数据挖掘实践指南读书笔记1

原创

mb5fe55c8710ded 2020-12-28 16:42:48 ©著作权

©著作权归作者所有：来自51CTO博客作者mb5fe55c8710ded的原创作品，请联系作者获取转载授权，否则将追究法律责任

写在之前

本书涉及的源程序和数据都可以在以下网站中找到：http://guidetodatamining.com/ 这本书理论比较简单，书中错误较少，动手锻炼较多，如果每个代码都自己写出来，收获不少。总结：适合入门。欢迎转载，转载请注明出处，如有问题欢迎指正。合集地址：https://www.zybuluo.com/hainingwyx/note/559139

协同过滤

相似用户评判标准：曼哈顿距离、欧氏距离、明氏距离。

# Manhattan.py
users = {
"Angelica": {"Blues Traveler": 3.5, "Broken Bells": 2.0, "Norah Jones": 4.5,
"Phoenix": 5.0, "Slightly Stoopid": 1.5, "The Strokes": 2.5,
"Vampire Weekend": 2.0},
"Bill":{"Blues Traveler": 2.0, "Broken Bells": 3.5, "Deadmau5": 4.0,
"Phoenix": 2.0,"Slightly Stoopid": 3.5, "Vampire Weekend": 3.0},
"Chan": {"Blues Traveler": 5.0, "Broken Bells": 1.0, "Deadmau5": 1.0,
"Norah Jones": 3.0, "Phoenix": 5, "Slightly Stoopid": 1.0},
"Dan": {"Blues Traveler": 3.0, "Broken Bells": 4.0, "Deadmau5": 4.5,
"Phoenix": 3.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0,
"Vampire Weekend": 2.0},
"Hailey": {"Broken Bells": 4.0, "Deadmau5": 1.0, "Norah Jones": 4.0,
"The Strokes": 4.0, "Vampire Weekend": 1.0},
"Jordyn": {"Broken Bells": 4.5, "Deadmau5": 4.0, "Norah Jones": 5.0,
"Phoenix": 5.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0,
"Vampire Weekend": 4.0},
"Sam": {"Blues Traveler": 5.0, "Broken Bells": 2.0, "Norah Jones": 3.0,
"Phoenix": 5.0, "Slightly Stoopid": 4.0, "The Strokes": 5.0},
"Veronica": {"Blues Traveler": 3.0, "Norah Jones": 5.0, "Phoenix": 4.0,
"Slightly Stoopid": 2.5, "The Strokes": 3.0}
}
def manhattan(rating1, rating2):
"""Computes the Manhattan distance. Both rating1 and rating2 are dictionaries
of the form {'The Strokes': 3.0, 'Slightly Stoopid': 2.5}"""
distance = 0
commonRatings = False
for key in rating1:
if key in rating2:
distance += abs(rating1[key] - rating2[key])
commonRatings = True
if commonRatings:
return distance
else:
return -1 #Indicates no ratings in common
def computeNearestNeighbor(username, users):
"""creates a sorted list of users based on their distance to username"""
distances = []
for user in users:
if user != username:
distance = manhattan(users[user], users[username])
distances.append((distance, user))
# sort based on distance -- closest first
distances.sort()
return distances
def recommend(username, users):
"""Give list of recommendations"""
# first find nearest neighbor
nearest = computeNearestNeighbor(username, users)[0][1]
print nearest
recommendations = []
# now find bands neighbor rated that user didn't
neighborRatings = users[nearest]
userRatings = users[username]
for artist in neighborRatings:
if not artist in userRatings:
recommendations.append((artist, neighborRatings[artist]))
# using the fn sorted for variety - sort is more efficient
return sorted(recommendations, key=lambda artistTuple: artistTuple[1], reverse = True)

