def input_converter():
"""Input converter context from Python objects to RPY2 objects."""
return localconverter(
default_converter + pandas2ri.converter + numpy2ri.converter
)
def R2pd(self, rdf):
with localconverter(RO.default_converter + pandas2ri.converter):
pd_from_r_df = RO.conversion.rpy2py(rdf)
return pd_from_r_df
def numpy_conversion():
with conversion.localconverter(robjects.default_converter +
rpyn.converter) as lc:
yield
def test_ri2pandas(self):
rdataf = robjects.r('data.frame(a=1:2, '
' row.names=c("a", "b"))')
with localconverter(default_converter + rpyp.converter) as cv:
pandas_df = cv.rpy2py(rdataf)
assert all(x == y for x, y in zip(rdataf.rownames, pandas_df.index))
def test_series_int(self, dtype):
Series = pandas.core.series.Series
s = Series(range(5), index=['a', 'b', 'c', 'd', 'e'], dtype=dtype)
with localconverter(default_converter + rpyp.converter) as cv:
rp_s = robjects.conversion.py2rpy(s)
assert isinstance(rp_s, rinterface.IntSexpVector)
def test_object2String_with_None(self):
series = pandas.Series([None, "a", "b", "c", "a"], dtype="O")
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.py2rpy(series)
assert isinstance(rp_c, rinterface.StrSexpVector)
def test_category2Factor(self):
category = pandas.Series(["a", "b", "c", "a"], dtype="category")
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.py2rpy(category)
assert isinstance(rp_c, robjects.vectors.FactorVector)
def get_r_df(y_tr):
with localconverter(ro.default_converter + pandas2ri.converter):
r_y_tr = ro.conversion.py2rpy(y_tr)
return r_y_tr
def get_brms_data(dataset_name: str):
"A helper function for importing different datasets included in brms."
with localconverter(default_converter + pandas2ri.converter +
numpy2ri.converter) as cv:
return pd.DataFrame(
rpackages.data(brms).fetch(dataset_name)[dataset_name])
def glm_gam_poi(
adata: AnnData,
*,
groupby: str,
contrasts: Sequence[Tuple[Sequence[str], Sequence[str]]],
cofactors: Sequence[str] = None,
layer: Optional[str] = None,
subsample_disp=2000,
n_cores_per_job: int = 4,
n_jobs: int = 4,
):
"""
Perform DE analysis using edgeR.
Requires that an R installation and the following packages are available
GlmGamPoi
BiocParallel
RhpcBLASctl
Install them with `conda install bioconductor-glmgampoi bioconductor-biocparallel r-rhpcblasctl`.
Parameters
----------
adata
annotated data matrix
groupby
The column in adata.obs to test for DE
contrast
Liste of tuples with tests to perform, e.g.
`[('A', 'B'), (('A', 'B'), ('C', 'D','E'))]` which is equivalent to
`[(('A', ), ('B', )), (('A', 'B'), ('C', 'D','E'))]
cofactors
Additional columns to include into the model
layer
layer in adata that contains raw counts. If None, use `X`.
subsample_disp
Subsample cells to this nubmer during estimation of overdispersion.
n_cores_per_job
Number of cores to run per job (including BLAS parallelization)
n_jobs
Number of tests to run in parallel.
"""
try:
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri, numpy2ri
from rpy2.robjects.conversion import localconverter
from rpy2 import robjects as ro
except ImportError:
raise ImportError("edger requires rpy2 to be installed. ")
try:
base = importr("base")
glm = importr("glmGamPoi")
stats = importr("stats")
blasctl = importr("RhpcBLASctl")
bcparallel = importr("BiocParallel")
except ImportError:
raise ImportError(
"GlmGamPoi requires a valid R installation with the following packages: "
"glmGamPoi, BiocParallal, RhpcBLASctl")
blasctl.blas_set_num_threads(n_cores_per_job)
blasctl.omp_set_num_threads(n_cores_per_job)
logging.info("Preparing R objects")
# Define model formula
cofactors = [] if cofactors is None else _make_names(cofactors)
groupby = _make_names([groupby])[0]
model = f"~ 0 + {groupby} + {' + '.join(cofactors)}"
contrasts = _fix_contrasts(contrasts, groupby)
bcparallel.register(bcparallel.MulticoreParam(n_jobs))
with localconverter(ro.default_converter + pandas2ri.converter):
tmp_obs = adata.obs.loc[:, [groupby] + cofactors]
tmp_obs.columns = _make_names(tmp_obs.columns)
for col in tmp_obs.columns:
if not is_numeric_dtype(tmp_obs[col]):
tmp_obs[col] = _make_names(tmp_obs[col])
obs_r = ro.conversion.py2rpy(tmp_obs)
with localconverter(ro.default_converter + pandas2ri.converter):
expr = adata.X if layer is None else adata.layers[layer]
if issparse(expr):
expr = expr.T.toarray()
else:
expr = expr.T
expr = pd.DataFrame(expr)
expr.index = adata.var_names
expr.columns = adata.obs_names
expr_r = ro.conversion.py2rpy(expr)
