def plot_distance(data):
comb = combinations(data.keys(), 2)
all_dist = {
str(p1) + ':' + str(p2): sim_distance(data, p1, p2)
for p1, p2 in comb
}
S = Series(all_dist)
S = S.sort_values(ascending=False)
x_num = np.arange(len(S))
ax = S.plot()
ax.set_xticks(x_num)
ax.set_xticklabels(S.index, rotation=90, ha='center', va='top')
myfont = fm.FontProperties(fname=r'C:\Windows\Fonts\msyh.ttc')
ax.set_title('共同爱好程度', fontproperties=myfont)
ax.set_xlabel('相关度', fontproperties=myfont)
ax.set_xlabel('人物关系', fontproperties=myfont)
ax.legend(('皮尔逊相关度', ), prop=myfont)
plt.subplots_adjust(bottom=0.5)
return S
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 23 07:49:55 2017
@author: andres
"""
from recommendations import critics
from recommendations import sim_distance
from recommendations import sim_pearson
for p in critics:
print(p)
#Testing simdistance
sim_distance(critics, 'Lisa Rose', 'Gene Seymour')
sim_pearson(critics, 'Lisa Rose', 'Gene Seymour')
def test_DistEuclidiana(self):
self.assertEqual(
recommendations.sim_distance(recommendations.critics, 'Lisa Rose',
'Gene Seymour'), 0.14814814814814814)
def test_sim_distance_no_common_films(self):
distance = rec.sim_distance(self.prefs, 'fulano', 'sicrano')
self.assertEqual(distance, 0)
#import pydelicious
#pydelicious.get_popular(tag='programming')
#from deliciousrec import *
#delusers=initializeUserDict('programming')
#delusers['tsegaran']={}
#fillIteams(delusers)
import recommendations
#print recommendations.critics['Lisa Rose']['Lady in the Water']
print recommendations.critics['Lisa Rose']
print recommendations.critics['Gene Seymour']
print recommendations.sim_distance(recommendations.critics,'Lisa Rose','Gene Seymour')
print recommendations.sim_pearson(recommendations.critics,'Lisa Rose','Gene Seymour')
print recommendations.topMatches(recommendations.critics,'Toby',n=3)
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')
#!/usr/bin/env python # -*- coding: utf-8 -*- # @Time : 2017/2/26 16:19 # @Author : Shuqi.qin # @Site : # @File : test.py # @Software: PyCharm import recommendations as rc res1 = rc.sim_distance(rc.critics, "Lisa Rose", "Gene Seymour") res2 = rc.sim_pearson(rc.critics, "Lisa Rose", "Gene Seymour") res3 = rc.topMatches(rc.critics, "Toby", n=3) res4 = rc.getRecommendationsBaseOnPersonSimilarity(rc.critics, "Toby") print 'over' import pydelicious print pydelicious.get_popular(tag='programming')
def testSimDistanceForDifferentRatings(self): actual = recommendations.sim_distance(self.ratings, 'joe', 'jeff') self.assertEqual(0.5, actual)
return tag_map
if __name__ == '__main__':
# stupid little demo
import recommendations
print 'getting users...'
users = initializeUserDict('programming')
users['thakis'] = {}
users['ytamshg'] = {}
users['tubanator'] = {}
print 'getting their posts (takes a while) ...'
fillItems(users)
print 'Distances:'
print recommendations.sim_distance(users, 'thakis', 'ytamshg')
print recommendations.sim_distance(users, 'thakis', 'tubanator')
print recommendations.sim_distance(users, 'tubanator', 'ytamshg')
print 'Pearsons:'
print recommendations.sim_pearson(users, 'thakis', 'ytamshg')
print recommendations.sim_pearson(users, 'thakis', 'tubanator')
print recommendations.sim_pearson(users, 'tubanator', 'ytamshg')
print 'Recommendations:'
print recommendations.getRecommendations(users, 'thakis')[0:10]
print recommendations.getRecommendations(users, 'ytamshg')[0:10]
print recommendations.getRecommendations(users, 'tubanator')[0:10]
#!/usr/bin/env python
# coding=utf-8
# filename : recommendations_test.py
# author : Chase
# update : 2016/09/10
import recommendations
print("distance between Leo and Cathy is:",
recommendations.sim_distance(recommendations.critics, 'Leo', 'Cathy'))
print("distance between Susie and Cathy is:",
recommendations.sim_distance(recommendations.critics, 'Susie', 'Cathy'))
print("Antonio TopMatches:",
recommendations.topMatches(recommendations.critics, 'Antonio', n=3))
print("Leo's recommendations:",
recommendations.getRecommendations(recommendations.critics, 'Leo'))
import recommendations
#@todo сделать вывод в виде таблицы
for item in recommendations.critics :
print(item)
for value in recommendations.critics :
if item == value : continue
print(value)
result = recommendations.sim_distance(recommendations.critics, item, value)
print(result)
def get_similarity_data(
prefs, other_id
): # This function is part of the multi-threading process for the above.
