def main():
# do stuff
parser = argparse.ArgumentParser(
prog="Remove taxa taxonomy",
description=
"""Removes taxa from a taxonomy (or indeed any) tree that aren't in a dataset""",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument('input_file',
metavar='input_file',
nargs=1,
help="Your input Phyml")
parser.add_argument('input_tree',
metavar='input_tree',
nargs=1,
help="Your input tree files")
parser.add_argument('new_file',
metavar='new_file',
nargs=1,
help="The new tree file")
args = parser.parse_args()
verbose = args.verbose
input_file = args.input_file[0]
input_tree = args.input_tree[0]
new_file = args.new_file[0]
# load tree
tree = stk.import_tree(input_tree)
tree_taxa = stk._getTaxaFromNewick(tree)
# grab taxa in dataset
XML = stk.load_phyml(input_file)
taxa = stk.get_all_taxa(XML)
# build our subs up
deleteme = []
for taxon in tree_taxa:
if not taxon in taxa:
deleteme.append(taxon)
new_tree = stk._sub_taxa_in_tree(tree, deleteme)
t = stk._parse_tree(new_tree)
t.writeNexus(fName=new_file)
tree_taxa = stk._getTaxaFromNewick(new_tree)
tree_taxa.sort()
for t in tree_taxa:
print t
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="plot year histogram",
description="""Plot a histogram of data years from Phyml""",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument('input_file',
metavar='input_file',
nargs=1,
help="Your pyhml or data file")
parser.add_argument('output_file',
metavar='output_file',
nargs=1,
help="The output graphics. .png, .pdf, or .svg")
args = parser.parse_args()
verbose = args.verbose
input_file = args.input_file[0]
output_file = args.output_file[0]
# grab taxa in dataset
fileName, fileExtension = os.path.splitext(input_file)
if (fileExtension == '.phyml'):
XML = stk.load_phyml(input_file)
years = stk.get_publication_years(XML)
else:
f = open(input_file, "r")
years = {}
for line in f:
data = line.strip().split()
years[int(data[0][0:-2])] = float(data[1])
f.close()
year_dist = years.keys()
year_data = years.values()
fig = figure(figsize=(11.7, 8.3), dpi=90) #A4 landscape
fig.subplots_adjust(bottom=0.2)
ax = fig.add_subplot(1, 1, 1)
plt.xticks(rotation=70)
rects1 = plt.bar(year_dist, year_data, 1, color='b')
xlabel('Year')
ylabel('Number of publications')
savefig(output_file, dpi=90)
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="pages to string",
description="""Make page numbers string not integers in PHYML files""",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument(
'input_files',
metavar='input_files',
nargs='+',
help=
"""List of phyml files. These files will be overwritten - make a backup first"""
)
args = parser.parse_args()
verbose = args.verbose
input_files = args.input_files
print input_files
for phyml in input_files:
xml_root = stk._parse_xml(stk.load_phyml(phyml))
pages = xml_root.findall(".//page_number")
for page in pages:
string = etree.Element("string_value")
string.text = page[0].text
string.tail = "\n "
page.replace(page[0], string)
string.attrib['lines'] = "1"
f = open(phyml, "w")
f.write("<?xml version='1.0' encoding='utf-8'?>\n")
XML = etree.tostring(xml_root, pretty_print=True)
f.write(XML)
f.close()
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="Create colours for iTOL",
description=
"Generate a asthetically pleasing colour scheme for iToL based" +
" on a Phyml and a taxonomy csv file",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument('--scheme',
choices=['pastel', 'bright', 'dark', 'faded'],
default='pastel',
help="Choose a colour scheme")
parser.add_argument(
'--level',
choices=[
'Genus', 'Subfamily', 'Family', 'Superfamily', 'Infraorder',
'Suborder', 'Order'
],
default='Family',
help=
"Which taxonomic level to colour at. Note that not all will return data. Family and Order will always work."