# convert as dataframe and then convert to matrix - didn't keep rownames otherwise.
expr_r = base.as_matrix(expr_r)
design = stats.model_matrix(stats.as_formula(model), data=obs_r)
contrasts = [
f'({"+".join(b)}) / {len(b)} - ({"+".join(a)}) / {len(a)}'
for a, b in contrasts
]
logging.info("Fitting GLM")
fit = glm.glm_gp(expr_r, design=design, subsample=subsample_disp)
ro.globalenv["fit"] = fit
ro.globalenv["contrasts"] = contrasts
ro.r("""
library(dplyr)
de_res = BiocParallel::bplapply(contrasts, function(contrast) {
glmGamPoi::test_de(fit, contrast) %>%
mutate(comparision = contrast)
}) %>% bind_rows()
""")
with localconverter(ro.default_converter + numpy2ri.converter +
pandas2ri.converter):
return ro.conversion.rpy2py(ro.globalenv["de_res"])
def mast(
adata: AnnData,
*,
groupby: str,
groups: Union[Literal["all"], Sequence[str]],
cofactors: Sequence[str] = None,
layer: Optional[str] = None,
n_cores_per_job: int = 4,
n_jobs: int = 4,
):
"""
Perform DE analysis using edgeR.
Requires that an R installation and the following packages are available
MAST
BiocParallel
Install them with `conda install bioconductor-mast bioconductor-biocparallel`.
Parameters
----------
adata
annotated data matrix. X must contain normalized and log-transformed values.
groupby
The column in adata.obs to test for DE
cofactors
Additional columns to include into the model
layer
layer in adata that contains raw counts. If None, use `X`.
subsample_disp
Subsample cells to this nubmer during estimation of overdispersion.
n_cores_per_job
Number of cores to run per job (including BLAS parallelization)
n_jobs
Number of tests to run in parallel.
"""
try:
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri
from rpy2.robjects.conversion import localconverter
from rpy2 import robjects as ro
import anndata2ri
except ImportError:
raise ImportError(
"MAST requires rpy2 and anndata2ri to be installed. ")
try:
mast = importr("MAST")
bcparallel = importr("BiocParallel")
except ImportError:
raise ImportError(
"MAST requires a valid R installation with the following packages: "
"MAST, BiocParallel")
bcparallel.register(bcparallel.MulticoreParam(n_jobs))
logging.info("Preparing AnnData")
tmp_adata = AnnData(
X=adata.X if layer is None else adata.layers[layer],
obs=adata.obs,
var=adata.var,
)
tmp_adata.obs.columns = _make_names(tmp_adata.obs.columns)
tmp_adata.obs[groupby] = _make_names(tmp_adata.obs[groupby])
contrasts = []
for group in tmp_adata.obs[groupby].unique():
contrasts.append(f"is_group_{group}")
tmp_adata.obs[f"is_group_{group}"] = tmp_adata.obs[groupby] == group
logging.info("Preparing R objects")
with localconverter(anndata2ri.converter):
sce = ro.conversion.py2rpy(tmp_adata)
sca = mast.SceToSingleCellAssay(sce)
groupby = _make_names([groupby])[0]
cofactor_formula = ("" if cofactors is None else "+ " +
" + ".join(_make_names(cofactors)))
logging.info("Running MAST")
ro.globalenv["cpus_per_thread"] = n_cores_per_job
ro.globalenv["contrasts"] = contrasts
ro.globalenv["cofactor_formula"] = cofactor_formula
ro.globalenv["sca"] = sca
ro.r("""
library(dplyr)
de_res = bplapply(contrasts, function(model_col) {
op = options(mc.cores=cpus_per_thread)
on.exit(options(op))
contrast_to_test = paste0(model_col, "TRUE")
fit = zlm(as.formula(paste0("~", model_col, cofactor_formula)), sca)
res = summary(fit, doLRT=contrast_to_test)$datatable
merge(
res[contrast==contrast_to_test & component=='H', .(primerid, `Pr(>Chisq)`)], #P-vals
res[contrast==contrast_to_test & component=='logFC', .(primerid, coef)],
by='primerid'
) %>% mutate(comparison=model_col)
}) %>% bind_rows()
""")
with localconverter(ro.default_converter + pandas2ri.converter):
de_res = ro.conversion.rpy2py(ro.globalenv["de_res"])
de_res["comparison"] = de_res["comparison"].str.replace("is_group_", "")
return de_res
def edger(
adata: AnnData,
*,
groupby: str,
groups: Union[Literal["all"], Sequence[str]],
cofactors: Sequence[str] = None,
layer: Optional[str] = None,
n_cores_per_job: int = 4,
n_jobs: int = 4,
) -> pd.DataFrame:
"""
Perform DE analysis using edgeR.
