def fastme(self):
"""Use fastme to make a minimum-evolution tree, which is returned.
The resulting tree is read in by p4, and is returned.
We interact with fastme by writing files, but care is taken that
existing files are not overwritten, because new file names are
made to be unique.
If the branch lengths are less than zero, they are made to be zero.
"""
gm = ["DistanceMatrix.fastme()"]
flob_dm, dmFName_fq = func.uniqueFile('tmp.dm')
flob_tf, treeFName_fq = func.uniqueFile(
'tmp.tree') #tempfile.mkstemp(suffix='tree', dir=theDir)
flob_tf.close()
# Throw the dir and dirname away.
dirname, dmFName = os.path.split(dmFName_fq)
dirname, treeFName = os.path.split(treeFName_fq)
# Write the files, do the analysis
self.writePhylipToOpenFile(flob_dm, 6)
flob_dm.close()
os.system("fastme -i %s -o %s" % (dmFName, treeFName))
# This is the result. The tree, if it exists, is read in by p4.
oldLen = len(var.trees)
func.read(treeFName)
newLen = len(var.trees)
if newLen == oldLen + 1:
pass
else:
gm.append("I was expecting exactly one tree. Got %i" %
(oldLen - newLen))
raise Glitch, gm
t = var.trees.pop()
# Tidy up.
os.remove(treeFName)
os.remove(dmFName)
for n in t.iterNodesNoRoot():
if n.br.len < 0.0:
n.br.len = 0.0
if not n.isLeaf:
n.name = None
return t
def fastme(self):
"""Use fastme to make a minimum-evolution tree, which is returned.
The resulting tree is read in by p4, and is returned.
We interact with fastme by writing files, but care is taken that
existing files are not overwritten, because new file names are
made to be unique.
If the branch lengths are less than zero, they are made to be zero.
"""
gm = ["DistanceMatrix.fastme()"]
flob_dm, dmFName_fq = func.uniqueFile('tmp.dm')
# tempfile.mkstemp(suffix='tree', dir=theDir)
flob_tf, treeFName_fq = func.uniqueFile('tmp.tree')
flob_tf.close()
# Throw the dir and dirname away.
dirname, dmFName = os.path.split(dmFName_fq)
dirname, treeFName = os.path.split(treeFName_fq)
# Write the files, do the analysis
self.writePhylipToOpenFile(flob_dm, 6)
flob_dm.close()
os.system("fastme -i %s -o %s" % (dmFName, treeFName))
# This is the result. The tree, if it exists, is read in by p4.
oldLen = len(var.trees)
func.read(treeFName)
newLen = len(var.trees)
if newLen == oldLen + 1:
pass
else:
gm.append("I was expecting exactly one tree. Got %i" %
(oldLen - newLen))
raise P4Error(gm)
t = var.trees.pop()
# Tidy up.
os.remove(treeFName)
os.remove(dmFName)
for n in t.iterNodesNoRoot():
if n.br.len < 0.0:
n.br.len = 0.0
if not n.isLeaf:
n.name = None
return t
def func2():
data = pd.read_csv('./data/train.csv')
data = data[['user_id','brand_id','type','month','day']]
data = np.array(data)
user_id = func.read('user_id')
item_id = func.read('item_id')
user_item_time = func.build_user_item_time(data,user_id)
item_time = itemmodel.build_item_time(data,item_id)
item_factor = itemmodel.cal_item_time_factor(item_time)
func.write(user_item_time,'user_item_time')
func.write(item_time,'item_time')
return (user_item_time,item_time,item_factor)
def func3():
train,test = func.divide_data()
user_id = func.read('user_id')
item_id = func.read('item_id')
train_u_i_t = func.build_user_item_time(train,user_id)
#建立测试集的用户-物品词典，这里不需要时间序列
test_u_i = func.build_user_item(test,user_id)
#建立训练集的物品-时间词典
train_item_time = itemmodel.build_item_time(train,item_id)
#建立物品的时间衰减因子
item_factor = itemmodel.cal_item_time_factor(train_item_time)
func.write(train_u_i_t,'train_user_item_time')
func.write(test_u_i,'test_user_item')
func.write(train_item_time,'train_item_time')
return (train_u_i_t,test_u_i,train_item_time,item_factor)
def fun1():
data = pd.read_csv('./data/train.csv')
data = data[['user_id','brand_id','type','month','day']]
data = np.array(data)
user_id = func.read('user_id')
user_time_item = func.build_user_time_item(data,user_id)
func.write(user_time_item,'user_time_item')
def index():
""
''' We store guest messages in a json file.
