def setUp(self):
self.movies = CsvFileHandler("..\\data", "sample_movie_dataset.csv")
self.movies.extract_data()
self.movies_data_frame = self.movies.get_data_frame()
self.valid_cb = ContentBased("Avatar", self.movies_data_frame, ["Title", "Genre", "Director", "Actors"])
self.invalid_cb = ContentBased("Avatar", self.movies_data_frame, ["Title", "Ge", "Director", "Actors"])
def content_based_filtering(key,
movies,
filter_list=[
"Title", "Genre", "Director", "Actors"
]):
cb = ContentBased(key, movies, filter_list)
return cb.filter()
def handle_client(conn, addr):
# print(f"[NEW CONNECTION] {addr} connected.")
msg = conn.recv(HEADER).decode(FORMAT)
json_msg = json.loads(msg)
print('abc')
try:
algorithm_t = json_msg['algorithm_t']
table_name = json_msg['tableName']
pkey_column_name = json_msg['pkey_column_name']
pkey_val = json_msg['pkey_val']
if table_name == "movies":
collection = db['movies']
filter_list = ["Title", "Genre", "Director", "Actors"]
elif table_name == "caregivers":
collection = db['caregivers']
filter_list = [
"Name", "Occupation", "Services", "Availability", "Location"
]
dataset = list(collection.find())
df = DataFrame(dataset)
cb = ContentBased(pkey_column_name, pkey_val, df, filter_list)
recommendations = cb.get_recommendations(10)
conn.send(json.dumps(recommendations, default=str).encode(FORMAT))
conn.close()
except:
conn.send(json.dumps([], default=str).encode(FORMAT))
conn.close()
def handle_client(conn, addr):
print(f"[NEW CONNECTION] {addr} connected.")
while True:
msg = conn.recv(HEADER).decode(FORMAT) # length of the message
json_msg = json.loads(msg)
print(type(json_msg))
print(json_msg)
collection = []
filter_list = []
algorithm_t = json_msg['algorithm_t']
tableName = json_msg['tableName']
pkey_column_name = json_msg['pkey_column_name']
pkey_val = json_msg['pkey_val']
if tableName == "movies":
collection = db['movies']
filter_list = [
pkey_column_name, "Title", "Genre", "Director", "Actors"
]
else:
collection = db['caregivers']
filter_list = [
pkey_column_name, "Name", "Occupation", "Services",
"Availability", "Location"
]
result = collection.find()
df = DataFrame(list(result))
cb = ContentBased(pkey_val, df, filter_list).filter()
obj = [{"key1": "7", "key2": "abc"}, {"key1": "8", "key2": "def"}]
conn.send(json.dumps(cb.tolist()).encode(FORMAT))
# conn.send(str(obj).encode(FORMAT))
break
conn.close()
def handle_client(conn, addr):
# print(f"[NEW CONNECTION] {addr} connected.")
msg = conn.recv(HEADER).decode(FORMAT)
json_msg = json.loads(msg)
try:
algorithm_t = json_msg['algorithm_t']
table_name = json_msg['tableName']
pkey_column_name = json_msg['pkey_column_name']
pkey_val = json_msg['pkey_val']
# dataset = list(collection.find())
# df = DataFrame(dataset)
filter_list = ["official_occupation", "travel_radius"]
mycursor.execute("SELECT * FROM caregiver")
myresult = mycursor.fetchall()
mylist = myresult
mydf = DataFrame(mylist)
mycursor.execute("SELECT column_name FROM information_schema.columns WHERE table_name='caregiver';")
mycolumnnames = mycursor.fetchall()
my_col_list = list(mycolumnnames)
formatted_names = [''.join(i) for i in my_col_list]
mydf.columns = formatted_names
print(mydf)
cb = ContentBased(pkey_column_name, pkey_val, mydf, filter_list)
recommendations = cb.get_recommendations(10)
conn.send(json.dumps(recommendations, default=str).encode(FORMAT))
conn.close()
except:
conn.send(json.dumps([], default=str).encode(FORMAT))
conn.close()
class TestContentBased(unittest.TestCase):
def setUp(self):
self.movies = CsvFileHandler("..\\data", "sample_movie_dataset.csv")
self.movies.extract_data()
self.movies_data_frame = self.movies.get_data_frame()
self.valid_cb = ContentBased("Avatar", self.movies_data_frame, ["Title", "Genre", "Director", "Actors"])
self.invalid_cb = ContentBased("Avatar", self.movies_data_frame, ["Title", "Ge", "Director", "Actors"])
def test_constructor(self):
self.assertIsInstance(self.valid_cb, ContentBased)
self.assertIsInstance(self.invalid_cb, ContentBased)
self.assertRaises(TypeError, ContentBased, "Avatar", None, None)
self.assertRaises(TypeError, ContentBased, None, self.movies_data_frame, None)
self.assertRaises(TypeError, ContentBased, None, None, [])
self.assertRaises(TypeError, ContentBased, None, None, None)
def test_filter(self):
self.assertIsInstance(self.valid_cb.filter(), list)
self.assertRaises(KeyError, self.invalid_cb.filter)
key = sys.argv[2]
prim_key = sys.argv[3]
if sys.argv[4] == "movies":
collection = db['movies']
filter_list = [prim_key, "Title", "Genre", "Director", "Actors"]
else:
collection = db['caregivers']
filter_list = [
prim_key, "Name", "Occupation", "Services", "Availability",
"Location"
]
result = collection.find()
df = DataFrame(list(result))
cb = ContentBased(key, df, filter_list).filter()
for e in cb[:10]:
print(e.to_json())
# import csv
# import json
# import pandas as pd
# from pymongo import MongoClient
#
# csvfile = open('C:\\Users\\Alex\\OneDrive\\Semester 6\\Indust App Dev\\Software_Project\\Python\\data\\sample_movie_dataset.csv')
# reader = csv.DictReader(csvfile)
# client = MongoClient('mongodb://localhost:27017/')
#
# db = client['moviesDB']
# collection = db['movies']