# -*- coding: utf-8 -*-
from math import sqrt
users = {"Angelica": {"Blues Traveler": 3.5, "Broken Bells": 2.0, "Norah Jones": 4.5, "Phoenix": 5.0, "Slightly Stoopid": 1.5, "The Strokes": 2.5, "Vampire Weekend": 2.0},
"Bill":{"Blues Traveler": 2.0, "Broken Bells": 3.5, "Deadmau5": 4.0, "Phoenix": 2.0, "Slightly Stoopid": 3.5, "Vampire Weekend": 3.0},
"Chan": {"Blues Traveler": 5.0, "Broken Bells": 1.0, "Deadmau5": 1.0, "Norah Jones": 3.0, "Phoenix": 5, "Slightly Stoopid": 1.0},
"Dan": {"Blues Traveler": 3.0, "Broken Bells": 4.0, "Deadmau5": 4.5, "Phoenix": 3.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0, "Vampire Weekend": 2.0},
"Hailey": {"Broken Bells": 4.0, "Deadmau5": 1.0, "Norah Jones": 4.0, "The Strokes": 4.0, "Vampire Weekend": 1.0},
"Jordyn": {"Broken Bells": 4.5, "Deadmau5": 4.0, "Norah Jones": 5.0, "Phoenix": 5.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0, "Vampire Weekend": 4.0},
"Sam": {"Blues Traveler": 5.0, "Broken Bells": 2.0, "Norah Jones": 3.0, "Phoenix": 5.0, "Slightly Stoopid": 4.0, "The Strokes": 5.0},
"Veronica": {"Blues Traveler": 3.0, "Norah Jones": 5.0, "Phoenix": 4.0, "Slightly Stoopid": 2.5, "The Strokes": 3.0}
}
#明氏距离
def minkowski(rating1,rating2,r):
distance=0
commonRatings=False
for key in rating1:
if key in rating2:
distance += pow(abs(rating1[key]-rating2[key]),r)
commonRatings=True
distance = pow(distance,1.0/r)
if commonRatings:
return distance
else:
return -1 #Indicates no ratings in common
def computeNearestNeighbor(username, users):
"""creates a sorted list of users based on their distance to username"""
distances = []
for user in users:
if user != username:
distance = minkowski(users[user], users[username],3)
distances.append((distance, user))
# sort based on distance -- closest first
distances.sort()
return distances
def recommend(username, users):
"""Give list of recommendations"""
# first find nearest neighbor
nearest = computeNearestNeighbor(username, users)[0][1]
print nearest
recommendations = []
# now find bands neighbor rated that user didn't
neighborRatings = users[nearest]
userRatings = users[username]
for artist in neighborRatings:
if not artist in userRatings:
recommendations.append((artist, neighborRatings[artist]))
# using the fn sorted for variety - sort is more efficient
return sorted(recommendations, key=lambda artistTuple: artistTuple[1], reverse = True)

但是可能存在常数差别，但是两者爱好相同的问题。皮尔逊相关系数：

# Pearson.py
from math import sqrt
users = {"Angelica": {"Blues Traveler": 3.5, "Broken Bells": 2.0, "Norah Jones": 4.5, "Phoenix": 5.0, "Slightly Stoopid": 1.5, "The Strokes": 2.5, "Vampire Weekend": 2.0},
"Bill":{"Blues Traveler": 2.0, "Broken Bells": 3.5, "Deadmau5": 4.0, "Phoenix": 2.0, "Slightly Stoopid": 3.5, "Vampire Weekend": 3.0},
"Chan": {"Blues Traveler": 5.0, "Broken Bells": 1.0, "Deadmau5": 1.0, "Norah Jones": 3.0, "Phoenix": 5, "Slightly Stoopid": 1.0},
"Dan": {"Blues Traveler": 3.0, "Broken Bells": 4.0, "Deadmau5": 4.5, "Phoenix": 3.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0, "Vampire Weekend": 2.0},
"Hailey": {"Broken Bells": 4.0, "Deadmau5": 1.0, "Norah Jones": 4.0, "The Strokes": 4.0, "Vampire Weekend": 1.0},
"Jordyn": {"Broken Bells": 4.5, "Deadmau5": 4.0, "Norah Jones": 5.0, "Phoenix": 5.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0, "Vampire Weekend": 4.0},
"Sam": {"Blues Traveler": 5.0, "Broken Bells": 2.0, "Norah Jones": 3.0, "Phoenix": 5.0, "Slightly Stoopid": 4.0, "The Strokes": 5.0},
"Veronica": {"Blues Traveler": 3.0, "Norah Jones": 5.0, "Phoenix": 4.0, "Slightly Stoopid": 2.5, "The Strokes": 3.0}
}
# 这里为了简单使用近似代替
def pearson(rating1,rating2):
sum_xy=0
sum_x=0
sum_y=0
sum_x2=0
sum_y2=0
n=0
for key in rating1:
if key in rating2:
n += 1
x = rating1[key]
y = rating2[key]
sum_xy += x*y
sum_x += x
sum_y += y
sum_x2 += x**2
sum_y2 += y**2
denominnator = sqrt(sum_x2-(sum_x**2)/n)*sqrt(sum_y2-(sum_y**2)/n)
if denominnator == 0:
return 0
else:
return (sum_xy-(sum_x*sum_y)/n)/denominnator
def cos_like(rating1,rating2):
innerProd=0
vector_x=0
vectoy_y=0
for key in rating1:
if key in rating2:
x=rating1[key]
y=rating2[key]
innerProd += x*y
vector_x += x**2
vectoy_y += y**2
denominnator = sqrt(vector_x) * sqrt(vectoy_y)
if denominnator == 0:
return 0
else:
return innerProd / denominnator

