I have a dataset with 12000 users and 500 items, and I used it to build a recommender model by different approaches. With user based collaborative filtering I have precision=0.1, with content based model precision=0.45. I expected to increase the precision value with TensorFlow by obvious reasons, but precision=0.0013, which does not make any sense. I tried your basic_usage code, which generates ratings, user_features and item_features randomly by the function tensorrec.util.generate_dummy_data(), and I see precision=0.003. It makes sense because in this case we don't have any correlations between ratings and user-item features. Please, clarify why real data and random numbers give the same level of precision.

I have read through (most of) the issues and have the recommendation up and running but the result is not as good as I hoped. I have a few questions looking for your answer. Below is info about my current dataset:

user_features.shape = (79770, 26035) # avg features/user = 2
item_features.shape = (21093, 20157) # avg features/item = 4
interactions.shape = (79770, 21093)

I train with this code, which is similar to your example:

model = tensorrec.TensorRec()
model.fit(interactions, user_features, item_features, epochs=1000, verbose=True)

However, my hardware is not powerful enough so I had to picked samples from the full dataset instead of running it in full:

sample_user_features.shape = (4, 26035)
sample_interactions.shape = (4, 21093)

predicted_ranks = model.predict_rank(user_features=sample_user_features, item_features=item_features)
r_at_k = tensorrec.eval.recall_at_k(predicted_ranks, sample_interactions, k=10)
print(np.mean(r_at_k))

The recall@10 value is 0.00006. I manually inspected the predicted item for these users and it's not good. So my questions are:

1. I think my avg features/user of 2 and avg features/item of 4 are too small. Do you think so? Should the recommendation works with such low density?
2. I choose 4 user ids from the dataset and build sample matrix to run the recall. I'm not confident about this step. Is this mathematically and statistically correct?
3. I understand that you have implemented fit_partial. In my situation, the item features can increase over time. Will fit_partial works with resized matrix?

Thank you.

Here is the code I copy from the sample: https://colab.research.google.com/drive/1VPBOMyc9GEUknlK1hgflLHtquaLK3IRg

I got the following error. I think it is the problem with the tensorflow version, the version on the colab is 1.13.0 I think

  "Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-1-beee77fbc4f6> in <module>()
     19 
     20 # # Fit the model for 5 epochs
---> 21 model.fit(interactions, user_features, item_features, epochs=5, verbose=True)
     22 
     23 # Predict scores and ranks for all users and all items

/usr/local/lib/python3.6/dist-packages/tensorrec/tensorrec.py in fit(self, interactions, user_features, item_features, epochs, learning_rate, alpha, verbose, user_batch_size, n_sampled_items)
    535                          verbose=verbose,
    536                          user_batch_size=user_batch_size,
--> 537                          n_sampled_items=n_sampled_items)
    538 
    539     def fit_partial(self, interactions, user_features, item_features, epochs=1, learning_rate=0.1,

/usr/local/lib/python3.6/dist-packages/tensorrec/tensorrec.py in fit_partial(self, interactions, user_features, item_features, epochs, learning_rate, alpha, verbose, user_batch_size, n_sampled_items)
    603             # Numbers of features are either learned at fit time from the shape of these two matrices or specified at
    604             # TensorRec construction and cannot be changed.
--> 605             self._build_tf_graph(n_user_features=n_user_features, n_item_features=n_item_features)
    606             session.run(tf.global_variables_initializer())
    607 

/usr/local/lib/python3.6/dist-packages/tensorrec/tensorrec.py in _build_tf_graph(self, n_user_features, n_item_features)
    490 
    491         # Record the new node names
--> 492         self._record_graph_hook_names()
    493 
    494     def fit(self, interactions, user_features, item_features, epochs=100, learning_rate=0.1, alpha=0.00001,

/usr/local/lib/python3.6/dist-packages/tensorrec/tensorrec.py in _record_graph_hook_names(self)
    176             hook = self.__getattribute__(graph_iterator_hook_attr_name)
    177             iterator_resource_name = hook._iterator_resource.name
--> 178             output_types = hook._output_types
    179             output_shapes = hook._output_shapes
    180             output_classes = hook._output_classes

AttributeError: 'Iterator' object has no attribute '_output_types'```

I think that with the described architecture a user with the same features but different actions will receive the same recommendations, is this correct?

