from IPython.display import Image
Image(filename="../figure/species_OTU_IGS.png",width=800)

Image(filename="../figure/median_kmer_frequency_represent_coverage.png",width=600)

Image(filename="../figure/correlation_mapping_median_coverage.png")

Image(filename="../figure/from_reads_to_IGS.png")

Image(filename="../figure/number_of_IGS_table.png")

Image(filename="../figure/IGSs_figure.jpg",width=800)

Image(filename="../figure/e.coli_alpha_observed_full_curve.png",width=800)

Image(filename="../figure/e.coli_alpha_observed_beginning_curve.png",width=800)

Image(filename="../figure/lander_saturation.png",width=400)

Image(filename="../figure/e.coli_alpha_chao1_full_curve.png",width=800)

Image(filename="../figure/alphs_error_correct.png",width=800)

Image(filename="../figure/alphs_error_correct_chao1.png",width=800)

Image(filename="../Figure/gos_igs_begin.png", width=800)

Image(filename="../Figure/gos_chao_begin.png", width=800)

Image(filename="../Figure/gos_igs_full.png", width=800)

Image(filename="../Figure/gos_chao_full.png", width=800)

Image(filename="../figure/IGS_compare.jpg", width=800)

import pandas as pd
MH=pd.read_csv('../data/sample1_ABC.freq.IGS_abund',delimiter=' ',names = ['IGS','count'])
MH

MH=pd.read_csv('../data/sample1_ABC.freq.IGS',delimiter=' ',names = ['IGS_ID','sample1A_freq','sample1B_freq','sample1C_freq'])
MH

import pandas as pd
import numpy as np
import scipy
from IPython.display import HTML
from scipy.cluster.hierarchy import linkage, dendrogram
from scipy.spatial.distance import pdist, squareform
from IPython.display import Image
from pandas import *


GOS=pd.read_csv('../data/matrix.out',delimiter=' ',header=None)
#label=pd.read_csv('../data/config-GOS.txt',delimiter='  ',header=None)
label = GOS[0]
label_list = []
for i in GOS[0]:
    label = i.split('.')[0]
    label_list.append(label)
len(label_list)
GOS=GOS.ix[:,1:46]
GOS.columns=label_list
GOS.index=label_list
GOS=1-GOS
GOS


figure(num=None, figsize=(12, 12))
R = dendrogram(linkage(GOS, method='average'),labels=label_list, leaf_font_size=20,orientation='left')

ylabel('points')
xlabel('Height')
xlim(1,1.6)
suptitle('GOS: average', fontweight='bold', fontsize=20)

Image(filename="../Figure/comp.png")

Image(filename="../Figure/GOS1.png")

Image(filename="../figure/metahit_cluster.png")

GOS=pd.read_csv('../data/GPGC_matrix.txt',delimiter=',',header=None)
#label=pd.read_csv('../data/config-GOS.txt',delimiter='  ',header=None)
print GOS
label = GOS[0]
print label
label_list = []
for i in GOS[0]:
    label = i.split(',')[0]
    print label
    label_list.append(label)
print len(label_list)
GOS=GOS.ix[:,1:9]
GOS.columns=label_list
GOS.index=label_list

GOS


figure(num=None, figsize=(12, 12))
R = dendrogram(linkage(GOS, method='average'),labels=label_list, leaf_font_size=20,orientation='left')

ylabel('points')
xlabel('Height')
#xlim(1,1.6)
suptitle('GPGC: average', fontweight='bold', fontsize=20)

Image(filename="../figure/metahit_pca_2d.png")

Image(filename="../figure/metahit_pca_3d.png")

Image(filename="MetHit.png")