)
parser.add_argument(
'--tree',
help=
"Give a tree to colour and the colour will go around the tree, rather than be sorted alphabetically",
action='store_true',
default=False,
)
parser.add_argument(
'input_file',
metavar='input_file',
nargs=1,
help=
"Your Phyml *or* a taxa lis *or* a tree file (use --tree in this case)t"
)
parser.add_argument('input_taxonomy',
metavar='input_taxonomy',
nargs=1,
help="Your taxonomy")
parser.add_argument('output_file',
metavar='output_file',
nargs=1,
help="The output file for iToL")
args = parser.parse_args()
verbose = args.verbose
level = args.level
scheme = args.scheme
input_file = args.input_file[0]
input_taxonomy = args.input_taxonomy[0]
output_file = args.output_file[0]
tree = args.tree
saturation = 0.5
value = 0.95
if (scheme == 'bright'):
saturation = 0.99
value = 0.99
elif (scheme == 'dark'):
saturation = 0.6
value = 0.8
elif (scheme == 'faded'):
saturation = 0.25
value = 0.8
if (tree):
tree_data = stk.import_tree(input_file)
# rather than simply grabbing taxa, just go through in "tree order"
tree_data = tree_data.replace("(", "")
tree_data = tree_data.replace(")", "")
tree_data = tree_data.replace(";", "")
taxa = tree_data.split(",")
for i in range(0, len(taxa)):
taxa[i] = taxa[i].strip()
else:
# grab taxa in dataset - ignore if tree
fileName, fileExtension = os.path.splitext(input_file)
if (fileExtension == '.phyml'):
print "Parsing PHYML"
XML = stk.load_phyml(input_file)
taxa = stk.get_all_taxa(XML)
else:
f = open(input_file, "r")
taxa = []
for line in f:
taxa.append(line.strip())
f.close()
print len(taxa)
taxonomy = {}
index = 0
with open(input_taxonomy, 'r') as f:
reader = csv.reader(f)
i = 0
for row in reader:
if i == 0:
# find index of the level required
j = 0
for r in row:
if r.lower() == level.lower():
index = j
i = 1
break
j = j + 1
if j == len(row):
print "Error finding the desired level in your taxonomy file."
print "You asked for: " + level.lower()
print "Your taxonomy contains: " + " ".join(row)
sys.exit()
else:
taxonomy[row[0].replace(" ", "_")] = row[
index] # the replace is to make sure we're consistant across PHYML, tree and taxonomy
print len(taxonomy)
values = taxonomy.values()
values = _uniquify(values)
n = len(values)
colours = get_colours(n, format="HEX", saturation=saturation, value=value)
output_colours = {}
i = 0
for v in values:
output_colours[v] = colours[i]
i += 1
f = open(output_file, "w")
# write header
f.write("""DATASET_COLORSTRIP
#=================================================================#
# MANDATORY SETTINGS #
#=================================================================#
SEPARATOR COMMA
#label is used in the legend table (can be changed later)
DATASET_LABEL,""")
f.write(level + "\n")
f.write("""
#dataset color (can be changed later)
COLOR,#000000
#=================================================================#
# OPTIONAL SETTINGS #
#=================================================================#
COLOR_BRANCHES,1
#=================================================================#
# Actual data follows after the "DATA" keyword #
#=================================================================#
DATA
""")
for t in taxa:
tt = t.replace(" ", "_")
try:
if (taxonomy[tt] == "-"):
f.write(t + ",#000000\n")
else:
f.write(t + ",#" + output_colours[taxonomy[tt]] + "," +
taxonomy[tt] + "\n")
except KeyError:
#print "Couldn't find "+tt
f.write(t + ",#000000\n")
f.close()
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="plot tree-taxa matrix",
description="""Plot a matrix of trees against taxa""",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument(
'-t',
'--taxonomy',
help=
"Use taxonomy to sort the taxa on the axis. Supply a STK taxonomy file",
)
parser.add_argument(
'--level',
choices=['family', 'superfamily', 'infraorder', 'suborder', 'order'],
default='family',
help="""What level to group the taxonomy at. Default is family.