I understand that there is a use case for this, but I just want to get things clear in my understanding.

The only possibility I see is creating a model per user using his/her specific actions.

Have you think about how to overcome this?

On a fresh install of tensorrec and tf tensorflow==1.8.0 tensorrec==0.25.1

(prototype) examples❯ python plot_movielens.py tensorrec/git/master

Traceback (most recent call last): File "plot_movielens.py", line 16, in from test.datasets import get_movielens_100k ImportError: No module named datasets

pulled down the entire repo and am in the examples directory

Hi and thanks for the great project, may be the question was already here but i can not find it . I whold like to implement prediction for some new user with some known interactions on known products . Currently all model functions accept user_features item_features which are identity matrixes for the simple case :

I can extract the info for some existing user :

model.predict(user_features=user_features[75], item_features=item_features[100:103]) but i can not do something like this:

model.predict(user_features=zero vector , item_features=item_features, user_interactions = [
0 0 0 ... 1 ... 1 
] )

for the new customer that likes 2 products.

Addresses https://github.com/jfkirk/tensorrec/issues/8

1. Adds methods for saving/loading the TensorRec object and the TensorFlow session behind it.

2. Adds a test for the saving/loading methods.

3. Refactors graph hook management to be done with lists of attr/node names. This allows us to quickly strip all hooks from the Python object before serializing it.

4. Removes many unnecessary graph hooks. A hook was necessary if it was used to power an API function outside of graph construction.

WMRB is supposed to be WARP adapted for a batch setting right? According to my movie lens tests, the difference seems a bit large:

10D Embeddings, 10 Epochs: WARP p@10: 0.110 WMRB p@10: 0.032

Test: https://gist.github.com/eggie5/863133def026a1dc0bf43c4ba3faaefd

Any idea why?

When I run the code in check_movielens_losses.py or any other example application, I see the same error message--see the stack trace below:

Python 3.6.4 |Anaconda, Inc.| (default, Jan 16 2018, 10:22:32) [MSC v.1900 64 bit (AMD64)]
Type "copyright", "credits" or "license" for more information.

IPython 6.2.1 -- An enhanced Interactive Python.

runfile('C:/temp/RecommenderSystems/tensorrec-master/examples/check_movielens_losses.py', wdir='C:/temp/RecommenderSystems/tensorrec-master/examples')
C:\ProgramData\Anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
C:\ProgramData\Anaconda3\lib\site-packages\lightfm\_lightfm_fast.py:9: UserWarning: LightFM was compiled without OpenMP support. Only a single thread will be used.
  warnings.warn('LightFM was compiled without OpenMP support. '
INFO:root:Processing interaction and feature data
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gradients_impl.py:100: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
  "Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
INFO:root:Beginning fitting
Traceback (most recent call last):

  File "<ipython-input-1-c519eabf3859>", line 1, in <module>
    runfile('C:/temp/RecommenderSystems/tensorrec-master/examples/check_movielens_losses.py', wdir='C:/temp/RecommenderSystems/tensorrec-master/examples')

  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfile
    execfile(filename, namespace)

  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "C:/temp/RecommenderSystems/tensorrec-master/examples/check_movielens_losses.py", line 93, in <module>
    fit_kwargs)

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\eval.py", line 155, in fit_and_eval
    interactions=train_interactions, **fit_kwargs)

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\tensorrec.py", line 539, in fit
    n_sampled_items=n_sampled_items)

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\tensorrec.py", line 629, in fit_partial
    feed_dict=feed_dict

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 905, in run
    run_metadata_ptr)

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1140, in _run
    feed_dict_tensor, options, run_metadata)