Requires that an R installation and the following packages are available
edgeR
BiocParallel
RhpcBLASctl
Install them with `conda install bioconductor-edger bioconductor-biocparallel r-rhpcblasctl`.
Parameters
----------
adata
annotated data matrix
groupby
The column in adata.obs to test for DE
groups
Subset of groups, e.g. `['g1', 'g2', 'g3']`, to which comparison shall
be restricted, or `'all'` (default), for all groups.
cofactors
Additional columns to include into the model
layer
layer in adata that contains raw counts. If None, use `X`.
n_cores_per_job
Number of cores to run per job (including BLAS parallelization)
n_jobs
Number of tests to run in parallel.
Returns
-------
DataFrame with differential expression results
"""
try:
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri, numpy2ri
from rpy2.robjects.conversion import localconverter
from rpy2 import robjects as ro
except ImportError:
raise ImportError("edger requires rpy2 to be installed. ")
try:
base = importr("base")
edger = importr("edgeR")
stats = importr("stats")
limma = importr("limma")
blasctl = importr("RhpcBLASctl")
bcparallel = importr("BiocParallel")
except ImportError:
raise ImportError(
"edgeR requires a valid R installation with the following packages: "
"edgeR, BiocParallel, RhpcBLASctl")
# Set parallelism
blasctl.blas_set_num_threads(n_cores_per_job)
blasctl.omp_set_num_threads(n_cores_per_job)
bcparallel.register(bcparallel.MulticoreParam(n_jobs))
logging.info("Preparing R objects")
cofactor_formula = ("" if cofactors is None else
f"+ {' + '.join(_make_names(cofactors))}")
groupby = _make_names(groupby)
model = f"~ 0 + {groupby} {cofactor_formula}"
tmp_adata = (adata if groups == "all" else
adata[adata.obs[groupby].isin(groups), :]).copy()
tmp_adata.obs.columns = _make_names(tmp_adata.obs.columns)
for col in tmp_adata.obs.columns:
if not is_numeric_dtype(tmp_adata.obs[col]):
tmp_adata.obs[col] = _make_names(tmp_adata.obs[col])
groups = tmp_adata.obs[groupby].unique()
if len(groups) < 2:
raise ValueError("Need at least two groups to compare. ")
with localconverter(ro.default_converter + pandas2ri.converter):
obs_r = ro.conversion.py2rpy(
tmp_adata.obs.loc[:, [groupby] +
([] if cofactors is None else cofactors)])
# just need the index
var_r = ro.conversion.py2rpy(
pd.DataFrame({"gene_symbol": tmp_adata.var_names},
index=tmp_adata.var_names))
with localconverter(ro.default_converter + numpy2ri.converter):
expr = tmp_adata.X if layer is None else tmp_adata.layers[layer]
if issparse(expr):
expr = expr.T.toarray()
else:
expr = expr.T
expr_r = ro.conversion.py2rpy(expr)
design = stats.model_matrix(stats.as_formula(model), data=obs_r)
dge = edger.DGEList(counts=expr_r, samples=obs_r, genes=var_r)
contrasts_r = limma.makeContrasts(
contrasts=[
f'({"+".join([f"{groupby}{g}" for g in groups if g != group])})'
f" / {len(groups) - 1}"
f" - {groupby}{group}" for group in groups
],
levels=base.colnames(design),
)
logging.info("Calculating NormFactors")
dge = edger.calcNormFactors(dge)
logging.info("Estimating Dispersions")
dge = edger.estimateDisp(dge, design=design)
logging.info("Fitting linear model")
fit = edger.glmQLFit(dge, design=design)
ro.globalenv["fit"] = fit
ro.globalenv["contrasts"] = contrasts_r
ro.r("""
library(dplyr)
de_res = BiocParallel::bplapply(1:ncol(contrasts), function(i) {
test = edgeR::glmQLFTest(fit, contrast=contrasts[, i])
edgeR::topTags(test, n=Inf, adjust.method="BH")$table %>%
