Add py files

Author: susanli2016

bpr.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+from util import m_normal, learning_rate, get_lambda
+from classes import ret
+import random as random
+import numpy as np
+import math
+def bpr_update(users, movies):
+    count = 0
+    lr = learning_rate()
+    lam = get_lambda()
+    for u1 in users:
+        u = users[u1]
+        userid = u.userid
+        Vu = u.factor
+        if (len(u.movies_train) > 0):
+
+            rand_pos = random.sample(u.movies_train.keys(), 1)[0]
+            rand_neg = random.sample(movies.keys(), 1)[0]
+
+            if rand_neg not in u.movies_train:
+                Vi = movies[rand_pos].factor
+                Vj = movies[rand_neg].factor
+                firstterm = calculate_first_term(Vu, Vi, Vj)
+
+                # USER FACTOR
+                diff = Vi - Vj
+                d = firstterm * diff
+                derivative = d
+                Vu = Vu + lr * (derivative + lam * np.linalg.norm(Vu))
+                users[u1].factor = Vu
+
+                # ITEM POSITIVE FACTOR
+                d = firstterm * Vu
+                derivative = d
+                Vi = Vi + lr * (derivative + lam * np.linalg.norm(Vi))
+                movies[rand_pos].factor = Vi
+
+                #ITEM NEGATIVE FACTOR
+                negvu = -1 * Vu
+                d = firstterm * negvu
+                derivative = d
+                Vj = Vj + lr * (derivative + lam * np.linalg.norm(Vj))
+                movies[rand_neg].factor = Vj
+
+def calculate_first_term(Vu, Vi, Vj):
+    boughtdot = np.dot(Vu, Vi)
+    notboughtdot = np.dot(Vu, Vj)
+    negxuij = (boughtdot - notboughtdot) * -1
+    if negxuij > 500:
+        negxuij = 500
+    numerator = math.exp(negxuij)
+    denominator = 1 + math.exp(negxuij)
+    firstterm = numerator / denominator
+    return firstterm
+

classes.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+from util import random_vector
+class user:
+    def __init__(self, userid):
+        self.userid = userid
+        self.movies_train = dict()
+        self.movies_test = dict()
+        self.movies_all = dict()
+        self.factor = random_vector()
+    
+class movie:
+    def __init__(self, movieid, rating=0, title=None, genres=None):
+        self.movieid = movieid
+        self.rating = rating
+        self.title = title
+        self.genres = genres
+        self.factor = random_vector()
+
+class ret:
+    def __init__(self):
+        self.userid = None
+        self.movieid = None
+        self.isuser = True
+        self.retvalue = []
+    
+class usermovie:
+    def __init__(self):
+        self.userid = None
+        self.movieid = None
+        self.rating = 0
+

filereader.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+from classes import user
+from classes import movie
+from numpy import random
+from util import min_rating, random_vector, num_users
+from random import seed
+import pandas as pd
+import numpy as np
+def read_ratings(filename):
+    seed(42)
+    np.random.seed(42)
+    r_cols = ['user_id', 'movie_id', 'rating', 'timestamp']
+    ratings = pd.read_csv(filename,  sep=',', names=r_cols, encoding='latin-1')
+
+    ratings['user_id'] = ratings['user_id'].astype(int)
+    ratings['movie_id'] = ratings['movie_id'].astype(int)
+    ratings['rating'] = ratings['rating'].astype(float)
+
+    numusers = num_users()
+
+    msks = ratings['user_id'] < numusers
+    ratings = ratings[msks]
+    users = dict()
+    testcount = 0
+    traincount = 0
+    trainuserdict = dict()
+
+    for index, row in ratings.iterrows():
+        userid = int(row['user_id'])
+        movieid = int(row['movie_id'])
+        rating1 = float(row['rating'])
+        minmovierating = min_rating()
+        if rating1 >= minmovierating:
+            if random.random() < 0.7:
+                traincount = traincount + 1
+                if userid in users.keys():
+                    user1 = users[userid]
+                    user1.movies_train[movieid] = rating1
+                else:
+                    user1 = user(userid)
+                    user1.factor = random_vector()
+                    user1.movies_train[movieid] = rating1
+                    users[userid] = user1
+                    trainuserdict[userid] = 1
+            else:
+                testcount = testcount + 1
+                if userid in users.keys():
+                    user1 = users[userid]
+                    user1.movies_test[movieid] = rating1
+                else:
+                    user1 = user(userid)
+                    user1.factor = random_vector()
+                    user1.movies_test[movieid] = rating1
+                    users[userid] = user1
+
+    for index, row in ratings.iterrows():
+        userid = int(row['user_id'])
+        movieid = int(row['movie_id'])
+        rating1 = float(row['rating'])
+        if userid in users.keys():
+            user1 = users[userid]
+            user1.movies_all[movieid] = rating1
+
+    return users
+
+def read_movies(filename):
+    r_cols = ['movie_id', 'title', 'genres']
+    df = pd.read_csv(filename, sep=",", encoding='latin-1', names=r_cols)
+    movies = dict()
+    for index, row in df.iterrows():
+        movieid = row['movie_id']
+        movie1 = movie(movieid, 0)
+        movie1.factor = random_vector()
+        movies[movieid] = movie1
+
+    return movies
+

