def difficulty_vs_time(data, the_skill, concepts=False):
data.filter_data(0, 100)
pk, level = data.get_skill_id(the_skill)
data.trim_times()
data.add_log_response_times()
m = EloPriorCurrentModel(KC=2, KI=0.5)
items = data.get_items_df()
items = items[items["visualization"] != "pairing"]
items = items.join(get_difficulty(data, m))
items = items.join(pd.Series(data.get_dataframe_all().groupby(["item"])["log_response_time"].mean(), name="log_response_time_mean"))
items = items[items["skill_lvl_"+str(level)] == pk]
if concepts:
skills = data.get_skills_df()
skills = skills.join(items.groupby("skill_lvl_3")["difficulty"].mean())
skills = skills.join(items.groupby("skill_lvl_3")["log_response_time_mean"].mean())
skills = skills[skills.index.isin(items["skill_lvl_3"].unique())]
for id, skill in skills.iterrows():
plt.plot(skill["difficulty"], skill["log_response_time_mean"], "ok")
plt.text(skill["difficulty"], skill["log_response_time_mean"], skill["name"])
else:
colors = "rgbyk"
visualizations = list(items["visualization"].unique())
for id, item in items.iterrows():
plt.plot(item["difficulty"], item["log_response_time_mean"], "o", color=colors[visualizations.index(item["visualization"])])
plt.text(item["difficulty"], item["log_response_time_mean"], item["name"])
for i, vis in enumerate(visualizations):
plt.plot(-1, 2, "o", color=colors[i], label=vis)
plt.xlabel("difficulty according to " + str(m))
plt.ylabel("mean of log time")
plt.legend(loc=0)
plt.title(the_skill)
################################################################################
################################################################################
################################################################################
################################################################################
## MAIN ########################################################################
################################################################################
if __name__ == '__main__':
## RANDOM TESTING ##############################################################
data, classes = load_data_from_csv('../data/classifier-data.csv', 4, float)
data, classes = arr(data), arr(classes)
bd1, bc1 = filter_data(data, classes, lambda x, y: y == 2)
bd1, bc1 = np.array(bd1), np.array(bc1)
def test(trd, trc, ted, tec):
print('tc', '\n')
tc = TreeClassify(trd, trc)
print(tc, '\n')
# print(tc.predict(ted), '\n')
# print(tc.predict_soft(ted), '\n')
# print(tc.confusion(ted, tec), '\n')
# print(tc.auc(ted, tec), '\n')
# print(tc.roc(ted, tec), '\n')
err = tc.err(ted, tec)
print(err, '\n')
return err
################################################################################
################################################################################
## MAIN ########################################################################
################################################################################
if __name__ == '__main__':
## RANDOM TESTING ##############################################################
data,classes = load_data_from_csv('../data/classifier-data.csv', 4, float)
data,classes = arr(data), arr(classes)
bd1,bc1 = filter_data(data, classes, lambda x,y: y == 2)
bd1,bc1 = np.array(bd1), np.array(bc1)
def test(trd, trc, ted, tec):
print('gbc', '\n')
gbc = GaussBayesClassify(trd, trc)
print(gbc, '\n')
# print(gbc.predict(ted), '\n')
# print(gbc.predict_soft(ted), '\n')
# print(gbc.confusion(ted, tec), '\n')
# print(gbc.auc(ted, tec), '\n')
# print(gbc.roc(ted, tec), '\n')
err = gbc.err(ted, tec)
print(err, '\n')
return err
