def ssr_curve(self,
x,
y,
slopes=[
0.1, 0.2, 0.3, 0.4, 0.5, 0.75, 1.0, 1.5, 2.0, 2.5, 3.0,
4.0, 5.0, 7.5, 10.0
]):
ssrs = []
for slope in slopes:
yint = (np.mean(y) - slope * np.mean(x))
ssrs.append(
self.get_ss_res(zip(x, y), lambda val: slope * val + yint))
image_manager = ImageManager()
plotter = Plotter()
plotter.set_title('Sum of Squared Residuals')
plotter.set_axis_labels('Slope Selected', 'Sum of Squared Residual')
plotter.set_output_filename(g.files['ls-ssr'])
ssr_plot = ScatterSketch()
ssr_plot.add_x(slopes)
ssr_plot.add_y(ssrs)
plotter.load(ssr_plot)
plotter.save()
plotter.close()
g.debug.prn(self, 'Drawn Sum of Squared Residuals Plot')
image_manager.scale(g.files['ls-ssr'], g.files['ls-ssr'], 250)
def plot_roc(self):
plotter = Plotter()
plotter.set_title('Receiver Operating Characteristic')
plotter.set_axis_labels('')
plotter.set_output_filename() #TODO: Fill filename
plotter.close()
pass # Save the image as "roc.png"
def plot(self):
plotter = Plotter()
image_manager = ImageManager()
sketches = []
plotter.set_output_filename(g.files['ridge-regression'])
plotter.set_title('Ridge Regression')
g.debug.prn(self, 'Plot basics set.')
min_x = min(self.training_x)
max_x = max(self.training_x)
x_vals = []
y_vals = []
for x in range(min_x * 100, max_x * 100):
x_vals.append([x / 100])
y_vals.append([self.f(x / 100)])
sketches.append(SmoothSketch())
sketches[-1].add_x(x_vals)
sketches[-1].add_y(y_vals)
g.debug.prn(self, 'Linear curve saved as SmoothSketch.')
sketches.append(ScatterSketch())
sketches[-1].add_x(list(self.training_x))
sketches[-1].add_y(list(self.training_y))
g.debug.prn(self, 'Points saved as ScatterSketch.')
for i in range(len(self.training_x)):
if self.f(self.training_x[i]) > self.training_y[i]:
y_max = self.f(self.training_x[i])
y_min = self.training_y[i]
else:
y_min = self.f(self.training_x[i])
y_max = self.training_y[i]
sketches.append(VerticalLineSketch())
sketches[-1].set_y_max(y_max)
sketches[-1].set_y_min(y_min)
sketches[-1].set_x(self.training_x[i])
g.debug.prn(self, 'Vertical line appended.', 3)
g.debug.prn(self, 'SSR lines drawn as VerticalLineSketch(s).')
plotter.load(sketches)
plotter.save()
plotter.close()
g.debug.prn(self, 'All sketches loaded and saved.')
image_manager.scale(g.files['ridge-regression'],
g.files['ridge-regression'], 250)
del plotter
del image_manager
g.debug.prn(self, 'Plotter and ImageManager objects deleted', 3)
def plot(self):
plotter = Plotter()
image_manager = ImageManager()
sketches = []
plotter.set_output_filename(g.files['least-squares'])
plotter.set_title('Least Squares')
# min_x = min(self.training.get_output()[x_index])
# max_x = max(self.training.get_output()[x_index])
min_x = min(self.training_x)
max_x = max(self.training_x)
x_vals = []
y_vals = []
for x in range(min_x * 100, max_x * 100):
x_vals.append([x / 100])
y_vals.append([self.f(x / 100)])
sketches.append(SmoothSketch())
sketches[-1].add_x(x_vals)
sketches[-1].add_y(y_vals)
sketches.append(ScatterSketch())
sketches[-1].add_x(list(self.training_x))
sketches[-1].add_y(list(self.training_y))
for i in range(len(self.training_x)):
if self.f(self.training_x[i]) > self.training_y[i]:
y_max = self.f(self.training_x[i])
y_min = self.training_y[i]
else:
y_min = self.f(self.training_x[i])
y_max = self.training_y[i]
sketches.append(VerticalLineSketch())
sketches[-1].set_y_max(y_max)
sketches[-1].set_y_min(y_min)
sketches[-1].set_x(self.training_x[i])
plotter.load(sketches)
plotter.save()
plotter.close()
image_manager.scale(g.files['least-squares'], g.files['least-squares'],
250)
del plotter
del image_manager
def f_dist(self, model_type, trials):
plotter = Plotter()
image_manager = ImageManager()
plotter.set_title('F Distribution')
plotter.set_axis_labels('Frequency', 'F Score')
plotter.set_output_filename(g.files['least-squares-f'])
histogram = HistogramSketch()
for i in range(trials):
x_vals = g.randomizer.random_list(g.points_to_gen, g.lower_x_bound,
g.upper_x_bound)
y_vals = g.randomizer.random_list(g.points_to_gen, g.lower_y_bound,
g.upper_y_bound)
if model_type == LinearModel:
slope, yint = self.least_squares_slope_yint_eqn(x_vals, y_vals)
func = lambda x: slope * x + yint
else:
g.debug.prn(self, 'Incompatible model type.', 1)
break
ss_fit = self.get_ss_res(zip(x_vals, y_vals), func)
ss_mean = self.get_ss_res(zip(x_vals, y_vals),
lambda x: np.mean(x_vals))
p_fit = 2 # TODO: Update for Dataframe
p_mean = 1 # ""
n = len(x_vals)
if ss_fit == 0 or (n - p_fit) == 0 or (p_fit - p_mean) == 0:
self.debug.prn(self, 'F distribution cannot divide by zero.',
1)
continue
numerator = (ss_mean - ss_fit) / (p_fit - p_mean)
denominator = ss_fit / (n - p_fit)
histogram.add_x(numerator / denominator)
histogram.set_bins()
plotter.load(histogram)
plotter.save()
plotter.close()
image_manager.scale(g.files['least-squares-f'],
g.files['least-squares-f'], 250)
self.debug.prn(self, 'F distribution created.')
def plot(self):
plotter = Plotter()
image_manager = ImageManager()
sketches = []
plotter.set_output_filename(g.files['logistic-regression'])
plotter.set_title('Logistic Regression')
g.debug.prn(self, 'Plot basics set.')
min_x = min(self.training_x)
max_x = max(self.training_x)
min_y = min(self.training_y)
max_y = max(self.training_y)
x_vals = []
y_vals = []
for x in range(min_x * 100, max_x * 100):
y_adjust = self.f(x / 100) * (max_y - min_y) + min_y
x_vals.append([x / 100])
y_vals.append([y_adjust])
sketches.append(SmoothSketch())
sketches[-1].add_x(x_vals)
sketches[-1].add_y(y_vals)
g.debug.prn(self, 'Curve added to sketches list.')
sketches.append(ScatterSketch())
sketches[-1].add_x(list(self.training_x))
sketches[-1].add_y(list(self.training_y))
g.debug.prn(self, 'Scatter of points added to sketches list.')
plotter.load(sketches)
plotter.save()
plotter.close()
g.debug.prn(self, 'All sketches loaded and saved.')
image_manager.scale(g.files['logistic-regression'],
g.files['logistic-regression'], 250)
del plotter
del image_manager
g.debug.prn(self, 'Plotter and ImageManager objects deleted', 3)