hitrate.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+from classes import usermovie
+import numpy as np
+from sklearn.metrics import mean_squared_error
+from math import sqrt
+
+def hit_rate(users, movies):
+    hits = 0
+    denom = 0
+    actual = []
+    predicted = []
+    actualall = []
+    predictedall = []
+    for u1 in users:
+        u = users[u1]
+        userid = u.userid
+        usermovies = []
+        if userid in users:
+            denom = denom + 1
+            ufactor = users[userid].factor
+            for m1 in movies:
+                m = movies[m1]
+                mfactor = m.factor
+                dotp = np.dot(ufactor, mfactor)
+                if m.movieid in u.movies_all:
+                    actualall.append(u.movies_all[m.movieid])
+                    predictedall.append(float(dotp))
+
+                if m.movieid in u.movies_test:
+                    actual.append(u.movies_test[m.movieid])
+                    predicted.append(dotp)
+
+                usermovied = usermovie()
+                usermovied.userid = userid
+                usermovied.movieid = m.movieid
+                usermovied.rating = dotp
+                usermovies.append(usermovied)
+
+            usermovies.sort(key=lambda x: x.rating, reverse=True)
+            count = 0
+            for um in usermovies:
+                userid = um.userid
+                movieid = um.movieid
+                #rating = um.rating
+                if movieid in users[userid].movies_test:
+                    hits = hits + 1
+                    break
+                count = count + 1
+                if count > 9:
+                    break
+
+    sortedpredicted = predicted
+    least = min(sortedpredicted)
+    sortedpredicted = [x + least for x in sortedpredicted]
+    sortedpredicted = [x / max(sortedpredicted) for x in sortedpredicted]
+    sortedpredicted = [x * 5 for x in sortedpredicted]
+    predicted = sortedpredicted
+
+    sortedpredicted = predictedall
+    least = min(sortedpredicted)
+    sortedpredicted = [x + least for x in sortedpredicted]
+    sortedpredicted = [x / max(sortedpredicted) for x in sortedpredicted]
+    sortedpredicted = [x * 5 for x in sortedpredicted]
+    predictedall = sortedpredicted
+
+    rms = sqrt(mean_squared_error(actual, predicted))
+    rmsall = sqrt(mean_squared_error(actualall, predictedall))
+
+    return hits, denom, rms, rmsall
+
+def hit_rate_SVD(users, movies, svd):
+    hits = 0
+    denom = 0
+    actual = []
+    predicted = []
+    actualall = []
+    predictedall = []
+    for u1 in users:
+        u = users[u1]
+        userid = u.userid
+        usermovies = []
+        if userid in users:
+            denom = denom + 1
+            for m1 in movies:
+                m = movies[m1]
+                dotp = float(svd.predict(int(userid), int(m.movieid))[3])
+
+                if m.movieid in u.movies_all:
+                    actualall.append(u.movies_all[m.movieid])
+                    predictedall.append(float(dotp))
+
+                if (str(m.movieid) in u.movies_test) | (int(m.movieid) in u.movies_test):
+                    actual.append(u.movies_test[m.movieid])
+                    predicted.append(float(dotp))
+
+                usermovied = usermovie()
+                usermovied.userid = userid
+                usermovied.movieid = m.movieid
+                usermovied.rating = dotp
+                usermovies.append(usermovied)
+
+            usermovies.sort(key=lambda x: x.rating, reverse=True)
+            count = 0
+            for um in usermovies:
+                userid = um.userid
+                movieid = um.movieid
+
+                if (str(movieid) in users[userid].movies_test) | (int(movieid) in users[userid].movies_test):
+                    hits = hits + 1
+                    break
+                count = count + 1
+                if count > 9:
+                    break
+
+    rms = sqrt(mean_squared_error(actual, predicted))
+    rmsall = sqrt(mean_squared_error(actualall, predictedall))
+
+    return hits, denom, rms, rmsall
+

util.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+from numpy import random
+import numpy as np
+
+def num_users():
+    return 1000000
+
+def dimension():
+    return 50
+
+def min_rating():
+    return 4
+
+def learning_rate():
+    return 1
+
+def get_lambda():
+    return 0.1
+
+def random_vector():
+    dim = dimension()
+    cov_mtx = cov_matrix()
+    return random.multivariate_normal(np.zeros(dim), cov_mtx)
+
+def cov_matrix():
+    dim = dimension()
+    cov = np.zeros((dim, dim), dtype=float)
+    for i in range(dim):
+        cov[i][i] = 0.1
+    return cov
+
+def m_normal(mean):
+    cov_mtx = cov_matrix()
+    return random.multivariate_normal(mean=mean, cov=cov_mtx)
+