Answer To: Q1.1 [30 points] Collect data from TMDb and build a graph For this Q1.1, you will be using and...
Vicky answered on Feb 03 2021
import http.client
import json
import csv
#############################################################################################################################
# All instructions, code comments, etc. contained within this notebook are part of the assignment instructions.
# Portions of this file will auto-graded in Gradescope using different sets of parameters / data to ensure that values are not
# hard-coded.
#
# Instructions: Implement all methods in this file that have a return
# value of 'NotImplemented'. See the documentation within each method for specific details, including
# the expected return value
#
# Helper Functions:
# You are permitted to write additional helper functions/methods or use additional instance variables within
# the `Graph` class or `TMDbAPIUtils` class so long as the originally included methods work as required.
#
# Use:
# The `Graph` class is used to represent and store the data for the TMDb co-actor network graph. This class must
# also provide some basic analytics, i.e., number of nodes, edges, and nodes with the highest degree.
#
# The `TMDbAPIUtils` class is used to retrieve Actor/Movie data using themoviedb.org API. We have provided a few necessary methods
# to test your code w/ the API, e.g.: get_movie_cast(), get_movie_credits_for_person(). You may add additional
# methods and instance variables as desired (see Helper Functions).
#
# The data that you retrieve from the TMDb API is used to build your graph using the Graph class. After you build your graph using the
# TMDb API data, use the Graph class write_edges_file & write_nodes_file methods to produce the separate nodes and edges
# .csv files for use with the Argo-Lite graph visualization tool.
#
# While building the co-actor graph, you will be required to write code to expand the graph by iterating
# through a portion of the graph nodes and finding similar artists using the TMDb API. We will not grade this code directly
# but will grade the resulting graph data in your Argo-Lite graph snapshot.
#
#############################################################################################################################
class Graph:
# Do not modify
def __init__(self, with_nodes_file=None, with_edges_file=None):
"""
option 1: init as an empty graph and add nodes
option 2: init by specifying a path to nodes & edges files
"""
self.nodes = []
self.edges = []
if with_nodes_file and with_edges_file:
nodes_CSV = csv.reader(open(with_nodes_file))
nodes_CSV = list(nodes_CSV)[1:]
self.nodes = [(n[0],n[1]) for n in nodes_CSV]
edges_CSV = csv.reader(open(with_edges_file))
edges_CSV = list(edges_CSV)[1:]
self.edges = [(e[0],e[1]) for e in edges_CSV]
def add_node(self, id: str, name: str)->None:
"""
add a tuple (id, name) representing a node to self.nodes if it does not already exist
The graph should not contain any duplicate nodes
"""
if (id, name) not in self.nodes:
self.nodes.append((id, name))
def add_edge(self, source: str, target: str)->None:
"""
Add an edge between two nodes if it does not already exist.
An edge is represented by a tuple containing two strings: e.g.: ('source', 'target').
Where 'source' is the id of the source node and 'target' is the id of the target node
e.g., for two nodes with ids 'a' and 'b' respectively, add the tuple ('a', 'b') to self.edges
"""
if (source, target) not in self.edges:
self.edges.append((source, target))
def total_nodes(self)->int:
"""
Returns an integer value for the total number of nodes in the graph
"""
return len(self.nodes)
def total_edges(self)->int:
"""
Returns an integer value for the total number of edges in the graph
"""
return len(self.edges)
def max_degree_nodes(self)->dict:
"""
Return the node(s) with the highest degree
Return multiple nodes in the event of a tie
Format is a dict where the key is the node_id and the value is an integer for the node degree
e.g. {'a': 8}
or {'a': 22, 'b': 22}
"""
degree = {}
for (id, name) in self.nodes:
count = 0
for (source, target) in self.edges:
if name in (source, target):
count += 1
degree[name] = count
max_value = max(degree.values())
max_degree = {}
for source, target in degree.items():
if max_value == target:
max_degree[source] = target
return max_degree
def print_nodes(self):
"""
No further implementation required
May be used for de-bugging if necessary
"""
print(self.nodes)
def print_edges(self):
"""
No further implementation required
May be used for de-bugging if necessary
"""
...