mutate(contrast_idx = i - 1)
}) %>% bind_rows()
""")
with localconverter(ro.default_converter + numpy2ri.converter +
pandas2ri.converter):
de_res = ro.conversion.rpy2py(ro.globalenv["de_res"])
# TODO fix this
# de_res["group"] = [groups[i] for i in de_res["contrast_idx"]]
return de_res
def test_dataframe_columnnames(self):
pd_df = pandas.DataFrame({'the one': [1, 2], 'the other': [3, 4]})
# Convert to R
with localconverter(default_converter + rpyp.converter) as cv:
rp_df = robjects.conversion.py2rpy(pd_df)
assert tuple(rp_df.names) == ('the one', 'the other')
def test_series_obj_str(self, data, dtype):
Series = pandas.core.series.Series
s = Series(data, index=['a', 'b', 'c'], dtype=dtype)
with localconverter(default_converter + rpyp.converter) as cv:
rp_s = robjects.conversion.py2rpy(s)
assert isinstance(rp_s, rinterface.StrSexpVector)
def pandas2R(df):
"""Local conversion of pandas dataframe to R dataframe as recommended by rpy2"""
with localconverter(robjects.default_converter + pandas2ri.converter):
data = robjects.conversion.py2rpy(df)
return data
def r_to_py(object_):
if isinstance(object_, robjects.DataFrame):
with localconverter(pandas2ri.converter):
py_object_ = robjects.conversion.rpy2py(object_)
return py_object_
return object_
def test_series_obj_allnone(self):
Series = pandas.core.series.Series
s = Series([None, None, None], index=['a', 'b', 'c'])
with localconverter(default_converter + rpyp.converter) as cv:
rp_s = robjects.conversion.py2rpy(s)
assert isinstance(rp_s, rinterface.BoolSexpVector)
def testObject2String(self):
series = pandas.Series(["a", "b", "c", "a"], dtype="O")
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.py2ro(series)
self.assertEqual(robjects.vectors.StrVector, type(rp_c))
def test_orderedFactor2Category(self):
factor = robjects.vectors.FactorVector(('a', 'b', 'a'), ordered=True)
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.rpy2py(factor)
assert isinstance(rp_c, pandas.Categorical)
def testOrderedFactor2Category(self):
factor = robjects.vectors.FactorVector(('a', 'b', 'a'), ordered=True)
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.ri2py(factor)
self.assertEqual(pandas.Categorical, type(rp_c))
def test_categorywithNA2Factor(self):
category = pandas.Series(['a', 'b', 'c', numpy.nan], dtype='category')
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.py2rpy(category)
assert isinstance(rp_c, robjects.vectors.FactorVector)
assert rp_c[3] == rinterface.NA_Integer
def testCategory2Factor(self):
category = pandas.Series(["a", "b", "c", "a"], dtype="category")
with localconverter(default_converter + rpyp.converter) as cv:
rp_c = robjects.conversion.py2ro(category)
self.assertEqual(robjects.vectors.FactorVector, type(rp_c))
def test_series(self):
Series = pandas.core.series.Series
s = Series(numpy.random.randn(5), index=['a', 'b', 'c', 'd', 'e'])
with localconverter(default_converter + rpyp.converter) as cv:
rp_s = robjects.conversion.py2rpy(s)
assert isinstance(rp_s, rinterface.FloatSexpVector)
def testSeries(self):
Series = pandas.core.series.Series
s = Series(numpy.random.randn(5), index=['a', 'b', 'c', 'd', 'e'])
with localconverter(default_converter + rpyp.converter) as cv:
rp_s = robjects.conversion.py2ri(s)
self.assertEqual(rinterface.FloatSexpVector, type(rp_s))
def R(self, line, cell=None, local_ns=None):
"""
Execute code in R, optionally returning results to the Python runtime.
