def test_dsres_load_dataset(self):
path, _ = os.path.split(sdf.__file__)
filename = os.path.join(path, 'examples', 'IntegerNetwork1.mat')
ds = sdf.load(filename, objectname='/booleanPulse2/period')
self.assertEqual(ds.data, 2.0)
self.assertEqual(ds.unit, 's')
self.assertEqual(ds.comment, 'Time for one period')
ds = sdf.load(filename, objectname='/booleanPulse2/y')
self.assertEqual(ds.data.dtype, np.dtype(np.int32))
self.assertEqual(ds.data.size, 552)
self.assertEqual(ds.data[0], True)
self.assertEqual(ds.data[93], False)
s = ds.scales[0]
self.assertEqual(s.data.size, 552)
self.assertEqual(s.data.dtype, np.dtype(np.float32))
self.assertEqual(s.unit, 's')
self.assertEqual(s.comment, 'Simulation time')
ds = sdf.load(filename, objectname='/integerConstant/k')
self.assertEqual(ds.data.dtype, np.dtype(np.int32))
self.assertEqual(ds.data, 1)
def test_dsres_load_all(self):
path, _ = os.path.split(sdf.__file__)
filename = os.path.join(path, 'examples', 'IntegerNetwork1.mat')
g = sdf.load(filename)
s = g['Time']
self.assertEqual(s.data.size, 552)
self.assertEqual(s.data.dtype, np.dtype(np.float32))
self.assertEqual(s.unit, 's')
self.assertEqual(s.comment, 'Simulation time')
ds = g['booleanPulse2']['period']
self.assertEqual(ds.data, 2.0)
self.assertEqual(ds.unit, 's')
self.assertEqual(ds.comment, 'Time for one period')
ds = g['booleanPulse2']['y']
self.assertEqual(ds.data.dtype, np.int32)
self.assertEqual(ds.data.size, 552)
self.assertEqual(ds.data[0], True)
self.assertEqual(ds.data[93], False)
self.assertEqual(ds.scales[0], s)
ds = g['integerConstant']['k']
self.assertEqual(ds.data.dtype, np.int32)
self.assertEqual(ds.data, 1)
def test_roundtrip(self):
# create a scale
ds1 = sdf.Dataset('DS1',
comment='dataset 1',
data=np.array([0.1, 0.2, 0.3]),
display_name='Scale 1',
scale_name='Scale 1',
quantity='Q1',
unit='U1',
display_unit='DU1',
is_scale=True)
# create a 1D dataset
ds2 = sdf.Dataset('DS2',
comment='dataset 2',
data=np.array([1, 2, 3]),
display_name='Dataset 2',
quantity='Q2',
unit='U2',
display_unit='DU2',
scales=[ds1])
ds3 = sdf.Dataset('DS3',
comment='dataset 3',
data=np.array([0.1, 0.2, 0.3]),
display_name='Scale 1',
scale_name='Scale 1',
quantity='Q1',
unit='U1',
display_unit='DU1',
is_scale=True)
# create a group
g = sdf.Group(name='/DS2',
comment='my comment',
attributes={'A1': 'my string', 'A2': 0.1, 'A3': 1},
datasets=[ds1, ds2])
g2 = sdf.Group(name='/G2',
comment='my comment111',
attributes={'A1': 'my string', 'A2': 0.1, 'A3': 1},
datasets=[ds3])
g.groups.append(g2)
# save the group
sdf.save('test.sdf', g)
# load DS2 from the file
ds2r = sdf.load('test.sdf', '/DS2')
print ds2r.name
# make sure the content is still the same
self.assertEqual(ds2, ds2r)
def plot_time_series(filename, datasets):
params = {
# 'legend.fontsize': 'medium',
'figure.figsize': (10, 8),
'axes.labelsize': 'small',
# 'axes.titlesize': 'medium',
'xtick.labelsize': 'small',
'ytick.labelsize': 'small'
}
pylab.rcParams.update(params)
figure, axes = plt.subplots(len(datasets), sharex=True)
# figure = plt.figure()
figure.canvas.set_window_title(filename)
figure.patch.set_facecolor('white')
for ax, path in zip(axes, datasets):
dataset = sdf.load(filename, path)
scale = dataset.scales[0]
y = dataset.data
x = scale.data if scale is not None else range(len(y))
# ax = figure.add_subplot(len(datasets), 1, i + 1)
ax.plot(x, y, 'b')
