Repository navigation
Expand file tree
/
Copy pathload_ml100k.py
More file actions
59 lines (48 loc) · 1.61 KB
/
Copy pathload_ml100k.py
File metadata and controls
59 lines (48 loc) · 1.61 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
# This code is supporting material for the book
# Building Machine Learning Systems with Python
# by Willi Richert and Luis Pedro Coelho
# published by PACKT Publishing
#
# It is made available under the MIT License
def load():
'''Load ML-100k data
Returns the review matrix as a numpy array'''
import numpy as np
from scipy import sparse
from os import path
if not path.exists('data/ml-100k/u.data'):
raise IOError("Data has not been downloaded.\nTry the following:\n\n\tcd data\n\t./download.sh")
# The input is in the form of a CSC sparse matrix, so it's a natural fit to
# load the data, but we then convert to a more traditional array before
# returning
data = np.loadtxt('data/ml-100k/u.data')
ij = data[:, :2]
ij -= 1 # original data is in 1-based system
values = data[:, 2]
reviews = sparse.csc_matrix((values, ij.T)).astype(float)
return reviews.toarray()
def get_train_test(reviews=None, random_state=None):
'''Split data into training & testing
Parameters
----------
reviews : ndarray, optional
Input data
Returns
-------
train : ndarray
training data
test : ndarray
testing data
'''
import numpy as np
import random
r = random.Random(random_state)
if reviews is None:
reviews = load()
U,M = np.where(reviews)
test_idxs = np.array(r.sample(range(len(U)), len(U)//10))
train = reviews.copy()
train[U[test_idxs], M[test_idxs]] = 0
test = np.zeros_like(reviews)
test[U[test_idxs], M[test_idxs]] = reviews[U[test_idxs], M[test_idxs]]
return train, test