def store_word_graph(word_graph, file_name=None):
from .word_graphs import WordGraph, expand_word_graph # For circular import
if file_name is None:
file_name = word_graph.file_name
file_name = add_output_folder(file_name)
if isinstance(word_graph, WordGraph):
vertex_count = word_graph.vertex_count
edge_count = word_graph.edge_count
words = list(word_graph.directed_neighborhoods.keys())
else:
vertex_count = len(expand_word_graph(word_graph))
edge_count = sum(len(neighors) for neighors in word_graph.values())
words = list(word_graph)
word_graph_data = ["Vertex count: " + str(vertex_count),
"Edge count: " + str(edge_count) + "\n\n"]
words.sort()
for word in words:
if (isinstance(word_graph, WordGraph)
and word_graph.directed_neighborhoods[word]):
neighborhood = word + ": " + str(
word_graph.directed_neighborhoods[word]).replace("\'", "")
elif type(word_graph) == dict and word_graph[word]:
neighborhood = word + ": " + str(word_graph[word]).replace("\'", "")
word_graph_data.append(neighborhood)
store_data(word_graph_data, file_name)
def store_subgraph_statistics(subgraph_statistics, ascending_order,
name_base="word_graph", name_suffix=""):
file_name = name_base + "_" + name_suffix + "_subgraph_statistics.txt"
file_name = add_output_folder(file_name)
title = ((name_base + "_" + name_suffix).replace("_", " ").title()
+ " Subgraph Statistics")
if ascending_order:
"Ascending Order " + title
subgraph_data = ["\n" + title]
for size in subgraph_statistics:
subgraph_data.append("\n\n---------------- Words of size <= "
+ str(size) + " ----------------")
subgraph_data.append(
"\nVertices: " + str(subgraph_statistics[size]["vertices"]))
subgraph_data.append(
"Edges: " + str(subgraph_statistics[size]["edges"]))
for subgraph_type, statistics_dict in subgraph_statistics[size].items():
if isinstance(statistics_dict, dict):
for subgraph_class, value in statistics_dict.items():
if subgraph_class == "total":
subgraph_data.append("\n" + subgraph_type.title()
+ "s: " + str(value))
else:
subgraph_data.append(subgraph_class.title() + " "
+ subgraph_type + "s: " + str(value))
store_data(subgraph_data, file_name)
def store_words(word_list, list_type="dow", extra_suffix=""):
if list_type == "all":
length = max_word_length(word_list)
size = None
else:
size = max_word_size(word_list)
length = None
file_name = get_word_filename(list_type,
size,
length,
extra_suffix=extra_suffix)
store_data(word_list, file_name)
def store_external_paths(external_paths_container, ascending_order, name_base):
file_name = name_base + "_minimal_external_paths.txt"
if ascending_order:
file_name = "ao" + file_name
file_name = add_output_folder(file_name)
external_path_data = []
for size, minimal_external_paths in external_paths_container.items():
identifier = get_word_graph_filename(ascending_order, size, name_base)
external_path_data.append("\n\n" + identifier + "\n")
for vertex1 in paths_by_vertex in minimal_external_paths.items():
for vertex2, paths in paths_by_vertex.items():
external_path_data.append("\n" + vertex1 + " --> " + vertex2 + ":")
for path in paths:
external_path_data.append(path)
store_data(external_path_data, file_name)
def store_homology_data(ascending_order,
size,
homology_data,
max_simplex_types,
name_base="word_graph_size",
name_suffix=""):
file_name = get_word_graph_filename(ascending_order, size, name_base,
name_suffix)[:-4]
file_name += "_homology_" + "_".join(max_simplex_types) + ".txt"
print_data = []
for i, homology_group in enumerate(homology_data):
print_data.append("\nBetti number " + i + " : " + homology_group[0])
if len(homology_group) > 1:
print_data.append("\nBoundary matrix of dimension " + i)
print_data.append(homology_group[1])
print_data.append("\nReduced boundary matrix of dimension " + i)
print_data.append(homology_group[2])
print_data.append("\n--------------------------\n")
store_data(print_data, file_name)
def store_word_subgraphs(subgraphs, subgraph_type, ascending_order,
size, name_base="word_graph_size", name_suffix=""):
sorted_ = True if type(subgraphs) == dict else False
subgraph_count = (len(subgraphs) if type(subgraphs) == list
else sum(len(subgraph_list) for subgraph_list
in subgraphs.values()))
subgraph_data = [subgraph_type.title() + " subgraph count: "
+ str(subgraph_count) + "\n"]
if (subgraph_type in ["triangle", "3-path", "4-path", "square"] and not sorted_):
subgraph_data += subgraphs
elif sorted_:
for subgraph_class, subgraph_list in subgraphs.items():
subgraph_data.append(str(subgraph_class) + " " + subgraph_type
+ " subgraph count: " + str(len(subgraph_list)))
subgraph_data.append("\n\n")
for subgraph_class, subgraph_list in subgraphs.items():
subgraph_data.append(str(subgraph_class) + ":\n")
subgraph_data += subgraph_list
subgraph_data.append("\n\n")
subgraph_file_name = add_output_folder(get_word_subgraph_filename(
ascending_order, size, subgraph_type,
name_base, name_suffix, sorted_))
store_data(subgraph_data, subgraph_file_name)