def testRepr(self):
# this should go to testVector, with other tests for repr()
l = (('b', numpy.array([True, False, True], dtype=numpy.bool_)),
('i', numpy.array([1, 2, 3], dtype="i")),
('f', numpy.array([1, 2, 3], dtype="f")),
('s', numpy.array(["a", "b", "c"], dtype="S")),
('u', numpy.array([u"a", u"b", u"c"], dtype="U")))
od = OrderedDict(l)
pd_df = pandas.core.frame.DataFrame(od)
rp_df = rpyp.pandas2ri(pd_df)
s = repr(rp_df) # used to fail with a TypeError
s = s.split('\n')
self.assertEqual('[Array, Array, Array, FactorV..., FactorV...]', s[1].strip())
def generateLocalMetrics(self, resource_url):
# read pandas dataframe
df = pd.DataFrame()
try:
response = requests.get(resource_url)
content = io.StringIO(response.content.decode('utf-8'))
if self.is_arff(resource_url):
data, meta = arff.loadarff(content)
print('*** arff data: ', meta)
df = pd.DataFrame(data)
df = df.select_dtypes(
exclude=['number']).applymap(lambda x: x.replace("'", ""))
if self.is_csv(resource_url):
df = pd.read_csv(content) # not tested yet
except Exception as e:
print('Exception caught: ', e)
#df = df.apply(pd.to_numeric, errors='ignore')
print('*** Numeric df: ', df.dtypes)
# convert to R dataframe
# Assuming that the last column is the output values
pandas2ri.activate()
# print('** pandas2ri methods: ', dir(pandas2ri))
# Latest pyr2 docs recommend to use pandas2ri.py2ri functionality, but we are not able to use latest version of pyr2 due to dependence on python 2 forced by CKAN. The following works for pyr2=2.4.0, not tested on other versions.
inputD = pandas2ri.pandas2ri(df)
# inputR = pandas2ri.pandas2ri(df.iloc[:, :-1])
# outputR = pandas2ri.pandas2ri(df.iloc[:, -1:])
# Call R functions on dataframe
ro.r('require(ECoL)')
ro.globalenv['dat'] = inputD
## Conversion from pandas sets column types to StrVector, we need them to be FactorVectors in the APIs we invoke.
ro.r('''dat[,1:ncol(dat)]=lapply(1:ncol(dat),function(x) {
tryCatch({
as.factor(dat[[x]])
},warning = function(w) {
dat[[x]]}
)} )''')
# ro.globalenv['xvar'] = inputR
# ro.globalenv['yvar'] = outputR
# result = ro.r('complexity(xvar, yvar)')
## For the lack of knowledge of input data, we are making an assumption that the last column of dataset is the dependent attribute.
result = ro.r('complexity(dat[-ncol(dat)], dat[ncol(dat)])')
print('*** Complexity output: ', pandas2ri.ri2pandas(result),
' type: ', dir(result))
for name in result.names:
print('** Datacard metric: ', name, ' -> ', result.rx2(name)[0])
group, metric = name.split('.', 1)
value = result.rx2(name)[0]
self.add_to_datacard(group, metric, value)
def testDataFrame(self):
l = (('b', numpy.array([True, False, True], dtype=numpy.bool_)),
('i', numpy.array([1, 2, 3], dtype="i")),
('f', numpy.array([1, 2, 3], dtype="f")),
('s', numpy.array(["a", "b", "c"], dtype="S")),
('u', numpy.array([u"a", u"b", u"c"], dtype="U")),
('dates', [datetime(2012, 5, 2),
datetime(2012, 6, 3),
datetime(2012, 7, 1)]))
od = OrderedDict(l)
pd_df = pandas.core.frame.DataFrame(od)
rp_df = rpyp.pandas2ri(pd_df)
self.assertEqual(pd_df.shape[0], rp_df.nrow)
self.assertEqual(pd_df.shape[1], rp_df.ncol)
def testRepr(self):
# this should go to testVector, with other tests for repr()
l = (('b', numpy.array([True, False, True],
dtype=numpy.bool_)), ('i',
numpy.array([1, 2, 3],
dtype="i")),
('f', numpy.array([1, 2, 3], dtype="f")),
('s', numpy.array(["a", "b", "c"],
dtype="S")), ('u',
numpy.array([u"a", u"b", u"c"],
dtype="U")))
od = OrderedDict(l)
pd_df = pandas.core.frame.DataFrame(od)
rp_df = rpyp.pandas2ri(pd_df)
s = repr(rp_df) # used to fail with a TypeError
s = s.split('\n')
self.assertEqual('[Array, Array, Array, FactorV..., FactorV...]',
s[1].strip())
def predict(self, X):
if self._model is not None:
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri
mgcv = importr('mgcv')
import pandas as pd
n_channels = self.n_channels
lin_model = self._linear_model
N = X.shape[0]
w = np.copy(lin_model.get_weights())
m = w.shape[0] / n_channels
chan_ind = np.reshape(np.arange(w.shape[0]), (m, n_channels),
order='F')
Yw_pred = np.zeros((N, n_channels))
for j in range(n_channels):
# predictions for channel j
Yw_pred[:, j] = np.dot(X[:, chan_ind[:, j]], w[chan_ind[:, j]])
y = np.zeros((N, ))
YX = np.hstack((np.atleast_2d(y).T, Yw_pred))
df = pd.DataFrame(YX, columns=self.columns)
try:
df_r = pandas2ri.py2ri(df)
except BaseException:
df_r = pandas2ri.pandas2ri(df)
y_pred = mgcv.predict_gam(self._model,
df_r,
type="response",
se="False")
return np.asarray(y_pred)
else:
raise ValueError('Fit model first!')
