results = defaultdict(lambda: defaultdict(lambda : {}))
for response_modification in [
None,
# TimeLimitResponseModificator([(time_median, 0.5)]),
LinearDrop(time_median * 2),
]:
data = basic_data(response_modification)
model = basic_model(None)
data.trim_times()
answers = data.get_dataframe_all()
Runner(data, model).run(force=True)
for concept in ['numbers', 'addition', 'subtraction', 'multiplication', 'division']:
items = list(set(data.get_items()) & set(items_in_concept(data, concept)))
concept_answers = answers[answers['item'].isin(items)]
students = concept_answers.groupby('student').apply(len)
students = students[students >= min_answers]
results[concept][str(response_modification)] = (
items,
model.get_skills(students.index, concept),
model.get_difficulties(items),
concept_answers.groupby('student')['response_time'].median().loc[students.index],
concept_answers.groupby('student')['correct'].mean().loc[students.index],
concept_answers.groupby('item')['response_time'].median().loc[items],
concept_answers.groupby('item')['correct'].mean().loc[items],
)
for concept, r in results.items():
data = d.Data("../data/matmat/2016-11-28/answers.pd")
data.trim_times()
answers_all = data.get_dataframe_all()
difficulties = get_difficulties(answers_all)
time_intensity = get_difficulties(answers_all,
model=TimePriorCurrentModel(alpha=0.4, beta=0.04, KC=0.3, KI=0.3, first_level=False),
data=data, name="time_intensity")
# answers_all = answers_all[~answers_all['answer'].isnull()] # filter missing answers
output = defaultdict(lambda: '')
for concept in ['numbers', 'addition', 'subtraction', 'multiplication', 'division']:
answers = answers_all[answers_all['item'].isin(items_in_concept(data, concept))]
time_median = answers['response_time'].median()
for transformation, answers_transform in {
"C + lin T": LinearDrop(time_median * 2).modify(answers.copy()),
"C + binary T": TimeLimitResponseModificator([(time_median, 0.5)]).modify(answers.copy()),
}.items():
metrics = {'C': answers['correct'], transformation: answers_transform['correct']}
orders = get_order(answers, metrics)
# sns.jointplot('C', transformation, data=orders, kind='kde')
output[transformation] += '{:<15} -- spearman: {:.3f}, kendall: {:.3f}, sessions: {:>4}, time median: {:.1f}\n'.format(
concept,
orders.corr('spearman')['C'][transformation],
orders.corr('kendall')['C'][transformation],
10, runs=5, data_ratio=ratio,
# eval_data=data_test
)
if 1:
ratio = 1
model1 = basic_model(None)
model2 = basic_model(None)
data1 = Data(filename, train_size=ratio)
median = data1.get_dataframe_all()['response_time'].median()
print('time median', median)
data2 = Data(filename, response_modification=LinearDrop(median * 2), train_size=ratio)
# data2 = Data(filename, response_modification=TimeLimitResponseModificator([(median, 0.5)]), train_size=ratio)
# data2 = Data(filename, response_modification=ExpDrop(median / 2, 0.9), train_size=ratio)
Runner(data1, model1).run(force=True, only_train=True)
Runner(data2, model2).run(force=True, only_train=True)
items_ids = data1.get_items()
items_ids = list(items_in_concept(data(None), 'division'))
v1 = model1.get_difficulties(items_ids)
v2 = model2.get_difficulties(items_ids)
for item, x, y in zip(items_ids, v1, v2):
plt.plot(x, y, ".")
plt.text(x, y, items.loc[item])
plt.xlabel(str(data1))
plt.ylabel(str(data2))
plt.show()
