LouisdeBruijn

## load_data.py
import os
import sys
import pandas as pd
import numpy as np
from scipy.sparse import csr_matrix, save_npz, load_npz, vstack, hstack, lil_matrix
import implicit
import pickle
from implicit.evaluation import train_test_split, precision_at_k, mean_average_precision_at_k

def load_data():

## sparse_matrices.py
def sparse_matrices(df):
    '''creates the sparse user-item and item-user matrices'''

    # using a scalar value (40) to convert ratings from a scale (1-5) to a like/click/view (1)
    alpha = 40

    sparse_user_item = csr_matrix( ([alpha]*len(df['movie_id']), (df['user_id'], df['movie_id']) ))
    # transposing the item-user matrix to create a user-item matrix
    sparse_item_user = sparse_user_item.T.tocsr()
    # save the matrices for recalculating user on the fly

## model.py
def model():
    '''computes p@k and map@k evaluation metrics and saves model'''
    sparse_item_user = load_npz("sparse_item_user.npz")

    train, test = train_test_split(sparse_item_user, train_percentage=0.8)

    model = implicit.als.AlternatingLeastSquares(factors=100,
        regularization=0.1, iterations=20, calculate_training_loss=False)
    model.fit(train)

## mappings.py
def map_movies(movie_ids):
    '''takes a list of movie_ids and returns a list of dictionaries with movies information'''
    df = pd.read_csv('ml-1m/movies.dat', delimiter='::', header=None,
        names=['movie_id', 'title', 'genre'], engine='python')

    # add years to a new column 'year' and remove them from the movie title
    df['year'] = df['title'].str[-5:-1]
    df['title'] = df['title'].str[:-6]

    # creates an ordered list of dictionaries with the movie information for all movie_ids

## similar.py
def most_similar_items(item_id, n_similar=10):
    '''computes the most similar items'''
    with open('model.sav', 'rb') as pickle_in:
        model = pickle.load(pickle_in)

    similar, _ = zip(*model.similar_items(item_id, n_similar)[1:])

    return map_movies(similar)


## recommendations.py
def recommend(user_id):
    '''recommend N items to user'''
    sparse_user_item = load_npz("sparse_user_item.npz")

    with open('model.sav', 'rb') as pickle_in:
        model = pickle.load(pickle_in)

    recommended, _ =  zip(*model.recommend(user_id, sparse_user_item))

    return recommended, map_movies(recommended)

## recalculate_user.py

def recalculate_user(user_ratings):
    '''adds new user and its liked items to sparse matrix and returns recalculated recommendations'''

    alpha = 40
    m = load_npz('sparse_user_item.npz')
    n_users, n_movies = m.shape

    ratings = [alpha for i in range(len(user_ratings))]

## contact.html
{% extends "base.html" %}

<form action="/contact" id="contact-form" method="POST" enctype="text/plain">
    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
    <div class="row">
        <div class="input-field col s6">
            <input type="text" class="validate" name ="first-name" id="first-name" pattern="[a-zA-Z]*" required/>
            <label for="first-name">First name</label>
            <span class="helper-text" data-error="Only text is accepted." data-success=""></span>
        </div>

## base.html
<head>
  {% block links %}
      <!-- Bootstrap CSS -->
      <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css" integrity="sha384-ggOyR0iXCbMQv3Xipma34MD+dH/1fQ784/j6cY/iJTQUOhcWr7x9JvoRxT2MZw1T" crossorigin="anonymous">
      <!-- jQuery script-->
      <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.4.1/jquery.min.js"></script>
      <!--Import materialize.css-->
      <link type="text/css" rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/1.0.0/css/materialize.min.css"  media="screen,projection"/>
      <!--Let browser know website is optimized for mobile-->
      <meta name="viewport" content="width=device-width, initial-scale=1.0"/>

## contact.js
$('#contact-form-button').click(function(event){
    // Prevent redirection with AJAX for contact form
    var form = $('#contact-form');
    var form_id = 'contact-form';
    var url = form.prop('action');
    var type = form.prop('method');
    var formData = getContactFormData(form_id);

