def main():
prefs = r.loadMovieLens(
os.getcwd() +
"/ml-100k") # Calculates the preferences using recommendations.py
movie_recommendations = r.getRecommendations(
prefs, str(sub_id)) # Calculates all recommendations for sub user.
print("\nThe most recommended movies for " + get_user(sub_id) +
" (which is the substitute) are:")
for i in range(
5): # This section prints out the recommendations for sub user.
u = movie_recommendations[i][1]
print(u)
print("\nThe least recommended movies for the substitute are: ")
for i in range(5):
u = movie_recommendations[len(movie_recommendations) - (i + 1)][1]
print(u)
similiar_item_data = r.calculateSimilarItems(
prefs) # Calculate all similar movie data.
print("\nFive similar movies to my favorite movie " + favorite_movie +
" are:")
fav_mov_sim = similiar_item_data[favorite_movie][
0:5] # For real me, some recommended movies for my preferences.
for mov in fav_mov_sim:
print(mov[1] + " " + str(mov[0]))
print("\nFive similar movies to my least favorite movie " +
least_favorite_movie + " are:")
lea_fav_mov_sim = similiar_item_data[least_favorite_movie][0:5]
for mov in lea_fav_mov_sim:
print(mov[1] + " " + str(mov[0]))
def get_most_and_least_similar_users():
"""
Calculates users that are similar to the substitute user from problem one. Early on, I noticed that the program
took a while to execute, so I multi-threaded the sim_distance function to expedite execution.
:return:
Prints out data on the top five most similar and least similar users to the substitute user.
"""
pool = mp.Pool(mp.cpu_count())
prefs = r.loadMovieLens(os.getcwd() + "/ml-100k")
similarity_data = [
pool.apply(get_similarity_data, args=(prefs, other_id + 1))
for other_id in range(943)
]
pool.close()
similarity_data = sorted(similarity_data, key=lambda x: x[1])
print("The most similar users to " + get_user(sub_id) +
" (which is the substitute) are:")
for i in range(5):
u = get_user(similarity_data[len(similarity_data) - (i + 1)][0])
print(u)
print("\nThe least similar users are: ")
for i in range(5):
u = get_user(similarity_data[i][0]).split("\n")[0]
print(u)
def main():
check_ids = find_similar_users()
lens_data = recommendations.loadMovieLens()
substitute_me = '645'
find_favorite_movies(check_ids, lens_data)
find_least_favorite_movies(check_ids, lens_data)
find_correlated_users_subsitute(substitute_me, lens_data)
find_least_correlated_users_subsitute(substitute_me, lens_data)
get_top_recomendations(substitute_me,lens_data)
get_worst_recomendations(substitute_me, lens_data)
find_corerelated_films(lens_data)
def main():
results = {}
resultsOfloadMovieLens = recommendations.loadMovieLens()
uniqueValues = resultsOfloadMovieLens.keys()
length = len(resultsOfloadMovieLens)
for key in range(0,length):
resultsOftopMatches = recommendations.topMatches(resultsOfloadMovieLens,uniqueValues[key],n=length)
for value in resultsOftopMatches:
if value[1] == uniqueValues[key]:
pass
for key, value in sorted(results.items(), key=lambda e: e[1], reverse=True):
print key, results[key]
def main():
count = "Top Gun (1986)"
resultsOfloadMovieLens = recommendations.loadMovieLens()
resultsOfcalculateSimilarItems = recommendations.calculateSimilarItems(resultsOfloadMovieLens, n=80)
print "*" * 60
print "Movies received ratings most like or least like Top Gun"
print "*" * 60
print "value\t\t\t\t\t", "Movie Name"
print "-" * 60
for key, value in sorted(resultsOfcalculateSimilarItems.items(), key=lambda e: e[1], reverse=True):
variable = key
if count == variable:
for value, movie in value:
print value, movie
def main():
count = 'Top Gun (1986)'
resultsOfloadMovieLens = recommendations.loadMovieLens()
resultsOfcalculateSimilarItems = recommendations.calculateSimilarItems(resultsOfloadMovieLens,n=80)
print "*" * 60
print "Movies received ratings most like or least like Top Gun"
print "*" * 60
print "value\t\t\t\t\t","Movie Name"
print "-" * 60
for key, value in sorted(resultsOfcalculateSimilarItems.items(), key=lambda e: e[1], reverse=True):
variable = key
if (count == variable):
for value , movie in value:
print value , movie
def main():
results = {}
resultsOfloadMovieLens = recommendations.loadMovieLens()
uniqueValues = resultsOfloadMovieLens.keys()
length = len(resultsOfloadMovieLens)
for key in range(0, length):
resultsOftopMatches = recommendations.topMatches(
resultsOfloadMovieLens, uniqueValues[key], n=length)
for value in resultsOftopMatches:
if value[1] == uniqueValues[key]:
pass
for key, value in sorted(results.items(), key=lambda e: e[1],
reverse=True):
print key, results[key]
# Valentina Neblitt-Jones
# CS 595 Introduction to Web Science
# Fall 2013
# Assignment #8 Question #5
# What movie received ratings most like Top Gun? Which movie received ratings that were least like Top Gun (negative correlation)?
