start+add],'m')
# plt.plot(single_set_motif[0][0][12][start:start+add],color='orange',label ='Half Motif, Half Empty')
# plt.plot(single_set_motif[0][0][13][start:start+add],color='orange')

plt.plot(single_set_motif[0][0][2][start:start+add],color='lightgrey',label='All 1')
plt.plot(single_set_motif[0][0][3][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][4][start:start+add],color='lightgrey',label ='Random w/ Bin(100,0.1) empty')
plt.plot(single_set_motif[0][0][5][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][6][start:start+add],color='lightgrey',label ='Random w/ Bin(100,0.5) empty')
plt.plot(single_set_motif[0][0][7][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][8][start:start+add],color='lightgrey',label ='Random w/ Bin(100,0.9) empty')
plt.plot(single_set_motif[0][0][9][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][10][start:start+add],color='lightgrey',label ='All Motif')
plt.plot(single_set_motif[0][0][11][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][12][start:start+add],color='lightgrey',label ='Half Motif, Half Empty')
plt.plot(single_set_motif[0][0][13][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][14][start:start+add],color='lightgrey',label ='Half Motif, Half Random')
plt.plot(single_set_motif[0][0][15][start:start+add],color='lightgrey')
plt.plot(single_set_motif[0][0][0][start:start+add],color='k',label='Empty')
plt.plot(single_set_motif[0][0][1][start:start+add],color='k')


ax = plt.gca()
for tick in ax.xaxis.get_major_ticks():
    tick.label.set_fontsize(14) 
for tick in ax.yaxis.get_major_ticks():
    tick.label.set_fontsize(14) 

# plt.legend(loc='upper right',ncol=2,fontsize=12)
plt.xlabel('Time',fontsize=14)
plt.ylabel('Motif Frequency',fontsize=14)
plt.savefig('convergence_initialconditions_motif10000_bias9_fontsize.pdf',rasterized=True)


    

In [55]:

    

start = 1000
add = 6000
plt.figure()
plt.plot(range(start,start+add),single_set_motif[0][0][0][start:start+add],'r',label='Empty')
plt.plot(range(start,start+add),single_set_motif[0][0][1][start:start+add],'r')
plt.plot(range(start,start+add),single_set_motif[0][0][2][start:start+add],'b',label='All 1')
plt.plot(range(start,start+add),single_set_motif[0][0][3][start:start+add],'b')
plt.plot(range(start,start+add),single_set_motif[0][0][4][start:start+add],'g',label ='Random 1 (0.9)')
plt.plot(range(start,start+add),single_set_motif[0][0][5][start:start+add],'g')
plt.plot(range(start,start+add),single_set_motif[0][0][6][start:start+add],'y',label ='Random 2 (0.5)')
plt.plot(range(start,start+add),single_set_motif[0][0][7][start:start+add],'y')
plt.plot(range(start,start+add),single_set_motif[0][0][8][start:start+add],'c',label ='Random 3 (0.1)')
plt.plot(range(start,start+add),single_set_motif[0][0][9][start:start+add],'c')
plt.plot(range(start,start+add),single_set_motif[0][0][10][start:start+add],'m',label ='All Motif')
plt.plot(range(start,start+add),single_set_motif[0][0][11][start:start+add],'m')
plt.legend(loc='lower right',ncol=2)


    

    
Out[55]:





<matplotlib.legend.Legend at 0x112c6a810>






    

In [108]:

    

plt.figure()
for trial in range(6):

    plt.plot(single_set_motif[1][0][trial][30000:30200],'r')
    plt.plot(single_set_motif[1][0][trial][200:400],"b")


    #plt.scatter(range(len(single_set_motif[1][3][trial][1000:])),single_set_motif[1][3][trial][1000:])
# plt.xlim(0,6050)
   # plt.ylim(0.010,0.015)
plt.figure()


    

    
Out[108]:





<matplotlib.figure.Figure at 0x110696690>






    













    






<matplotlib.figure.Figure at 0x110696690>

In [141]:

    

plt.figure()
plt.plot(reoriented_lengths,reoriented_means)
plt.xlim(0,6050)


    

    
Out[141]:





(0, 6050)






    

In [67]:

    

mean_pair = []
mean_pair2 = []
mean_pair3 = []
for bias in range(len(biaslist)):
    mean_pair.append([])
    mean_pair2.append([])
    mean_pair3.append([])
    for trial in range(20):
        mean_pair[bias].append([np.mean(single_set_motif[1][bias][trial][1000:16000]),np.mean(single_set_motif[1][bias][trial][25000:40000])])
        mean_pair2[bias].append([np.mean(single_set_motif[1][bias][trial][10000:20000]),np.mean(single_set_motif[1][bias][trial][30000:40000])])
        mean_pair3[bias].append([np.mean(single_set_motif[1][bias][trial][1000:7000]),np.mean(single_set_motif[1][bias][trial][33000:40000])])


    

In [78]:

    

for bias in range(len(biaslist)): 
    plt.figure()
    plt.title(str(biaslist[bias])+' bias')
    for trial in range(20):
        plt.plot([1,2],mean_pair[bias][trial],label='1000-16000;25000-40000')
    for trial in range(20):
        plt.plot([3,4],mean_pair2[bias][trial],label='10000-20000;30000-40000')
    for trial in range(20):
        plt.plot([5,6],mean_pair3[bias][trial],label='1000-7000;33000-40000')
    plt.xlim(0.5,6.5)


    

In [70]:

    

for bias in range(len(biaslist)):
    plt.figure()
    plt.title(str(biaslist[bias])+' bias')
    plt.errorbar([1,1.5],[np.mean([mean_pair[bias][trial][0] for trial in range(20)]),np.mean([mean_pair[bias][trial][1] for trial in range(20)])],yerr=[np.std([mean_pair[bias][trial][0] for trial in range(20)])/math.sqrt(20),np.std([mean_pair[bias][trial][1] for trial in range(20)])/math.sqrt(20)],label='1000-16000;25000-40000')
#     plt.ylim(0.035,0.039)
    plt.errorbar([1.1,1.6],[np.mean([mean_pair2[bias][trial][0] for trial in range(20)]),np.mean([mean_pair2[bias][trial][1] for trial in range(20)])],yerr=[np.std([mean_pair2[bias][trial][0] for trial in range(20)])/math.sqrt(20),np.std([mean_pair2[bias][trial][1] for trial in range(20)])/math.sqrt(20)],label='10000-20000;30000-40000')
    # plt.ylim(0.035,0.039)
    plt.errorbar([1.2,1.7],[np.mean([mean_pair3[bias][trial][0] for trial in range(20)]),np.mean([mean_pair3[bias][trial][1] for trial in range(20)])],yerr=[np.std([mean_pair3[bias][trial][0] for trial in range(20)])/math.sqrt(20),np.std([mean_pair3[bias][trial][1] for trial in range(20)])/math.sqrt(20)],label='1000-7000;33000-40000')
    # plt.ylim(0.035,0.039)
    plt.xlim(0.9,1.8)
    plt.legend()


    

In [52]:

    

import math
plt.figure()
for trial in range(20):
    plt.plot([1,2],mean_pair[trial])
plt.figure()
for trial in range(20):
    plt.plot([1,2],mean_pair2[trial])
plt.figure()
for trial in range(20):
    plt.plot([1,2],mean_pair3[trial])
plt.figure()
sns.distplot([mean_pair[trial][0] for trial in range(20)],label='1000-16000',norm_hist=False)
sns.distplot([mean_pair[trial][1] for trial in range(20)],label='25000-40000',norm_hist=False)
plt.legend()
plt.figure()
sns.distplot([mean_pair2[trial][0] for trial in range(20)],label='10000-20000',norm_hist=False)
sns.distplot([mean_pair2[trial][1] for trial in range(20)],label='30000-40000',norm_hist=False)
plt.legend()
plt.figure()
sns.distplot([mean_pair3[trial][0] for trial in range(20)],label='1000-7000',norm_hist=False)
sns.distplot([mean_pair3[trial][1] for trial in range(20)],label='33000-40000',norm_hist=False)
plt.legend()
plt.figure()
plt.errorbar([1,2],[np.mean([mean_pair[trial][0] for trial in range(20)]),np.mean([mean_pair[trial][1] for trial in range(20)])],yerr=[np.std([mean_pair[trial][0] for trial in range(20)])/math.sqrt(20),np.std([mean_pair[trial][1] for trial in range(20)])/math.sqrt(20)])
# plt.ylim(0.035,0.039)
plt.xlim(0.9,2.1)
plt.figure()
plt.errorbar([1,2],[np.mean([mean_pair2[trial][0] for trial in range(20)]),np.mean([mean_pair2[trial][1] for trial in range(20)])],yerr=[np.std([mean_pair2[trial][0] for trial in range(20)])/math.sqrt(20),np.std([mean_pair2[trial][1] for trial in range(20)])/math.sqrt(20)])
# plt.ylim(0.035,0.039)
plt.xlim(0.9,2.1)
plt.figure()
plt.errorbar([1,2],[np.mean([mean_pair3[trial][0] for trial in range(20)]),np.mean([mean_pair3[trial][1] for trial in range(20)])],yerr=[np.std([mean_pair3[trial][0] for trial in range(20)])/math.sqrt(20),np.std([mean_pair3[trial][1] for trial in range(20)])/math.sqrt(20)])
# plt.ylim(0.035,0.039)
plt.xlim(0.9,2.1)


    

    
Out[52]:





(0.9, 2.1)






    













    













    













    













    













    













    













    













    

In [25]:

    

means2 = []
cell_means2 = []
strands_means2 = []
medians2 = []
cell_medians2 = []
strands_medians2 = []
for trial in range(20):
    means2.append([])
    cell_means2.append([])
    strands_means2.append([])
    medians2.append([])
    cell_medians2.append([])
    strands_medians2.append([])
    for window in range(1001,40001,100):
        means2[trial].append(np.mean(single_set_motif[trial][1000:window]))
        cell_means2[trial].append(np.mean(single_set_cell[trial][1000:window]))
        strands_means2[trial].append(np.mean(single_set_strands[trial][1000:window]))
        medians2[trial].append(np.median(single_set_motif[trial][1000:window]))
        cell_medians2[trial].append(np.median(single_set_cell[trial][1000:window]))
        strands_medians2[trial].append(np.median(single_set_strands[trial][1000:window]))
        
# medians2 = []
# cell_medians2 = []
# strands_medians2 = []
# for trial in range(10):
#     medians2.append([])
#     cell_medians2.append([])
#     strands_medians2.append([])
#     for window in range(1001,7001,1):
#         medians2[trial].append(np.median(single_set_motif[trial][1000:window]))
#         cell_medians2[trial].append(np.median(single_set_cell[trial][1000:window]))
#         strands_medians2[trial].append(np.median(single_set_strands[trial][1000:window]))


    

In [26]:

    

plt.figure()
for trial in range(20):
    plt.plot(range(1001,40001,100),means2[trial])
plt.title('Motif Mean')
plt.figure()
for trial in range(20):
    plt.plot(range(1001,40001,100),medians2[trial])
plt.title('Motif Median')

plt.figure()
for trial in range(20):
    plt.plot(range(1001,40001,100),cell_means2[trial])
plt.title('Cell Mean')
plt.figure()
for trial in range(20):
    plt.plot(range(1001,40001,100),cell_medians2[trial])
plt.title('Cell Median')

plt.figure()
for trial in range(20):
    plt.plot(range(1001,40001,100),strands_means2[trial])
plt.title('Strands Mean')
plt.figure()
for trial in range(20):
    plt.plot(range(1001,40001,100),strands_medians2[trial])
plt.title('Strands Median')


