def test_clean_data_X_only():
"""Test that nan-containing X rows are removed without y."""
X = np.array([[1, 2, np.nan], [4, 5, 6], [np.nan, np.nan, np.nan]])
expected = np.array([[4, 5, 6]])
observed = filter_missing(X)
np.testing.assert_array_equal(expected, observed)
def test_clean_data_X_only_no_nans():
"""Test that an array with no nulls is returned intact."""
X = np.array([
[1, 2, 3],
[4, 5, 6],
[7, 8, 9],
])
observed = filter_missing(X)
np.testing.assert_array_equal(X, observed)
def test_clean_data_X_only_no_nans():
"""Test that an array with no nulls is returned intact."""
X = np.array([
[1, 2, 3],
[4, 5, 6],
[7, 8, 9],
])
observed = filter_missing(X)
np.testing.assert_array_equal(X, observed)
def test_clean_data_clean_X_dirty_y():
"""Test that nan-containing X, y rows are removed when y contains nans."""
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]])
y = np.array([np.nan, 44, np.nan, 66])
expected_X = np.array([[4, 5, 6], [10, 11, 12]])
expected_y = np.array([44, 66])
observed_X, observed_y = filter_missing(X, y)
np.testing.assert_array_equal(expected_X, observed_X)
np.testing.assert_array_equal(expected_y, observed_y)
def test_clean_data_dirty_X_clean_y():
"""Test that nan-containing X, y rows are removed when X contains nans."""
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, np.nan], [np.nan, np.nan, np.nan]])
y = np.array([33, 44, 55, 66])
expected_X = np.array([[1, 2, 3], [4, 5, 6]])
expected_y = np.array([33, 44])
observed_X, observed_y = filter_missing(X, y)
np.testing.assert_array_equal(expected_X, observed_X)
np.testing.assert_array_equal(expected_y, observed_y)
def test_clean_data_X_only():
"""Test that nan-containing X rows are removed without y."""
X = np.array([
[1, 2, np.nan],
[4, 5, 6],
[np.nan, np.nan, np.nan],
])
expected = np.array([
[4, 5, 6]
])
observed = filter_missing(X)
np.testing.assert_array_equal(expected, observed)
def test_clean_data_dirty_X_dirty_y():
"""Test that nan-containing X, y rows are removed when both contain nans."""
X = np.array([
[1, 2, 3],
[4, 5, 6],
[7, 8, np.nan],
[np.nan, np.nan, np.nan],
])
y = np.array([33, np.nan, 44, np.nan])
expected_X = np.array([
[1, 2, 3],
])
expected_y = np.array([33])
observed_X, observed_y = filter_missing(X, y)
np.testing.assert_array_equal(expected_X, observed_X)
np.testing.assert_array_equal(expected_y, observed_y)
def test_clean_data_clean_X_dirty_y():
"""Test that nan-containing X, y rows are removed when y contains nans."""
X = np.array([
[1, 2, 3],
[4, 5, 6],
[7, 8, 9],
[10, 11, 12]
])
y = np.array([np.nan, 44, np.nan, 66])
expected_X = np.array([
[4, 5, 6],
[10, 11, 12]
])
expected_y = np.array([44, 66])
observed_X, observed_y = filter_missing(X, y)
np.testing.assert_array_equal(expected_X, observed_X)
np.testing.assert_array_equal(expected_y, observed_y)
def draw(self, X, y, **kwargs):
"""
Called from the fit method, this method creates the radviz canvas and
draws each instance as a class or target colored point, whose location
is determined by the feature data set.