余弦相似度：$$cos(x, y)=\frac{x·y}{||x||\times ||y||}$$ 总结：如果数据稠密使用欧氏距离；如果数据稀疏，使用余弦相似度；如果用户评级范围不同，使用皮尔逊相关系数。但是如果仅仅是基于一个用户进行推荐，个别用户的怪癖也会被推荐。

k近邻：利用k个最相似的用户确定推荐结果，K和应有有关。利用皮尔逊系数来确定每个人的影响因子。

# A dictionary of movie critics and their ratings of a small
# set of movies
critics={'Lisa Rose': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
'Just My Luck': 3.0, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5,
'The Night Listener': 3.0},
'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5,
'Just My Luck': 1.5, 'Superman Returns': 5.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 3.5},
'Michael Phillips': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.0,
'Superman Returns': 3.5, 'The Night Listener': 4.0},
'Claudia Puig': {'Snakes on a Plane': 3.5, 'Just My Luck': 3.0,
'The Night Listener': 4.5, 'Superman Returns': 4.0,
'You, Me and Dupree': 2.5},
'Mick LaSalle': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'Just My Luck': 2.0, 'Superman Returns': 3.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 2.0},
'Jack Matthews': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'The Night Listener': 3.0, 'Superman Returns': 5.0, 'You, Me and Dupree': 3.5},
'Toby': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0,'Superman Returns':4.0}}
from math import sqrt
# Returns a distance-based similarity score for person1 and person2
def sim_distance(prefs,person1,person2):
# Get the list of shared_items
si={}
for item in prefs[person1]:
if item in prefs[person2]: si[item]=1
# if they have no ratings in common, return 0
if len(si)==0: return 0
# Add up the squares of all the differences
sum_of_squares=sum([pow(prefs[person1][item]-prefs[person2][item],2)
for item in prefs[person1] if item in prefs[person2]])
return 1/(1+sum_of_squares)
# Returns the Pearson correlation coefficient for p1 and p2
def sim_pearson(prefs,p1,p2):
# Get the list of mutually rated items
si={}
for item in prefs[p1]:
if item in prefs[p2]: si[item]=1
# if they are no ratings in common, return 0
if len(si)==0: return 0
# Sum calculations
n=len(si)
# Sums of all the preferences
sum1=sum([prefs[p1][it] for it in si])
sum2=sum([prefs[p2][it] for it in si])
# Sums of the squares
sum1Sq=sum([pow(prefs[p1][it],2) for it in si])
sum2Sq=sum([pow(prefs[p2][it],2) for it in si])
# Sum of the products
pSum=sum([prefs[p1][it]*prefs[p2][it] for it in si])
# Calculate r (Pearson score)
num=pSum-(sum1*sum2/n)
den=sqrt((sum1Sq-pow(sum1,2)/n)*(sum2Sq-pow(sum2,2)/n))
if den==0: return 0
r=num/den
return r
# Returns the best matches for person from the prefs dictionary.
# Number of results and similarity function are optional params.
def topMatches(prefs,person,n=5,similarity=sim_pearson):
scores=[(similarity(prefs,person,other),other)
for other in prefs if other!=person]
scores.sort()
scores.reverse()
return scores[0:n]
# Gets recommendations for a person by using a weighted average
# of every other user's rankings
def getRecommendations(prefs,person,similarity=sim_pearson):
totals={}
simSums={}
for other in prefs:
# 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
def transformPrefs(prefs):
result={}
for person in prefs:
for item in prefs[person]:
result.setdefault(item,{})
# Flip item and person
result[item][person]=prefs[person][item]
return result
def calculateSimilarItems(prefs,n=10):
# Create a dictionary of items showing which other items they
# are most similar to.
result={}
# Invert the preference matrix to be item-centric
itemPrefs=transformPrefs(prefs)
c=0
for item in itemPrefs:
# Status updates for large datasets
c+=1
if c%100==0: print "%d / %d" % (c,len(itemPrefs))
# Find the most similar items to this one
scores=topMatches(itemPrefs,item,n=n,similarity=sim_distance)
result[item]=scores
return result
def getRecommendedItems(prefs,itemMatch,user):
userRatings=prefs[user]
scores={}
totalSim={}
# Loop over items rated by this user
for (item,rating) in userRatings.items( ):
# Loop over items similar to this one
for (similarity,item2) in itemMatch[item]:
# Ignore if this user has already rated this item
if item2 in userRatings: continue
# Weighted sum of rating times similarity
scores.setdefault(item2,0)
scores[item2]+=similarity*rating
# Sum of all the similarities
totalSim.setdefault(item2,0)
totalSim[item2]+=similarity
# Divide each total score by total weighting to get an average
rankings=[(score/totalSim[item],item) for item,score in scores.items( )]
# Return the rankings from highest to lowest
rankings.sort( )
rankings.reverse( )
return rankings
def loadMovieLens(path='C:\Users\WangYixin\Desktop\PCI_Code\PCI_Code Folder\chapter2\data'):
# Get movie titles
movies={}
for line in open(path+'/u.item'):
(id,title)=line.split('|')[0:2]
movies[id]=title
# Load data
prefs={}
for line in open(path+'/u.data'):
(user,movieid,rating,ts)=line.split('\t')
prefs.setdefault(user,{})
prefs[user][movies[movieid]]=float(rating)
return prefs