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1321, in _do_run
    run_metadata)

  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1340, in _do_call
    raise type(e)(node_def, op, message)

InvalidArgumentError: 0-th value returned by pyfunc_0 is int32, but expects int64
	 [[Node: PyFunc = PyFunc[Tin=[DT_INT64, DT_INT64, DT_INT64], Tout=[DT_INT64], token="pyfunc_0", _device="/job:localhost/replica:0/task:0/device:CPU:0"](IteratorGetNext_3:3, IteratorGetNext_2:3, _arg_Placeholder_0_0)]]

Caused by op 'PyFunc', defined at:
  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 268, in <module>
    main()
  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 264, in main
    kernel.start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 478, in start
    self.io_loop.start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 233, in dispatch_shell
    handler(stream, idents, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 208, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 537, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2728, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2856, in run_ast_nodes
    if self.run_code(code, result):
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2910, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-1-c519eabf3859>", line 1, in <module>
    runfile('C:/temp/RecommenderSystems/tensorrec-master/examples/check_movielens_losses.py', wdir='C:/temp/RecommenderSystems/tensorrec-master/examples')
  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfile
    execfile(filename, namespace)
  File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)
  File "C:/temp/RecommenderSystems/tensorrec-master/examples/check_movielens_losses.py", line 93, in <module>
    fit_kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\eval.py", line 155, in fit_and_eval
    interactions=train_interactions, **fit_kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\tensorrec.py", line 539, in fit
    n_sampled_items=n_sampled_items)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\tensorrec.py", line 607, in fit_partial
    self._build_tf_graph(n_user_features=n_user_features, n_item_features=n_item_features)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorrec\tensorrec.py", line 303, in _build_tf_graph
    Tout=tf.int64)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\script_ops.py", line 330, in py_func
    func=func, inp=inp, Tout=Tout, stateful=stateful, eager=False, name=name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\script_ops.py", line 231, in _internal_py_func
    input=inp, token=token, Tout=Tout, name=name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_script_ops.py", line 129, in py_func
    "PyFunc", input=input, token=token, Tout=Tout, name=name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3290, in create_op
    op_def=op_def)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1654, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): 0-th value returned by pyfunc_0 is int32, but expects int64
	 [[Node: PyFunc = PyFunc[Tin=[DT_INT64, DT_INT64, DT_INT64], Tout=[DT_INT64], token="pyfunc_0", _device="/job:localhost/replica:0/task:0/device:CPU:0"](IteratorGetNext_3:3, IteratorGetNext_2:3, _arg_Placeholder_0_0)]]

pip freeze:

(base) C:\Users\user>pip freeze
absl-py==0.1.13
alabaster==0.7.10
anaconda-client==1.6.9
anaconda-navigator==1.7.0
anaconda-project==0.8.2
asn1crypto==0.24.0
astor==0.6.2
astroid==1.6.1
astropy==2.0.3
attrs==17.4.0
Babel==2.5.3
backports.shutil-get-terminal-size==1.0.0
beautifulsoup4==4.6.0
bitarray==0.8.1
bkcharts==0.2
blaze==0.11.3
bleach==1.5.0
bokeh==0.12.13
boto==2.48.0
Bottleneck==1.2.1
certifi==2018.1.18
cffi==1.11.4
chardet==3.0.4
click==6.7
cloudpickle==0.5.2
clyent==1.2.2
colorama==0.3.9
comtypes==1.1.4
conda==4.4.10
conda-build==3.4.1
conda-verify==2.0.0
contextlib2==0.5.5
cryptography==2.1.4
cycler==0.10.0
Cython==0.27.3
cytoolz==0.9.0
dask==0.16.1
dataIO==0.0.5
datashape==0.5.4
decorator==4.2.1
distributed==1.20.2
docutils==0.14
entrypoints==0.2.3
et-xmlfile==1.0.1
fastcache==1.0.2
filelock==2.0.13
Flask==0.12.2
Flask-Cors==3.0.3
gast==0.2.0
gevent==1.2.2
glob2==0.6
greenlet==0.4.12
grpcio==1.10.1
h5py==2.7.1
heapdict==1.0.0
html5lib==0.9999999
idna==2.6
imageio==2.2.0
imagesize==0.7.1
ipython==6.2.1
ipython-genutils==0.2.0
ipywidgets==7.1.1
isort==4.2.15
itsdangerous==0.24
jdcal==1.3
jedi==0.11.1
Jinja2==2.10
jsonschema==2.6.0
jupyter==1.0.0
jupyter-client==5.2.2
jupyter-console==5.2.0
jupyter-core==4.4.0
jupyterlab==0.31.4
jupyterlab-launcher==0.10.2
Keras==2.1.5
lazy-object-proxy==1.3.1
lightfm==1.15
llvmlite==0.21.0
locket==0.2.0
lxml==4.1.1
Markdown==2.6.11
MarkupSafe==1.0
matplotlib==2.1.2
mccabe==0.6.1
menuinst==1.4.11
mistune==0.8.3
mpmath==1.0.0
msgpack-python==0.5.1
multipledispatch==0.4.9
navigator-updater==0.1.0
nbconvert==5.3.1
nbformat==4.4.0
networkx==2.1
nltk==3.2.5
normalization==0.4
nose==1.3.7
notebook==5.4.0
numba==0.36.2
numexpr==2.6.4
numpy==1.14.0
numpydoc==0.7.0
odo==0.5.1
olefile==0.45.1
openpyxl==2.4.10
packaging==16.8
pandas==0.22.0
pandocfilters==1.4.2
parso==0.1.1
partd==0.3.8
path.py==10.5
pathlib2==2.3.0
patsy==0.5.0
pep8==1.7.1
pickleshare==0.7.4
Pillow==5.0.0
pkginfo==1.4.1
pluggy==0.6.0
ply==3.10
prompt-toolkit==1.0.15
protobuf==3.5.2.post1
psutil==5.4.3
py==1.5.2
pycodestyle==2.3.1
pycosat==0.6.3
pycparser==2.18
pycrypto==2.6.1
pycurl==7.43.0.1
pyflakes==1.6.0
Pygments==2.2.0
pylint==1.8.2
pymongo==3.6.1
pyodbc==4.0.22
pyOpenSSL==17.5.0
pyparsing==2.2.0
PySocks==1.6.7
pytest==3.3.2
python-dateutil==2.6.1
pytz==2017.3
PyWavelets==0.5.2
pywin32==222
pywinpty==0.5
PyYAML==3.12
pyzmq==16.0.3
QtAwesome==0.4.4
qtconsole==4.3.1
QtPy==1.3.1
requests==2.18.4
rope==0.10.7
ruamel-yaml==0.15.35
scikit-image==0.13.1
scikit-learn==0.19.1
scipy==1.0.0
seaborn==0.8.1
Send2Trash==1.4.2
simplegeneric==0.8.1
singledispatch==3.4.0.3
six==1.11.0
snowballstemmer==1.2.1
sortedcollections==0.5.3
sortedcontainers==1.5.9
Sphinx==1.6.6
sphinxcontrib-websupport==1.0.1
spyder==3.2.6
SQLAlchemy==1.2.1
statsmodels==0.8.0
sympy==1.1.1
tables==3.4.2
tblib==1.3.2
tensorboard==1.7.0
tensorflow==1.7.0
tensorrec==0.25.3
termcolor==1.1.0
terminado==0.8.1
testpath==0.3.1
toolz==0.9.0
tornado==4.5.3
traitlets==4.3.2
typing==3.6.2
unicodecsv==0.14.1
urllib3==1.22
wcwidth==0.1.7
webencodings==0.5.1
Werkzeug==0.14.1
widgetsnbextension==3.1.0
win-inet-pton==1.0.1
win-unicode-console==0.5
wincertstore==0.2
wrapt==1.10.11
xlrd==1.1.0
XlsxWriter==1.0.2
xlwings==0.11.5
xlwt==1.3.0
zict==0.1.3