return [other_id, r.sim_distance(prefs, str(sub_id), str(other_id))]
import recommendations
#@todo сделать вывод в виде таблицы
for item in recommendations.critics:
print(item)
for value in recommendations.critics:
if item == value: continue
print(value)
result = recommendations.sim_distance(recommendations.critics, item,
value)
print(result)
''' Created on 2015-6-12 @author: XXYF18 ''' from recommendations import critics,sim_distance,sim_pearson,topMatches,getRecommendations #critics['Lisa Rose']['Lady in the Water'] # #critics['Toby']['Snakes on a Plane']=4.5 #critics['Toby'] import pydelicious pydelicious.get_popular(tag='programming') print sim_distance(critics, 'Lisa Rose','Gene Seymour') print sim_pearson(critics,'Lisa Rose','Gene Seymour') print topMatches(critics,'Toby',n=3) print getRecommendations(critics,'Toby') print getRecommendations(critics,'Toby', similarity=sim_distance)
if __name__ == '__main__':
# stupid little demo
import recommendations
print 'getting users...'
users = initializeUserDict('programming')
users['thakis'] = {}
users['ytamshg'] = {}
users['tubanator'] = {}
print 'getting their posts (takes a while) ...'
fillItems(users)
print 'Distances:'
print recommendations.sim_distance(users, 'thakis', 'ytamshg')
print recommendations.sim_distance(users, 'thakis', 'tubanator')
print recommendations.sim_distance(users, 'tubanator', 'ytamshg')
print 'Pearsons:'
print recommendations.sim_pearson(users, 'thakis', 'ytamshg')
print recommendations.sim_pearson(users, 'thakis', 'tubanator')
print recommendations.sim_pearson(users, 'tubanator', 'ytamshg')
print 'Recommendations:'
print recommendations.getRecommendations(users, 'thakis')[0:10]
print recommendations.getRecommendations(users, 'ytamshg')[0:10]
print recommendations.getRecommendations(users, 'tubanator')[0:10]
# encoding: utf-8 ''' Created on 2015年7月19日 @author: HCY ''' from recommendations import critics, sim_distance, sim_pearson import recommendations #print(critics['Lisa Rose']['Lady in the Water']) print(critics['Hcy']) print(recommendations.sim_distance(critics, 'Lisa Rose', 'Gene Seymour')) print(recommendations.sim_pearson(critics, 'Lisa Rose', 'Gene Seymour')) print(recommendations.topMatches(critics, 'Hcy',n=3,similarity=sim_pearson)) print(recommendations.topMatches(critics, 'Hcy',n=3,similarity=sim_distance)) print(recommendations.getRecommendations(critics, 'Hcy'))
import recommendations
import operator
rating_distance = {}
for person1 in recommendations.critics:
ratings = {}
for person2 in recommendations.critics:
if person1 != person2:
print(person1 + ', ' + person2)
ratings.update({
person2:
recommendations.sim_distance(recommendations.critics, person1,
person2)
})
rating_distance.update({person1: ratings})
#rating_distance.sort()
print(rating_distance)
#sort the distance by closest to 1 first.
#show the closest related person to each person.
closest_person = []
for person in rating_distance.keys():
sorted_distance = sorted(rating_distance.get(person).items(),
key=operator.itemgetter(1),
reverse=True)
closest_person.append({person: sorted_distance[0]})
print(closest_person)
from recommendations import critics
from recommendations import sim_distance
from recommendations import sim_pearson
from recommendations import pearsonTopMatches
from recommendations import distanceTopMatches
from recommendations import getRecommendations
print(critics['Lisa Rose']['Lady in the Water'])
critics['Toby']['Snakes on a Plane'] = 5.0
print(critics['Toby'])
result = {
'euclidean distance socre': sim_distance(critics, 'Lisa Rose',
'Gene Seymour')
}
print(result)
result = {
'Pearson correlation score': sim_pearson(critics, 'Lisa Rose',
'Gene Seymour')
}
print(result)
print(distanceTopMatches(critics, 'Toby', n=3))
print(pearsonTopMatches(critics, 'Toby', n=3))
print('-------------------------------------')
print(getRecommendations(critics, 'Toby'))
print('-------------------------------------')
print('-------------------------------------')
print(getRecommendations(critics, 'Toby', similarity=sim_distance))
# Split prefs into train and test prefs
movies = prefs.keys()
random.shuffle(movies)
movies_train, movies_test = movies[:int(0.9 * len(movies))], movies[int(0.1 * len(movies)):]
train = {m: prefs[m] for m in movies_train}
test = {m: prefs[m] for m in movies_test}
for movie in test:
sim_distances = []
sim_pearsons = []
for other_movie in train:
# Calculate distance using euclidean distance
sim_distances.append((r.sim_distance(prefs, movie, other_movie), other_movie))