Note data for a particular levelmay be missing in taxonomy."""
)
parser.add_argument('input_file',
metavar='input_file',
nargs=1,
help="Your pyhml")
parser.add_argument('output_file',
metavar='output_file',
nargs=1,
help="The output graphics. .png, .pdf, or .svg")
args = parser.parse_args()
verbose = args.verbose
input_file = args.input_file[0]
output_file = args.output_file[0]
taxonomy = args.taxonomy
level = args.level
XML = stk.load_phyml(input_file)
if not taxonomy == None:
taxonomy = stk.load_taxonomy(taxonomy)
all_taxa = stk.get_all_taxa(XML)
taxa_tree_matrix = {}
for t in all_taxa:
taxa_tree_matrix[t] = []
if not taxonomy == None:
tax_data = {}
new_all_taxa = []
for t in all_taxa:
taxon = t.replace("_", " ")
try:
if taxonomy[taxon][level] == "":
# skip this
continue
tax_data[t] = taxonomy[taxon][level]
except KeyError:
print "Couldn't find " + t + " in taxonomy. Adding as null data"
tax_data[t] = 'zzzzz' # it's at the end...
from sets import Set
unique = set(tax_data.values())
unique = list(unique)
unique.sort()
print "Groups are:"
print unique
counts = []
for u in unique:
count = 0
for t in tax_data:
if tax_data[t] == u:
count += 1
new_all_taxa.append(t)
counts.append(count)
all_taxa = new_all_taxa
# cumulate counts
count_cumulate = []
count_cumulate.append(counts[0])
for c in counts[1::]:
count_cumulate.append(c + count_cumulate[-1])
print count_cumulate
trees = stk.obtain_trees(XML)
i = 0
for t in trees:
taxa = stk.get_taxa_from_tree(XML, t, sort=True)
for taxon in taxa:
taxon = taxon.replace(" ", "_")
taxa_tree_matrix[taxon].append(i)
i += 1
# create a map
y = []
for i in range(0, len(all_taxa)):
for j in range(0, len(trees)):
if (j in taxa_tree_matrix[all_taxa[i]]):
y.append(j)
tree_count = Counter(y)
tree_dict = dict(tree_count)
tree_order = sorted(tree_dict.items(), key=lambda x: x[1], reverse=True)
new_x = []
new_y = []
for i in range(0, len(all_taxa)):
counter = 0
for t in tree_order:
j = t[0]
if (j in taxa_tree_matrix[all_taxa[i]]):
new_x.append(i)
new_y.append(counter)
counter += 1
fig = figure(figsize=(22, 17), dpi=90)
fig.subplots_adjust(left=0.3)
ax = fig.add_subplot(1, 1, 1)
ax.scatter(new_x, new_y, 50, marker='o', c='k', lw=0)
ax.set_xlim(0, len(all_taxa))
ax.set_ylim(0, len(trees))
xlabel('Taxa')
ylabel('Tree Number')
savefig(output_file, dpi=90)
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="plot character data",
description="""Plot a line plot of character data from Phyml""",
)
parser.add_argument(
'-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False
)
parser.add_argument(
'input_file',
metavar='input_file',
nargs=1,
help="Your pyhml"
)
parser.add_argument(
'output_file',
metavar='output_file',
nargs=1,
help="The output graphics. .png, .pdf, or .svg"
)
args = parser.parse_args()
verbose = args.verbose
input_file = args.input_file[0]
output_file = args.output_file[0]
# grab taxa in dataset
fileName, fileExtension = os.path.splitext(input_file)
XML = stk.load_phyml(input_file)
trees = stk.obtain_trees(XML)
years = stk.get_publication_years(XML).keys()
years.sort()
min_year = min(years)
max_year = max(years)
mol = {}
morph = {}
other = {}
for y in range(min_year,max_year+1,1):
mol[y] = 0
morph[y] = 0
other[y] = 0
for t in trees:
current_chars = stk.get_character_types_from_tree(XML,t)
current_year = stk.get_publication_year_tree(XML,t)
for c in current_chars:
if c == "molecular":
mol[current_year] += 1
elif c == "morphological":
morph[current_year] += 1
else:
other[current_year] += 1
mol_data = []
morph_data = []
other_data = []
for y in years:
try:
mol_data.append(mol[y])
except KeyError:
mol_data.append(0)
try:
morph_data.append(morph[y])
except KeyError:
morph_data.append(0)
try:
other_data.append(other[y])
except KeyError:
other_data.append(0)
fig=figure(figsize=(11.7,8.3),dpi=90) #A4 landscape
fig.subplots_adjust(left=0.3)
ax = fig.add_subplot(1,1,1)
plot(years,mol_data,'b-',lw=3,label="Molecular ("+str(sum(mol_data))+")")
plot(years,morph_data,'r-',lw=3,label="Morphological ("+str(sum(morph_data))+")")
if (sum(other_data) > 0):
plot(years,other_data,'g-',lw=3,label="Other ("+str(sum(other_data))+")")
legend(loc=2)
ax.set_xlim([min_year,max_year])
xlabel('Year')
ylabel('Number trees')
savefig(output_file, dpi=90)
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="remove poorly contrained taxa",
description="""Remove taxa that appea in one source tree only.""",
)
parser.add_argument(
'-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False
)
parser.add_argument(
'--delete_list',
help="Produce a deleted taxa list. Give filename."
)
parser.add_argument(
'--poly_only',
default=False,
action='store_true',
help="Restrict removal of taxa that are in polytomies only in source trees. Default"+
" to removal those in polytomies *and* only in one other tree."
)
parser.add_argument(
'--tree_only',
default=False,
action='store_true',
help="Restrict removal of taxa that only occur in one source tree. Default"+
" to removal those in polytomies *and* only in one other tree."
)
parser.add_argument(
'input_phyml',
metavar='input_phyml',
nargs=1,
help="Your input phyml"
)
parser.add_argument(
'input_tree',
metavar='input_tree',
nargs=1,
help="Your tree - can be NULL or None"
)
parser.add_argument(
'output_tree',
metavar='output_tree',
nargs=1,
help="Your output tree or phyml - if input_tree is none, this is the Phyml"
)
args = parser.parse_args()
verbose = args.verbose
delete_list_file = args.delete_list
if (delete_list_file == None):
dl = False
else:
dl = True
poly_only = args.poly_only
input_tree = args.input_tree[0]
if input_tree == 'NULL' or input_tree == 'None':
input_tree = None
output_file = args.output_tree[0]
input_phyml = args.input_phyml[0]
XML = stk.load_phyml(input_phyml)
# load tree
if (not input_tree == None):
supertree = stk.import_tree(input_tree)
taxa = stk._getTaxaFromNewick(supertree)
else:
supertree = None
taxa = stk.get_all_taxa(XML)
# grab taxa
delete_list = []
# loop over taxa in supertree and get some stats
for t in taxa:
#print "Looking at "+t
nTrees = 0
nResolved = 0
nPoly = 0
# search each source tree
xml_root = stk._parse_xml(XML)
# By getting source, we can then loop over each source_tree
find = etree.XPath("//source")
sources = find(xml_root)
# loop through all sources
for s in sources:
# for each source, get source name
name = s.attrib['name']
for tr in s.xpath("source_tree/tree/tree_string"):
tree = tr.xpath("string_value")[0].text
current_taxa = stk._getTaxaFromNewick(tree)
# if tree contains taxa
if (t in current_taxa):
nTrees += 1
tree_obj = stk._parse_tree(tree,fixDuplicateTaxa=True)
siblings = stk._get_all_siblings(tree_obj.node(t))
# check where it occurs - polytomies only?
if (len(siblings) > 3): #2?
