-
Notifications
You must be signed in to change notification settings - Fork 1
/
otu_habitat.py
182 lines (104 loc) · 2.58 KB
/
otu_habitat.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
#!/usr/bin/python
import sys
f=open(sys.argv[1],'r')
h=open(sys.argv[2],'r')
g=open(sys.argv[3],'w')
level=sys.argv[4]
samples=f.readline().rstrip("\n").split("\t")[1:]
#get habitat data
habitat={}
for j in h:
sp=j.split("\t")[0]
hab = j.rstrip("\n").split("\t")[1]
habitat[sp]=hab
def genus(habitat,samples,f):
genhabs={}
for i in habitat.keys():
k = i.split("_")[0]
hab= habitat[i]
if k not in genhabs.keys():
genhabs[k]=[]
genhabs[k].append(hab)
else:
genhabs[k].append(hab)
#print genhabs
genprops={}
for i in genhabs.keys():
genprops[i]={}
for j in list(set(genhabs[i])):
prop=float(genhabs[i].count(j))/float(len(genhabs[i])) #get proportion of habitat in list
genprops[i][j]=prop
#print genprops
data={}
for i in f:
gen=i.split("_")[0]
line=i.rstrip("\n").split("\t")
if gen in genprops.keys():
hab=genprops[gen]
print gen, hab
for j in hab.keys():
if j not in data.keys():
data[j]=[]
for x in line[1:]:
data[j].append(float(x)*hab[j])
else:
c=-1
for x in line[1:]:
c=c+1
data[j][c]=data[j][c]+(float(x)*hab[j])
else:
hab="unknown"
if hab not in data.keys():
data[hab]=[]
for x in line[1:]:
data[hab].append(float(x))
else:
c=-1
for x in line[1:]:
c=c+1
data[hab][c]=data[hab][c]+int(float(x))
return data
#read otu table and get habitats
def species(habitat,f):
data={}
for i in f:
sp=i.split("\t")[0]
line=i.rstrip("\n").split("\t")
if sp in habitat.keys():
hab=habitat[sp]
print sp, hab
if hab not in data.keys():
data[hab]=[]
for x in line[1:]:
data[hab].append(int(float(x)))
else:
c=-1
for x in line[1:]:
c=c+1
data[hab][c]=data[hab][c]+int(float(x))
else:
hab="unknown"
print sp,hab
if hab not in data.keys():
data[hab]=[]
for x in line[1:]:
data[hab].append(int(float(x)))
else:
c=-1
for x in line[1:]:
c=c+1
data[hab][c]=data[hab][c]+int(float(x))
return data
if level=="species":
output=species(habitat,f)
elif level=="genus":
output=genus(habitat,samples,f)
else:
print "enter species or genus as taxonomic level"
title="habitat\t"+"\t".join(str(p) for p in samples)
g.write(title+"\n")
for i in output.keys():
output2 = "\t".join(str(p) for p in output[i])
g.write(i+"\t"+output2+"\n")
print 'Habitats found:'
print output.keys()