def __init__(self, x, y, **kwargs):
self.nvar = 1 if x.ndim==1 else x.shape[1]
assert (x.ndim==1 and x.size==y.size) or (x.ndim==2 and x.shape[0]==y.size), "X and Y inputs must have same number of rows"
assert (self.nvar < 5), "Maximum number of predictors is 4"
df = with_mode(NO_CONVERSION, r.data_frame)(x=x,y=y.flatten())
if x.ndim==1:
model = r("y ~ x")
else:
model = r("y ~ " + ' + '.join('x.%d' % (i+1) for i in range(4)))
self.smoother = with_mode(NO_CONVERSION, r.loess)(model, data=df, **kwargs)
def __init__(self, x, y, **kwargs):
self.nvar = 1 if x.ndim == 1 else x.shape[1]
assert (x.ndim == 1 and x.size == y.size) or (
x.ndim == 2 and x.shape[0]
== y.size), "X and Y inputs must have same number of rows"
assert (self.nvar < 5), "Maximum number of predictors is 4"
df = with_mode(NO_CONVERSION, r.data_frame)(x=x, y=y.flatten())
if x.ndim == 1:
model = r("y ~ x")
else:
model = r("y ~ " + ' + '.join('x.%d' % (i + 1) for i in range(4)))
self.smoother = with_mode(NO_CONVERSION, r.loess)(model,
data=df,
**kwargs)
def wilcox_test(x,y=None,**kwargs):
"""
Paired or unpaired wilcoxon rank sum (signed rank) test
Returns p value, and V/W statistic
Optional arguments:
paired - set to true for paired test
mu - value for null hypothesis (default 0.0)
alternative - 'two.sided' (default), 'less', 'greater'
"""
if y==None:
wc = with_mode(NO_CONVERSION, r.wilcox_test)(x, **kwargs)
else:
wc = with_mode(NO_CONVERSION, r.wilcox_test)(x,y, **kwargs)
return r['$'](wc, 'p.value'), r['$'](wc, 'statistic')
def wilcox_test(x, y=None, **kwargs):
"""
Paired or unpaired wilcoxon rank sum (signed rank) test
Returns p value, and V/W statistic
Optional arguments:
paired - set to true for paired test
mu - value for null hypothesis (default 0.0)
alternative - 'two.sided' (default), 'less', 'greater'
"""
if y == None:
wc = with_mode(NO_CONVERSION, r.wilcox_test)(x, **kwargs)
else:
wc = with_mode(NO_CONVERSION, r.wilcox_test)(x, y, **kwargs)
return r['$'](wc, 'p.value'), r['$'](wc, 'statistic')
def research_pair(
analysis,
categs,
pair,
max_separation = 45
):
"""Look for infomation about a particular pair
analysis: The analysis file or object
categs: Go categories R object
pair: The definition of the pair
"""
import rpy
in_analysis = find_pair_in_analysis(
analysis,
pair,
max_separation
)
genes = [ s.split()[0] for s in in_analysis ]
print '%s is in:\n%s' % ( str(pair), "\n".join( genes ) )
result = rpy.with_mode(
rpy.NO_CONVERSION,
rpy.r.analyseGoAnnotations
)(
categs,
genes
)
def mask_array_construct(self):
data = rpy.with_mode(0, rpy.r.read_table)(self.dataset_source, row_names=1)
'''
!Important!
if the dataset_source has too few data, conversion from R to python will be a problem.
The whole data matrix will be converted to a python string matrix.
R's NA is not converted to nan in python.
The problem has been found.
r.as_matrix converts small dataset to character type.
r.matrix won't rig the class type, but it rigs the structure.
The only to sovle this is add a colClasses vector to r.read_table.
such as: colClasses=c('character',rep('double',11))
But you have to know the no_of_cols in advance.
As our dataset is really big, this problem hasn't appeared.
'''
#print r.as_matrix(data)
array = ma.masked_inside(rpy.r.as_matrix(data), -1.0e20, 1.0e20)
#all are set to be masked except nan. weird! So have to do a converse.
