def scatter_plot(plot: plt, df: HogwartsDataDescriber, course1: str,
course2: str):
"""
Scatter plot for 2 courses
:param plot: matplotlib.axes._subplots.AxesSubplot
:param df: HogwartsDataDescriber
:param course1: course 1 name
:param course2: course 2 name
:return: None
"""
for house, color in zip(df.houses, df.colors):
# choose course marks of students belonging to the house
x = df[course1][df['Hogwarts House'] == house]
y = df[course2][df['Hogwarts House'] == house]
plot.scatter(x, y, color=color, alpha=0.5)
def plot_ecdf(x_:ndarray,ax:pyplot=None,figsize:tuple=FIGSIZE,fontsize:int=FONTSIZE,grid:bool=False,
xlabel:str='x', ylabel:str='y',
lw:int=1,color:str=None,dots_marker:str=None,dots_color:str='red',dots_size:float=10,
zorder:float=None, plot_data_ticks:bool=True, plot_data_dots:bool=True) -> pyplot:
x = dataseries(x_).value
fig=[]
if ax is None:
fig,ax = pyplot.subplots(figsize=figsize)
if grid: ax.grid()
ax.set_xlabel(xlabel,fontsize=fontsize)
ax.set_ylabel(ylabel,fontsize=fontsize)
ax.tick_params(direction='out', grid_alpha=0.5, labelsize='large')
x1,y1 = stairs(x)
ax.plot(x1,y1,color=color,zorder=zorder,lw=lw)
if plot_data_ticks: ax.scatter(x,[0]*len(x),marker='|',s=200) # https://matplotlib.org/stable/api/markers_api.html
x2,p=ecdf(x)
if plot_data_dots: ax.scatter(x2,p,s=dots_size,color=dots_color,marker=dots_marker,zorder=zorder)
return fig, ax
def plot3D(ax: plt, sub3d: plt, X: np.ndarray, y: np.ndarray, w: np.ndarray,
name: str) -> None:
'''
Visualize decision boundary and data classes in 3D
:param ax: matplotlib
:param sub3d: fig.add_subplot(XXX, projection='3d')
:param X: data
:param y: data labels
:param w: model parameters
:param name: plot name identifier
:return:
'''
x1 = np.array(X[1, :]) # note: X_train[0,:] is the added row of 1s (bias)
x2 = np.array(X[2, :])
posterior1 = LOGREG().activationFunction(w, X)
posterior1 = np.squeeze(np.asarray(posterior1))
markers = ['o', '+']
groundTruthLabels = np.unique(y)
for li in range(len(groundTruthLabels)):
x1_sub = x1[y[:] == groundTruthLabels[li]]
x2_sub = x2[y[:] == groundTruthLabels[li]]
m_sub = markers[li]
posterior1_sub = posterior1[y[:] == groundTruthLabels[li]]
sub3d.scatter(x1_sub,
x2_sub,
posterior1_sub,
c=posterior1_sub,
vmin=0,
vmax=1,
marker=m_sub,
label='ground truth label = ' + str(li))
ax.legend()
x = np.arange(x1.min(), x1.max(), 0.1)
pms = [[0.1, 'k:'], [0.25, 'k--'], [0.5, 'r'], [0.75, 'k-.'], [0.9, 'k-']]
for (p, m) in pms:
yp = (-np.log((1 / p) - 1) - w[1] * x - w[0]) / w[2]
yp = np.squeeze(np.asarray(yp))
z = np.ones(yp.shape) * p
sub3d.plot(x, yp, z, m, label='p = ' + str(p))
ax.legend()
ax.xlabel('feature 1')
ax.ylabel('feature 2')
ax.title(name + '\n Posterior for class labeled 1')
def add_scatter_and_annotate(self,
fig: plt,
x_all: np.array,
y_all: np.array,
colour: str,
idxs: np.array,
annotate=False):
x = x_all[idxs]
y = y_all[idxs]
ax = fig.scatter(x, y, c=colour, alpha=self.opacity, s=20)
# Check if we want to annotate any of these with their gene IDs
if self.values_to_label is not None:
texts = []
labels = self.df[self.label_column].values[idxs]
for i, name in enumerate(labels):
if name in self.values_to_label:
lbl_bg = self.values_colours.get(name)
color = self.text_colours.get(name)
texts.append(
fig.text(x[i],
y[i],
name,
color=color,
fontsize=self.label_font_size,
bbox=dict(fc=lbl_bg, alpha=1.0)))
adjust_text(texts, force_text=2.0)
# Check if the user wants these labeled
if self.label_big_sig and annotate:
# If they do have a limit on the number of ones we show (i.e. we don't want 10000 gene names...)
max_values = -1 * self.max_labels
if len(y) < self.max_labels:
max_values = -1 * (len(y) - 1)
most_sig_idxs = np.argpartition(y, max_values)[max_values:]
labels = self.df[self.label_column].values[idxs][most_sig_idxs]
x = x[most_sig_idxs]
y = y[most_sig_idxs]
# We only label the ones with the max log fc
for i, name in enumerate(labels):
fig.annotate(name, (x[i], y[i]),
xytext=(0, 10),
textcoords='offset points',
ha='center',
va='bottom',
bbox=dict(boxstyle='round,pad=0.5',
fc='white',
alpha=0.2))
return ax