First we open it to load the data.
Then we pass the data to the read() function to transform it into the (<name>, <date>, <message>) format.
The transformed data will become a list containing the rows with the format above.
Finally we can pass the list to render_template() to display the messages when we visit index.html.
'''
with open('data.json', 'r') as file:
data = json.load(file)
rows = read(data)
num_messages_to_show = checkLen(rows) # We also want to check how many messages are in the data
# Here we instantiate a form object
form = InputForm()
''' If the user enters valid inputs and presses Post, the code block below will run.
We retrieve the user's name and message and store them in name and message.
Then we update the rows list to add the received message and return it.
Finally we can update the data json file using json.dump().
'''
if form.validate_on_submit():
name = form.name.data
message = form.message.data
data = write(rows, name, message)
with open('data.json', 'w') as file:
json.dump(data, file)
return redirect(url_for('index')) # We also want to refresh the index page to show the change
# In the render_template, you can pass the variables to be used in the html file. This is to connect the back-end to the front-end
return render_template('index.html', rows=rows, num_messages_to_show=num_messages_to_show, form=form)
def getdata(peer):
f = read("userdata/user_%s.pref" % (peer))
if not f:
d = _basic
write("userdata/user_%s.pref" % (peer), json.dumps(d))
else:
d = json.loads(f)
return d
def getdata(peer):
d = {}
f = read("custom/preset_%s.pref"%(peer))
if not f:
d = _basic
write("custom/preset_%s.pref"%(peer), json.dumps(d))
else:
d = json.loads(f)
return d
def __init__(self, supertree, inputTrees):
# There are two ways of decorating the supertree with the support values.
# Standard conforms to the consensus tree tradition, i.e. values are presented between
# 0 to 100 percent. Non standard adhears to the few supertree papers regarding support values
# i.e -1 to 1.
self.doStandardDecoration = True
# The decorated supertree can be saved to file
self.doSaveDecoratedTree = False
self.decoratedFilename = "superTreeSupport.nex"
# There is a option to save a supertree decorated with index values instead of support values.
# This can then be used with a csv file containing the support values for each index.
# Further analysis of the support values can be performed and then matched to the indecies in the
# decorated supertree
self.doSaveIndexTree = False
self.indexFilename = "supertreeIndex.nex"
self.csvFilename = "supertreeIndex.csv"
# Draws the decorated supertree to screen
self.doDrawTree = False
# Produces output to screen
self.verbose = 1
# Placeholders that allows access to the data after completing
# calculations
self.decoratedSuperTree = None
self.indexSuperTree = None
self.csvList = None
# Keeps track of splits for producing output
self.indexIntersections = []
self.csvValues = []
self.intersections = []
# Let t be the number of input trees,
# s the number of input trees supporting a supertree clade,
# r the number of input trees that are irrelevant to the supertree clade,
# q the number of input trees that conflict with the supertree clade,
# p the number of input trees that permit the supertree clade,
# so that t = p + q + r + s.
self.T = 0 # no. of input trees;
self.L = 0 # no. of leaves;
# coverage (average proportion of leaves in the input tree);
self.C = 0.0
self.SC = 0 # number of supertree clades;
self.U = 0 # no. of unsupported supertree clades;
# no. of unsupported supertree clades that conflict with at least one
# input tree;
self.UC = 0
# no. of unsupported clades conflicting with all relevant input trees;
self.UCC = 0
# average qualitative support for supertree clades. Figures in
# parentheses are ranges.
self.QS = 0.0
self.S = 0.0 # average support
self.P = 0.0 # average permitted
self.Q = 0.0 # average conflict
self.R = 0.0 # average relevance
self.wS = 0.0 # average weighted support
self.wP = 0.0 # average weighted permitance
self.V = 0.0 # average V for supertree cladesV = (s minus q)/(s + q)
self.VV = 0.0 # V+ = (s minus q +p)/(s + q + p)
self.Vv = 0.0 # V minus = (s minus q minus p)/(s + q + p)
self.wV = 0.0 # wV = (ws minus q)/(ws + q)
self.wVV = 0.0 # wVV = (ws minus q +wp)/(ws + q + wp)
self.wVv = 0.0 # wVv = (ws minus q minus wp)/(ws + q + wp)
gm = ["SuperTreeSupport()"]
var.warnReadNoFile = False
if type(inputTrees) == type([]):
for t in inputTrees:
if not isinstance(t, Tree):
gm.append("Input trees should be a list of p4 Tree objects. Got %s" % t)
raise P4Error(gm)
self.inputTrees = inputTrees
elif type(inputTrees) == type(""):
var.trees = []
read(inputTrees)
if len(var.trees) < 1:
gm.append("Sorry, at least one tree must be supplied as input tree")
raise P4Error(gm)
self.inputTrees = var.trees
else:
gm.append("Input trees are neither a list of p4 Tree objects nor a valid filename.")