    

    
Out[26]:





<matplotlib.text.Text at 0x11c7ccf90>






    













    













    













    













    













    

In [164]:

    

motifs_sliding = []
cell_sliding = []
strands_sliding = []
for trial in range(1):
    motifs_sliding.append([])
    cell_sliding.append([])
    strands_sliding.append([])
    for window in range(1,6001,1):
        motifs_sliding[trial].append(np.mean([single_set_motif[trial][current:current+window] for current in range(1000,7000-window+1)]))
#         cell_sliding[trial].append(np.mean(single_set_cell[trial][1000:window]))
#         strands_sliding[trial].append(np.mean(single_set_strands[trial][1000:window]))


    

    




---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-164-ea1cfb6a82ab> in <module>()
      7     strands_sliding.append([])
      8     for window in range(1,6001,1):
----> 9         motifs_sliding[trial].append(np.mean([single_set_motif[trial][current:current+window] for current in range(1000,7000-window+1)]))
     10 #         cell_sliding[trial].append(np.mean(single_set_cell[trial][1000:window]))
     11 #         strands_sliding[trial].append(np.mean(single_set_strands[trial][1000:window]))

/Users/grantkinsler/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/numpy/core/fromnumeric.pyc in mean(a, axis, dtype, out, keepdims)
   2714 
   2715     return _methods._mean(a, axis=axis, dtype=dtype,
-> 2716                             out=out, keepdims=keepdims)
   2717 
   2718 def std(a, axis=None, dtype=None, out=None, ddof=0, keepdims=False):

/Users/grantkinsler/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/numpy/core/_methods.pyc in _mean(a, axis, dtype, out, keepdims)
     48 
     49 def _mean(a, axis=None, dtype=None, out=None, keepdims=False):
---> 50     arr = asanyarray(a)
     51 
     52     rcount = _count_reduce_items(arr, axis)

/Users/grantkinsler/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/numpy/core/numeric.pyc in asanyarray(a, dtype, order)
    510 
    511     """
--> 512     return array(a, dtype, copy=False, order=order, subok=True)
    513 
    514 def ascontiguousarray(a, dtype=None):

KeyboardInterrupt: 

In [ ]:

    

plt.figure()
for trial in range(10):
    plt.plot(range(1,6001,1),motifs_sliding[trial])
plt.title('Motifs')
plt.figure()
for trial in range(10):
    plt.plot(range(1,6001,1),cell_sliding[trial])
plt.title('Cells')
plt.figure()
for trial in range(10):
    plt.plot(range(1,6001,1),strands_sliding[trial])
plt.title('Strands')


    

In [183]:

    

for motif in range(len(motiflist)):
    for bias in range(len(biaslist)):
#         for item in range(5,len(word_list[motif][bias])):
            for item in [5,6,7]:
#             print item
                ans = stats.kstest(word_list[motif][bias][item],'norm') # Kolmorgorov-Smirnov Test
#             print ans
                if ans[1] < 0.05:
                    print motif, bias, item, ans


    

    




0 0 5 (0.51482006944483882, 7.8181905394103524e-13)
0 0 6 (0.79709960703074723, 0.0)
0 0 7 (0.79808483706519873, 0.0)
0 1 5 (0.51916685140503283, 4.6518344731794059e-13)
0 1 6 (0.79710694903867541, 0.0)
0 1 7 (0.80620605472342088, 0.0)
0 2 5 (0.52380519030496209, 2.6556534749033744e-13)
0 2 6 (0.797244158901248, 0.0)
0 2 7 (0.81433905442116383, 0.0)
0 3 5 (0.52891919772702989, 1.4210854715202004e-13)
0 3 6 (0.79707136705979864, 0.0)
0 3 7 (0.81953646679534109, 0.0)
0 4 5 (0.53335106455100467, 8.2156503822261584e-14)
0 4 6 (0.79714365669788978, 0.0)
0 4 7 (0.82199639738523511, 0.0)
0 5 5 (0.53696742715428591, 5.2180482157382357e-14)
0 5 6 (0.79688661977623454, 0.0)
0 5 7 (0.82350362776236774, 0.0)
0 6 5 (0.5394127425572226, 3.8413716652030416e-14)
0 6 6 (0.79691148458306904, 0.0)
0 6 7 (0.82350362776236763, 0.0)
0 7 5 (0.5387109997670132, 4.1966430330830917e-14)
0 7 6 (0.79714648019965073, 0.0)
0 7 7 (0.82391799071234928, 0.0)
0 8 5 (0.5348483997609812, 6.8167693711984612e-14)
0 8 6 (0.797107513801943, 0.0)
0 8 7 (0.81958902677504719, 0.0)
0 9 5 (0.5282038582497145, 1.5520917884259688e-13)
0 9 6 (0.7972125434385875, 0.0)
0 9 7 (0.8092674533861175, 0.0)
0 10 5 (0.52436242204145334, 2.48245868306185e-13)
0 10 6 (0.79719616998792309, 0.0)
0 10 7 (0.78371457993783133, 0.0)
1 0 5 (0.51453676167833362, 8.0846440653203899e-13)
1 0 6 (0.79715664461160318, 0.0)
1 0 7 (0.7980285189194487, 0.0)
1 1 5 (0.518744928281897, 4.89386309254769e-13)
1 1 6 (0.79710807856427146, 0.0)
1 1 7 (0.80735757287483201, 0.0)
1 2 5 (0.52269987434349352, 3.0375701953744283e-13)
1 2 6 (0.79701544499204391, 0.0)
1 2 7 (0.81514054148755566, 0.0)
1 3 5 (0.52801748384610725, 1.5876189252139739e-13)
1 3 6 (0.79721084966997269, 0.0)
1 3 7 (0.82272503640343597, 0.0)
1 4 5 (0.53237883710663969, 9.2592600253738055e-14)
1 4 6 (0.79701600990742227, 0.0)
1 4 7 (0.82603192360155775, 0.0)
1 5 5 (0.5355513359868892, 6.2394533983933798e-14)
1 5 6 (0.79706515395116306, 0.0)
1 5 7 (0.82940078897241887, 0.0)
1 6 5 (0.53698092978130274, 5.2180482157382357e-14)
1 6 6 (0.79716737338302412, 0.0)
1 6 7 (0.83066589386932388, 0.0)
1 7 5 (0.53576337425352216, 6.0840221749458578e-14)
1 7 6 (0.79725432038875688, 0.0)
1 7 7 (0.83172391608170937, 0.0)
1 8 5 (0.5300561207358393, 1.2345680033831741e-13)
1 8 6 (0.7970984774769807, 0.0)
1 8 7 (0.83127099975683416, 0.0)
1 9 5 (0.51938638106953128, 4.531930386519889e-13)
1 9 6 (0.79706571878391574, 0.0)
1 9 7 (0.8295022194905135, 0.0)
1 10 5 (0.50461581256348575, 2.5843771567224394e-12)
1 10 6 (0.79721310802624767, 0.0)
1 10 7 (0.81747913948483175, 0.0)