"""
# Convert from dataframe
if is_dataframe(X):
X = X.values
# Clean out nans and warn that the user they aren't plotted
nan_warnings.warn_if_nans_exist(X)
X, y = nan_warnings.filter_missing(X, y)
# Get the shape of the data
nrows, ncols = X.shape
# Set the axes limits
self.ax.set_xlim([-1, 1])
self.ax.set_ylim([-1, 1])
# Create a data structure to hold scatter plot representations
to_plot = {label: [[], []] for label in self.classes_}
# Compute the arcs around the circumference for each feature axis
# TODO: make this an independent function for override
s = np.array([
(np.cos(t), np.sin(t))
for t in [2.0 * np.pi * (i / float(ncols)) for i in range(ncols)]
])
# Compute the locations of the scatter plot for each class
# Normalize the data first to plot along the 0, 1 axis
for i, row in enumerate(self.normalize(X)):
row_ = np.repeat(np.expand_dims(row, axis=1), 2, axis=1)
xy = (s * row_).sum(axis=0) / row.sum()
label = self._label_encoder[y[i]]
to_plot[label][0].append(xy[0])
to_plot[label][1].append(xy[1])
# Add the scatter plots from the to_plot function
# TODO: store these plots to add more instances to later
# TODO: make this a separate function
for label in self.classes_:
color = self.get_colors([label])[0]
self.ax.scatter(to_plot[label][0],
to_plot[label][1],
color=color,
label=label,
alpha=self.alpha,
**kwargs)
# Add the circular axis path
# TODO: Make this a seperate function (along with labeling)
self.ax.add_patch(
patches.Circle(
(0.0, 0.0),
radius=1.0,
facecolor="none",
edgecolor="grey",
linewidth=0.5,
))
# Add the feature names
for xy, name in zip(s, self.features_):
# Add the patch indicating the location of the axis
self.ax.add_patch(
patches.Circle(xy, radius=0.025, facecolor="#777777"))
# Add the feature names offset around the axis marker
if xy[0] < 0.0 and xy[1] < 0.0:
self.ax.text(
xy[0] - 0.025,
xy[1] - 0.025,
name,
ha="right",
va="top",
size="small",
)
elif xy[0] < 0.0 and xy[1] >= 0.0:
self.ax.text(
xy[0] - 0.025,
xy[1] + 0.025,
name,
ha="right",
va="bottom",
size="small",
)
elif xy[0] >= 0.0 and xy[1] < 0.0:
self.ax.text(
xy[0] + 0.025,
xy[1] - 0.025,
name,
ha="left",
va="top",
size="small",
)
elif xy[0] >= 0.0 and xy[1] >= 0.0:
self.ax.text(
xy[0] + 0.025,
xy[1] + 0.025,
name,
ha="left",
va="bottom",
size="small",
)
self.ax.axis("equal")
return self.ax
def draw(self, X, y, **kwargs):
"""
Called from the fit method, this method creates the radviz canvas and
draws each instance as a class or target colored point, whose location
is determined by the feature data set.
"""
# Convert from dataframe
if is_dataframe(X):
X = X.values
# Clean out nans and warn that the user they aren't plotted
nan_warnings.warn_if_nans_exist(X)
X, y = nan_warnings.filter_missing(X, y)
# Get the shape of the data
nrows, ncols = X.shape
# Set the axes limits
self.ax.set_xlim([-1, 1])
self.ax.set_ylim([-1, 1])
# Create the colors
# TODO: Allow both colormap, listed colors, and palette definition
# TODO: Make this an independent function or property for override!
color_values = resolve_colors(n_colors=len(self.classes_),
colormap=self.colormap,
colors=self.color)
self._colors = dict(zip(self.classes_, color_values))
# Create a data structure to hold scatter plot representations
to_plot = {}
for kls in self.classes_:
to_plot[kls] = [[], []]
# Compute the arcs around the circumference for each feature axis
# TODO: make this an independent function for override
s = np.array([
(np.cos(t), np.sin(t))
for t in [2.0 * np.pi * (i / float(ncols)) for i in range(ncols)]
])
# Compute the locations of the scatter plot for each class
# Normalize the data first to plot along the 0, 1 axis
for i, row in enumerate(self.normalize(X)):
row_ = np.repeat(np.expand_dims(row, axis=1), 2, axis=1)
xy = (s * row_).sum(axis=0) / row.sum()
kls = self.classes_[y[i]]
to_plot[kls][0].append(xy[0])
to_plot[kls][1].append(xy[1])
# Add the scatter plots from the to_plot function
# TODO: store these plots to add more instances to later
# TODO: make this a separate function
for i, kls in enumerate(self.classes_):
self.ax.scatter(to_plot[kls][0],
to_plot[kls][1],
color=self._colors[kls],
label=str(kls),
alpha=self.alpha,
**kwargs)
# Add the circular axis path
# TODO: Make this a seperate function (along with labeling)
self.ax.add_patch(
patches.Circle((0.0, 0.0),
radius=1.0,
facecolor='none',
edgecolor='grey',
linewidth=.5))
# Add the feature names
for xy, name in zip(s, self.features_):
# Add the patch indicating the location of the axis
self.ax.add_patch(
patches.Circle(xy, radius=0.025, facecolor='#777777'))
# Add the feature names offset around the axis marker
if xy[0] < 0.0 and xy[1] < 0.0:
self.ax.text(xy[0] - 0.025,
xy[1] - 0.025,
name,
ha='right',
va='top',
size='small')
elif xy[0] < 0.0 and xy[1] >= 0.0:
self.ax.text(xy[0] - 0.025,
xy[1] + 0.025,
name,
ha='right',
va='bottom',
size='small')
elif xy[0] >= 0.0 and xy[1] < 0.0:
self.ax.text(xy[0] + 0.025,
xy[1] - 0.025,
name,
ha='left',
va='top',
size='small')
elif xy[0] >= 0.0 and xy[1] >= 0.0:
self.ax.text(xy[0] + 0.025,
xy[1] + 0.025,
name,
ha='left',
va='bottom',
size='small')
self.ax.axis('equal')
def draw(self, X, y, **kwargs):
"""
Called from the fit method, this method creates the radviz canvas and
draws each instance as a class or target colored point, whose location
is determined by the feature data set.
