dawenl
Error in python 3.5+
Hi all,
Is there a way to get the hit ratio along with ndcg from the code? Any help would be appreciated.
Thanks
In the file 'eval_funcs.py' there's the computation of the NDCG. The input to the HR is the same as the one to the NDCG. You could implement a function with the same header and then call it where the NDCG is called.
Another question, when I try to load the train.csv file. I get the following error. Any idea why? and how to resolve it?
Solved the above issue. Now I have another issue. I am using python 3.5+ and when I ran the following block. I get this error and I have attached the traceback here. Any help would be appreciated.
Code:
np.seterr(divide='ignore', invalid='ignore') #Added by me ndcgs_vad = []
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
best_ndcg = -np.inf
update_count = 0.0
for epoch in list(range(n_epochs)):
np.random.shuffle(list(idxlist))
# train for one epoch
for bnum, st_idx in enumerate(range(0, N, batch_size)):
end_idx = min(st_idx + batch_size, N)
X = train_data[idxlist[st_idx:end_idx]]
if sparse.isspmatrix(X):
X = X.toarray()
X = X.astype('float32')
if total_anneal_steps > 0:
anneal = min(anneal_cap, 1. * update_count / total_anneal_steps)
else:
anneal = anneal_cap
feed_dict = {vae.input_ph: X,
vae.keep_prob_ph: 0.5,
vae.anneal_ph: anneal,
vae.is_training_ph: 1}
sess.run(train_op_var, feed_dict=feed_dict)
if bnum % 100 == 0:
summary_train = sess.run(merged_var, feed_dict=feed_dict)
summary_writer.add_summary(summary_train,
global_step=epoch * batches_per_epoch + bnum)
update_count += 1
# compute validation NDCG
ndcg_dist = []
for bnum, st_idx in enumerate(range(0, N_vad, batch_size_vad)):
end_idx = min(st_idx + batch_size_vad, N_vad)
X = vad_data_tr[idxlist_vad[st_idx:end_idx]]
if sparse.isspmatrix(X):
X = X.toarray()
X = X.astype('float32')
pred_val = sess.run(logits_var, feed_dict={vae.input_ph: X} )
# exclude examples from training and validation (if any)
pred_val[X.nonzero()] = -np.inf
ndcg_dist.append(NDCG_binary_at_k_batch(pred_val, vad_data_te[idxlist_vad[st_idx:end_idx]]))
ndcg_dist = np.concatenate(ndcg_dist)
ndcg_ = ndcg_dist.mean()
ndcgs_vad.append(ndcg_)
merged_valid_val = sess.run(merged_valid, feed_dict={ndcg_var: ndcg_, ndcg_dist_var: ndcg_dist})
summary_writer.add_summary(merged_valid_val, epoch)
# update the best model (if necessary)
if ndcg_ > best_ndcg:
saver.save(sess, '{}/model'.format(chkpt_dir))
best_ndcg = ndcg_
Error Traceback:
InvalidArgumentError Traceback (most recent call last) ~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args) 1333 try: -> 1334 return fn(*args) 1335 except errors.OpError as e:
~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata) 1318 return self._call_tf_sessionrun( -> 1319 options, feed_dict, fetch_list, target_list, run_metadata) 1320
~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata) 1406 self._session, options, feed_dict, fetch_list, target_list, -> 1407 run_metadata) 1408
InvalidArgumentError: Nan in summary histogram for: ndcg_at_k_hist_validation [[{{node ndcg_at_k_hist_validation}} = HistogramSummary[T=DT_DOUBLE, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ndcg_at_k_hist_validation/tag, _arg_Placeholder_1_0_0)]]
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata) 927 try: 928 result = self._run(None, fetches, feed_dict, options_ptr, --> 929 run_metadata_ptr) 930 if run_metadata: 931 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata) 1150 if final_fetches or final_targets or (handle and feed_dict_tensor): 1151 results = self._do_run(handle, final_targets, final_fetches, -> 1152 feed_dict_tensor, options, run_metadata) 1153 else: 1154 results = []
~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata) 1326 if handle is None: 1327 return self._do_call(_run_fn, feeds, fetches, targets, options, -> 1328 run_metadata) 1329 else: 1330 return self._do_call(_prun_fn, handle, feeds, fetches)
~.conda\envs\reco_base\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args) 1346 pass 1347 message = error_interpolation.interpolate(message, self._graph) -> 1348 raise type(e)(node_def, op, message) 1349 1350 def _extend_graph(self):
InvalidArgumentError: Nan in summary histogram for: ndcg_at_k_hist_validation
[[node ndcg_at_k_hist_validation (defined at
Caused by op 'ndcg_at_k_hist_validation', defined at:
File "C:\Users\Karthik.conda\envs\reco_base\lib\runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "C:\Users\Karthik.conda\envs\reco_base\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\Karthik.conda\envs\reco_base\lib\site-packages\ipykernel_launcher.py", line 16, in
InvalidArgumentError (see above for traceback): Nan in summary histogram for: ndcg_at_k_hist_validation
[[node ndcg_at_k_hist_validation (defined at
When I print
sess.run(train_op_var, feed_dict=feed_dict)
in the above code.
I get None
Any help would be appreciated. I am using a different dataset but I made it exactly same movielens dataset except I didn't have a timestamp. I have userid, custid, ratings
I get the same error and I don't understand why. Did you manage to solve it?
I have the same error too. Have you found a solution to figure it out yet?
Hi. It's been months since I last worked on this project. I couldn't find any definitive solution so what I did was to ignore the dcg with zero as value which was causing a division by zero error and creating NaNs. It's not the best solution but it was the only way I could make it work. Good luck with everything. I hope you'll be able to find a better way to solve the issue. If you do find a better solution let me know as well. Have a great day. Best, Alina.
Sent from Yahoo Mail on Android
On Tue, Nov 10, 2020 at 5:24 PM, tuanbmhust[email protected] wrote:
I have the same error too. Have you found a solution to figure it out yet?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.