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 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 item_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]
items = items[items["visualization"] != "pairing"]
corr = compute_corr(data)
corr = pd.DataFrame(corr, index=items.index, columns=items.index)
print("Corr ({}) contain total {} values and from that {} nans".format(corr.shape, corr.size, corr.isnull().sum().sum()))
corr[corr.isnull()] = 0
sc = SpectralClusterer(corr, kcut=corr.shape[0] / 2, mutual=True)
# sc = SpectralClusterer(corr, kcut=30, mutual=True)
labels = sc.run(cluster_number=cluster_number, KMiter=50, sc_type=2)
if plot:
colors = "rgbyk"
visualizations = list(items["visualization"].unique())
for i, p in enumerate(corr.columns):
item = items.loc[p]
plt.plot(sc.eig_vect[i,1], sc.eig_vect[i,2], "o", color=colors[visualizations.index(item["visualization"])])
# 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], item["name"])
for i, vis in enumerate(visualizations):
plt.plot(0, 0, "o", color=colors[i], label=vis)
plt.title(data)
plt.legend(loc=3)
return labels