raise P4Error(gm)
if isinstance(supertree, Tree):
self.supertree = supertree # not a list.
elif type(supertree) == type(""):
var.trees = []
read(supertree)
if len(var.trees) > 1:
gm.append("Sorry, supply only one tree as supertree")
raise P4Error(gm)
# this was originally a list, ie [var.trees.pop()]
self.supertree = var.trees.pop()
else:
gm.append("Supertree was neither a p4 Tree nor a valid filename")
gm.append("Got %s" % supertree)
raise P4Error(gm)
for tree in self.inputTrees:
if not tree._taxNames:
tree._setTaxNamesFromLeaves()
# Mean and median overlap of the input trees
overlapList = []
meanOverlap = 0.0
index = 0
for i in range(0, len(self.inputTrees) - 1):
for j in range(i + 1, len(self.inputTrees)):
overlap = len(set(self.inputTrees[i].taxNames).intersection(set(self.inputTrees[j].taxNames)))
overlapList.append(overlap)
meanOverlap += overlap
index += 1
if index == 0:
self.mean = 0
self.median = 0
else:
self.mean = meanOverlap / index
overlapList.sort()
self.median = overlapList[len(overlapList) / 2]
commonLeafSet = CommonLeafSet()
self.splits = commonLeafSet.updateTreesToCommonLeafSet([self.inputTrees, [self.supertree]])
self.bitkeys = commonLeafSet.getCommonBitkeys()
self.taxnames = commonLeafSet.getCommonTaxNames()
self.taxa2Bitkey = commonLeafSet.getCommonTaxa2Bitkey()
def __init__(self, inputTree, distributionTrees=None):
"""
SuperTreeInputTrees is a utility to create sets of input trees.
The input trees are primarily to be used to evaluate super tree
construction methods.
Invocation removing a fixed number of taxa from each prospective input tree:
stit = SuperTreeInputTrees(inputTree)
stit.writeInputTreesToFile = True
stit.outputFile = 'myInputtrees.tre'
stit.noTaxaToRemove = 32
stit.noOutputTrees = 10
stit.generateInputTrees()
Invocation using built in distribution gathered from real world super tree cases::
stit = SuperTreeInputTrees(inputTree)
stit.writeInputTreesToFile = True
stit.outputFile = 'myInputtrees.tre'
stit.useTaxonDistribution = True
stit.generateInputTrees()
The user can generate a distribution of their own by supplying a list of p4 trees or a tree file.
The order of the trees is important, supertree and then all other trees. This goes for both list and
file. Like so::
stit = SuperTreeInputTrees(inputTree, distributionTrees='myTreefile.nex')
stit.writeInputTreesToFile = True
stit.outputFile = 'myInputtrees.tre'
stit.useTaxonDistribution = True
stit.generateInputTrees()
Placeholders which allow access to data after completed computations::
stit.outputTrees
stit.dist
"""
self.writeInputTreesToFile = False
self.outputFile = "inputtrees.tre"
# Set to False if you want to have a set number of taxa in the output
# trees
self.useTaxonDistribution = False
# Only meaningful if setting useTaxonDistribution = False
self.noTaxaToRemove = 32
self.noOutputTrees = 10
gm = ["SuperTreeInputTrees()"]
if isinstance(inputTree, Tree):
self.inputTree = inputTree # not a list.