nPoly += 1
else:
nResolved += 1
# record stats for this taxon and decide if to delete it
if (poly_only):
if (nPoly == nTrees): # all in polytomies
delete_list.append(t)
else:
if (nPoly == nTrees or # all in polytomies
(nResolved == 1 and (nPoly+nResolved)==nTrees) # only 1 resolved and rest (if any) polytomies
):
delete_list.append(t)
print "Taxa: "+str(len(taxa))
print "Deleting: "+str(len(delete_list))
if not supertree == None:
# done, so delete the problem taxa from the supertree
for t in delete_list:
# remove taxa from supertree
supertree = stk._sub_taxa_in_tree(supertree,t)
# save supertree
tree = {}
tree['Tree_1'] = supertree
output = stk._amalgamate_trees(tree,format='nexus')
# write file
f = open(output_file,"w")
f.write(output)
f.close()
else:
new_phyml = stk.substitute_taxa(XML,delete_list)
# write file
f = open(output_file,"w")
f.write(new_phyml)
f.close()
if (dl):
# write file
delete_list.sort()
f = open(delete_list_file,"w")
string = '\n'.join(delete_list)
f.write(string)
f.close()
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="plot chracter taxa matrix",
description="""Plot a matrix of character availability against taxa""",
)
parser.add_argument(
'-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False
)
parser.add_argument(
'-t',
'--taxonomy',
help="Use taxonomy to sort the taxa on the axis. Supply a STK taxonomy file",
)
parser.add_argument(
'--level',
choices=['family','superfamily','infraorder','suborder','order'],
default='family',
help="""What level to group the taxonomy at. Default is family.
Note data for a particular levelmay be missing in taxonomy."""
)
parser.add_argument(
'input_file',
metavar='input_file',
nargs=1,
help="Your pyhml"
)
parser.add_argument(
'output_file',
metavar='output_file',
nargs=1,
help="The output graphics. .png, .pdf, or .svg"
)
args = parser.parse_args()
verbose = args.verbose
input_file = args.input_file[0]
output_file = args.output_file[0]
taxonomy = args.taxonomy
level = args.level
XML = stk.load_phyml(input_file)
if not taxonomy == None:
taxonomy = stk.load_taxonomy(taxonomy)
all_taxa = stk.get_all_taxa(XML)
all_chars_d = stk.get_all_characters(XML)
all_chars = []
for c in all_chars_d:
all_chars.extend(all_chars_d[c])
if not taxonomy == None:
tax_data = {}
new_all_taxa = []
for t in all_taxa:
taxon = t.replace("_"," ")
try:
if taxonomy[taxon][level] == "":
# skip this
continue
tax_data[t] = taxonomy[taxon][level]
except KeyError:
print "Couldn't find "+t+" in taxonomy. Adding as null data"
tax_data[t] = 'zzzzz' # it's at the end...
from sets import Set
unique = set(tax_data.values())
unique = list(unique)
unique.sort()
print "Groups are:"
print unique
counts = []
for u in unique:
count = 0
for t in tax_data:
if tax_data[t] == u:
count += 1
new_all_taxa.append(t)
counts.append(count)
all_taxa = new_all_taxa
# cumulate counts
count_cumulate = []
count_cumulate.append(counts[0])
for c in counts[1::]:
count_cumulate.append(c+count_cumulate[-1])
print count_cumulate
taxa_character_matrix = {}
for t in all_taxa:
taxa_character_matrix[t] = []
trees = stk.obtain_trees(XML)
for t in trees:
chars = stk.get_characters_from_tree(XML,t,sort=True)
taxa = stk.get_taxa_from_tree(XML,t, sort=True)
for taxon in taxa:
taxon = taxon.replace(" ","_")
if taxon in all_taxa:
taxa_character_matrix[taxon].extend(chars)
for t in taxa_character_matrix:
array = taxa_character_matrix[t]
taxa_character_matrix[t] = list(set(array))
# create a map
x = []
y = []
for i in range(0,len(all_taxa)):
