def read(self):
tbl = np.loadtxt(self.filename, ndmin=2)
domvals = tbl.T[0] # first column is attribute name
from orangecontrib.infrared.preprocess import features_with_interpolation
domain = Orange.data.Domain(features_with_interpolation(domvals), None)
datavals = tbl.T[1:]
return Orange.data.Table(domain, datavals)
def test_autointerpolate(self):
d1 = Orange.data.Table("peach_juice.dpt")
d2 = Orange.data.Table("collagen.csv")
d3 = Orange.data.Table(d1.domain, d2)
d1x = getx(d1)
d2x = getx(d2)
#have the correct number of non-nan elements
validx = np.where(d1x >= min(d2x), d1x, np.nan)
validx = np.where(d1x <= max(d2x), validx, np.nan)
self.assertEqual(np.sum(~np.isnan(validx)),
np.sum(~np.isnan(d3.X[0])))
#check roundtrip
atts = features_with_interpolation(d2x)
ndom = Orange.data.Domain(atts, None)
dround = Orange.data.Table(ndom, d3)
#edges are unknown, the rest roughly the same
np.testing.assert_allclose(dround.X[:, 1:-1], d2.X[:, 1:-1], rtol=0.011)
def read(self):
with open(self.filename, "rb") as f:
# read first row separately because of two empty columns
header = f.readline().decode("ascii").rstrip().split("\t")
header = [a.strip() for a in header]
assert header[0] == header[1] == ""
dom_vals = [float(v) for v in header[2:]]
from orangecontrib.infrared.preprocess import features_with_interpolation
domain = Orange.data.Domain(features_with_interpolation(dom_vals),
None)
tbl = np.loadtxt(f, ndmin=2)
data = Orange.data.Table(domain, tbl[:, 2:])
metas = [
ContinuousVariable.make('map_x'),
ContinuousVariable.make('map_y')
]
domain = Orange.data.Domain(domain.attributes, None, metas=metas)
data = data.transform(domain)
data[:, metas[0]] = tbl[:, 0].reshape(-1, 1)
data[:, metas[1]] = tbl[:, 1].reshape(-1, 1)
return data