In line mode, this will evaluate an expression and convert the returned
value to a Python object. The return value is determined by rpy2's
behaviour of returning the result of evaluating the final expression.
Multiple R expressions can be executed by joining them with
semicolons::
In [9]: %R X=c(1,4,5,7); sd(X); mean(X)
Out[9]: array([ 4.25])
In cell mode, this will run a block of R code. The resulting value
is printed if it would be printed when evaluating the same code
within a standard R REPL.
Nothing is returned to python by default in cell mode::
In [10]: %%R
....: Y = c(2,4,3,9)
....: summary(lm(Y~X))
Call:
lm(formula = Y ~ X)
Residuals:
1 2 3 4
0.88 -0.24 -2.28 1.64
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.0800 2.3000 0.035 0.975
X 1.0400 0.4822 2.157 0.164
Residual standard error: 2.088 on 2 degrees of freedom
Multiple R-squared: 0.6993,Adjusted R-squared: 0.549
F-statistic: 4.651 on 1 and 2 DF, p-value: 0.1638
In the notebook, plots are published as the output of the cell::
%R plot(X, Y)
will create a scatter plot of X bs Y.
If cell is not None and line has some R code, it is prepended to
the R code in cell.
Objects can be passed back and forth between rpy2 and python via the
-i -o flags in line::
In [14]: Z = np.array([1,4,5,10])
In [15]: %R -i Z mean(Z)
Out[15]: array([ 5.])
In [16]: %R -o W W=Z*mean(Z)
Out[16]: array([ 5., 20., 25., 50.])
In [17]: W
Out[17]: array([ 5., 20., 25., 50.])
The return value is determined by these rules:
* If the cell is not None (i.e., has contents), the magic returns None.
* If the final line results in a NULL value when evaluated
by rpy2, then None is returned.
* No attempt is made to convert the final value to a structured array.
Use %Rget to push a structured array.
* If the -n flag is present, there is no return value.
* A trailing ';' will also result in no return value as the last
value in the line is an empty string.
"""
args = parse_argstring(self.R, line)
# arguments 'code' in line are prepended to
# the cell lines
if cell is None:
code = ''
return_output = True
line_mode = True
else:
code = cell
return_output = False
line_mode = False
code = ' '.join(args.code) + code
# if there is no local namespace then default to an empty dict
if local_ns is None:
local_ns = {}
if args.converter is None:
converter = self.converter
else:
try:
converter = local_ns[args.converter]
except KeyError:
try:
converter = self.shell.user_ns[args.converter]
except KeyError:
raise NameError(
"name '%s' is not defined" % args.converter
)
if not isinstance(converter, Converter):
raise TypeError("'%s' must be a %s object (but it is a %s)."
% (args.converter, Converter,
type(localconverter)))
if args.input:
for input in ','.join(args.input).split(','):
try:
val = local_ns[input]
except KeyError:
try:
val = self.shell.user_ns[input]
except KeyError:
raise NameError("name '%s' is not defined" % input)
with localconverter(converter) as cv:
ro.r.assign(input, val)
if args.display:
try:
cell_display = local_ns[args.display]
except KeyError:
try:
cell_display = self.shell.user_ns[args.display]
except KeyError:
raise NameError("name '%s' is not defined" % args.display)
else:
cell_display = CELL_DISPLAY_DEFAULT
tmpd = self.setup_graphics(args)
text_output = ''
try:
if line_mode:
for line in code.split(';'):
text_result, result, visible = self.eval(line)
text_output += text_result
if text_result:
# The last line printed something to the console so
# we won't return it.
return_output = False
else:
text_result, result, visible = self.eval(code)
text_output += text_result
if visible:
with contextlib.ExitStack() as stack:
if self.cache_display_data:
stack.enter_context(
rpy2.rinterface_lib
.callbacks
.obj_in_module(rpy2.rinterface_lib
.callbacks,
'consolewrite_print',
self.write_console_regular))
cell_display(result, args)
text_output += self.flush()
except RInterpreterError as e:
# TODO: Maybe we should make this red or something?
print(e.stdout)
if not e.stdout.endswith(e.err):
print(e.err)
raise e
finally:
if self.device in ['png', 'svg']:
ro.r('dev.off()')
if text_output:
# display_data.append(('RMagic.R', {'text/plain':text_output}))
displaypub.publish_display_data(
data={'text/plain': text_output}, source='RMagic.R')
# publish the R images
if self.device in ['png', 'svg']:
display_data, md = self.publish_graphics(
tmpd, args.isolate_svgs
)
for tag, disp_d in display_data:
displaypub.publish_display_data(data=disp_d, source=tag,
metadata=md)
# kill the temporary directory - currently created only for "svg"
# and "png" (else it's None)
if tmpd:
rmtree(tmpd)
if args.output:
with localconverter(converter) as cv:
for output in ','.join(args.output).split(','):
output_ipy = ro.globalenv.find(output)
self.shell.push({output: output_ipy})
# this will keep a reference to the display_data
# which might be useful to other objects who happen to use
# this method
if self.cache_display_data:
self.display_cache = display_data
# We're in line mode and return_output is still True,
# so return the converted result
if return_output and not args.noreturn:
if result is not ri.NULL:
with localconverter(converter) as cv:
res = cv.rpy2py(result)
return res
def convert_pd_df_to_r(pd_df):
with localconverter(ro.default_converter + pandas2ri.converter):
r_df = ro.conversion.py2rpy(pd_df)
return r_df
from rpy2.robjects import pandas2ri
from rpy2.robjects.conversion import localconverter
base = importr('base')
utils = importr('utils')
## only need to install once ##
# utils.install_packages('PlayerRatings')
# utils.chooseCRANmirror(ind=65)
pyPR = importr('PlayerRatings')
pd_df = pd.DataFrame({
'Time Period': [1, 1, 1],
'Player 1': [1, 2, 3],
'Player 2': [2, 3, 1],
'Result': [1, 0, 0]
})
print(pd_df)
with localconverter(ro.default_converter + pandas2ri.converter):
r_from_pd_df = ro.conversion.py2rpy(pd_df)
print(r_from_pd_df)
sobj = pyPR.steph(r_from_pd_df, cval=8, hval=8)
#
r('''
f <- function() {
data(quasiflow)
qf <- quasiflow[1:1000,1:3]
qf.label <- quasiflow[1:1000,4]
thr <- c(0.25, -0.3)
qf.prim <- prim.box(x=qf, y=qf.label, threshold=thr, threshold.type=0)
jpeg('rplot.jpg')
plot(qf.prim)
dev.off()
}
''')
from rpy2.robjects.conversion import localconverter
from rpy2.robjects import pandas2ri
with localconverter(robjects.default_converter + pandas2ri.converter):
qf = robjects.conversion.py2rpy(df)
print(qf)
resp = robjects.FloatVector(response)
h=r.hist(resp)
hf = robjects.conversion.converter.rpy2py(h)
pf = pd.DataFrame(hf)
print(h)
print(pf)
print(pf.attrs)
#print(prim_response)
#thr = robjects.FloatVector([1.0,2.0])
#rprim = r['prim.box']
#prim_res = rprim(x=qf,y=prim_response,threshold=thr)
from scipy import stats
os.chdir(
"/srv/uom-data1-q.unimelb.edu.au/6300-afournier/home/student.unimelb.edu.au/andhikap/Clim_GWAS/Clim_GWAS_2"
)
from rpy2.robjects.packages import importr
import rpy2.robjects as ro
import pandas as pd
from rpy2.robjects import r
from rpy2.robjects import pandas2ri
from rpy2.robjects import default_converter
from rpy2.robjects.conversion import localconverter
#Get the snp data
ro.r('load("AllPlantings_Corrected_SNPs_unique.RData")') #Load the file
with localconverter(default_converter + pandas2ri.converter) as cv:
pd_snps = r('snps')
snps = pd_snps.iloc[:, 1:len(pd_snps.columns) + 1]
SNP_data = np.array(snps)
#get the phenotype data
ro.r('load("Phenotypes_dtbfixed.RData")')
with localconverter(default_converter + pandas2ri.converter) as cv:
pd_phenotypes = r('phenotypes')
Pheno_data = np.array(
pd_phenotypes.iloc[:, 1]) #Days-to-bolting phenotypes only
#include the kinship matrix
def conversion_rpy2py_local(conv_mod: ConversionModule, dataset: Callable[[], Sexp]) -> Any:
# Needs default_converter to e.g. call `as` on a SummarizedExperiment:
# Calling a R function returning a S4 object requires py2rpy[RS4], py2rpy[str], …
with localconverter(default_converter + conv_mod.converter):
return dataset()
