def domain_adaptation_plot_helper(classifiers, metric='acc'):
print "Plotting domain_adaptation, classifiers: %s" % classifiers
METHODS = ['target_only', 'source_only', 'relabeled', 'augment', 'coral']
dfs = []
for method in METHODS:
for classifier in classifiers:
df = get_da_results(classifier, method, metric)
util.print_ci_from_df(df['folds'], method, classifier)
dfs.append(df)
dfs = pd.concat(dfs)
if metric == 'acc':
y_label = "Accuracy"
elif metric == 'fms':
y_label = "F-Measure"
else:
y_label = "AUC"
plot_specs = {
'x_col': 'method',
'y_col': 'folds',
'hue_col': 'model',
'x_label': 'Model',
'figsize': (10, 8),
'font_scale': 1.2,
'fontsize': 20,
'y_label': y_label,
'y_lim': (0, 1)
}
figname = 'domain_adapt_plot_%s_%s.pdf' % (metric, classifiers[1])
bar_plot(dfs, figname, **plot_specs)
def vanilla_feature_set_plot(show=False):
print "Plotting vanilla_feature_set_plot"
dfs = []
classifiers = models.CLASSIFIER_KEYS
for classifier in classifiers:
for metric in models.METRICS:
df = get_vanilla_results(classifier, metric)
util.print_ci_from_df(df['folds'], classifier, metric)
dfs.append(df)
dfs = pd.concat(dfs)
plot_specs = {
'x_col': 'model',
'y_col': 'folds',
'hue_col': 'metric',
'x_label': 'Model',
'y_label': 'Performance',
'figsize': (12, 10),
'font_scale': 1.2,
'fontsize': 20,
'y_lim': None,
'show': show,
'title': "10-Fold Cross Validation Performance"
}
figname = 'vanilla_results.pdf'
bar_plot(dfs, figname, **plot_specs)
def blog_plot():
print "Plotting blog_plot"
metrics = models.METRICS
dfs = []
for classifier in models.CLASSIFIER_KEYS:
for metric in metrics:
df = get_blog_results(classifier, metric)
util.print_ci_from_df(df['folds'], classifier, metric)
dfs.append(df)
dfs = pd.concat(dfs)
plot_specs = {
'x_col': 'model',
'y_col': 'folds',
'hue_col': 'metric',
'x_label': 'Model',
'y_label': 'Performance',
'font_scale': 1.2,
'fontsize': 20,
'rotation': 15
}
figname = 'blog_plot.pdf'
bar_plot(dfs, figname, **plot_specs)
def selected_feature_set_result(metric, feature_sets):
name, _ = feature_sets
print "Getting results of %s, metric: %s" % (name, metric)
classifiers = list(models.CLASSIFIER_KEYS)
for fs in ['none']:
for classifier in classifiers:
df = get_selected_feature_results(classifier, metric, name)
util.print_ci_from_df(df['folds'], fs, classifier)
def print_fraser_comparision(metric='fms'):
print 'metric %s' % metric
t0 = 'results_new_features_fraser_comparision_none'
t1 = 'results_new_features_fraser_comparision_halves'
t2 = 'results_new_features_poly_halves'
t3 = 'results_new_features_none'
df0 = util.get_max_fold_from_table(metric, t0)
df1 = util.get_max_fold_from_table(metric, t1)
df2 = util.get_max_fold_from_table(metric, t2)
df3 = util.get_max_fold_from_table(metric, t3)
util.print_ci_from_df(df0['folds'], "without_age_without_halves", "LogReg")
util.print_ci_from_df(df1['folds'], "without_age_with_halves", "LogReg")
util.print_ci_from_df(df2['folds'], "with_age_with_halves", "LogReg")
util.print_ci_from_df(df3['folds'], "with_age_without_halves", "LogReg")
def blog_ablation_plot(metric='acc'):
print "Plotting blog_ablation_plot, metric: %s" % metric
classifiers = models.CLASSIFIER_KEYS
ablation_sets = models.BLOG_FEATURE_SETS
classifiers.remove('DummyClassifier')
dfs = []
for classifier in classifiers:
for ab_set in ablation_sets:
df = get_ablation_results(ab_set, classifier, metric,
BLOG_ABLATION_PREFIX)
util.print_ci_from_df(df['folds'], classifier, metric)
dfs.append(df)
dfs = pd.concat(dfs)
human_readable = {"acc": "Accuracy", "fms": "F-Measure", "roc": "AUC"}
plot_specs = {
'x_col': 'ablation_set',
'y_col': 'folds',
'hue_col': 'model',
'x_label': 'Feature Set',
'y_label': "Change in %s " % human_readable[metric],
'title': "Feature Ablation",
'figsize': (10, 8),
'fontsize': 20,
'font_scale': 1.2,
'y_lim': None,
'errwidth': 0.75,
'labelsize': 10,
'rotation': 15
}
figname = 'blog_ablation_plot.pdf'
bar_plot(dfs, figname, **plot_specs)
def new_feature_set_plot(metric='acc', absolute=True, poly=True, show=False):
print "Plotting new_feature_set_plot, metric: %s" % metric
classifiers = list(models.CLASSIFIER_KEYS)
new_features = []
if absolute:
new_features += ['none']
new_features += models.NEW_FEATURE_SETS
classifiers.remove('DummyClassifier')
dfs = []
for fs in new_features:
for classifier in classifiers:
df = get_new_feature_results(fs,
classifier,
metric,
absolute=absolute,
poly=poly)
util.print_ci_from_df(df['folds'], fs, classifier)
dfs.append(df)
dfs = pd.concat(dfs)
dfs = dfs.replace('none', 'baseline')
y_lim = (.68, .90)
if metric == 'acc':
y_label = "Accuracy"
elif metric == 'fms':
y_label = "F-Measure"
else:
y_label = "AUC"
y_lim = (.70, .95)
figname = 'new_feature_plot_%s' % metric
title = 'Performance w/ New Feature Sets'
if not absolute:
y_label = "Change in %s" % y_label
y_lim = (-.10, .10)
figname = figname + '_relative'
title = 'Change in Performance w/ New Feature Sets'
plot_specs = {
'x_col': 'new_feature_set',
'y_col': 'folds',
'hue_col': 'model',
'x_label': 'Feature Set',
'y_label': y_label,
'y_lim': y_lim,
'figsize': (10, 8),
'fontsize': 20,
'font_scale': 1.2,
'labelsize': 15,
'show': show,
'title': title,
}
# We use polynomial terms as well for halves
if poly:
dfs = dfs.replace('halves', 'halves+quadratic')
else:
figname = figname + '_without_quadratic'
figname = figname + '.pdf'
bar_plot(dfs, figname, **plot_specs)