for j in range(0,len(all_chars)):
if (all_chars[j] in taxa_character_matrix[all_taxa[i]]):
x.append(i)
y.append(j)
i = 0
for j in all_chars:
# do a substitution of character names to tidy things up
if j.lower().startswith('mitochondrial carrier; adenine nucleotide translocator'):
j = "ANT"
if j.lower().startswith('mitochondrially encoded 12s'):
j = '12S'
if j.lower().startswith('complete mitochondrial genome'):
j = 'Mitogenome'
if j.lower().startswith('mtdna'):
j = "mtDNA restriction sites"
if j.lower().startswith('h3 histone'):
j = 'H3'
if j.lower().startswith('mitochondrially encoded cytochrome'):
j = 'COI'
if j.lower().startswith('rna, 28s'):
j = '28S'
if j.lower().startswith('rna, 18s'):
j = '18S'
if j.lower().startswith('mitochondrially encoded 16s'):
j = '16S'
all_chars[i] = j
i += 1
fig=figure(figsize=(22,17),dpi=90)
fig.subplots_adjust(left=0.3)
ax = fig.add_subplot(1,1,1)
ax.scatter(x,y,50,marker='o',c='r',lw=0)
yticks(range(0,len(all_chars)), all_chars)
ax.set_xlim(0,len(all_taxa))
ax.set_ylim(0,len(all_chars))
xlabel('Taxa')
ylabel('Characters')
savefig(output_file, dpi=90)
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="collect analyses and characters",
description=
"""Grab all the characters and optimality_ctiterions from a list of Phyml files and create
the correct RNC files""",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument(
'input_files',
metavar='input_files',
nargs='+',
help=
"""List of phyml files. Output will be analyses.rnc and characters.rnc"""
)
args = parser.parse_args()
verbose = args.verbose
input_files = args.input_files
characters = []
analyses = []
for phyml in input_files:
xml = stk.load_phyml(phyml)
char = stk.get_characters_used(xml)
characters.extend(char)
an = stk.get_analyses_used(xml)
analyses.extend(an)
# uniquify them - this is technically a private function...
analyses = stk._uniquify(analyses)
characters = stk._uniquify(characters)
analyses.sort()
characters.sort(key=lambda x: x[0].lower())
header = """
characters =
(
element character {
attribute name { string },
attribute type { "morphological"|"molecular"|"behavioural"|"other" },
char_info
}|"""
i = 0
for c in characters:
new_char = '\n element character {\n attribute name { "' + c[
0] + '" },'
new_char += '\n attribute type { "' + c[1] + '" },'
if (i < len(characters) - 1):
new_char += '\n char_info\n }|'
else:
new_char += '\n char_info\n }+\n)'
header += new_char
i += 1
characters_rnc = header
header = """
analysis =
(
element optimality_criterion {
attribute name {string}
}|"""
i = 0
for a in analyses:
new_analysis = '\n element character {\n\tattribute name { "' + a + '" }'
if (i < len(analyses) - 1):
new_analysis += '\n }|'
else:
new_analysis += '\n }\n)'
header += new_analysis
i += 1
analyses_rnc = header
f = open("analyses.rnc", "w")
f.write(analyses_rnc)
f.close()
f = open("characters.rnc", "w")
f.write(characters_rnc)
f.close()
f = open("analyses.txt", "w")
for a in analyses:
f.write(a + "\n")
f.close()
f = open("characters.txt", "w")
for c in characters:
f.write(c[0] + " (" + c[1] + ")\n")
f.close()
def main():
# do stuff
parser = argparse.ArgumentParser(
prog="Create a taxonomy",
description=
"Generate a taxonomy from Phyml. Fills in most taxonomic levels. Uses EOL and ITIS",
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help="Verbose output: mainly progress reports.",
default=False)
parser.add_argument(
'--pref_db',
help="Preferred database. Need to be able to list avialable databases?"
