from graphfile import GraphFile
# Load manufacturing paths paths
# ==============================
paths = GraphFile("data/manufacturing_paths.txt").read_paths_with_count()
number_of_manufactured_items = sum(paths.values())
# Load edges
# ==========
edges = GraphFile("data/manufacturing_edges.txt").read_edges_from_file()
# Filter out edges that only serve a handfull of items
# ====================================================
threshold = 0.001 * number_of_manufactured_items
edges_to_remove = [k for k,v in edges.items() if v < threshold]
edges_to_remove = set(edges_to_remove)
# Clean manufacturing paths
# =========================
clean_paths = {}
for k,v in paths.items():
e = [(i,j) for (i,j) in zip(k, k[1:])]
e = set(e)
if len(edges_to_remove.intersection(e)) == 0:
clean_paths[k] = clean_paths.get(k, 0) + v
# Get clean edges
# ===============
clean_edges = {}
for k,v in clean_paths.items():
# full_path = "/mnt/irisgpfs/users/yomar/manufacturing_entropy_article/"
filename_paths = "data/clean_manufacturing_paths.txt"
# filename_paths = full_path + filename_paths
filename_edges = "data/clean_manufacturing_edges.txt"
# filename_edges = full_path + filename_edges
edges = GraphFile(filename_edges).read_edges_from_file()
paths = GraphFile(filename_paths).read_paths_with_count()
# =========================================================================
# CALCULATE ENTROPY
# =========================================================================
if method == 1:
# Method 1: binary, directed graph with self-loops on all nodes
# Due to computation issues, this is deployed in an HPC!!!
# =============================================================
edges = {k: 1 for k, v in edges.items()}
G = Graph(edges)
nodes = G.nodes
for n in G.nodes:
G.addEdge(n, n, 1)
# Check that all edges have a value of 1
assert len(set(G.edges.values())) == 1
print("\nNumber of nodes: ", len(G.nodes))
print("Number of edges: ", len(G.edges.keys()))
print("Binary, directed graph with self-loops on all nodes\n")
pool = multiprocessing.Pool()
start = datetime.datetime.now()
# Yamila Mariel Omar
# Date of original code: 9th February 2021
# Date of code last modification: 9th February 2021
from graphviz import Digraph
import sys
sys.path.append('..')
from graphfile import GraphFile
from graph import Graph
# Load edges
# ==========
filename = "data/F2.txt"
edges = GraphFile(filename).read_edges_from_file()
total_items = sum([v for k, v in edges.items() if "source" in k])
edges = {k: v / total_items for k, v in edges.items()}
G = Graph(edges)
# Get node list
# =============
nodes = G.nodes
# Nodes positions in plot
# =======================
positions = {
'source': "0,9!",
'24': "-1,8!",
'25': "1,8!",
'26': "-1,7!",
# ======================================
filename_paths = "data/clean_manufacturing_paths.txt"
filename_edges = "data/clean_manufacturing_edges.txt"
edges = GraphFile(filename_edges).read_edges_from_file()
paths = GraphFile(filename_paths).read_paths_with_count()
# Generate graph from clean edges
# ===============================
edges = add_self_loops(paths, edges)
G = Graph(edges)
# ==========================================================================
# Get frequency of n in paths
# ==========================================================================
freq_n_in_paths = {n: 0 for n in G.nodes}
for p, v in paths.items():
for n in p:
freq_n_in_paths[n] += v
number_of_paths = sum(list(paths.values()))
freq_n_in_paths = {
k: v / number_of_paths
for k, v in freq_n_in_paths.items()
}
# Make plot
# =========
x = list(freq_n_in_paths.keys())
x.sort()
freq = [freq_n_in_paths[n] for n in x]