ax.grid(b=True, which='both', color='0.8', linestyle='-')
ax.set_xlim([np.nanmin(x), np.nanmax(x)])
ylabel = path
if dataset.unit is not None:
ylabel += " / %s" % dataset.unit
ax.set_ylabel(ylabel)
ax.margins(y=0.05)
# x-axis label
if scale is not None:
xlabel = scale.name
if scale.unit is not None:
xlabel += " / %s" % scale.unit
else:
xlabel = 'Index'
ax.set_xlabel(xlabel)
figure.tight_layout()
plt.show()
def test_data_types(self):
ds_f = sdf.Dataset(name='f',
data=np.asarray([1, 2, 3], dtype=np.float32))
ds_d = sdf.Dataset(name='d',
data=np.asarray([1, 2, 3], dtype=np.float64))
ds_i = sdf.Dataset(name='i',
data=np.asarray([1, 2, 3], dtype=np.int32))
g = sdf.Group(name='/', datasets=[ds_f, ds_d, ds_i])
sdf.save('data_types.sdf', g)
g = sdf.load('data_types.sdf')
self.assertEqual(g['f'].data.dtype, np.float32)
self.assertEqual(g['d'].data.dtype, np.float64)
self.assertEqual(g['i'].data.dtype, np.int32)
def test_hierarchy(self):
# create a scale
ds_time = sdf.Dataset('Time',
comment="A scale",
data=np.linspace(0, 10, 101),
unit='s',
is_scale=True)
ds_sine = sdf.Dataset('sine',
comment="A 1-d dataset /w attached scale",
data=np.sin(ds_time.data),
scales=[ds_time])
# create the root group
g = sdf.Group(name='/',
comment="A test file",
attributes={'A1': "my string"},
datasets=[ds_time, ds_sine])
# create a scalar dataset
ds_alpha = sdf.Dataset(
'alpha',
comment="A scalar /w unit, display unit and display name",
data=np.pi,
display_name='Angle',
unit='rad',
display_unit='deg')
# create a sub group
g1 = sdf.Group(name='g1',
comment="A sub-group",
attributes={'A2': "Attribute in sub group"},
datasets=[ds_alpha])
g.groups.append(g1)
# save the group
sdf.save('roundtrip.sdf', g)
# load the group from the file
g2 = sdf.load('roundtrip.sdf', '/')
def test_roundtrip(self):
# create a scale
ds1 = sdf.Dataset('DS1',
comment='dataset 1',
data=np.array([0.1, 0.2, 0.3]),
display_name='Scale 1',
scale_name='Scale 1',
quantity='Q1',
unit='U1',
display_unit='DU1',
is_scale=True)
# create a 1D dataset
ds2 = sdf.Dataset('DS2',
comment='dataset 2',
data=np.array([1, 2, 3]),
display_name='Dataset 2',
quantity='Q2',
unit='U2',
display_unit='DU2',
scales=[ds1])
# create a group
g = sdf.Group(name='/',
comment='my comment',
attributes={
'A1': 'my string',
'A2': 0.1,
'A3': 1
},
datasets=[ds1, ds2])
# save the group
sdf.save('test.sdf', g)
# load DS2 from the file
ds2r = sdf.load('test.sdf', '/DS2')
# make sure the content is still the same
self.assertEqual(ds2, ds2r)
def test_roundtrip(self):
# create a scale
ds1 = sdf.Dataset('DS1',
comment="dataset 1",
data=np.array([0.1, 0.2, 0.3]),
display_name='Scale 1',
unit='U1',
display_unit='DU1',
is_scale=True)
# create a 1D dataset
ds2 = sdf.Dataset('DS2',
comment="dataset 2",
data=np.array([1, 2, 3]),
display_name='Dataset 2',
relative_quantity=True,
unit='U2',
display_unit='DU2',
scales=[ds1])
# create a group
g = sdf.Group(name='/',
comment="my comment",
attributes={'A1': 'my string'},
datasets=[ds1, ds2])
g2 = sdf.Group(name='G2')
g.groups.append(g2)
# save the group
sdf.save('test.sdf', g)
# load DS2 from the file
ds2r = sdf.load('test.sdf', '/DS2')
# make sure the content is still the same
self.assertDatasetsEqual(ds2, ds2r)
self.assertDatasetsEqual(ds2.scales[0], ds2r.scales[0])
def get_x(filename, ds_name):