In [204]:

    

for motif in range(len(motiflist)):
    for bias in range(len(biaslist)):
#         for item in range(5,len(word_list[motif][bias])):
        for item in [5,6,7]:
#             print item
            ans = stats.shapiro(word_list[motif][bias][item]) # Shapiro-Wilk test 
#             print ans
            if ans[1] < 0.05:
                print motiflist[motif], biaslist[bias], item, ans
                print stats.kstest(word_list[motif][bias][item],'norm')
                print stats.anderson(word_list[motif][bias][item],dist='norm')
#                 plt.figure()
#                 sm.qqplot(np.array(word_list[motif][bias][item]),dist=norm,fit=True,line='45')
                plt.figure()
                sns.distplot(word_list[motif][bias][item],kde=True,fit=norm)


    

    




10000 0.75 6 (0.9409385323524475, 0.014677424915134907)
(0.79688661977623454, 0.0)
(1.1746073551961658, array([ 0.538,  0.613,  0.736,  0.858,  1.021]), array([ 15. ,  10. ,   5. ,   2.5,   1. ]))
00001 0.5 5 (0.8792614936828613, 0.00010627110168570653)
(0.51453676167833362, 8.0846440653203899e-13)
(1.825867640017627, array([ 0.538,  0.613,  0.736,  0.858,  1.021]), array([ 15. ,  10. ,   5. ,   2.5,   1. ]))
00001 0.5 7 (0.9321839809417725, 0.006690580863505602)
(0.7980285189194487, 0.0)
(1.1358388214247412, array([ 0.538,  0.613,  0.736,  0.858,  1.021]), array([ 15. ,  10. ,   5. ,   2.5,   1. ]))






    













    













    

In [95]:

    

# Plotting the Distribution of Means 
print len(word_list[0][0][5])
plt.figure()
sns.distplot(word_list[0][0][5],fit=norm,kde=False,norm_hist=False)
plt.figure()
sns.distplot(word_list[0][1][5],fit=norm,kde=False,norm_hist=False)
plt.figure()
sns.distplot(word_list[0][2][5],fit=norm,kde=False,norm_hist=False)
plt.figure()
sns.distplot(word_list[0][3][5],fit=norm,kde=False,norm_hist=False)


    

    




50






    
Out[95]:





<matplotlib.axes._subplots.AxesSubplot at 0x11c05f350>






    













    













    













    

In [72]:

    

# Plotting Cell Distribution
print word_list[0][0][6]
plt.figure()
sns.distplot(word_list[0][0][6],fit=norm,kde=True,norm_hist=True)
plt.figure()
sns.distplot(word_list[0][1][6],fit=norm,kde=True,norm_hist=False)
plt.figure()
sns.distplot(word_list[0][2][6],fit=norm,kde=True,norm_hist=False)
plt.figure()
sns.distplot(word_list[0][3][6],fit=norm,kde=True,norm_hist=False)


    

    




[0.8332226666666664, 0.8325553333333331, 0.8338746666666664, 0.8333453333333333, 0.8329973333333333, 0.8331493333333339, 0.8332126666666666, 0.8332626666666674, 0.8340740000000001, 0.8329753333333336, 0.8328246666666665, 0.8339919999999998, 0.8325093333333332, 0.8340273333333332, 0.8342759999999996, 0.8339553333333334, 0.8331479999999998, 0.8322286666666666, 0.8323699999999999, 0.8343373333333339, 0.8340486666666662, 0.8336180000000001, 0.8338506666666667, 0.8329153333333333, 0.8322786666666666, 0.8329180000000004, 0.8325093333333332, 0.8326706666666664, 0.8330553333333333, 0.8324733333333333, 0.832362, 0.833538, 0.8321826666666665, 0.8328306666666666, 0.8335199999999999, 0.834026, 0.8330473333333335, 0.8313886666666662, 0.8353199999999998, 0.833484666666666, 0.8319446666666666, 0.8334333333333335, 0.8336460000000004, 0.8327940000000001, 0.8333066666666669, 0.8331999999999998, 0.8334539999999999, 0.8337280000000001, 0.8325873333333335, 0.8333846666666669]






    
Out[72]:





<matplotlib.axes._subplots.AxesSubplot at 0x1190aeb90>






    













    













    













    

In [75]:

    

