def get_clust_samples(fullset):
result = []
for row in fullset:
disaster_prob_vec = row[:common.N_DISASTER]
categorized_vec = common.categorize(disaster_prob_vec, 0.4, 0.6)
if common.is_certain(categorized_vec) and sum(categorized_vec) != 0:
result.append(categorized_vec)
return np.array(result)
def span(categorized_vec):
having_nodata_vecs = collections.deque([categorized_vec])
possible_vecs = []
while having_nodata_vecs:
top_vec = having_nodata_vecs.pop()
if not common.is_certain(top_vec):
zerovec, onevec = remove_leftmost_nodata(top_vec)
having_nodata_vecs.appendleft(zerovec)
having_nodata_vecs.appendleft(onevec)
else:
possible_vecs.append(top_vec)
return possible_vecs
def get_codes(fullset):
results = []
for i, row in enumerate(fullset):
disaster_prob_vec = row[:common.N_DISASTER]
feature_vec = row[common.N_DISASTER:]
categorized_vec = common.categorize(disaster_prob_vec, 0.4, 0.6)
if common.is_certain(categorized_vec):
label = common.classify(categorized_vec)
results.append(label)
elif -99 in feature_vec:
results.append(-99)
else:
results.append(common.N_CLASS)
return np.array(results)
def get_types(fullset):
results = []
for row in fullset:
disaster_prob_vec = row[:common.N_DISASTER]
feature_vec = row[common.N_DISASTER:]
categorized_vec = common.categorize(disaster_prob_vec, 0.4, 0.6)
if common.is_certain(categorized_vec):
label = common.classify(categorized_vec)
results.append(label)
elif -99 in feature_vec:
results.append(-99)
else:
results.append(UNCERTAIN_LABEL)
return np.array(results)
def get_trainset(fullset, upward=False, with_id=False):
result = []
if upward:
fullset = np.flipud(fullset.reshape(common.N_ROWS, common.N_COLS, -1)).reshape(-1, fullset.shape[-1])
for row in fullset:
disaster_prob_vec = row[:common.N_DISASTER]
feature_vec = row[common.N_DISASTER:]
categorized_vec = common.categorize(disaster_prob_vec, 0.4, 0.6)
if common.is_certain(categorized_vec) and -99 not in feature_vec:
label = common.classify(categorized_vec)
result.append(feature_vec.tolist() + [label])
if with_id:
return np.concatenate((np.arange(len(result))[:, np.newaxis], result), axis=1)
else:
return np.array(result)