ZhengHui
/
kernelNet
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

init

Browse Source
master
Zhenghui-Z 4 years ago
parent 1cd49fb2b9
commit 1dca992a8d
8 changed files with 1010730 additions and 14 deletions
Show Stats Download Patch File Download Diff File

202
LICENSE-2.0.txt
Unescape View File

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [2019] [Lorenz K Muller]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

38
README.md
Unescape View File

@ -1,19 +1,29 @@
#### 从命令行创建一个新的仓库
# kernelNet MovieLens-1M
```bash
touch README.md
git init
git add README.md
git commit -m "first commit"
git remote add origin https://bdgit.educoder.net/ZhengHui/kernelNet.git
git push -u origin master
State of the art model for MovieLens-1M.
```
This is a minimal implementation of a kernelNet sparsified autoencoder for MovieLens-1M.
See http://proceedings.mlr.press/v80/muller18a.html
#### 从命令行推送已经创建的仓库
## Setup
Download this repository
```bash
git remote add origin https://bdgit.educoder.net/ZhengHui/kernelNet.git
git push -u origin master
### Requirements
* numpy
* scipy
* tensorflow (tested with version 1.13)
```
### Dataset
Expects MovieLens-1M dataset in a subdirectory named ml-1m.
Get it here https://grouplens.org/datasets/movielens/1m/
or on linux run in the project directory
```wget --output-document=ml-1m.zip http://www.grouplens.org/system/files/ml-1m.zip; unzip ml-1m.zip```
## Run
```python kernelNet_ml1m.py```
optional arguments are the L2 and sparsity regularization strength. Default is 60. and 0.013
### Results
with the default parameters this slightly outperforms the paper model at 0.823 validation RMSE (10-times repeated random sub-sampling validation)

66
dataLoader.py
Unescape View File

@ -0,0 +1,66 @@
'''
written by Lorenz Muller
'''
import numpy as np
from time import time
def loadData(path='./', valfrac=0.1, delimiter='::', seed=1234,
transpose=False):
'''
loads ml-1m data
:param path: path to the ratings file
:param valfrac: fraction of data to use for validation
:param delimiter: delimiter used in data file
:param seed: random seed for validation splitting
:param transpose: flag to transpose output matrices (swapping users with movies)
:return: train ratings (n_u, n_m), valid ratings (n_u, n_m)
'''
np.random.seed(seed)
tic = time()
print('reading data...')
data = np.loadtxt(path, skiprows=0, delimiter=delimiter).astype('int32')
print('data read in', time() - tic, 'seconds')
n_u = np.unique(data[:, 0]).shape[0] # number of users
n_m = np.unique(data[:, 1]).shape[0] # number of movies
n_r = data.shape[0] # number of ratings
# these dictionaries define a mapping from user/movie id to to user/movie number (contiguous from zero)
udict = {}
for i, u in enumerate(np.unique(data[:, 0]).tolist()):
udict[u] = i
mdict = {}
for i, m in enumerate(np.unique(data[:, 1]).tolist()):
mdict[m] = i
# shuffle indices
idx = np.arange(n_r)
np.random.shuffle(idx)
trainRatings = np.zeros((n_u, n_m), dtype='float32')
validRatings = np.zeros((n_u, n_m), dtype='float32')
for i in range(n_r):
u_id = data[idx[i], 0]
m_id = data[idx[i], 1]
r = data[idx[i], 2]
# the first few ratings of the shuffled data array are validation data
if i <= valfrac * n_r:
validRatings[udict[u_id], mdict[m_id]] = int(r)
# the rest are training data
else:
trainRatings[udict[u_id], mdict[m_id]] = int(r)
if transpose:
trainRatings = trainRatings.T
validRatings = validRatings.T
print('loaded dense data matrix')
return trainRatings, validRatings