"""
# Convert from dataframe
if is_dataframe(X):
X = X.values
# Clean out nans and warn that the user they aren't plotted
nan_warnings.warn_if_nans_exist(X)
X, y = nan_warnings.filter_missing(X, y)
# Get the shape of the data
nrows, ncols = X.shape
# Set the axes limits
self.ax.set_xlim([-1,1])
self.ax.set_ylim([-1,1])
# Create the colors
# TODO: Allow both colormap, listed colors, and palette definition
# TODO: Make this an independent function or property for override!
color_values = resolve_colors(
n_colors=len(self.classes_), colormap=self.colormap, colors=self.color
)
self._colors = dict(zip(self.classes_, color_values))
# Create a data structure to hold scatter plot representations
to_plot = {}
for kls in self.classes_:
to_plot[kls] = [[], []]
# Compute the arcs around the circumference for each feature axis
# TODO: make this an independent function for override
s = np.array([
(np.cos(t), np.sin(t))
for t in [
2.0 * np.pi * (i / float(ncols))
for i in range(ncols)
]
])
# Compute the locations of the scatter plot for each class
# Normalize the data first to plot along the 0, 1 axis
for i, row in enumerate(self.normalize(X)):
row_ = np.repeat(np.expand_dims(row, axis=1), 2, axis=1)
xy = (s * row_).sum(axis=0) / row.sum()
kls = self.classes_[y[i]]
to_plot[kls][0].append(xy[0])
to_plot[kls][1].append(xy[1])
# Add the scatter plots from the to_plot function
# TODO: store these plots to add more instances to later
# TODO: make this a separate function
for i, kls in enumerate(self.classes_):
self.ax.scatter(
to_plot[kls][0], to_plot[kls][1], color=self._colors[kls],
label=str(kls), alpha=self.alpha, **kwargs
)
# Add the circular axis path
# TODO: Make this a seperate function (along with labeling)
self.ax.add_patch(patches.Circle(
(0.0, 0.0), radius=1.0, facecolor='none', edgecolor='grey', linewidth=.5
))
# Add the feature names
for xy, name in zip(s, self.features_):
# Add the patch indicating the location of the axis
self.ax.add_patch(patches.Circle(xy, radius=0.025, facecolor='#777777'))
# Add the feature names offset around the axis marker
if xy[0] < 0.0 and xy[1] < 0.0:
self.ax.text(xy[0] - 0.025, xy[1] - 0.025, name, ha='right', va='top', size='small')
elif xy[0] < 0.0 and xy[1] >= 0.0:
self.ax.text(xy[0] - 0.025, xy[1] + 0.025, name, ha='right', va='bottom', size='small')
elif xy[0] >= 0.0 and xy[1] < 0.0:
self.ax.text(xy[0] + 0.025, xy[1] - 0.025, name, ha='left', va='top', size='small')
elif xy[0] >= 0.0 and xy[1] >= 0.0:
self.ax.text(xy[0] + 0.025, xy[1] + 0.025, name, ha='left', va='bottom', size='small')
self.ax.axis('equal')