# Calculate similarity using pearson
sim_pearsons.append((r.sim_pearson(prefs, movie, other_movie), other_movie))
# distance sort ascending
sim_distances.sort()
# similarity sort descending
sim_pearsons.sort(reverse=True)
# select 1st top of the list
sim_most_related_movie = sim_distances[0][1]
pear_most_related_movie = sim_pearsons[0][1]
# Compare
print 'Using euclidean distance : Actual movie = {}, Predicted movie = {}'.format(movie, sim_most_related_movie)
print 'Using pearson similarity : Actual movie = {}, Predicted movie = {}'.format(movie, pear_most_related_movie)
def test_DistEuclidiana(self):
self.assertEqual(recommendations.sim_distance(recommendations.critics, 'Lisa Rose','Gene Seymour'), 0.14814814814814814)
def testSimDistanceForSameRatings(self): self.ratings['jeff']['Ford'] = 1 actual = recommendations.sim_distance(self.ratings, 'joe', 'jeff') self.assertEqual(1, actual)
import recommendations print "distance" print recommendations.sim_distance(recommendations.critics, 'ming', 'lin') print recommendations.sim_distance(recommendations.critics, 'ming', 'michael') print recommendations.sim_distance(recommendations.critics, 'ming', 'mick') print "pearson" print recommendations.sim_pearson(recommendations.critics, 'ming', 'lin') print recommendations.sim_pearson(recommendations.critics, 'ming', 'michael') print recommendations.sim_pearson(recommendations.critics, 'ming', 'mick') print "top match" print recommendations.topMatches(recommendations.critics, 'ming', n = 3) print "recommendation" print recommendations.getRecommendations(recommendations.critics, 'ming') print "recommend items" items = recommendations.transformPrefs(recommendations.critics) print recommendations.topMatches(items, 'lady in the water', n =3) print recommendations.sim_pearson(items, 'lady in the water', 'snake on a plane') print "item similarity use distance" print recommendations.calculateSimilarItems(recommendations.critics) print 'item similarity use pearson' print recommendations.calculateSimilarItems(recommendations.critics, similarity = recommendations.sim_pearson) print 'recommendation base on items' itemsim = recommendations.calculateSimilarItems(recommendations.critics)
# don't compare me to myself
if other == person: continue
sim = similarity(prefs, person, other)
# ignore scores of zero or lower
if sim <= 0: continue
for item in prefs[other]:
# only score movies I haven't seen yet
if item not in prefs[person] or prefs[person][item] == 0:
# Similarity * Score
totals.setdefault(item, 0)
totals[item] += prefs[other][item] * sim
# Sum of similarities
simSums.setdefault(item, 0)
simSums[item] += sim
# Create the normalized list
rankings = [(total / simSums[item], item) for item, total in totals.items()]
# Return the sorted list
rankings.sort()
rankings.reverse()
return rankings
if __name__ == '__main__':
d = sim_distance(critics, 'Lisa Rose', 'Claudia Puig')
print d
d = getRecommendations(critics,'Toby')
print d
import recommendations
reload(recommendations)
# Finds distances for all critics:
distances = []
for p1 in critics:
for p2 in critics:
if p1 != p2:
distances.append((recommendations.sim_distance(recommendations.critics, p1, p2), p1, p2))
distances.sort()
distances.reverse()
distances
###########################
reload(recommendations)
recommendations.sim_distance(recommendations.critics, 'Lisa Rose','Gene Seymour')
recommendations.sim_pearson(recommendations.critics, 'Lisa Rose','Gene Seymour')
recommendations.topMatches(recommendations.critics,'Toby', n = 3)
######################################################
# del.icio.us:
######################################################
delusers = deliciousrec.initializeUserDict('gratis')
delusers['lpagliari'] = {} # Add yourself to the dictionary if you use delicious
deliciousrec.fillItems(delusers)
delusers
###########################
# pick random user and find users similar to him/her:
#!/usr/bin/env python from math import sqrt # Euclidean distance euclidean_distance = sqrt(pow(5-4,2)+pow(4-1,2)) print euclidean_distance # avoid zero divide inversed_ed = 1/(1+sqrt(pow(5-4,2)+pow(4-1,2))) print inversed_ed import recommendations sim_distance_result = recommendations.sim_distance( recommendations.critics, 'Lisa Rose', 'Gene Seymour' ) print sim_distance_result
def test_sim_distance(self):
distance = rec.sim_distance(self.prefs, 'fulano', 'beltrano')
self.assertAlmostEqual(distance, 0.47516409872148213)