我正在阅读一本书（A Programmer's Guide to Data Mining），该书附有以下数据BX-Dump，有10万用户的评分，每个都有一些评级的书。我想将整个数据集移动到pandas数据帧中，它比作者的实现加载速度快10倍：
%time r.loadBookDB('/Users/danialt/Downloads/BX-Dump/')
1700018
CPU times: user 16.1 s, sys: 373 ms, total: 16.5 s
Wall time: 16.5 s
和我的：
# Mine
%time ratings = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Book-Ratings.csv', sep=";", quotechar="\"", escapechar="\\")
%time books = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Books.csv', sep=";", quotechar="\"", escapechar="\\")
%time users = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Users.csv', sep=";", quotechar="\"", escapechar="\\")
#Output[5]
CPU times: user 484 ms, sys: 73.3 ms, total: 557 ms
Wall time: 567 ms
CPU times: user 1.28 s, sys: 138 ms, total: 1.41 s
Wall time: 1.45 s
CPU times: user 148 ms, sys: 25.7 ms, total: 173 ms
Wall time: 178 ms
#/Output
现在，要计算相关性ratings.corr()，我需要将用户放在索引上，将书籍放在列上，将评级作为值：
ratings_piv = ratings.pivot(index='User-ID', columns='ISBN', values='Book-Rating')
但这会失败，因为会形成一个100k x 400k矩阵！
是否有一种更好/更优雅的方法来计算这个非常稀疏矩阵的相关性而不会在每一行中循环？
示例代码:(不要运行最后一行，它会杀死你的RAM）
import numpy as np
import pandas as pd
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')
for line in f:
i += 1
#separate line into fields
fields = line.split(';')
user = fields[0].strip('"')
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
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]
r = recommender(users)
# The author implementation
r.loadBookDB('/Users/danialt/Downloads/BX-Dump/')
# The alternative loading
ratings = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Book-Ratings.csv', sep=";", quotechar="\"", escapechar="\\")
books = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Books.csv', sep=";", quotechar="\"", escapechar="\\")
users = pd.read_csv('/Users/danialt/BX-CSV-Dump/BX-Users.csv', sep=";", quotechar="\"", escapechar="\\")
pivot_rating = ratings.pivot(index='User-ID', columns='ISBN', values='Book-Rating')
答案 0 :(得分：3)
小心这样的基准。 Pandas可能正在使用延迟加载，即它可能会返回但实际上还没有读取数据。在这种情况下，测量的墙壁时间将毫无价值。尝试对所有数据执行一些简单的操作，以确保它真正被读取。
至于相关性：您的输入矩阵可能是稀疏的，但相关矩阵可能不是那么稀疏;因为通常情况之间存在一些极小的相关性。
请注意，相关矩阵将是正方形，即如果您有100k个用户，则用户 - 用户相关矩阵将为100k x 100k（由于对称性，您可以节省一半的内存，但不会帮助那么多。
如果要加快计算速度，请考虑是否需要所有数据，是否需要全精度数据，以及是否可以利用内存中的数据布局来加速计算。 例如，协方差（在关联中使用）可以通过利用稀疏性来加速，并且仅在列中处理非零值而不是在行中工作。
但是，为了快速 ，你必须放弃在矩阵中的思考。相反，考虑散列和索引结构避免将所有内容与其他所有内容进行比较（这在成本上自然是二次方的）。在矩阵中思考时，请始终考虑在内存或磁盘上不存在的稀疏矩阵。