# -*- coding: utf-8 -*-
# 推荐类
import codecs
from math import sqrt
users = {"Angelica": {"Blues Traveler": 3.5, "Broken Bells": 2.0,
"Norah Jones": 4.5, "Phoenix": 5.0,
"Slightly Stoopid": 1.5,
"The Strokes": 2.5, "Vampire Weekend": 2.0},
"Bill":{"Blues Traveler": 2.0, "Broken Bells": 3.5,
"Deadmau5": 4.0, "Phoenix": 2.0,
"Slightly Stoopid": 3.5, "Vampire Weekend": 3.0},
"Chan": {"Blues Traveler": 5.0, "Broken Bells": 1.0,
"Deadmau5": 1.0, "Norah Jones": 3.0, "Phoenix": 5,
"Slightly Stoopid": 1.0},
"Dan": {"Blues Traveler": 3.0, "Broken Bells": 4.0,
"Deadmau5": 4.5, "Phoenix": 3.0,
"Slightly Stoopid": 4.5, "The Strokes": 4.0,
"Vampire Weekend": 2.0},
"Hailey": {"Broken Bells": 4.0, "Deadmau5": 1.0,
"Norah Jones": 4.0, "The Strokes": 4.0,
"Vampire Weekend": 1.0},
"Jordyn": {"Broken Bells": 4.5, "Deadmau5": 4.0,
"Norah Jones": 5.0, "Phoenix": 5.0,
"Slightly Stoopid": 4.5, "The Strokes": 4.0,
"Vampire Weekend": 4.0},
"Sam": {"Blues Traveler": 5.0, "Broken Bells": 2.0,
"Norah Jones": 3.0, "Phoenix": 5.0,
"Slightly Stoopid": 4.0, "The Strokes": 5.0},
"Veronica": {"Blues Traveler": 3.0, "Norah Jones": 5.0,
"Phoenix": 4.0, "Slightly Stoopid": 2.5,
"The Strokes": 3.0}
}
class recommender:
def __init__(self, data, k=1, metric='pearson', n=5):
""" initialize recommender
currently, if data is dictionary the recommender is initialized
to it.
For all other data types of data, no initialization occurs
k is the k value for k nearest neighbor
metric is which distance formula to use
n is the maximum number of recommendations to make"""
self.k = k
self.n = n
self.username2id = {}
self.userid2name = {}
self.productid2name = {}
# for some reason I want to save the name of the metric
self.metric = metric
if self.metric == 'pearson':
self.fn = self.pearson
#
# if data is dictionary set recommender data to it
#
if type(data).__name__ == 'dict':
self.data = data
def convertProductID2name(self, id):
"""Given product id number return product name"""
if id in self.productid2name:
return self.productid2name[id]
else:
return id
def userRatings(self, id, n):
"""Return n top ratings for user with id"""
print ("Ratings for " + self.userid2name[id])
ratings = self.data[id]
print(len(ratings))
ratings = list(ratings.items())
ratings = [(self.convertProductID2name(k), v)
for (k, v) in ratings]
# finally sort and return
ratings.sort(key=lambda artistTuple: artistTuple[1],
reverse = True)
ratings = ratings[:n]
for rating in ratings:
print("%s\t%i" % (rating[0], rating[1]))
def loadBookDB(self, path=''):
"""loads the BX book dataset. Path is where the BX files are
located"""
self.data = {}
i = 0
#
# First load book ratings into self.data
#
f = codecs.open(path + "BX-Book-Ratings.csv", 'r', 'utf8')
f.readline() #read the title
for line in f:
i += 1
#separate line into fields
fields = line.split(';') # still with ""
user = fields[0].strip('"') #delete “ in the fields
book = fields[1].strip('"')
rating = int(fields[2].strip().strip('"'))
if user in self.data:
currentRatings = self.data[user]
else:
currentRatings = {}
currentRatings[book] = rating
self.data[user] = currentRatings
#line = f.readline()
f.close()
