def print_cluster_details(cluster_details, shared_features):
for cluster_id in cluster_details.keys():
print "Cluster ID: {0}".format(cluster_id)
print "Silhouette Score: {0}".format(cluster_details[cluster_id]["silhouette"])
print "IPs: {0}".format(", ".join(sorted(cluster_details[cluster_id]["ips"])))
print ""
print "Shared Features:"
for feature in reduce_shared_features(shared_features[cluster_id]['positive']):
print " - ".join([i.encode("unicode-escape") for i in feature])
print ""
print ""
def display_vector_index_details(vector_index, vectors, vector_names, vectorizer):
# borrow the feature -> string method from get_common_features_from_cluster
output = ""
upf, unf, shared_features = get_common_features_from_cluster(vectors[vector_index, :].reshape(1, -1), np.array([0]), vectorizer)
ip = vector_names[vector_index]
features = set()
for feature in reduce_shared_features(shared_features[0]['positive']):
features.add(" - ".join([i.encode("unicode-escape") for i in feature]))
features = sorted(list(features))
output += "IP: {0}\n".format(ip)
for f in features:
output += f + "\n"
return output + "\n"
def print_cluster_details(cluster_details, shared_features):
for cluster_id in cluster_details.keys():
print "Cluster ID: {0}".format(cluster_id)
print "Silhouette Score: {0}".format(
cluster_details[cluster_id]["silhouette"])
print "IPs: {0}".format(", ".join(
sorted(cluster_details[cluster_id]["ips"])))
print ""
print "Shared Features:"
for feature in reduce_shared_features(
shared_features[cluster_id]['positive']):
print " - ".join([i.encode("unicode-escape") for i in feature])
print ""
print ""
def display_shared_vector_indeces_details(vector_indeces, vectors, vector_names, vectorizer):
# borrow the feature -> string method from get_common_features_from_cluster
output = ""
upf, unf, shared_features = get_common_features_from_cluster(vectors[vector_indeces, :], np.array([0] * len(vector_indeces)), vectorizer)
features = set()
for feature in reduce_shared_features(shared_features[0]['positive']):
features.add(" - ".join([i.encode("unicode-escape") for i in feature]))
features = sorted(list(features))
if len(features) == 0:
return "No shared features\n"
for f in features:
output += f + "\n"
return output + "\n"
def display_vector_index_details(vector_index, vectors, vector_names,
vectorizer):
# borrow the feature -> string method from get_common_features_from_cluster
output = ""
upf, unf, shared_features = get_common_features_from_cluster(
vectors[vector_index, :].reshape(1, -1), np.array([0]), vectorizer)
ip = vector_names[vector_index]
features = set()
for feature in reduce_shared_features(shared_features[0]['positive']):
features.add(" - ".join([i.encode("unicode-escape") for i in feature]))
features = sorted(list(features))
output += "IP: {0}\n".format(ip)
for f in features:
output += f + "\n"
return output + "\n"
def display_shared_vector_indeces_details(vector_indeces, vectors,
vector_names, vectorizer):
# borrow the feature -> string method from get_common_features_from_cluster
output = ""
upf, unf, shared_features = get_common_features_from_cluster(
vectors[vector_indeces, :], np.array([0] * len(vector_indeces)),
vectorizer)
features = set()
for feature in reduce_shared_features(shared_features[0]['positive']):
features.add(" - ".join([i.encode("unicode-escape") for i in feature]))
features = sorted(list(features))
if len(features) == 0:
return "No shared features\n"
for f in features:
output += f + "\n"
return output + "\n"
