def plot_first_session_vs_total(figure, answers, verbose=False):
answers = decorator.session_number(answers)
ax = figure.add_subplot(111)
total = user.answers_per_user(answers)
total_first = user.answers_per_user(answers[answers['session_number'] == 0])
users = answers['user'].unique()
vals = lambda x: [x.get(i, 0) for i in users]
pairs = map(lambda (x, y): (x, y - x), sorted(zip(vals(total_first), vals(total))))
total_first, total = zip(*pairs)
ax.plot(total_first, total, 'o', alpha=0.3, linewidth=0, color='black')
ax.set_xlabel('number of answers in the first session')
ax.set_ylabel('number of answer at all')
ax.set_xscale('log')
ax.set_yscale('log')
def hist_answers_per_user(figure,
answers,
group_column,
group_name_mapping=None,
verbose=False):
ax = figure.add_subplot(111)
to_plots = []
group_names = []
for group_name, group_data in answers.groupby(group_column):
to_plots.append(numpy.log10(
user.answers_per_user(group_data).values()))
group_names.append(group_name)
if group_name_mapping:
group_names = [
group_name_mapping[group_name] for group_name in group_names
]
else:
group_names = map(str, group_names)
group_names, to_plots = zip(
*sorted(zip(group_names, to_plots), key=lambda x: x[0]))
ax.hist(
to_plots,
label=[
group_name + ' (' + str(len(to_plot)) + ')'
for group_name, to_plot in zip(group_names, to_plots)
],
normed=True,
)
ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))
ax.set_xlabel("Number of Answers (log)")
ax.set_ylabel("Number of Users (normed)")
figure.tight_layout()
def boxplot_feedback_vs_number_of_answers(figure,
feedback,
answers,
verbose=False):
ax = figure.add_subplot(111)
first_feedback = (feedback.sort('id').drop_duplicates('user').groupby(
'user').apply(lambda x: x['value'].mean()).to_dict())
labels = []
to_plot = []
answers = answers[answers['user'].isin(first_feedback.keys())]
answers['temp_group'] = answers['user'].apply(lambda u: first_feedback[u])
for group_name, group_data in answers.groupby('temp_group'):
number = user.answers_per_user(group_data)
to_plot.append(number.values())
labels.append('%s (%s)' % (FEEDBACK_MAPPING[group_name], len(number)))
del answers['temp_group']
ax.set_yscale('log')
ax.set_ylabel('Number of Answers')
ax.set_xlabel('First Feedback')
_boxplot(ax,
to_plot,
labels,
name='Feedback vs Number of Answers',
verbose=verbose)
figure.tight_layout()
def plot_first_session_vs_total(figure, answers, verbose=False):
answers = decorator.session_number(answers)
ax = figure.add_subplot(111)
total = user.answers_per_user(answers)
total_first = user.answers_per_user(
answers[answers['session_number'] == 0])
users = answers['user'].unique()
vals = lambda x: [x.get(i, 0) for i in users]
pairs = map(lambda (x, y): (x, y - x),
sorted(zip(vals(total_first), vals(total))))
total_first, total = zip(*pairs)
ax.plot(total_first, total, 'o', alpha=0.3, linewidth=0, color='black')
ax.set_xlabel('number of answers in the first session')
ax.set_ylabel('number of answer at all')
ax.set_xscale('log')
ax.set_yscale('log')
def plot_answers_vs_prior_skill(figure, answers, prior_skill, verbose=False):
answers = decorator.session_number(answers)
ax = figure.add_subplot(111)
total = user.answers_per_user(answers)
users = answers['user'].unique()
vals = lambda x: [x[i] for i in users]
total, prior_skill = zip(*sorted(zip(vals(total), vals(prior_skill))))
ax.plot(total, prior_skill, 'o', alpha=0.3, linewidth=0, color='black')
ax.set_xlabel('number of answer at all')
ax.set_ylabel('prior skill')
ax.set_xscale('log')
def plot_answers_vs_prior_skill(figure, answers, prior_skill, verbose=False):
answers = decorator.session_number(answers)
ax = figure.add_subplot(111)
total = user.answers_per_user(answers)
users = answers['user'].unique()
vals = lambda x: [x[i] for i in users]
total, prior_skill = zip(*sorted(zip(vals(total), vals(prior_skill))))
ax.plot(total, prior_skill, 'o', alpha=0.3, linewidth=0, color='black')
ax.set_xlabel('number of answer at all')
ax.set_ylabel('prior skill')
ax.set_xscale('log')
def plot_first_session_vs_session_number(figure, answers, verbose=False):
answers = decorator.session_number(answers)
ax = figure.add_subplot(111)