136
kernelNet_ml1m.py
Unescape View File

@ -0,0 +1,136 @@
'''
written by Lorenz Muller
'''
import numpy as np
import tensorflow as tf
from time import time
import sys
from dataLoader import loadData
import os
seed = int(time())
np.random.seed(seed)
# load data
tr, vr = loadData('./ml-1m/ratings.dat', delimiter='::',
seed=seed, transpose=True, valfrac=0.1)
tm = np.greater(tr, 1e-12).astype('float32') # masks indicating non-zero entries
vm = np.greater(vr, 1e-12).astype('float32')
n_m = tr.shape[0] # number of movies
n_u = tr.shape[1] # number of users (may be switched depending on 'transpose' in loadData)
# Set hyper-parameters
n_hid = 500
lambda_2 = float(sys.argv[1]) if len(sys.argv) > 1 else 60.
lambda_s = float(sys.argv[2]) if len(sys.argv) > 2 else 0.013
n_layers = 2
output_every = 50 # evaluate performance on test set; breaks l-bfgs loop
n_epoch = n_layers * 10 * output_every
verbose_bfgs = True
use_gpu = True
if not use_gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = ''
# Input placeholders
R = tf.placeholder("float", [None, n_u])
# define network functions
def kernel(u, v):
"""
Sparsifying kernel function
:param u: input vectors [n_in, 1, n_dim]
:param v: output vectors [1, n_hid, n_dim]
:return: input to output connection matrix
"""
dist = tf.norm(u - v, ord=2, axis=2)
hat = tf.maximum(0., 1. - dist**2)
return hat
def kernel_layer(x, n_hid=500, n_dim=5, activation=tf.nn.sigmoid, lambda_s=lambda_s,
lambda_2=lambda_2, name=''):
"""
a kernel sparsified layer
:param x: input [batch, channels]
:param n_hid: number of hidden units
:param n_dim: number of dimensions to embed for kernelization
:param activation: output activation
:param name: layer name for scoping
:return: layer output, regularization term
"""
# define variables
with tf.variable_scope(name):
W = tf.get_variable('W', [x.shape[1], n_hid])
n_in = x.get_shape().as_list()[1]
u = tf.get_variable('u', initializer=tf.random_normal([n_in, 1, n_dim], 0., 1e-3))
v = tf.get_variable('v', initializer=tf.random_normal([1, n_hid, n_dim], 0., 1e-3))
b = tf.get_variable('b', [n_hid])
# compute sparsifying kernel
# as u and v move further from each other for some given pair of neurons, their connection
# decreases in strength and eventually goes to zero.
w_hat = kernel(u, v)
# compute regularization terms
sparse_reg = tf.contrib.layers.l2_regularizer(lambda_s)
sparse_reg_term = tf.contrib.layers.apply_regularization(sparse_reg, [w_hat])
l2_reg = tf.contrib.layers.l2_regularizer(lambda_2)
l2_reg_term = tf.contrib.layers.apply_regularization(l2_reg, [W])
# compute output
W_eff = W * w_hat
y = tf.matmul(x, W_eff) + b
y = activation(y)
return y, sparse_reg_term + l2_reg_term
# Instantiate network
y = R
reg_losses = None
for i in range(n_layers):
y, reg_loss = kernel_layer(y, n_hid, name=str(i))
reg_losses = reg_loss if reg_losses is None else reg_losses + reg_loss
prediction, reg_loss = kernel_layer(y, n_u, activation=tf.identity, name='out')
reg_losses = reg_losses + reg_loss
# Compute loss (symbolic)
diff = tm*(R - prediction)
sqE = tf.nn.l2_loss(diff)
loss = sqE + reg_losses
# Instantiate L-BFGS Optimizer
optimizer = tf.contrib.opt.ScipyOptimizerInterface(loss, options={'maxiter': output_every,
'disp': verbose_bfgs,
'maxcor': 10},
method='L-BFGS-B')
# Training and validation loop
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for i in range(int(n_epoch / output_every)):
optimizer.minimize(sess, feed_dict={R: tr}) #do maxiter optimization steps
pre = sess.run(prediction, feed_dict={R: tr}) #predict ratings
error = (vm * (np.clip(pre, 1., 5.) - vr) ** 2).sum() / vm.sum() #compute validation error
error_train = (tm * (np.clip(pre, 1., 5.) - tr) ** 2).sum() / tm.sum() #compute train error
print('.-^-._' * 12)
print('epoch:', i, 'validation rmse:', np.sqrt(error), 'train rmse:', np.sqrt(error_train))
print('.-^-._' * 12)
with open('summary_ml1m.txt', 'a') as file:
for a in sys.argv[1:]:
file.write(a + ' ')
file.write(str(np.sqrt(error)) + ' ' + str(np.sqrt(error_train))
+ ' ' + str(seed) + '\n')
file.close()

