#coding:utf-8

__author__ = 'similarface'

from collections import defaultdict

PMRAdata=defaultdict(list)

for line in open('/Users/similarface/Documents/PMRA_Marker_List_Detailed2.txt','r'):

    if not line.startswith("affy_snp_id"):

        lines=line.strip().split('\t')

        PMRAdata[lines[1]].append(lines[2])

wegeneRawData=defaultdict(list)

for line in open('/Users/similarface/Documents/wegeneRawData.txt','r'):

    if not line.startswith("#"):

        lines=line.strip().split('\t')

        try:

            wegeneRawData[lines[1]].append(lines[2])

        except Exception,e:

            pass

print(wegeneRawData.keys())

v23andmeData=defaultdict(list)

for line in open('/Users/similarface/Documents/genome_wang_mian_Full_20151021231213.txt','r'):

    if not line.startswith("#"):

        lines=line.strip().split('\t')

        v23andmeData[lines[1]].append(lines[2])

PMRAdrawdata={}

for k,v in PMRAdata.items():

    PMRAdrawdata[k]=len(v)

wegeneRawdrawdata={}

for k,v in wegeneRawData.items():

    wegeneRawdrawdata[k]=len(v)

v23andmePMRAdrawdata={}

for k,v in v23andmeData.items():

    v23andmePMRAdrawdata[k]=len(v)

import numpy as np,array

from matplotlib import pyplot as plt

plt.figure(figsize=(9,6))

X =  [str(i) for i in np.arange(22)+1]+['X','Y','MT']

#X=np.arange(22)+1

#X是1,2,3,4,5,6,7,8,柱的个数

# numpy.random.uniform(low=0.0, high=1.0, size=None), normal

#uniform均匀分布的随机数，normal是正态分布的随机数，0.5-1均匀分布的数，一共有n个

Y=[]

for i in X:

   Y.append(PMRAdrawdata[i])

Y1=[]

for i in X:

   Y1.append(wegeneRawdrawdata[i])

Y2=[]

for i in X:

   Y2.append(v23andmePMRAdrawdata[i])

Y=np.array(Y)

Y1=np.array(Y1)

Y2=np.array(Y2)

plt.bar(np.arange(len(X)),Y,width=0.3,facecolor = 'green',edgecolor = 'white')

plt.bar(np.arange(len(X))+0.3,Y1,width = 0.3,facecolor = 'blue',edgecolor = 'white')

plt.bar(np.arange(len(X))+0.6,Y2,width = 0.3,facecolor = 'red',edgecolor = 'white')

plt.xticks(np.arange(len(X)),X)

plt.legend(('PMRA','wegene','23andme'))

plt.xlabel("chr")

plt.ylabel("Number of Markers")

plt.title(u"PMRA wegene 23andme 各染色体分布")

plt.show()

#coding:utf-8

__author__ = 'similarface'

import numpy as np,array

from matplotlib import pyplot as plt

plt.figure(figsize=(9,6))

X =  [str(i) for i in np.arange(22)+1]+['X','Y','MT']

Y=np.array([196416,289003,70031,411185,79632,394154])

plt.bar(np.arange(6)+0.1,Y,width=0.3,facecolor = 'green',edgecolor = 'white')

plt.xticks(np.arange(6),['P_0_0.05','P_0.05_1','w_0_0.05','w_0.05_1','23me_0_0.05','23me_0.05_1'])

k=[902676.0,902676.0,596768.0,596768.0,610565.0,610565.0]

i=0

X=np.arange(6)

for x,y in zip(X,Y):

    plt.text(x+0.25, y+0.1, '%.2f' % (y*100/k[i])+"%", ha='center', va= 'bottom')

    i=i+1

plt.xlabel(u"频率标志")

plt.ylabel("Number of Markers")

plt.title(u"PMRA wegene 23andme 频率分布")

plt.show()