# Plotting within Sample Distribution for Motifs
print word_list[0][0][8]
plt.figure()
sns.distplot(word_list[0][0][8],bins=10,fit=norm,kde=True,norm_hist=True)
plt.figure()
sns.distplot(word_list[0][0][9],bins=10,fit=norm,kde=True,norm_hist=True)
plt.figure()
sns.distplot(word_list[0][0][10],bins=10,fit=norm,kde=True,norm_hist=True)
plt.figure()
sns.distplot(word_list[0][0][11],bins=10,fit=norm,kde=True,norm_hist=True)
plt.figure()
sns.distplot(word_list[0][0][12],bins=10,fit=norm,kde=True,norm_hist=True)
# sns.distplot(word_list[0][0][11],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][12],bins=10,fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][13],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][14],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][15],bins=10,fit=norm,kde=False,norm_hist=False)


    

    




[0.03399265663863556, 0.03938782773757266, 0.03821579264617239, 0.0368901706320596, 0.03946583999046143, 0.037771934018646904, 0.03713080168776371, 0.03588690188496858, 0.034499455271758864, 0.04239609384303918, 0.0351506456241033, 0.035155776457752454, 0.04122974261201144, 0.039024975984630166, 0.04105991883504417, 0.039140352983551445, 0.0392512077294686, 0.038063966922047915, 0.0373618452666987, 0.03040459660043093, 0.0378176562688185, 0.03671602263151559, 0.034623707622024526, 0.034335273850540575, 0.038102084831056794, 0.03750748951467945, 0.03442916915720263, 0.032790808999521304, 0.038137632338787295, 0.04131534569983136, 0.03816331475648171, 0.04072666824982189, 0.035795251163345664, 0.037350417019219144, 0.032968340871221136, 0.03619801030804267, 0.037438305043938844, 0.039581328200192493, 0.04083333333333333, 0.03946102021174206, 0.03796108392025785, 0.040582477918357604, 0.0380859375, 0.03733493397358944, 0.03793352601156069, 0.03879566821373319, 0.03547459252157239, 0.03830863751355258, 0.035479951397326855, 0.03550011993283761, 0.040395614871306, 0.036792112540579534, 0.031992244304411055, 0.03671602263151559, 0.039516225601724346, 0.039493910370107604, 0.03984206748025843, 0.03656635894976622, 0.031757575757575755, 0.03489483747609943, 0.03768326669090028, 0.037116858237547894, 0.03742676073179481, 0.040096038415366145, 0.03846616179829306, 0.038792074480783006, 0.036098493903896724, 0.04092163686547462, 0.04019678425725942, 0.03702801461632156, 0.0406464841394283, 0.03812597107684953, 0.0405982905982906, 0.03332935133197945, 0.034834834834834835, 0.032053582107403424, 0.04009205426356589, 0.041706615532118886, 0.0373676068070927, 0.041948742746615086, 0.037891465455414775, 0.04152207730046668, 0.04002389486260454, 0.035385534967124925, 0.036525291361287994, 0.04012976090352036, 0.03733843944471039, 0.034703748488512695, 0.03781261218140481, 0.03897509924215085, 0.042831215970961886, 0.04249224158510384, 0.04126679462571977, 0.03524441762220881, 0.03544119431969899, 0.042606817090734515, 0.034462055715658024, 0.0390465924062762, 0.03583842742418794, 0.04111548087236325, 0.03850345078096622, 0.035623409669211195, 0.04151580979966208, 0.04020282506338283, 0.0379429662331464, 0.04105501849862752, 0.03667153996101365, 0.03985550872968092, 0.03676733914289125, 0.03802189868848514, 0.03857566765578635, 0.03883023904865914, 0.03870043000477783, 0.03430841459010473, 0.03777939747327502, 0.04084098598356694, 0.03951661631419939, 0.04102870813397129, 0.03674979119436821, 0.04226532567049809, 0.0401477245651656, 0.037742674544796816, 0.03884546001202646, 0.03701478187717822, 0.03535536989950357, 0.038576734155984185, 0.0390465924062762, 0.0360997841208923, 0.039980904642558775, 0.03749848796419499, 0.039674952198852774, 0.041250594388968144, 0.03703261259108828, 0.03946273624153097, 0.038512139696208585, 0.04015967098100883, 0.03754184600669536, 0.03819361037713188, 0.03791412510465255, 0.043220338983050846, 0.0393719519448079, 0.033023984572737135, 0.04040889957907396, 0.04404237590763004, 0.03660146405856234, 0.03948620361560418, 0.037459478929043104, 0.034819937991891245, 0.03751941689568646, 0.034123222748815164]






    
Out[75]:





<matplotlib.axes._subplots.AxesSubplot at 0x11b610890>






    













    













    













    













    

In [79]:

    

print word_list[0][0][8+50+1]
plt.figure()

# sns.distplot(word_list[0][0][8+50+1],fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][8+50+2],fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][8+50+3],fit=norm,kde=False,norm_hist=True)

sns.distplot(word_list[0][0][9],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][10],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][11],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][12],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][13],kde=False,norm_hist=True)
plt.xlim(0.025,0.05)
plt.figure()
sns.distplot(word_list[0][0][5],fit=norm,kde=False,norm_hist=True)
plt.xlim(0.025,0.05)


    

    