elif type(inputTree) == type(""):
var.trees = []
read(inputTree)
if len(var.trees) > 1:
gm.append("Sorry, supply only one tree as supertree")
raise P4Error(gm)
# this was originally a list, ie [var.trees.pop()]
self.inputTree = var.trees.pop()
else:
gm.append("Input tree was neither a p4 Tree nor a valid filename")
gm.append("Got %s" % inputTree)
raise P4Error(gm)
if not self.inputTree._taxNames:
self.inputTree._setTaxNamesFromLeaves()
self.outputTrees = []
self.normalizedDist = []
# Distributions gathered from real world supertree input
# The dists are first a list of input tree taxon set sizes and the supertree taxon set size
# Using this data we can normalize the dists to fit the size of trees
# we want
# BunnyRSVNormal set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11, 11, 12, 12, 13, 13, 13, 13, 13, 14, 14, 15, 17, 17, 18, 18, 18, 18, 18, 19, 19, 19, 20, 20, 20, 21, 22, 22, 23, 24, 25, 25, 25, 25, 25, 25, 26, 27, 28, 29, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 37, 38, 38, 40, 40, 41, 47, 51, 51, 52, 52, 52, 68, 70, 78, 78, 79, 80, 80], 80]
# CanidaeRVS set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 5, 6, 7, 8, 8, 9, 10, 11, 11, 11, 12, 16, 16, 20, 23, 24, 30, 30, 33, 34, 34, 34, 34, 34], 34]
# CarnivoraRVS set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 8, 8, 8, 8, 9, 9, 9, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12], 12]
# DavideDinoMRP set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[4, 4, 4, 5, 6, 6, 6, 7, 8, 8, 9, 9, 9, 10, 10, 10, 10, 10, 11, 11, 11, 12, 12, 12, 13, 14, 14, 14, 14, 15, 15, 15, 15, 16, 16, 17, 18, 18, 18, 18, 19, 19, 19, 19, 19, 19, 20, 20, 20, 22, 23, 23, 24, 24, 25, 26, 27, 27, 28, 28, 29, 29, 29, 29, 29, 30, 30, 30, 31, 31, 31, 31, 33, 33, 33, 33, 36, 37, 37, 38, 38, 39, 42, 45, 47, 48, 50, 53, 53, 66, 70, 71, 74, 74, 75, 75, 76, 78, 78, 80, 86, 86, 92, 94, 96, 100, 101, 102, 102, 103, 105, 110, 111, 111, 139, 148, 149, 153, 173, 199, 204, 217, 240, 269, 270, 271, 272, 272, 273, 273, 273, 273, 274, 275], 277]
# FelidaeRVS set from Wilkinson et al 2005, Syst Biol 54:823
self.dist = [
[
3,
3,
3,
3,
3,
4,
4,
4,
5,
6,
6,
6,
7,
7,
7,
7,
9,
9,
10,
10,
14,
16,
17,
24,
25,
28,
29,
29,
30,
30,
32,
34,
36,
36,
36,
36,
36,
36,
36,
36,
],
36,
]
# KennedyPageData set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[14, 16, 17, 20, 30, 30, 90], 122]
# ViverridaeRVS set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[4, 5, 10, 16, 19, 33, 34, 34, 34], 34]
if distributionTrees:
self.useTaxonDistribution = True
if type(distributionTrees) == type([]):
for t in distributionTrees:
if not isinstance(t, Tree):
gm.append("Input trees should be a list of p4 Tree objects. Got %s" % t)
raise P4Error(gm)
superTree = distributionTrees.pop(0)
inputTrees = distributionTrees
elif type(distributionTrees) == type(""):
var.trees = []
read(distributionTrees)
if len(var.trees) < 1:
gm.append("Sorry, at least one tree must be supplied as input tree")
raise P4Error(gm)
superTree = var.trees.pop(0)
inputTrees = var.trees
self._generateDistribution(superTree, inputTrees)
def njUsingPaup(self, paupPath='paup'):
"""Use paup to make a neighbor-joining tree, which is returned.
The resulting tree is read in by p4, and is returned.
We interact with paup by writing files, but care is taken that
existing files are not overwritten, because new file names are
made to be unique.
If this does not work well, try setting the paupPath arg.
"""
gm = ["DistanceMatrix.njUsingPaup()"]
#filename = sha.new(str(os.getpid())).hexdigest()[-10:]
#dmFName = os.path.join(pathPrefix, "%s.dmat" % filename)
#treeFName = os.path.join(pathPrefix, "%s.tree" % filename)
#pFName = os.path.join(pathPrefix, "%s.cmds" % filename)
#tempfile.mkstemp(suffix='', prefix='tmp', dir=None, text=False)
#if pathPrefix:
# theDir = pathPrefix
#else:
# theDir = None
flob_dm, dmFName_fq = func.uniqueFile('tmp.dm')
flob_tf, treeFName_fq = func.uniqueFile('tmp.tree') #tempfile.mkstemp(suffix='tree', dir=theDir)
flob_tf.close()
flob_pf, pFName = func.uniqueFile('tmp.cmds') # tempfile.mkstemp(suffix='cmds', dir=theDir)