self.mask_array = ma.array(array, mask=ma.logical_not(ma.getmask(array)))
self.genelabels = rpy.r.rownames(data)
self.no_of_genes = len(self.genelabels)
self.no_of_cols = len(array[0])
self.mask_matrix=ma.identity(self.no_of_cols)
del array ,data
def categorise_genes( mart, genes ):
"""Annotate/categorise genes according to GO"""
import rpy
return rpy.with_mode(
rpy.NO_CONVERSION,
rpy.r.categoriseGenes
)(
genes,
mart
)
def funcion(dato, variable, caso, opciones):
"""Funcion que convierte los datos de entrada en los resultados"""
import rpy #pylint: disable=import-error
diccionario = {}
r_data = {"Variable":[], "Factor":[]}
for x in dato.query(variable, caso = caso):
r_data["Variable"].append(float(x))
for x in dato.query(opciones["Factor"], caso = caso):
r_data["Factor"].append(repr(x))
# lista=[float(x) for x in dato.getCol(variable,caso=caso)]
# agrupacion=[x for x in dato.getCasos(opciones["Factor"])]
# agrupacion2=[x for x in dato.getCol(opciones["Factor"],caso=caso)]
# mifuncion=lambda f:agrupacion.index(f)
# agrupacionfinal=map(mifuncion,agrupacion2)
r_data_table = rpy.with_mode(rpy.NO_CONVERSION, rpy.r.data_frame)(r_data)
modelo = rpy.r("Variable ~ Factor")
aov = rpy.with_mode(rpy.NO_CONVERSION, rpy.r.aov)(modelo, r_data_table)
diccionario = rpy.r.summary(aov)
return diccionario
def get_mart( dataset = "mmusculus_gene_ensembl" ):
"""Gets ensembl mart for dataset"""
if not dataset in _marts:
_marts[ dataset ] = rpy.with_mode(
rpy.NO_CONVERSION,
rpy.r.useMart
)(
"ensembl",
dataset = dataset
)
return _marts[ dataset ]
def r_from_str(s):
"Returns an R object in a representation as a list of strings."
from rpy import r, with_mode, NO_CONVERSION
from tempfile import mktemp
tmpfile = mktemp()
#logging.info('Tmpfile: %s' % tmpfile)
try:
open(tmpfile, 'w').write(s)
names = with_mode(NO_CONVERSION, lambda : r.load(file=tmpfile))()
finally:
if os.access(tmpfile, os.R_OK):
os.remove(tmpfile)
def r_from_str(s):
"Returns an R object in a representation as a list of strings."
from rpy import r, with_mode, NO_CONVERSION
from tempfile import mktemp
tmpfile = mktemp()
#logging.info('Tmpfile: %s' % tmpfile)
try:
open(tmpfile, 'w').write(s)
names = with_mode(NO_CONVERSION, lambda: r.load(file=tmpfile))()
finally:
if os.access(tmpfile, os.R_OK):
os.remove(tmpfile)
def research_pair(analysis, categs, pair, max_separation=45):
"""Look for infomation about a particular pair
analysis: The analysis file or object
categs: Go categories R object
pair: The definition of the pair
"""
import rpy
in_analysis = find_pair_in_analysis(analysis, pair, max_separation)
genes = [s.split()[0] for s in in_analysis]
print '%s is in:\n%s' % (str(pair), "\n".join(genes))
result = rpy.with_mode(rpy.NO_CONVERSION,
rpy.r.analyseGoAnnotations)(categs, genes)
def print_pairs_go_analysis( pairs, gene_universe, analysis ):
"""Prints the go analysis for the given pairs
"""
import rpy, r_go
mart = r_go.get_mart( "mmusculus_gene_ensembl" )
categs = r_go.categorise_genes( mart, gene_universe )
#pair = ( 'M00349', 'M00350', True, False )
for p in pairs:
pair = p.binder_pair
print pair
in_analysis = find_pair_in_analysis(
analysis,
pair,
max_separation = 45
)
genes = [
seq.split(' ')[0]
for seq, hits
in in_analysis.iteritems()
]
print len(genes)
print "\n".join( genes )
result = rpy.with_mode(
rpy.NO_CONVERSION,
rpy.r.analyseGoAnnotations
)(
categs,
genes
)
rpy.r.printAnnotationResult( result, 10 )
def print_pairs_go_analysis(pairs, gene_universe, analysis):
"""Prints the go analysis for the given pairs
"""
import rpy, r_go
mart = r_go.get_mart("mmusculus_gene_ensembl")
categs = r_go.categorise_genes(mart, gene_universe)
#pair = ( 'M00349', 'M00350', True, False )
for p in pairs:
pair = p.binder_pair
print pair
in_analysis = find_pair_in_analysis(analysis, pair, max_separation=45)
genes = [seq.split(' ')[0] for seq, hits in in_analysis.iteritems()]
print len(genes)
print "\n".join(genes)
result = rpy.with_mode(rpy.NO_CONVERSION,
rpy.r.analyseGoAnnotations)(categs, genes)
rpy.r.printAnnotationResult(result, 10)