I believe all relevant packages are up to date running on python 3.6.5

---

TypeError Traceback (most recent call last) in () 29 train_interactions, test_interactions, user_features, item_features, _ = get_book_crossing(user_indicators=False, 30 item_indicators=True, ---> 31 cold_start_users=True) 32 33 # Establish baseline metrics with random ranks for warm and cold start users

in get_book_crossing(min_positive_score, min_interactions_per_book, user_indicators, item_indicators, cold_start_users, cold_start_items)

/usr/local/lib/python3.6/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params) 737 delayed(_fit_transform_one)(trans, weight, X, y, 738 **fit_params) --> 739 for name, trans, weight in self._iter()) 740 741 if not result:

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in call(self, iterable) 777 # was dispatched. In particular this covers the edge 778 # case of Parallel used with an exhausted iterator. --> 779 while self.dispatch_one_batch(iterator): 780 self._iterating = True 781 else:

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator) 623 return False 624 else: --> 625 self._dispatch(tasks) 626 return True 627

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch) 586 dispatch_timestamp = time.time() 587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self) --> 588 job = self._backend.apply_async(batch, callback=cb) 589 self._jobs.append(job) 590

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback) 109 def apply_async(self, func, callback=None): 110 """Schedule a func to be run""" --> 111 result = ImmediateResult(func) 112 if callback: 113 callback(result)

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in init(self, batch) 330 # Don't delay the application, to avoid keeping the input 331 # arguments in memory --> 332 self.results = batch() 333 334 def get(self):

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in call(self) 129 130 def call(self): --> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items] 132 133 def len(self):

/usr/local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in (.0) 129 130 def call(self): --> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items] 132 133 def len(self):

/usr/local/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, weight, X, y, **fit_params) 579 **fit_params): 580 if hasattr(transformer, 'fit_transform'): --> 581 res = transformer.fit_transform(X, y, **fit_params) 582 else: 583 res = transformer.fit(X, y, **fit_params).transform(X)

/usr/local/lib/python3.6/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params) 281 Xt, fit_params = self._fit(X, y, **fit_params) 282 if hasattr(last_step, 'fit_transform'): --> 283 return last_step.fit_transform(Xt, y, **fit_params) 284 elif last_step is None: 285 return Xt

TypeError: fit_transform() takes 2 positional arguments but 3 were given

Could be useful to examine item biases, for example.

• [ ] Add predict_user_bias and predict_item_bias API method to TensorRec
• [ ] Add hooks to projected_user_biases and projected_item_biases in TensorRec that can be used by the new API and for saving/loading
• [ ] Add tests for the new prediction methods

Bumps pillow from 5.0.0 to 9.3.0.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

• pip install tensorrec takes forever to complete install
• do I need to install each time, on say, a kaggle notebook

Please respond at the earliest as I need to use tensorrec for a recommender system

Hello,this issue shows the reason that I commit this PR. I sincerely wish my PR will help you.And if you think my PR has a little work,Hoping you could merge it. Thank you,my friend.

Hello,I found a performance issue in the definition of create_tensorrec_dataset_from_tfrecord , jfkirk/tensorrec/blob/master/tensorrec/input_utils.py, tf.data.TFRecordDataset(tfrecord_path).map was called without num_parallel_calls. I think it will increase the efficiency of your program if you add this.

Here is the documemtation of tensorflow to support this thing.

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.

Hello , Great work on Tensorrec . For my use case i have both items as well as users features so can i initialize these Features to the hybrid model instead of initializing it with identity matrix.

I installed tensorrec in brand new Virtualenv and stuck here.

\lib\site-packages\tensorrec\session_management.py in get_session() 10 if _session is None: ---> 11 if tf.get_default_session() is not None: 12 _session = tf.get_default_session() 13 else:

AttributeError: module 'tensorflow' has no attribute 'get_default_session'

installed tensorflow 2.0.4 version