# Throw the dir and dirname away.
dirname, dmFName = os.path.split(dmFName_fq)
dirname, treeFName = os.path.split(treeFName_fq)
# Make the paup commands
paupCommandString = """#nexus
begin paup;
execute %s;
set crit=dist;
dset negbrlen=setzero;
nj;
savetrees file=%s format=altnex brlens=yes taxablk=yes replace=yes;
quit;
end;
""" % (dmFName, treeFName)
#print paupCommandString
# Write the files, do the analysis
#writeNexusToOpenFile(self, flob, writeTaxaBlock, append, digitsAfterDecimal)
self.writeNexusToOpenFile(flob_dm, True, False, 6)
flob_dm.close()
flob_pf.write(paupCommandString)
flob_pf.close()
os.system("%s -n %s > /dev/null" % (paupPath, pFName))
# This is the result. The tree, if it exists, is read in by p4.
oldLen = len(var.trees)
func.read(treeFName)
newLen = len(var.trees)
if newLen == oldLen + 1:
pass
else:
gm.append("I was expecting exactly one tree. Got %i" % (oldLen - newLen))
raise Glitch, gm
t = var.trees.pop()
# Tidy up.
os.remove(treeFName)
os.remove(pFName)
os.remove(dmFName)
for n in t.iterNodesNoRoot():
if n.br.len < 0.0:
n.br.len = 0.0
return t
def relist(self):
try:
print(self.library)
self.library is not None
except:
self.open()
print(self.library)
try:
self.library is not None
except:
return
self.list_cards.clear()
self.list_cards.setRowCount(0)
self.row = 0
if self.set.currentText() == 'HT':
self.esc = func.read(self.library)
self.cards = list(
map(lambda x: x[:x.rfind('.png')], list(self.esc.keys())))
for i in self.cards:
self.row += 1
self.list_cards.setRowCount(self.row + 1)
self.list_cards.setItem(self.row - 1, 0, QTableWidgetItem(i))
self.list_cards.setItem(self.row - 1, 1, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 2, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 3, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 4, QTableWidgetItem('1'))
self.list_cards.setRowCount(self.row - 1)
self.completer = QCompleter(self.cards)
self.name.setCompleter(self.completer)
elif self.set.currentText() == 'TK':
self.esc_TK = func.read(self.library[:self.library.rfind('/')] +
'/TK.xml')
self.TK = list(
map(lambda x: x[:x.rfind('.png')], list(self.esc_TK.keys())))
for i in self.TK:
self.row += 1
self.list_cards.setRowCount(self.row + 1)
self.list_cards.setItem(self.row - 1, 0, QTableWidgetItem(i))
self.list_cards.setItem(self.row - 1, 1, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 2, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 3, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 4, QTableWidgetItem('1'))
self.list_cards.setRowCount(self.row - 1)
self.completer = QCompleter(self.TK)
self.name.setCompleter(self.completer)
elif self.set.currentText() == 'Standart':
self.esc_std = func.read(self.library[:self.library.rfind('/')] +
'/StandardCards.xml')
self.std = list(
map(lambda x: x[:x.rfind('.png')], list(self.esc_std.keys())))
for i in self.std:
self.row += 1
self.list_cards.setRowCount(self.row + 1)
self.list_cards.setItem(self.row - 1, 0, QTableWidgetItem(i))
self.list_cards.setItem(self.row - 1, 1, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 2, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 3, QTableWidgetItem('1'))
self.list_cards.setItem(self.row - 1, 4, QTableWidgetItem('1'))
self.list_cards.setRowCount(self.row - 1)
self.completer = QCompleter(self.std)
self.name.setCompleter(self.completer)
else:
QMessageBox.about(self, "Ошибка", "Не удалось подгрузить карты")
self.list_cards.setHorizontalHeaderLabels(
["Имя", "Тип", "Класс", "Редкость", "Стоимость"])
def njUsingPaup(self, paupPath='paup'):
"""Use paup to make a neighbor-joining tree, which is returned.
The resulting tree is read in by p4, and is returned.
We interact with paup by writing files, but care is taken that
existing files are not overwritten, because new file names are
made to be unique.
If this does not work well, try setting the paupPath arg.