ses = user.session_per_user(answers)
total_first = user.answers_per_user(answers[answers['session_number'] == 0])
users = answers['user'].unique()
vals = lambda x: [x.get(i, 0) for i in users]
total_first, ses = zip(*sorted(zip(vals(total_first), vals(ses))))
ax.plot(total_first, ses, 'o', alpha=0.3, linewidth=0, color='black')
ax.set_xlabel('number of answers in the first session')
ax.set_ylabel('maximal session number')
ax.set_xscale('log')
def plot_first_session_vs_session_number(figure, answers, verbose=False):
answers = decorator.session_number(answers)
ax = figure.add_subplot(111)
ses = user.session_per_user(answers)
total_first = user.answers_per_user(
answers[answers['session_number'] == 0])
users = answers['user'].unique()
vals = lambda x: [x.get(i, 0) for i in users]
total_first, ses = zip(*sorted(zip(vals(total_first), vals(ses))))
ax.plot(total_first, ses, 'o', alpha=0.3, linewidth=0, color='black')
ax.set_xlabel('number of answers in the first session')
ax.set_ylabel('maximal session number')
ax.set_xscale('log')
def boxplot_answers_per_user(figure, answers, group_column, group_name_mapping=None, verbose=False):
ax = figure.add_subplot(111)
labels = []
to_plot = []
for group_name, group_data in answers.groupby(group_column):
number = user.answers_per_user(group_data)
to_plot.append(number.values())
labels.append(
str(group_name_mapping[group_name] if group_name_mapping else group_name) + '\n(' + str(len(number)) + ')')
ax.set_yscale('log')
ax.set_xlabel(group_name_mapping.get(group_column, group_column) if group_name_mapping else group_column)
ax.set_ylabel('Number of Answers')
ax.set_title('Implicit Feedback')
_boxplot(ax, to_plot, labels, name='Answers per User', verbose=verbose)
figure.tight_layout()
def boxplot_feedback_vs_number_of_answers(figure, feedback, answers, verbose=False):
ax = figure.add_subplot(111)
first_feedback = (feedback.sort('id').
drop_duplicates('user').
groupby('user').
apply(lambda x: x['value'].mean()).to_dict())
labels = []
to_plot = []
answers = answers[answers['user'].isin(first_feedback.keys())]
answers['temp_group'] = answers['user'].apply(lambda u: first_feedback[u])
for group_name, group_data in answers.groupby('temp_group'):
number = user.answers_per_user(group_data)
to_plot.append(number.values())
labels.append('%s (%s)' % (FEEDBACK_MAPPING[group_name], len(number)))
del answers['temp_group']
ax.set_yscale('log')
ax.set_ylabel('Number of Answers')
ax.set_xlabel('First Feedback')
_boxplot(ax, to_plot, labels, name='Feedback vs Number of Answers', verbose=verbose)
figure.tight_layout()
def hist_answers_per_user(figure, answers, group_column, group_name_mapping=None, verbose=False):
ax = figure.add_subplot(111)
to_plots = []
group_names = []
for group_name, group_data in answers.groupby(group_column):
to_plots.append(numpy.log10(user.answers_per_user(group_data).values()))
group_names.append(group_name)
if group_name_mapping:
group_names = [group_name_mapping[group_name] for group_name in group_names]
else:
group_names = map(str, group_names)
group_names, to_plots = zip(*sorted(zip(group_names, to_plots), key=lambda x: x[0]))
ax.hist(
to_plots,
label=[group_name + ' (' + str(len(to_plot)) + ')' for group_name, to_plot in zip(group_names, to_plots)],
normed=True,
)
ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))
ax.set_xlabel("Number of Answers (log)")
ax.set_ylabel("Number of Users (normed)")
figure.tight_layout()
def boxplot_answers_per_user(figure,
answers,
group_column,
group_name_mapping=None,
verbose=False):
ax = figure.add_subplot(111)
labels = []
to_plot = []
for group_name, group_data in answers.groupby(group_column):
number = user.answers_per_user(group_data)
to_plot.append(number.values())
labels.append(
str(group_name_mapping[group_name] if group_name_mapping else
group_name) + '\n(' + str(len(number)) + ')')
ax.set_yscale('log')
ax.set_xlabel(
group_name_mapping.get(group_column, group_column
) if group_name_mapping else group_column)
ax.set_ylabel('Number of Answers')
ax.set_title('Implicit Feedback')
_boxplot(ax, to_plot, labels, name='Answers per User', verbose=verbose)
figure.tight_layout()