[0.8325, 0.824, 0.83, 0.8262, 0.8376, 0.8412, 0.8394, 0.8292, 0.8216, 0.8328, 0.8336, 0.8328, 0.833, 0.8302, 0.8395, 0.8315, 0.8424, 0.8291, 0.8357, 0.8268, 0.8444, 0.8362, 0.8241, 0.8322, 0.8282, 0.8264, 0.8365, 0.8291, 0.8371, 0.8234, 0.8401, 0.8303, 0.8374, 0.8342, 0.8351, 0.8257, 0.835, 0.8412, 0.8381, 0.8246, 0.8448, 0.8369, 0.8355, 0.835, 0.8346, 0.8334, 0.8357, 0.8234, 0.8333, 0.8251, 0.8259, 0.8366, 0.8388, 0.8209, 0.8288, 0.8444, 0.8396, 0.8379, 0.8331, 0.8288, 0.8358, 0.833, 0.833, 0.8374, 0.8274, 0.826, 0.8336, 0.8285, 0.8324, 0.8305, 0.8321, 0.8274, 0.8351, 0.8346, 0.8304, 0.8434, 0.8327, 0.8321, 0.8371, 0.8304, 0.8306, 0.8374, 0.8273, 0.833, 0.842, 0.8321, 0.8264, 0.8351, 0.8351, 0.8283, 0.8384, 0.8332, 0.8411, 0.829, 0.8317, 0.8355, 0.8302, 0.8274, 0.8351, 0.836, 0.8196, 0.8278, 0.829, 0.8348, 0.8233, 0.8438, 0.8315, 0.8366, 0.8302, 0.8233, 0.8372, 0.837, 0.8357, 0.8358, 0.8305, 0.8279, 0.8312, 0.8311, 0.8285, 0.8252, 0.8383, 0.8295, 0.8357, 0.8464, 0.8262, 0.8276, 0.8359, 0.8312, 0.8411, 0.8231, 0.8385, 0.8319, 0.8294, 0.8335, 0.8236, 0.8305, 0.8383, 0.8252, 0.8376, 0.8345, 0.8324, 0.8283, 0.8347, 0.8339, 0.8343, 0.8274, 0.832, 0.8235, 0.8265, 0.8336]






    
Out[79]:





(0.025, 0.05)






    













    

In [78]:

    

print word_list[0][0][8+50+1]
plt.figure()

# sns.distplot(word_list[0][0][8+50+1],fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][8+50+2],fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][8+50+3],fit=norm,kde=False,norm_hist=True)

sns.distplot(word_list[0][0][8+50+1],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][8+50+2],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][8+50+3],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][8+50+4],kde=False,norm_hist=True)
sns.distplot(word_list[0][0][8+50+5],kde=False,norm_hist=True)
plt.xlim(0.815,0.855)
plt.figure()
sns.distplot(word_list[0][0][6],fit=norm,kde=False,norm_hist=True)
plt.xlim(0.815,0.855)
# plt.hist(word_list[0][0][8+50+1],normed=True)
# plt.hist(word_list[0][0][8+50+2],normed=True)
# plt.hist(word_list[0][0][8+50+3],normed=True)
# plt.hist(word_list[0][0][8+50+4],normed=True)
# plt.hist(word_list[0][0][8+50+5],normed=True)

# plt.hist(word_list[0][0][6],normed=True)

# sns.distplot(word_list[0][0][8+50+1],bins=10,fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][8+50+2],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][10],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][11],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][12],bins=10,fit=norm,kde=False,norm_hist=True)
# sns.distplot(word_list[0][0][8+50+6],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][14],bins=10,fit=norm,kde=False,norm_hist=False)
# sns.distplot(word_list[0][0][15],bins=10,fit=norm,kde=False,norm_hist=False)


    

    




[0.8325, 0.824, 0.83, 0.8262, 0.8376, 0.8412, 0.8394, 0.8292, 0.8216, 0.8328, 0.8336, 0.8328, 0.833, 0.8302, 0.8395, 0.8315, 0.8424, 0.8291, 0.8357, 0.8268, 0.8444, 0.8362, 0.8241, 0.8322, 0.8282, 0.8264, 0.8365, 0.8291, 0.8371, 0.8234, 0.8401, 0.8303, 0.8374, 0.8342, 0.8351, 0.8257, 0.835, 0.8412, 0.8381, 0.8246, 0.8448, 0.8369, 0.8355, 0.835, 0.8346, 0.8334, 0.8357, 0.8234, 0.8333, 0.8251, 0.8259, 0.8366, 0.8388, 0.8209, 0.8288, 0.8444, 0.8396, 0.8379, 0.8331, 0.8288, 0.8358, 0.833, 0.833, 0.8374, 0.8274, 0.826, 0.8336, 0.8285, 0.8324, 0.8305, 0.8321, 0.8274, 0.8351, 0.8346, 0.8304, 0.8434, 0.8327, 0.8321, 0.8371, 0.8304, 0.8306, 0.8374, 0.8273, 0.833, 0.842, 0.8321, 0.8264, 0.8351, 0.8351, 0.8283, 0.8384, 0.8332, 0.8411, 0.829, 0.8317, 0.8355, 0.8302, 0.8274, 0.8351, 0.836, 0.8196, 0.8278, 0.829, 0.8348, 0.8233, 0.8438, 0.8315, 0.8366, 0.8302, 0.8233, 0.8372, 0.837, 0.8357, 0.8358, 0.8305, 0.8279, 0.8312, 0.8311, 0.8285, 0.8252, 0.8383, 0.8295, 0.8357, 0.8464, 0.8262, 0.8276, 0.8359, 0.8312, 0.8411, 0.8231, 0.8385, 0.8319, 0.8294, 0.8335, 0.8236, 0.8305, 0.8383, 0.8252, 0.8376, 0.8345, 0.8324, 0.8283, 0.8347, 0.8339, 0.8343, 0.8274, 0.832, 0.8235, 0.8265, 0.8336]






    
Out[78]:





(0.815, 0.855)






    













    

In [11]:

    

# import random
# import numpy as np

# numSamples = 50

# sample_list = []

# for motif in range(len(motiflist)):
#     sample_list.append([])
#     for bias in range(len(biaslist)):
#         sample_list[motif].append([])
#         for trial in range(0,numTrials*3,3):
#             sample_list[motif][bias].append(np.mean(random.sample(datalist[motif][bias][trial][equil_start:numRounds],numSamples)))


    

In [5]:

    

motifcomposition_list = ["All 0","One 1","Two 1","Three 1","Four 1","All 1"]
motifcomposition_indices = []
for count_wanted in range(len(motifcomposition_list)):
    motifcomposition_indices.append([])
    for motif in motiflist:
        if motif.count('1') == count_wanted:
            motifcomposition_indices[count_wanted].append(motiflist.index(motif))


    

In [13]:

    

len(sample_list[0][0])


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-13-8f667b936ba5> in <module>()
----> 1 len(sample_list[0][0])

NameError: name 'sample_list' is not defined

In [6]:

    

import numpy as np
import math

equil_list = []

for motifcomposition in range(len(motifcomposition_list)):
    equil_list.append([])
    for bias in range(len(biaslist)):
        temp_sample_list = []
        for index in motifcomposition_indices[motifcomposition]:
            temp_sample_list += motif_mean[index][bias]
        equil_list[motifcomposition].append([np.mean(temp_sample_list),np.std(temp_sample_list),np.std(temp_sample_list)/math.sqrt(len(temp_sample_list))])


    

In [8]:

    

# %matplotlib inline
# import matplotlib.pyplot as plt
# import seaborn as sns

fig1 = plt.figure()
# fig1.set_figwidth(10)
# fig1.set_figheight(5)
sns.set_color_codes()
sns.set_palette(palette=['b','g','r','m','y','c'])
for motifcomposition in range(len(motifcomposition_list)):
    motifcomposition_mean_list = []
    motifcomposition_ci_list = []
    for bias in range(len(biaslist)):
        motifcomposition_mean_list.append(equil_list[motifcomposition][bias][0])
        motifcomposition_ci_list.append(1.96*equil_list[motifcomposition][bias][2])
    plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
plt.legend(loc='upper center',fontsize=18)
plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
# plt.ylim(0,0.11)
plt.xlabel(r"$b$",fontsize=20)
plt.ylabel('Motif Frequency at Steady State',fontsize=18)
current_palette = sns.color_palette()
plt.tick_params(labelsize=18)
# sns.despine()

fig1.savefig("motifcomposition_alldata_nogridticks_usetex_fontsize_allbias_newcaption_ipython_biglist_{}samples.pdf".format(numSamples),rasterized=True,bbox_inches='tight',pad_inches=0.1)


    

In [21]:

    




    

    




[(0.3333333333333333, 0.6588235294117647, 0.40784313725490196), (0.7686274509803922, 0.3058823529411765, 0.3215686274509804), (0.5058823529411764, 0.4470588235294118, 0.6980392156862745), (0.8, 0.7254901960784313, 0.4549019607843137), (0.39215686274509803, 0.7098039215686275, 0.803921568627451)]
[(0.7686274509803922, 0.3058823529411765, 0.3215686274509804), (0.5058823529411764, 0.4470588235294118, 0.6980392156862745), (0.8, 0.7254901960784313, 0.4549019607843137), (0.39215686274509803, 0.7098039215686275, 0.803921568627451)]

In [35]:

    

with sns.color_palette(current_palette[1:]):
    fig1 = plt.figure()
    # fig1.set_figwidth(10)
    # fig1.set_figheight(5)
    for motifcomposition in range(1,len(motifcomposition_list)):
        motifcomposition_mean_list = []
        motifcomposition_ci_list = []
        for bias in range(len(biaslist)):
            motifcomposition_mean_list.append(equil_list[motifcomposition][bias][0])
            motifcomposition_ci_list.append(1.96*equil_list[motifcomposition][bias][2])
        plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
    plt.legend(loc='upper left')
    plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
    # plt.ylim(0,0.11)
    plt.xlabel('Bias')
    plt.ylabel('Motif Frequency at Steady State')


#     fig1.savefig("motifcomposition_sansallzero_allbias_ipython_biglist_{}samples.pdf".format(numSamples),rasterized=True)


    

In [9]:

    

with sns.color_palette(current_palette[1:]):
    fig1 = plt.figure()
    # fig1.set_figwidth(10)
    # fig1.set_figheight(5)
    for motifcomposition in range(1,len(motifcomposition_list)-1):
        motifcomposition_mean_list = []
        motifcomposition_ci_list = []
        for bias in range(len(biaslist)):
            motifcomposition_mean_list.append(equil_list[motifcomposition][bias][0])
            motifcomposition_ci_list.append(1.96*equil_list[motifcomposition][bias][2])
        plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
    plt.legend(loc='upper center',fontsize=18)
    plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
    # plt.ylim(0,0.11)
    plt.xlabel(r"$b$",fontsize=20)
    plt.ylabel('Motif Frequency at Steady State',fontsize=18)
    current_palette = sns.color_palette()
    plt.tick_params(labelsize=18)


    fig1.savefig("motifcomposition_sansall_allbias_usetex_fontsize_nogridticks_newcaption_ipython_biglist_{}samples.pdf".format(numSamples),rasterized=True,bbox_inches='tight',pad_inches=0.1)


    

In [37]:

    

print sample_list[0][0]


    

    




[0.026190766232184189, 0.02947900372999639, 0.027454741637693323, 0.023474178403755867, 0.027667029116829771, 0.024585272705573459, 0.024402029475718772, 0.025591733749849813, 0.023937120400142908, 0.025131641933939686, 0.030201342281879196, 0.024334417540055414, 0.030422805126362439, 0.026353617632965981, 0.026256116481680393, 0.029432964920711197, 0.028334321280379372, 0.027166726770044475, 0.027485659655831739, 0.021616428485649094, 0.027247956403269755, 0.029461279461279462, 0.022639691714836225, 0.024634705953387272, 0.025970873786407767, 0.027036684135302524, 0.024428779776373359, 0.027817574021012415, 0.025650289017341042, 0.024223528000959348, 0.026752657351009197, 0.027527347036903474, 0.023579201934703749, 0.025831140875388663, 0.030842797369994023, 0.027926960257787327, 0.025974025974025976, 0.02708912806869029, 0.025780682643427741, 0.028087864602088584, 0.026959322438267923, 0.027744558718010046, 0.025087024366822711, 0.024823964673588734, 0.024885237980188452, 0.026331466698439176, 0.030335992264926274, 0.025470787059391597, 0.025426807119505995, 0.026210895035632321]