"""
gm = ["DistanceMatrix.njUsingPaup()"]
#filename = sha.new(str(os.getpid())).hexdigest()[-10:]
#dmFName = os.path.join(pathPrefix, "%s.dmat" % filename)
#treeFName = os.path.join(pathPrefix, "%s.tree" % filename)
#pFName = os.path.join(pathPrefix, "%s.cmds" % filename)
#tempfile.mkstemp(suffix='', prefix='tmp', dir=None, text=False)
#if pathPrefix:
# theDir = pathPrefix
#else:
# theDir = None
flob_dm, dmFName_fq = func.uniqueFile('tmp.dm')
flob_tf, treeFName_fq = func.uniqueFile(
'tmp.tree') #tempfile.mkstemp(suffix='tree', dir=theDir)
flob_tf.close()
flob_pf, pFName = func.uniqueFile(
'tmp.cmds') # tempfile.mkstemp(suffix='cmds', dir=theDir)
# Throw the dir and dirname away.
dirname, dmFName = os.path.split(dmFName_fq)
dirname, treeFName = os.path.split(treeFName_fq)
# Make the paup commands
paupCommandString = """#nexus
begin paup;
execute %s;
set crit=dist;
dset negbrlen=setzero;
nj;
savetrees file=%s format=altnex brlens=yes taxablk=yes replace=yes;
quit;
end;
""" % (dmFName, treeFName)
#print paupCommandString
# Write the files, do the analysis
#writeNexusToOpenFile(self, flob, writeTaxaBlock, append, digitsAfterDecimal)
self.writeNexusToOpenFile(flob_dm, True, False, 6)
flob_dm.close()
flob_pf.write(paupCommandString)
flob_pf.close()
os.system("%s -n %s > /dev/null" % (paupPath, pFName))
# This is the result. The tree, if it exists, is read in by p4.
oldLen = len(var.trees)
func.read(treeFName)
newLen = len(var.trees)
if newLen == oldLen + 1:
pass
else:
gm.append("I was expecting exactly one tree. Got %i" %
(oldLen - newLen))
raise Glitch, gm
t = var.trees.pop()
# Tidy up.
os.remove(treeFName)
os.remove(pFName)
os.remove(dmFName)
for n in t.iterNodesNoRoot():
if n.br.len < 0.0:
n.br.len = 0.0
return t
def __init__(self, supertree, inputTrees):
# There are two ways of decorating the supertree with the support values.
# Standard conforms to the consensus tree tradition, i.e. values are presented between
# 0 to 100 percent. Non standard adhears to the few supertree papers regarding support values
# i.e -1 to 1.
self.doStandardDecoration = True
# The decorated supertree can be saved to file
self.doSaveDecoratedTree = False
self.decoratedFilename = 'superTreeSupport.nex'
# There is a option to save a supertree decorated with index values instead of support values.
# This can then be used with a csv file containing the support values for each index.
# Further analysis of the support values can be performed and then matched to the indecies in the
# decorated supertree
self.doSaveIndexTree = False
self.indexFilename = 'supertreeIndex.nex'
self.csvFilename = 'supertreeIndex.csv'
# Draws the decorated supertree to screen
self.doDrawTree = False
# Produces output to screen
self.verbose = 1
# Placeholders that allows access to the data after completing
# calculations
self.decoratedSuperTree = None
self.indexSuperTree = None
self.csvList = None
# Keeps track of splits for producing output
self.indexIntersections = []
self.csvValues = []
self.intersections = []
# Let t be the number of input trees,
# s the number of input trees supporting a supertree clade,
# r the number of input trees that are irrelevant to the supertree clade,
# q the number of input trees that conflict with the supertree clade,
# p the number of input trees that permit the supertree clade,
# so that t = p + q + r + s.
self.T = 0 # no. of input trees;
self.L = 0 # no. of leaves;
# coverage (average proportion of leaves in the input tree);
self.C = 0.0
self.SC = 0 # number of supertree clades;
self.U = 0 # no. of unsupported supertree clades;