170
ml-1m/README
Unescape View File

@ -0,0 +1,170 @@
SUMMARY
================================================================================
These files contain 1,000,209 anonymous ratings of approximately 3,900 movies
made by 6,040 MovieLens users who joined MovieLens in 2000.
USAGE LICENSE
================================================================================
Neither the University of Minnesota nor any of the researchers
involved can guarantee the correctness of the data, its suitability
for any particular purpose, or the validity of results based on the
use of the data set. The data set may be used for any research
purposes under the following conditions:
* The user may not state or imply any endorsement from the
University of Minnesota or the GroupLens Research Group.
* The user must acknowledge the use of the data set in
publications resulting from the use of the data set
(see below for citation information).
* The user may not redistribute the data without separate
permission.
* The user may not use this information for any commercial or
revenue-bearing purposes without first obtaining permission
from a faculty member of the GroupLens Research Project at the
University of Minnesota.
If you have any further questions or comments, please contact GroupLens
<grouplens-info@cs.umn.edu>.
CITATION
================================================================================
To acknowledge use of the dataset in publications, please cite the following
paper:
F. Maxwell Harper and Joseph A. Konstan. 2015. The MovieLens Datasets: History
and Context. ACM Transactions on Interactive Intelligent Systems (TiiS) 5, 4,
Article 19 (December 2015), 19 pages. DOI=http://dx.doi.org/10.1145/2827872
ACKNOWLEDGEMENTS
================================================================================
Thanks to Shyong Lam and Jon Herlocker for cleaning up and generating the data
set.
FURTHER INFORMATION ABOUT THE GROUPLENS RESEARCH PROJECT
================================================================================
The GroupLens Research Project is a research group in the Department of
Computer Science and Engineering at the University of Minnesota. Members of
the GroupLens Research Project are involved in many research projects related
to the fields of information filtering, collaborative filtering, and
recommender systems. The project is lead by professors John Riedl and Joseph
Konstan. The project began to explore automated collaborative filtering in
1992, but is most well known for its world wide trial of an automated
collaborative filtering system for Usenet news in 1996. Since then the project
has expanded its scope to research overall information filtering solutions,
integrating in content-based methods as well as improving current collaborative
filtering technology.
Further information on the GroupLens Research project, including research
publications, can be found at the following web site:
http://www.grouplens.org/
GroupLens Research currently operates a movie recommender based on
collaborative filtering:
http://www.movielens.org/
RATINGS FILE DESCRIPTION
================================================================================
All ratings are contained in the file "ratings.dat" and are in the
following format:
UserID::MovieID::Rating::Timestamp
- UserIDs range between 1 and 6040
- MovieIDs range between 1 and 3952
- Ratings are made on a 5-star scale (whole-star ratings only)
- Timestamp is represented in seconds since the epoch as returned by time(2)
- Each user has at least 20 ratings
USERS FILE DESCRIPTION
================================================================================
User information is in the file "users.dat" and is in the following
format:
UserID::Gender::Age::Occupation::Zip-code
All demographic information is provided voluntarily by the users and is
not checked for accuracy. Only users who have provided some demographic
information are included in this data set.
- Gender is denoted by a "M" for male and "F" for female
- Age is chosen from the following ranges:
* 1: "Under 18"
* 18: "18-24"
* 25: "25-34"
* 35: "35-44"
* 45: "45-49"
* 50: "50-55"
* 56: "56+"
- Occupation is chosen from the following choices:
* 0: "other" or not specified
* 1: "academic/educator"
* 2: "artist"
* 3: "clerical/admin"
* 4: "college/grad student"
* 5: "customer service"
* 6: "doctor/health care"
* 7: "executive/managerial"
* 8: "farmer"
* 9: "homemaker"
* 10: "K-12 student"
* 11: "lawyer"
* 12: "programmer"
* 13: "retired"
* 14: "sales/marketing"
* 15: "scientist"
* 16: "self-employed"
* 17: "technician/engineer"
* 18: "tradesman/craftsman"
* 19: "unemployed"
* 20: "writer"
MOVIES FILE DESCRIPTION
================================================================================
Movie information is in the file "movies.dat" and is in the following
format:
MovieID::Title::Genres
- Titles are identical to titles provided by the IMDB (including
year of release)
- Genres are pipe-separated and are selected from the following genres:
* Action
* Adventure
* Animation
* Children's
* Comedy
* Crime
* Documentary
* Drama
* Fantasy
* Film-Noir
* Horror
* Musical
* Mystery
* Romance
* Sci-Fi
* Thriller
* War
* Western
- Some MovieIDs do not correspond to a movie due to accidental duplicate
entries and/or test entries
- Movies are mostly entered by hand, so errors and inconsistencies may exist

3883
ml-1m/movies.dat
View File

File diff suppressed because it is too large Load Diff

1000209
ml-1m/ratings.dat
View File

File diff suppressed because it is too large Load Diff

6040
ml-1m/users.dat
View File

File diff suppressed because it is too large Load Diff
Write Preview
Loading…
Cancel
Save