def hierarchical_clustering(data, skill, method='single', metric='euclidean', dendrogram=True, concepts=False, cluster_number=3, corr_as_vectors=False):
pk, level = data.get_skill_id(skill)
items = data.get_items_df()
skills = data.get_skills_df()
corr = compute_corr(data, merge_skills=concepts)
print("Corr ({}) contain total {} values and from that {} nans".format(corr.shape, corr.size, corr.isnull().sum().sum()))
corr[corr.isnull()] = 0
if concepts:
items = items[items["skill_lvl_" + str(level)] == pk]
skill_ids = items[~items["skill_lvl_3"].isnull()]["skill_lvl_3"].unique()
corr = pd.DataFrame(corr, index=skill_ids, columns=skill_ids)
labels = list(skills.loc[corr.index]["name"])
else:
items = items[items["skill_lvl_" + str(level)] == pk]
items = items[items["visualization"] != "pairing"]
corr = pd.DataFrame(corr, index=items.index, columns=items.index)
labels = ["{1} - {0}".format(item["name"], item["visualization"][0]) for id, item in list(items.iterrows())]
if corr_as_vectors:
Z = hr.linkage(corr, method=method, metric=metric)
else:
Z = hr.linkage(dst.squareform(1 - corr), method=method)
Z[Z < 0] = 0
if dendrogram:
plt.title('{}: method: {}, metric: {}, as vectors: {}'.format(skill, method, metric, corr_as_vectors))
plt.xlabel('items' if not concepts else "concepts")
plt.ylabel('distance')
hr.dendrogram(Z, leaf_rotation=90., leaf_font_size=10., labels=labels)
return hr.fcluster(Z, cluster_number, "maxclust")
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)
def concept_clustering(data, skill, cluster_number=3, plot=True):
pk, level = data.get_skill_id(skill)
items = data.get_items_df()
items = items[items["skill_lvl_" + str(level)] == pk]
skills = data.get_skills_df()
skill_ids = items[~items["skill_lvl_3"].isnull()]["skill_lvl_3"].unique()
corr = compute_corr(data, merge_skills=True)
corr = pd.DataFrame(corr, index=skill_ids, columns=skill_ids)
print("Corr ({}) contain total {} values and from that {} nans".format(corr.shape, corr.size, corr.isnull().sum().sum()))
corr[corr.isnull()] = 0
try:
sc = SpectralClusterer(corr, kcut=corr.shape[0] * 0.5, mutual=True)
labels = sc.run(cluster_number=cluster_number, KMiter=50, sc_type=2)
except np.linalg.linalg.LinAlgError:
sc = SpectralClusterer(corr, kcut=corr.shape[0] * 0.5, mutual=False)
labels = sc.run(cluster_number=cluster_number, KMiter=50, sc_type=2)
if plot:
colors = "rgbyk"
for i, p in enumerate(corr.columns):
skill = skills.loc[int(p)]
plt.plot(sc.eig_vect[i, 1], sc.eig_vect[i, 2], "o", color=colors[labels[i]])
plt.text(sc.eig_vect[i, 1], sc.eig_vect[i, 2], skill["name"])
plt.title(data)
return labels
def plot_skill_values(data, values):
colors = ["p", "b", "y", "k", "g", "r"]
skills = data.get_skills_df()
items = data.get_items_df()
skills = skills.join(items.groupby("skill")["skill_lvl_1"].first())
colors = dict(zip(skills["skill_lvl_1"].unique(), colors))
skills = skills.join(pd.Series(values, name="value"))
skills = skills[~skills["value"].isnull()]
for _, skill in skills.iterrows():
x = random.random()
# print(skill["value"], skill["name"])
plt.plot(x, skill["value"], "o", color=colors[skill["skill_lvl_1"]] if not np.isnan(skill["skill_lvl_1"]) else "k")
plt.text(x, skill["value"], skill["name"])