# no. of unsupported supertree clades that conflict with at least one
# input tree;
self.UC = 0
# no. of unsupported clades conflicting with all relevant input trees;
self.UCC = 0
# average qualitative support for supertree clades. Figures in
# parentheses are ranges.
self.QS = 0.0
self.S = 0.0 # average support
self.P = 0.0 # average permitted
self.Q = 0.0 # average conflict
self.R = 0.0 # average relevance
self.wS = 0.0 # average weighted support
self.wP = 0.0 # average weighted permitance
self.V = 0.0 # average V for supertree cladesV = (s minus q)/(s + q)
self.VV = 0.0 # V+ = (s minus q +p)/(s + q + p)
self.Vv = 0.0 # V minus = (s minus q minus p)/(s + q + p)
self.wV = 0.0 # wV = (ws minus q)/(ws + q)
self.wVV = 0.0 # wVV = (ws minus q +wp)/(ws + q + wp)
self.wVv = 0.0 # wVv = (ws minus q minus wp)/(ws + q + wp)
gm = ['SuperTreeSupport()']
var.warnReadNoFile = False
if type(inputTrees) == type([]):
for t in inputTrees:
if not isinstance(t, Tree):
gm.append(
"Input trees should be a list of p4 Tree objects. Got %s" % t)
raise P4Error(gm)
self.inputTrees = inputTrees
elif type(inputTrees) == type(""):
var.trees = []
read(inputTrees)
if len(var.trees) < 1:
gm.append(
'Sorry, at least one tree must be supplied as input tree')
raise P4Error(gm)
self.inputTrees = var.trees
else:
gm.append(
"Input trees are neither a list of p4 Tree objects nor a valid filename.")
raise P4Error(gm)
if isinstance(supertree, Tree):
self.supertree = supertree # not a list.
elif type(supertree) == type(""):
var.trees = []
read(supertree)
if len(var.trees) > 1:
gm.append('Sorry, supply only one tree as supertree')
raise P4Error(gm)
# this was originally a list, ie [var.trees.pop()]
self.supertree = var.trees.pop()
else:
gm.append("Supertree was neither a p4 Tree nor a valid filename")
gm.append("Got %s" % supertree)
raise P4Error(gm)
for tree in self.inputTrees:
if not tree._taxNames:
tree._setTaxNamesFromLeaves()
# Mean and median overlap of the input trees
overlapList = []
meanOverlap = 0.0
index = 0
for i in range(0, len(self.inputTrees) - 1):
for j in range(i + 1, len(self.inputTrees)):
overlap = len(set(self.inputTrees[i].taxNames).intersection(
set(self.inputTrees[j].taxNames)))
overlapList.append(overlap)
meanOverlap += overlap
index += 1
if index == 0:
self.mean = 0
self.median = 0
else:
self.mean = meanOverlap / index
overlapList.sort()
self.median = overlapList[len(overlapList) / 2]
commonLeafSet = CommonLeafSet()
self.splits = commonLeafSet.updateTreesToCommonLeafSet(
[self.inputTrees, [self.supertree]])
self.bitkeys = commonLeafSet.getCommonBitkeys()
self.taxnames = commonLeafSet.getCommonTaxNames()
self.taxa2Bitkey = commonLeafSet.getCommonTaxa2Bitkey()
def __init__(self, inputTree, distributionTrees=None):
"""
SuperTreeInputTrees is a utility to create sets of input trees.
The input trees are primarily to be used to evaluate super tree
construction methods.
Invocation removing a fixed number of taxa from each prospective input tree:
stit = SuperTreeInputTrees(inputTree)
stit.writeInputTreesToFile = True
stit.outputFile = 'myInputtrees.tre'
stit.noTaxaToRemove = 32
stit.noOutputTrees = 10
stit.generateInputTrees()
Invocation using built in distribution gathered from real world super tree cases::
stit = SuperTreeInputTrees(inputTree)
stit.writeInputTreesToFile = True
stit.outputFile = 'myInputtrees.tre'
stit.useTaxonDistribution = True
stit.generateInputTrees()
The user can generate a distribution of their own by supplying a list of p4 trees or a tree file.
The order of the trees is important, supertree and then all other trees. This goes for both list and
file. Like so::
stit = SuperTreeInputTrees(inputTree, distributionTrees='myTreefile.nex')
stit.writeInputTreesToFile = True
stit.outputFile = 'myInputtrees.tre'
stit.useTaxonDistribution = True
stit.generateInputTrees()
Placeholders which allow access to data after completed computations::
stit.outputTrees
stit.dist
"""
self.writeInputTreesToFile = False
self.outputFile = 'inputtrees.tre'
# Set to False if you want to have a set number of taxa in the output
# trees
self.useTaxonDistribution = False
# Only meaningful if setting useTaxonDistribution = False
self.noTaxaToRemove = 32
self.noOutputTrees = 10
gm = ['SuperTreeInputTrees()']
if isinstance(inputTree, Tree):
self.inputTree = inputTree # not a list.