print ds_name
ds = sdf.load(filename, ds_name)
return PIModelData.convert_from_si(ds_name, ds.data)
def create_plot(filename, datasets):
params = {
# 'legend.fontsize': 'medium',
# 'figure.figsize': (10, 8),
'legend.fontsize': 'small',
'axes.labelsize': 'small',
'axes.titlesize': 'small',
'xtick.labelsize': 'small',
'ytick.labelsize': 'small'
}
pylab.rcParams.update(params)
figure = plt.figure(figsize=(12, 8))
figure.canvas.set_window_title(filename)
figure.patch.set_facecolor('white')
nrows = len(datasets)
for row, dataset in enumerate(datasets):
# load the datasets
C1 = sdf.load(filename, dataset)
ncols = C1.scales[2].data.size
norm = colors.Normalize(vmin=np.nanmin(C1.data),
vmax=np.nanmax(C1.data))
subs = [0] * C1.data.ndim
subs[0] = slice(None)
subs[1] = slice(None)
ax0 = None
for i in range(ncols):
x = C1.scales[1].data
y = C1.scales[0].data
subs[2] = i
Z = C1.data[subs].T
X, Y = np.meshgrid(x, y, indexing='ij')
ax = figure.add_subplot(len(datasets),
C1.data.shape[2], (row * ncols) + i + 1,
sharex=ax0,
sharey=ax0)
if i == 0:
ax0 = ax
ax.set_ylabel(C1.display_name + " / " + C1.unit + "\n" +
C1.scales[0].display_name + " / " +
C1.scales[0].unit)
# else:
# ax.get_yaxis().set_ticklabels([])
ax.grid(True)
CSF = plt.contourf(X, Y, Z, 10, cmap=plt.cm.viridis, norm=norm)
CS = plt.contour(X, Y, Z, 10, colors='k')
plt.clabel(CS=CS, fontsize=9, inline=1, colors='k')
scale3 = C1.scales[2]
ax.set_title(scale3.display_name + "=" + ("%g" % scale3.data[i]) +
" " + scale3.unit)
ax.set_xlabel(C1.scales[1].display_name + " / " +
C1.scales[1].unit)
cbar = figure.colorbar(CSF)
plt.tight_layout()
plt.show()
"""
df = pd.read_csv("data/Series3_6.15.17_padel.csv")
df.head()
# Which have missing values? How do they show when clustering?
df[df.IC50.isnull()]
df = pd.read_csv("data/Selleck_filtered_padel_corrected.csv", encoding='cp1252')
akt1 = pd.read_csv("data\Akt1_decoys_padel.csv")
akt1.head()
# Read sdf file to view contents
import sdf
sdf_file = sdf.load("data/malaria-2018-04-16.sdf", '/v')
# SDF File parser https://github.com/Actelion/openchemlib/tree/4633da5f2bfc3fbd59e2e01897c42d7be2b22b2d
df = pd.read_csv("data/result-2018-04-16.txt", delimiter="\t")
df.head()
len(df)
"""
Create a simple SDF file
"""
import sdf
import numpy as np
# create the data arrays
t = np.linspace(0, 10, 100)
v = np.sin(t)
# create the datasets
ds_t = sdf.Dataset('t', data=t, unit='s', is_scale=True, display_name='Time')
ds_v = sdf.Dataset('v', data=v, unit='V', scales=[ds_t])
# create the root group
g = sdf.Group('/', comment='A sine voltage', datasets=[ds_t, ds_v])
# write the SDF file
sdf.save('sine.sdf', g)
# read the SDF file
ds_v2 = sdf.load('sine.sdf', '/v', unit='V', scale_units=['s'])
ds_t2 = ds_v2.scales[0]
t2 = ds_t2.data
v2 = ds_v2.data
def load_ds_and_scales(self, filename, dsname):
ds = sdf.load(filename, dsname)
self.dataset = ds
def assert_results(self, sdf_filename, variable_name, position, value, message='assertion failed'):
ds = sdf.load(sdf_filename, variable_name)
# value = ds.data[position]
self.assertAlmostEqual(first, second, places=7, msg=message, delta=None)
def test_dsres_inverted_signals(self):
path = os.path.dirname(__file__)
filename = os.path.join(path, 'DoublePendulum.mat')
rvisobj = sdf.load(filename, '/world/y_label/cylinders[2]/rvisobj[1]')
self.assertTrue(rvisobj.data < 0)