    // submit form via AJAX
    send_form(form, form_id, url, type, modular_ajax, formData);
	import os
	import sys
	import pandas as pd
	import numpy as np
	from scipy.sparse import csr_matrix, save_npz, load_npz, vstack, hstack, lil_matrix
	import implicit
	import pickle
	from implicit.evaluation import train_test_split, precision_at_k, mean_average_precision_at_k

	def load_data():
	def sparse_matrices(df):
	'''creates the sparse user-item and item-user matrices'''

	# using a scalar value (40) to convert ratings from a scale (1-5) to a like/click/view (1)
	alpha = 40

	sparse_user_item = csr_matrix( ([alpha]*len(df['movie_id']), (df['user_id'], df['movie_id']) ))
	# transposing the item-user matrix to create a user-item matrix
	sparse_item_user = sparse_user_item.T.tocsr()
	# save the matrices for recalculating user on the fly
	def model():
	'''computes p@k and map@k evaluation metrics and saves model'''
	sparse_item_user = load_npz("sparse_item_user.npz")

	train, test = train_test_split(sparse_item_user, train_percentage=0.8)

	model = implicit.als.AlternatingLeastSquares(factors=100,
	regularization=0.1, iterations=20, calculate_training_loss=False)
	model.fit(train)
	def map_movies(movie_ids):
	'''takes a list of movie_ids and returns a list of dictionaries with movies information'''
	df = pd.read_csv('ml-1m/movies.dat', delimiter='::', header=None,
	names=['movie_id', 'title', 'genre'], engine='python')

	# add years to a new column 'year' and remove them from the movie title
	df['year'] = df['title'].str[-5:-1]
	df['title'] = df['title'].str[:-6]

	# creates an ordered list of dictionaries with the movie information for all movie_ids
	def most_similar_items(item_id, n_similar=10):
	'''computes the most similar items'''
	with open('model.sav', 'rb') as pickle_in:
	model = pickle.load(pickle_in)

	similar, _ = zip(*model.similar_items(item_id, n_similar)[1:])

	return map_movies(similar)
	def recommend(user_id):
	'''recommend N items to user'''
	sparse_user_item = load_npz("sparse_user_item.npz")

	with open('model.sav', 'rb') as pickle_in:
	model = pickle.load(pickle_in)

	recommended, _ = zip(*model.recommend(user_id, sparse_user_item))

	return recommended, map_movies(recommended)

	def recalculate_user(user_ratings):
	'''adds new user and its liked items to sparse matrix and returns recalculated recommendations'''

	alpha = 40
	m = load_npz('sparse_user_item.npz')
	n_users, n_movies = m.shape

	ratings = [alpha for i in range(len(user_ratings))]
	{% extends "base.html" %}

	<form action="/contact" id="contact-form" method="POST" enctype="text/plain">
	<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
	<div class="row">
	<div class="input-field col s6">
	<input type="text" class="validate" name ="first-name" id="first-name" pattern="[a-zA-Z]*" required/>
	<label for="first-name">First name</label>
	<span class="helper-text" data-error="Only text is accepted." data-success=""></span>
	</div>
	<head>
	{% block links %}
	<!-- Bootstrap CSS -->
	<link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.3.1/css/bootstrap.min.css" integrity="sha384-ggOyR0iXCbMQv3Xipma34MD+dH/1fQ784/j6cY/iJTQUOhcWr7x9JvoRxT2MZw1T" crossorigin="anonymous">
	<!-- jQuery script-->
	<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.4.1/jquery.min.js"></script>
	<!--Import materialize.css-->
	<link type="text/css" rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/1.0.0/css/materialize.min.css" media="screen,projection"/>
	<!--Let browser know website is optimized for mobile-->
	<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
	$('#contact-form-button').click(function(event){
	// Prevent redirection with AJAX for contact form
	var form = $('#contact-form');
	var form_id = 'contact-form';
	var url = form.prop('action');
	var type = form.prop('method');
	var formData = getContactFormData(form_id);

	// submit form via AJAX
	send_form(form, form_id, url, type, modular_ajax, formData);