In [53]:

    

pooled_equil_list = []

for motifcomposition in range(len(motifcomposition_list)):
    pooled_equil_list.append([])
    for bias in range(len(biaslist)):
        temp_mean = np.mean([np.mean(motif_mean[index][bias]) for index in motifcomposition_indices[motifcomposition]])
        temp_std = math.sqrt(sum([len(motif_mean[index][bias])*np.var(motif_mean[index][bias]) for index in motifcomposition_indices[motifcomposition]]) / sum([len(motif_mean[index][bias])-1 for index in motifcomposition_indices[motifcomposition]]))
        temp_se = 1.96*temp_std*math.sqrt(sum([1/len(motif_mean[index][bias]) for index in motifcomposition_indices[motifcomposition]]))
        pooled_equil_list[motifcomposition].append([temp_mean,temp_std,temp_se])


    

In [41]:

    

fig1 = plt.figure()
# fig1.set_figwidth(10)
# fig1.set_figheight(5)
sns.set_color_codes()
sns.set_palette(palette=['b','g','r','m','y','c'])
for motifcomposition in range(len(motifcomposition_list)):
    motifcomposition_mean_list = []
    motifcomposition_ci_list = []
    for bias in range(len(biaslist)):
        motifcomposition_mean_list.append(pooled_equil_list[motifcomposition][bias][0])
        motifcomposition_ci_list.append(pooled_equil_list[motifcomposition][bias][2])
    plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
plt.legend(loc='upper center')
plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
# plt.ylim(0,0.11)
plt.xlabel("Bias towards '0' monomer")
plt.ylabel('Motif Frequency at Steady State')
current_palette = sns.color_palette()

# fig1.savefig("motifcomposition_alldata_allbias_newcaption_ipython_pooled_{}samples.pdf".format(numSamples),rasterized=True)


    

In [42]:

    

with sns.color_palette(current_palette[1:]):
    fig1 = plt.figure()
    # fig1.set_figwidth(10)
    # fig1.set_figheight(5)
    for motifcomposition in range(1,len(motifcomposition_list)-1):
        motifcomposition_mean_list = []
        motifcomposition_ci_list = []
        for bias in range(len(biaslist)):
            motifcomposition_mean_list.append(pooled_equil_list[motifcomposition][bias][0])
            motifcomposition_ci_list.append(pooled_equil_list[motifcomposition][bias][2])
        plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
    plt.legend(loc='upper center')
    plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
    # plt.ylim(0,0.11)
    plt.xlabel("Bias towards '0' monomer")
    plt.ylabel('Motif Frequency at Steady State')


#     fig1.savefig("motifcomposition_sansall_allbias_newcaption_ipython_pooled_{}samples.pdf".format(numSamples),rasterized=True)÷


    

In [27]:

    

naive_equil_list = []

for motifcomposition in range(len(motifcomposition_list)):
    naive_equil_list.append([])
    for bias in range(len(biaslist)):
        
        temp_mean = np.mean([np.mean(sample_list[index][bias]) for index in motifcomposition_indices[motifcomposition]])
        temp_std = np.std([np.mean(sample_list[index][bias]) for index in motifcomposition_indices[motifcomposition]])
        temp_se = 1.96*temp_std/math.sqrt(len(motifcomposition_indices[motifcomposition]))
        naive_equil_list[motifcomposition].append([temp_mean,temp_std,temp_se])


    

In [47]:

    

fig1 = plt.figure()
# fig1.set_figwidth(10)
# fig1.set_figheight(5)
sns.set_color_codes()
sns.set_palette(palette=['b','g','r','m','y','c'])
for motifcomposition in range(len(motifcomposition_list)):
    motifcomposition_mean_list = []
    motifcomposition_ci_list = []
    for bias in range(len(biaslist)):
        motifcomposition_mean_list.append(naive_equil_list[motifcomposition][bias][0])
        motifcomposition_ci_list.append(naive_equil_list[motifcomposition][bias][2])
    plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
plt.legend(loc='upper center')
plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
# plt.ylim(0,0.11)
plt.xlabel("Bias towards '0' monomer")
plt.ylabel('Motif Frequency at Steady State')
current_palette = sns.color_palette()

fig1.savefig("motifcomposition_alldata_allbias_newcaption_ipython_naive_{}samples.pdf".format(numSamples),rasterized=True)


    

In [48]:

    

with sns.color_palette(current_palette[1:]):
    fig1 = plt.figure()
    # fig1.set_figwidth(10)
    # fig1.set_figheight(5)
    for motifcomposition in range(1,len(motifcomposition_list)-1):
        motifcomposition_mean_list = []
        motifcomposition_ci_list = []
        for bias in range(len(biaslist)):
            motifcomposition_mean_list.append(naive_equil_list[motifcomposition][bias][0])
            motifcomposition_ci_list.append(naive_equil_list[motifcomposition][bias][2])
        plt.errorbar(biaslist,motifcomposition_mean_list,yerr=motifcomposition_ci_list,label=motifcomposition_list[motifcomposition])
    plt.legend(loc='upper center')
    plt.xlim(min(biaslist)-0.01,max(biaslist)+0.01)
    # plt.ylim(0,0.11)
    plt.xlabel("Bias towards '0' monomer")
    plt.ylabel('Motif Frequency at Steady State')


    fig1.savefig("motifcomposition_sansall_allbias_newcaption_ipython_naive_{}samples.pdf".format(numSamples),rasterized=True)