)
parser.add_argument('input_file',
metavar='input_file',
nargs=1,
help="Your input taxa list or phyml")
parser.add_argument('output_file',
metavar='output_file',
nargs=1,
help="The output file. A CSV-based taxonomy")
args = parser.parse_args()
verbose = args.verbose
input_file = args.input_file[0]
output_file = args.output_file[0]
pref_db = args.pref_db
# grab taxa in dataset
fileName, fileExtension = os.path.splitext(input_file)
if (fileExtension == '.phyml'):
XML = stk.load_phyml(input_file)
taxa = stk.get_all_taxa(XML)
else:
f = open(input_file, "r")
taxa = []
for line in f:
taxa.append(line.strip())
f.close()
taxonomy = {}
for taxon in taxa:
taxon = taxon.replace("_", " ")
if (verbose):
print "Looking up ", taxon
# get the data from EOL on taxon
# What about synonyms?
taxonq = quote_plus(taxon)
URL = "http://eol.org/api/search/1.0.json?q=" + taxonq
req = urllib2.Request(URL)
opener = urllib2.build_opener()
f = opener.open(req)
data = json.load(f)
# check if there's some data
if len(data['results']) == 0:
taxonomy[taxon] = {}
continue
ID = str(data['results'][0]['id']) # take first hit
# Now look for taxonomies
URL = "http://eol.org/api/pages/1.0/" + ID + ".json"
req = urllib2.Request(URL)
opener = urllib2.build_opener()
f = opener.open(req)
data = json.load(f)
if len(data['taxonConcepts']) == 0:
taxonomy[taxon] = {}
continue
TID = str(data['taxonConcepts'][0]['identifier']) # take first hit
currentdb = str(data['taxonConcepts'][0]['nameAccordingTo'])
# loop through and get preferred one if specified
# now get taxonomy
if (not pref_db == None):
for db in data['taxonConcepts']:
currentdb = db['nameAccordingTo'].lower()
if (pref_db.lower() in currentdb):
TID = str(db['identifier'])
break
URL = "http://eol.org/api/hierarchy_entries/1.0/" + TID + ".json"
req = urllib2.Request(URL)
opener = urllib2.build_opener()
f = opener.open(req)
data = json.load(f)
this_taxonomy = {}
this_taxonomy['provider'] = currentdb
for a in data['ancestors']:
try:
this_taxonomy[a['taxonRank']] = a['scientificName']
except KeyError:
continue
try:
if (not data['taxonRank'].lower() == 'species'):
# higher taxa, add it in to the taxonomy!
this_taxonomy[data['taxonRank'].lower()] = taxon
except KeyError:
continue
taxonomy[taxon] = this_taxonomy
if (verbose):
print "Done basic taxonomy, getting more info from ITIS"
# fill in the rest of the taxonomy
# get all genera
genera = []
for t in taxonomy:
try:
genera.append(taxonomy[t]['genus'])
except KeyError:
continue
genera = _uniquify(genera)
for g in genera:
if (verbose):
print "Looking up ", g
try:
URL = "http://www.itis.gov/ITISWebService/jsonservice/searchByScientificName?srchKey=" + quote_plus(
g.strip())
except:
continue
req = urllib2.Request(URL)
opener = urllib2.build_opener()
f = opener.open(req)
string = unicode(f.read(), "ISO-8859-1")
data = json.loads(string)
if data['scientificNames'][0] == None:
continue
tsn = data["scientificNames"][0]["tsn"]
URL = "http://www.itis.gov/ITISWebService/jsonservice/getFullHierarchyFromTSN?tsn=" + str(
tsn)
req = urllib2.Request(URL)
opener = urllib2.build_opener()
f = opener.open(req)
try:
string = unicode(f.read(), "ISO-8859-1")
except:
continue
data = json.loads(string)
this_taxonomy = {}
for level in data['hierarchyList']:
if not level['rankName'].lower() in current_taxonomy_levels:
this_taxonomy[level['rankName'].lower()] = level['taxonName']
for t in taxonomy:
try:
if taxonomy[t]['genus'] == g:
taxonomy[t].update(this_taxonomy)
except KeyError:
continue
stk.save_taxonomy(taxonomy, output_file)