def testDataFrame(self):
l = (('b', numpy.array([True, False, True],
dtype=numpy.bool_)), ('i',
numpy.array([1, 2, 3],
dtype="i")),
('f', numpy.array([1, 2, 3],
dtype="f")), ('s',
numpy.array(["a", "b", "c"],
dtype="S")),
('u', numpy.array([u"a", u"b", u"c"], dtype="U")), ('dates', [
datetime(2012, 5, 2),
datetime(2012, 6, 3),
datetime(2012, 7, 1)
]))
od = OrderedDict(l)
pd_df = pandas.core.frame.DataFrame(od)
rp_df = rpyp.pandas2ri(pd_df)
self.assertEqual(pd_df.shape[0], rp_df.nrow)
self.assertEqual(pd_df.shape[1], rp_df.ncol)
def _fit_regression(self, dataset, target, **kwargs):
r_df_name = 'df_' + target['name']
r_model_name = 'model_' + target['name']
df = self._get_pd_df(dataset, target['name'])
# TODO - handle this feature gracefully
if '...' in set(df.columns):
df.drop('...', axis=1, inplace=True)
rpy2.robjects.globalenv[r_df_name] = pandas2ri.pandas2ri(df)
cmd = "lmer(%s, data=%s, REML=FALSE)"
formula = '%s ~ . %s %s' % (target['name'], ''.join(
' + (1|%s)' % varname for varname in self.confound_names), ''.join(
' - %s' % varname for varname in self.confound_names))
print "MIXED: fitting ", cmd % (formula, r_df_name)
model, params = self._train_r_model(cmd % (formula, r_df_name),
r_model_name)
return regression_base.ModelResult(model=model,
weights=params,
response_type='continuous')
def _fit_classifier(self, dataset, target, level=None, **kwargs):
r_df_name = 'df_%s_%s' % (target['name'], level)
r_model_name = 'model_%s_%s' % (target['name'], level)
df = self._get_pd_df(dataset, target['name'], level)
# TODO - handle this feature gracefully
if '...' in set(df.columns):
df.drop('...', axis=1, inplace=True)
rpy2.robjects.globalenv[r_df_name] = pandas2ri.pandas2ri(df)
cmd = "glmer(%s, family=binomial(link='logit'), data=%s, REML=FALSE)"
formula = '%s ~ . %s %s' % (
'%s.%s' % (target['name'], level) if level else target['name'],
''.join(' + (1|%s)' % varname
for varname in self.confound_names), ''.join(
' - %s' % varname for varname in self.confound_names))
model, params = self._train_r_model(cmd % (formula, r_df_name),
r_model_name)
return regression_base.ModelResult(model=model,
weights=params,
response_type='categorical')
def fit(self, X, y):
from lnpy import linear as linear_models
n_channels = self.n_channels
# estimation a GAM using all dimensions is not working well;
# thus we try to estimate the linear weights using a linear model
# and then fit a GAM to the linear predictions for each channel
from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri
import rpy2.robjects as ro
pandas2ri.activate()
import pandas as pd
try:
import pandas.rpy.common as com
com_available = True
except BaseException:
com_available = False
mgcv = importr('mgcv')
if self.linear_model is None:
lin_model = linear_models.ARD(verbose=False)
lin_model.fit(X, y)
elif isinstance(self.linear_model, string_types):
if self.linear_model.upper() == 'ARD':
lin_model = linear_models.ARD(verbose=False)
elif self.linear_model.upper() == 'RIDGE':
lin_model = linear_models.Ridge(verbose=False)
lin_model.fit(X, y)
N = X.shape[0]
w = np.copy(lin_model.get_weights())
m = w.shape[0] / n_channels
chan_ind = np.reshape(np.arange(w.shape[0]), (m, n_channels),
order='F')
Yw_pred = np.zeros((N, n_channels))
for j in range(n_channels):
# predictions for channel j
Yw_pred[:, j] = np.dot(X[:, chan_ind[:, j]], w[chan_ind[:, j]])
# fit GAM
YX = np.hstack((np.atleast_2d(y).T, Yw_pred))
df = pd.DataFrame(YX, columns=self.columns)
if com_available:
df_r = com.convert_to_r_dataframe(df)
else:
try:
df_r = pandas2ri.py2ri(df)
except BaseException:
df_r = pandas2ri.pandas2ri(df)
mod = self.model_string
m = mgcv.gam(ro.r(mod),
data=df_r,
family='gaussian()',
optimizer='perf')
self._model = m
self._linear_model = lin_model
def testSeries(self):
Series = pandas.core.series.Series
s = Series(numpy.random.randn(5), index=['a', 'b', 'c', 'd', 'e'])
rp_s = rpyp.pandas2ri(s)
self.assertEqual(rinterface.SexpVector, type(rp_s))
def testSeries(self):
Series = pandas.core.series.Series
s = Series(numpy.random.randn(5), index=['a', 'b', 'c', 'd', 'e'])
rp_s = rpyp.pandas2ri(s)
self.assertEqual(rinterface.SexpVector, type(rp_s))
