def gscv_line_plot(x, y, gscv, title=None, directory=None, filename=None):
"""Creates line plot from dictionary of GridSearchCV objects."""
# Extract data from dictionary of GridSearchCV objects
data = pd.DataFrame()
for name, gs in gscv.items():
results = pd.DataFrame(data=gs.cv_results_)
x_data = results.filter(like=x, axis=1).values.flatten()
y_data = results.filter(like=y, axis=1).values.flatten()
df = pd.DataFrame({
proper(x): x_data,
proper(y): y_data,
'Model': name
})
data = pd.concat([data, df], axis=0)
if title is None:
title = 'Gridsearch Cross-validation Plot'
# Initialize and render plot
fig, ax = _init_image(x, y)
ax = sns.lineplot(x=proper(x), y=proper(y), hue='Model', data=data, ax=ax)
# Save figure if requested
if directory is not None:
title = title.replace('\n', ' ')
save_plot(fig, directory=directory, filename=filename, title=title)
# Show plot
fig.tight_layout()
plt.show()
def _init_image(x, y, figsize=(12, 4), xlim=None, ylim=None, title=None, log=False):
"""Creates and sets the axis aesthetics, labels, scale, and limits."""
# Initialize plot
fig, ax = plt.subplots(figsize=figsize)
# Set aesthetics
sns.set(style="whitegrid", font_scale=1)
ax.set_facecolor('w')
ax.tick_params(colors='k')
ax.xaxis.label.set_color('k')
ax.yaxis.label.set_color('k')
ax.set_title(title, color='k')
# Set labels
ax.set_xlabel(proper(x))
ax.set_ylabel(proper(y))
# Change to log scale if requested
if log:
ax.set_xscale('log')
# Set x and y axis limits
if xlim:
ax.set_xlim(xlim)
if ylim:
ax.set_ylim(ylim)
return fig, ax
def _plot_train_val_score(model, title=None, figsize=(12,4)):
"""Plots training and validation score on single plot."""
# Format plot title
if title is None:
title = model.history.params.get('name') + "\n" + \
"Training and Validation Scores" +\
'\n' + proper(model.metric)
# Extract training and validation score
d = {'Epoch': model.history.epoch_log['epoch'],
'Training': model.history.epoch_log['train_score'],
'Validation': model.history.epoch_log.get('val_score')}
df = pd.DataFrame(data=d)
df = pd.melt(df, id_vars='Epoch', value_vars=['Training',
'Validation'],
var_name=['Dataset'], value_name='Score')
# Extract row with best score by dataset for scatterplot
if RegressionMetricFactory()(model.metric).mode == 'max':
best_score = df.loc[df.groupby('Dataset').Score.idxmax()]
else:
best_score = df.loc[df.groupby('Dataset').Score.idxmin()]
# Initialize figure and axes with appropriate figsize and title
fig, ax = _init_image(x='Epoch', y='Score', figsize=figsize,
title=title)
# Render score lineplot
ax = sns.lineplot(x='Epoch', y='Score', hue='Dataset', data=df,
legend='full', ax=ax)
# Render scatterplot showing minimum score points
ax = sns.scatterplot(x='Epoch', y='Score', hue='Dataset',
data=best_score, legend=False, ax=ax)
return fig, ax, title
def _plot_train_score(model, title=None, figsize=(12,4)):
"""Plots training score."""
if title is None:
title = model.history.params.get('name') + "\n" + \
"Training Scores" +\
'\n' + proper(model.metric)
# Extract training score
d = {'Epoch': model.history.epoch_log['epoch'],
'Score': model.history.epoch_log['train_score']}
df = pd.DataFrame(data=d)
# Extract row with best score for scatterplot
if RegressionMetricFactory()(model.metric).mode == 'max':
best_score = df.loc[df.Score.idxmax()]
else:
best_score = df.loc[df.Score.idxmin()]
best_score = pd.DataFrame({"Epoch": [best_score['Epoch']],
"Score": [best_score['Score']]})
# Initialize figure and axes with appropriate figsize and title
fig, ax = _init_image(x='Epoch', y='Score', figsize=figsize,
title=title)
# Render score lineplot
ax = sns.lineplot(x='Epoch', y='Score', data=df, ax=ax)
# Render scatterplot showing minimum score points
ax = sns.scatterplot(x='Epoch', y='Score', data=best_score, ax=ax)
return fig, ax, title
def plot_loss(model,
title=None,
figsize=(12, 4),
directory=None,
filename=None):
"""Plots training loss (and optionally validation loss) by epoch."""
# Validate request
if not isinstance(model, Estimator):
raise ValueError("Model is not a valid Estimator or subclass object.")
if not isinstance(figsize, tuple):
raise TypeError("figsize is not a valid tuple.")
# Format plot title
if title is None:
title = model.history.params.get('name') + "\n" + \
"Training Plot with Learning Rate" +\
'\n' + proper(model.history.params.get('cost')) + " Cost"
# If val loss is on the log, plot both training and validation loss
if 'val_cost' in model.history.epoch_log:
fig, _ = _plot_train_val_loss(model, title=title, figsize=figsize)
else:
fig, _ = _plot_train_loss(model, title=title, figsize=figsize)
# Save figure if directory is not None
if directory is not None:
title = title.replace('\n') + '.png'
save_plot(fig, directory, filename, title)
# Show plot
fig.tight_layout()
plt.show()
def _histogram(self, variable):
"""Prints and optionally saves individual histogram."""
# Designate whether the probability density should be rendered
histnorm = None
if self.density:
histnorm='probability'
# Obtain the histogram object
data=[go.Histogram(x=self.df[variable],
histnorm=histnorm,
nbinsx=100,
autobinx=True)]
# Specify the layout.
layout = go.Layout(
height=self.height,
width=self.width,
template=self.template
)
self.fig = go.Figure(data=data, layout=layout)
# Format the title and update trace and layout
if self.title is None:
title = "Histogram : " + proper(variable)
else:
title = self.title
text = "Histogram : " + proper(variable)
x = 0.5
y = 1.10
self.fig.update_layout(annotations = [dict(text=text, x=x, y=y,
xref='paper', yref='paper',
showarrow=False)])
# Update trace and layout
self.fig.update_layout(title=title)
def plot_score(model,
title=None,
figsize=(12, 4),
directory=None,
filename=None):
"""Plots training score (and optionally validation score) by epoch."""
# Validate request
if not model.history.early_stop:
raise Exception(
"No early stop callback designated, so no score available.")
elif not model.history.early_stop.metric:
raise Exception("No metric designated for score.")
if not isinstance(model, Estimator):
raise ValueError("Model is not a valid Estimator or subclass object.")
if not isinstance(figsize, tuple):
raise TypeError("figsize is not a valid tuple.")
# Format plot title
if title is None:
title = model.history.params.get('name') + "\n" + \
"Evaluation Plot with Learning Rate" +\
'\n' + proper(model.history.early_stop.metric) + " Score"
# If val score is on the log, plot both training and validation score
if 'val_score' in model.history.epoch_log:
fig, _ = _plot_train_val_score(model, title=title, figsize=figsize)
else:
fig, _ = _plot_train_score(model, title=title, figsize=figsize)
# Save figure if directory is not None
if directory is not None:
title = title.replace('\n', ' ')
save_plot(fig, directory, filename, title)
# Show plot
fig.tight_layout()
plt.show()