import sys
import pprint
sys.path.insert(0, '/Users/vneblitt/Documents/cs595-f13/assignment08/library')
import recommendations
g = open('topgun.txt', 'w')
prefs = recommendations.loadMovieLens(path='/Users/vneblitt/Documents/cs595-f13/assignment08/dataset')
answer = recommendations.calculateSimilarItems(prefs,n=1664)
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(answer['Top Gun (1986)'])
g.write(str(answer))
g.close()
print recommendations.topMatches(recommendations.critics,'Toby',n=3,similarity=recommendations.sim_distance) recommendations.getRecommendations(recommendations.critics,'Toby') recommendations.getRecommendations(recommendations.critics,'Toby',similarity=recommendations.sim_distance) movies=recommendations.transformPrefs(recommendations.critics) #print movies recommendations.topMatches(movies,'Superman Returns') recommendations.getRecommendations(movies,'Just My Luck') recommendations.getRecommendations(movies,'Lady in the Water') itemsim=recommendations.calculateSimilarItems(recommendations.critics,n=8) itemsim recommendations.getRecommendedItems(recommendations.critics,itemsim,'Toby') prefs=recommendations.loadMovieLens() prefs['87'] recommendations.getRecommendations(prefs,'87')[0:30] itemsim1=recommendations.calculateSimilarItems(prefs,n=50) recommendations.getRecommendedItems(prefs,itemsim1,'87')[0:30]
import recommendations as rec
pref = rec.loadMovieLens()
correlated = rec.topMatches(1, pref, '73')
noncorrelated = rec.topMatches(0, pref, '73')
print "Five Most Correlated Users: " + '73'
print "--------------------------------------------------------"
for user in correlated:
print user[1]
print "--------------------------------------------------------"
print "Five Least Correlated Users: " + '73'
print "--------------------------------------------------------"
for user in noncorrelated:
print user[1]
#
from appdata import AppData
import recommendations as rec
import sys
import pickle
if __name__ == '__main__':
prefs = rec.loadMovieLens('../data/movielens-100k')
itemPrefs=rec.transformPrefs(prefs)
try:
input = open('itemNeighbours.pkl', 'rb')
itemNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating itemNeighbours.pkl"
itemNeighbours = rec.calcNarestNeighbours(prefs, 10)
output = open('itemNeighbours.pkl', 'wb')
pickle.dump(itemNeighbours, output)
output.close()
try:
input = open('userNeighbours.pkl', 'rb')
userNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating userNeighbours.pkl"
userNeighbours = rec.calcNarestNeighbours(itemPrefs, 10)
output = open('userNeighbours.pkl', 'wb')
pickle.dump(userNeighbours, output)
output.close()
#!/usr/local/bin/python
import sys
import recommendations
if __name__ == '__main__':
fav_moviename = "Die Hard (1988)"
hate_moviename = "Kazaam (1996)"
prefs = recommendations.loadMovieLens()
itemPrefs = recommendations.transformPrefs(prefs)
fav_results = recommendations.topMatches(itemPrefs,fav_moviename,2000)
hate_results = recommendations.topMatches(itemPrefs,hate_moviename,2000)
print "Most 5 correlated for my top favourite movie"
for i in fav_results[0:5]:
print i[0],i[1]