#
# Now load books into self.productid2name
# Books contains isbn, title, and author among other fields
#
f = codecs.open(path + "BX-Books.csv", 'r', 'utf8')
for line in f:
i += 1
#separate line into fields
fields = line.split(';')
isbn = fields[0].strip('"')
title = fields[1].strip('"')
author = fields[2].strip().strip('"')
title = title + ' by ' + author
self.productid2name[isbn] = title
f.close()
#
# Now load user info into both self.userid2name and
# self.username2id
#
f = codecs.open(path + "BX-Users.csv", 'r', 'utf8')
for line in f:
i += 1
#print(line)
#separate line into fields
fields = line.split(';')
userid = fields[0].strip('"')
location = fields[1].strip('"')
if len(fields) > 3:
age = fields[2].strip().strip('"')
else:
age = 'NULL'
if age != 'NULL':
value = location + ' (age: ' + age + ')'
else:
value = location
self.userid2name[userid] = value
self.username2id[location] = userid
f.close()
print(i)
def pearson(self, rating1, rating2):
sum_xy = 0
sum_x = 0
sum_y = 0
sum_x2 = 0
sum_y2 = 0
n = 0
for key in rating1:
if key in rating2:
n += 1
x = rating1[key]
y = rating2[key]
sum_xy += x * y
sum_x += x
sum_y += y
sum_x2 += pow(x, 2)
sum_y2 += pow(y, 2)
if n == 0:
return 0
# now compute denominator
denominator = (sqrt(sum_x2 - pow(sum_x, 2) / n)
* sqrt(sum_y2 - pow(sum_y, 2) / n))
if denominator == 0:
return 0
else:
return (sum_xy - (sum_x * sum_y) / n) / denominator
def computeNearestNeighbor(self, username):
"""creates a sorted list of users based on their distance to
username"""
distances = []
for instance in self.data:
if instance != username:
distance = self.fn(self.data[username],
self.data[instance])
distances.append((instance, distance))
# sort based on distance -- closest first
distances.sort(key=lambda artistTuple: artistTuple[1],
reverse=True)
return distances
def recommend(self, user):
"""Give list of recommendations"""
recommendations = {}
# first get list of users ordered by nearness
nearest = self.computeNearestNeighbor(user)
# now get the ratings for the user
userRatings = self.data[user]
# determine the total distance
totalDistance = 0.0
for i in range(self.k):
totalDistance += nearest[i][1]
# now iterate through the k nearest neighbors
# accumulating their ratings
for i in range(self.k):
# compute slice of pie
weight = nearest[i][1] / totalDistance
# get the name of the person
name = nearest[i][0]
# get the ratings for this person
neighborRatings = self.data[name]
# get the name of the person
# now find bands neighbor rated that user didn't
for artist in neighborRatings:
if not artist in userRatings:
if artist not in recommendations:
recommendations[artist] = (neighborRatings[artist] * weight)
else:
recommendations[artist] = (recommendations[artist] + neighborRatings[artist] * weight)
# now make list from dictionary
recommendations = list(recommendations.items())
recommendations = [(self.convertProductID2name(k), v)
for (k, v) in recommendations]
# finally sort and return
recommendations.sort(key=lambda artistTuple: artistTuple[1],
reverse = True)
# Return the first n items
return recommendations[:self.n]
############test code############
#r = recommender(users)
#r.recommend('Jordyn')
#r.recommend('Hailey')
#r.loadBookDB('BX-CSV-Dump/')
#r.recommend('171118')
#r.userRatings('171118', 5)