elif type(inputTree) == type(""):
var.trees = []
read(inputTree)
if len(var.trees) > 1:
gm.append('Sorry, supply only one tree as supertree')
raise P4Error(gm)
# this was originally a list, ie [var.trees.pop()]
self.inputTree = var.trees.pop()
else:
gm.append("Input tree was neither a p4 Tree nor a valid filename")
gm.append("Got %s" % inputTree)
raise P4Error(gm)
if not self.inputTree._taxNames:
self.inputTree._setTaxNamesFromLeaves()
self.outputTrees = []
self.normalizedDist = []
# Distributions gathered from real world supertree input
# The dists are first a list of input tree taxon set sizes and the supertree taxon set size
# Using this data we can normalize the dists to fit the size of trees
# we want
# BunnyRSVNormal set from Wilkinson et al 2005, Syst Biol 54:823
# self.dist = [[3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11, 11, 12, 12, 13, 13, 13, 13, 13, 14, 14, 15, 17, 17, 18, 18, 18, 18, 18, 19, 19, 19, 20, 20, 20, 21, 22, 22, 23, 24, 25, 25, 25, 25, 25, 25, 26, 27, 28, 29, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 37, 38, 38, 40, 40, 41, 47, 51, 51, 52, 52, 52, 68, 70, 78, 78, 79, 80, 80], 80]
# CanidaeRVS set from Wilkinson et al 2005, Syst Biol 54:823
#self.dist = [[3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 5, 6, 7, 8, 8, 9, 10, 11, 11, 11, 12, 16, 16, 20, 23, 24, 30, 30, 33, 34, 34, 34, 34, 34], 34]
# CarnivoraRVS set from Wilkinson et al 2005, Syst Biol 54:823
#self.dist = [[3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 8, 8, 8, 8, 9, 9, 9, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12], 12]
# DavideDinoMRP set from Wilkinson et al 2005, Syst Biol 54:823
#self.dist = [[4, 4, 4, 5, 6, 6, 6, 7, 8, 8, 9, 9, 9, 10, 10, 10, 10, 10, 11, 11, 11, 12, 12, 12, 13, 14, 14, 14, 14, 15, 15, 15, 15, 16, 16, 17, 18, 18, 18, 18, 19, 19, 19, 19, 19, 19, 20, 20, 20, 22, 23, 23, 24, 24, 25, 26, 27, 27, 28, 28, 29, 29, 29, 29, 29, 30, 30, 30, 31, 31, 31, 31, 33, 33, 33, 33, 36, 37, 37, 38, 38, 39, 42, 45, 47, 48, 50, 53, 53, 66, 70, 71, 74, 74, 75, 75, 76, 78, 78, 80, 86, 86, 92, 94, 96, 100, 101, 102, 102, 103, 105, 110, 111, 111, 139, 148, 149, 153, 173, 199, 204, 217, 240, 269, 270, 271, 272, 272, 273, 273, 273, 273, 274, 275], 277]
# FelidaeRVS set from Wilkinson et al 2005, Syst Biol 54:823
self.dist = [[3, 3, 3, 3, 3, 4, 4, 4, 5, 6, 6, 6, 7, 7, 7, 7, 9, 9, 10, 10, 14,
16, 17, 24, 25, 28, 29, 29, 30, 30, 32, 34, 36, 36, 36, 36, 36, 36, 36, 36], 36]
# KennedyPageData set from Wilkinson et al 2005, Syst Biol 54:823
#self.dist = [[14, 16, 17, 20, 30, 30, 90], 122]
# ViverridaeRVS set from Wilkinson et al 2005, Syst Biol 54:823
#self.dist = [[4, 5, 10, 16, 19, 33, 34, 34, 34], 34]
if distributionTrees:
self.useTaxonDistribution = True
if type(distributionTrees) == type([]):
for t in distributionTrees:
if not isinstance(t, Tree):
gm.append(
"Input trees should be a list of p4 Tree objects. Got %s" % t)
raise P4Error(gm)
superTree = distributionTrees.pop(0)
inputTrees = distributionTrees
elif type(distributionTrees) == type(""):
var.trees = []
read(distributionTrees)
if len(var.trees) < 1:
gm.append(
'Sorry, at least one tree must be supplied as input tree')
raise P4Error(gm)
superTree = var.trees.pop(0)
inputTrees = var.trees
self._generateDistribution(superTree, inputTrees)