print '\n'
print "Least 5 correlated for my top favourite movie"
fav_results.reverse()
for i in fav_results[0:5]:
print i[0],i[1]
print '\n'
print "Most 5 correlated for my least favourite movie"
for i in hate_results[0:5]:
print i[0],i[1]
print '\n'
print "Least 5 correlated for my least favourite movie"
hate_results.reverse()
for i in hate_results[0:5]:
print i[0],i[1]
#
from appdata import AppData
import recommendations as rec
import sys
import pickle
if __name__ == '__main__':
prefs = rec.loadMovieLens('../data/movielens-100k')
itemPrefs = rec.transformPrefs(prefs)
try:
input = open('itemNeighbours.pkl', 'rb')
itemNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating itemNeighbours.pkl"
itemNeighbours = rec.calcNarestNeighbours(prefs, 10)
output = open('itemNeighbours.pkl', 'wb')
pickle.dump(itemNeighbours, output)
output.close()
try:
input = open('userNeighbours.pkl', 'rb')
userNeighbours = pickle.load(input)
input.close()
except Exception, e:
print "Calculating userNeighbours.pkl"
userNeighbours = rec.calcNarestNeighbours(itemPrefs, 10)
output = open('userNeighbours.pkl', 'wb')
pickle.dump(userNeighbours, output)
output.close()
def __init__(self):
#userId为数据集中的用户ID，类型为str。maxNum为想要的推荐电影数量。
self.userId = ''
self.maxNum = 0
self.resultList = []
self.prefs = recommendations.loadMovieLens()
#!/usr/local/bin/python
import sys
import pprint
sys.path.insert(0, '../starter-code')
import recommendations
if __name__ == '__main__':
film = sys.argv[1]
threshold = int(sys.argv[2])
direction = sys.argv[3]
prefs = recommendations.loadMovieLens('../data')
result = recommendations.calculateSimilarItems(prefs, n=1682)
if direction == 'most':
print "Movies most like '" + film + "': '"
for i in range(0, threshold):
print result[film][i][1] + ' (' + str(result[film][i][0]) + ')'
else:
print "Movies least like '" + film + "': '"
for i in range(1, threshold):
print result[film][-i][1] + ' (' + str(result[film][-i][0]) + ')'
import recommendations as rec
prefs = rec.loadMovieLens("../data/ml-100k")
def getTopAndBottomCorrelated(movie_info, movie):
m = movie_info[movie]
top = m[:5]
bottom = m[len(m) - 5 :]
bottom.reverse()
return top, bottom
movies_info = rec.calculateSimilarItems(prefs, n=2000, best=True)
best_movie = "Stargate (1994)"
worst_movie = "Batman Forever (1995)"
table = open("../docs/q4_table.tex", "w")
table.write("My favorite film from the data is: " + best_movie + "\n\n")
top, bottom = getTopAndBottomCorrelated(movies_info, best_movie)
table.write("The top 5 most correlated are:\n\n")
table.write("\\begin{longtable}{| c | c | c |}\n")
table.write("\\hline\n")
table.write("Position & Movie & Similarity\\\\\n")
count = 1
for l in top:
table.write("\\hline\n {} & {} & {:.3f}\\\\\n".format(count, l[1], l[0]))
count += 1
table.write("\\hline\n")
table.write("\\caption{Top 5 correlated to favorite movie}\n")
def load_directory(self, dir):
self.prefs = recommendations.loadMovieLens(dir)
def __init__(self):
#userId为数据集中的用户ID，类型为str。maxNum为想要的推荐电影数量。
self.userId = ''
self.maxNum = 0
self.resultList = []
self.prefs = recommendations.loadMovieLens()