Intial commit, with some work done to the 'shortest_path' method.

.gitignore

@@ -0,0 +1 @@
+__pycache__

degrees.py

@@ -0,0 +1,172 @@
+import csv
+import sys
+
+from util import Node, StackFrontier, QueueFrontier
+
+# Maps names to a set of corresponding person_ids
+names = {}
+
+# Maps person_ids to a dictionary of: name, birth, movies (a set of movie_ids)
+people = {}
+
+# Maps movie_ids to a dictionary of: title, year, stars (a set of person_ids)
+movies = {}
+
+
+def load_data(directory):
+	"""
+	Load data from CSV files into memory.
+	"""
+	# Load people
+	with open(f"{directory}/people.csv", encoding="utf-8") as f:
+		reader = csv.DictReader(f)
+		for row in reader:
+			people[row["id"]] = {
+				"name": row["name"],
+				"birth": row["birth"],
+				"movies": set()
+			}
+			if row["name"].lower() not in names:
+				names[row["name"].lower()] = {row["id"]}
+			else:
+				names[row["name"].lower()].add(row["id"])
+
+	# Load movies
+	with open(f"{directory}/movies.csv", encoding="utf-8") as f:
+		reader = csv.DictReader(f)
+		for row in reader:
+			movies[row["id"]] = {
+				"title": row["title"],
+				"year": row["year"],
+				"stars": set()
+			}
+
+	# Load stars
+	with open(f"{directory}/stars.csv", encoding="utf-8") as f:
+		reader = csv.DictReader(f)
+		for row in reader:
+			try:
+				people[row["person_id"]]["movies"].add(row["movie_id"])
+				movies[row["movie_id"]]["stars"].add(row["person_id"])
+			except KeyError:
+				pass
+
+
+def main():
+	if len(sys.argv) > 2:
+		sys.exit("Usage: python degrees.py [directory]")
+	directory = sys.argv[1] if len(sys.argv) == 2 else "large"
+
+	# Load data from files into memory
+	print("Loading data...")
+	load_data(directory)
+	print("Data loaded.")
+
+	source = person_id_for_name(input("Name: "))
+	if source is None:
+		sys.exit("Person not found.")
+	target = person_id_for_name(input("Name: "))
+	if target is None:
+		sys.exit("Person not found.")
+
+	path = shortest_path(source, target)
+
+	if path is None:
+		print("Not connected.")
+	else:
+		degrees = len(path)
+		print(f"{degrees} degrees of separation.")
+		path = [(None, source)] + path
+		for i in range(degrees):
+			person1 = people[path[i][1]]["name"]
+			person2 = people[path[i + 1][1]]["name"]
+			movie = movies[path[i + 1][0]]["title"]
+			print(f"{i + 1}: {person1} and {person2} starred in {movie}")
+
+
+def shortest_path(source, target):
+	"""
+	Returns the shortest list of (movie_id, person_id) pairs
+	that connect the source to the target.
+
+	If no possible path, returns None.
+	"""
+	frontier = QueueFrontier()
+	explored = StackFrontier()
+	frontier.add(Node(source, None, None))
+	results = [[]]
+	
+	while frontier:
+		currentNode = frontier.remove()
+		
+		if currentNode.state == target:
+			tmp = currentNode
+			print("Found %s" %(people[tmp.state]))
+			print("Found!")
+			cost = 0
+			r = []
+			r.append(tmp)
+			index = len(results)
+			
+			while tmp:
+				if not tmp.parent:
+					r.append(tmp.parent)
+					print("Parent found! %s" %(people[tmp.state]))
+					
+				tmp = tmp.parent
+				cost+=1
+			results.append(r)
+			print("Estimated Cost %d" %(cost))
+			#break
+		
+		if not explored.contains_state(currentNode.state):
+			# currentNode.state has person ID.
+			neighbors = neighbors_for_person(currentNode.state)
+			explored.add(currentNode)
+			
+			for i in neighbors:
+				frontier.add(Node(i[1], currentNode, None))
+			
+	return results
+
+def person_id_for_name(name):
+	"""
+	Returns the IMDB id for a person's name,
+	resolving ambiguities as needed.
+	"""
+	person_ids = list(names.get(name.lower(), set()))
+	if len(person_ids) == 0:
+		return None
+	elif len(person_ids) > 1:
+		print(f"Which '{name}'?")
+		for person_id in person_ids:
+			person = people[person_id]
+			name = person["name"]
+			birth = person["birth"]
+			print(f"ID: {person_id}, Name: {name}, Birth: {birth}")
+		try:
+			person_id = input("Intended Person ID: ")
+			if person_id in person_ids:
+				return person_id
+		except ValueError:
+			pass
+		return None
+	else:
+		return person_ids[0]
+
+
+def neighbors_for_person(person_id):
+	"""
+	Returns (movie_id, person_id) pairs for people
+	who starred with a given person.
+	"""
+	movie_ids = people[person_id]["movies"]
+	neighbors = set()
+	for movie_id in movie_ids:
+		for person_id in movies[movie_id]["stars"]:
+			neighbors.add((movie_id, person_id))
+	return neighbors
+
+
+if __name__ == "__main__":
+	main()

small/movies.csv

@@ -0,0 +1,6 @@
+id,title,year
+112384,"Apollo 13",1995
+104257,"A Few Good Men",1992
+109830,"Forrest Gump",1994
+93779,"The Princess Bride",1987
+95953,"Rain Man",1988

small/people.csv

@@ -0,0 +1,17 @@
+id,name,birth
+102,"Kevin Bacon",1958
+129,"Tom Cruise",1962
+144,"Cary Elwes",1962
+158,"Tom Hanks",1956
+1597,"Mandy Patinkin",1952
+163,"Dustin Hoffman",1937
+1697,"Chris Sarandon",1942
+193,"Demi Moore",1962
+197,"Jack Nicholson",1937
+200,"Bill Paxton",1955
+398,"Sally Field",1946
+420,"Valeria Golino",1965
+596520,"Gerald R. Molen",1935
+641,"Gary Sinise",1955
+705,"Robin Wright",1966
+914612,"Emma Watson",1990

small/stars.csv

@@ -0,0 +1,21 @@
+person_id,movie_id
+102,104257
+102,112384
+129,104257
+129,95953
+144,93779
+158,109830
+158,112384
+1597,93779
+163,95953
+1697,93779
+193,104257
+197,104257
+200,112384
+398,109830
+420,95953
+596520,95953
+641,109830
+641,112384
+705,109830
+705,93779

util.py

@@ -0,0 +1,38 @@
+class Node():
+    def __init__(self, state, parent, action):
+        self.state = state
+        self.parent = parent
+        self.action = action
+
+
+class StackFrontier():
+    def __init__(self):
+        self.frontier = []
+
+    def add(self, node):
+        self.frontier.append(node)
+
+    def contains_state(self, state):
+        return any(node.state == state for node in self.frontier)
+
+    def empty(self):
+        return len(self.frontier) == 0
+
+    def remove(self):
+        if self.empty():
+            raise Exception("empty frontier")
+        else:
+            node = self.frontier[-1]
+            self.frontier = self.frontier[:-1]
+            return node
+
+
+class QueueFrontier(StackFrontier):
+
+    def remove(self):
+        if self.empty():
+            raise Exception("empty frontier")
+        else:
+            node = self.frontier[0]
+            self.frontier = self.frontier[1:]
+            return node