Hi,
I;ve submitted via zip file and got the following error message:
Generate Predictions On Training Sample : Inference failed
I can’t seem to view the error log files to trace the causes. Could you assist with this please?
Submission #123205
Many thanks!
Hello @stochastickang
You need to click on the “Evaluation Status” to find the links to logs. In this case, the relevant logs are un generate-predictions link.
Hi,
Log says FileNotFoundError: [Errno 2] No such file or directory: ‘trained_model.pickle’
I left load_model and save_model from model.py intact. Also, I have not changed train.py and predict.py.
Can you assist to resolve this issue please?
Many thanks
Yes of course 
So in your submission I can see you have not actually uploaded the trained model. If you have not altered the save and load functions then once you run the train.py file, it should generate the trained_model.pickle file.
You need to upload that as well. See more on the logic of it here. Or if it’s unclear let me know how I can clarify 
I did test prior to submission and it did create trained_model.pickle file. But not sure why this isn’t the case when I submit.
Am I missing something with something relating to path or some admin matters?
Would be great if you could assist further with this issue.
Many thanks
Ah ok, if it did create the pickle file then maybe it’s just not created in the right place, all you have to do is to make sure the pickle file is in your zip file. That should work.
Could you try one more time, making sure the pickle file is in there, and then if you have run into an issue we can dig deeper and get to the bottom of it 
Same error as before ( Generate Predictions On Training Sample : Inference failed)
I’ve included trained_model.pickle file in the zip file… but unsuccessful…
Submission # 123281
Could you have a look into this please?
Thanks!
Ah ok, so this time the model is there!
But the error is actually different, if you click on the hyperlink that says generate-predictions you will see that the error this time is:
########## Generating Predictions on /data/mse_debug_data.csv #############
########## Generating Predictions on /data/mse_debug_data.csv #############
Traceback (most recent call last):
File "predict.py", line 56, in <module>
claims = model.predict_expected_claim(trained_model, Xraw)
File "/home/aicrowd/model.py", line 660, in predict_expected_claim
pred_prob = model_logit.predict_proba(X_processed)
File "/usr/local/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py", line 1468, in predict_proba
return super()._predict_proba_lr(X)
File "/usr/local/lib/python3.8/site-packages/sklearn/linear_model/_base.py", line 321, in _predict_proba_lr
prob = self.decision_function(X)
File "/usr/local/lib/python3.8/site-packages/sklearn/linear_model/_base.py", line 286, in decision_function
raise ValueError("X has %d features per sample; expecting %d"
ValueError: X has 93 features per sample; expecting 95
Traceback (most recent call last):
File "predict.py", line 56, in <module>
claims = model.predict_expected_claim(trained_model, Xraw)
File "/home/aicrowd/model.py", line 660, in predict_expected_claim
pred_prob = model_logit.predict_proba(X_processed)
File "/usr/local/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py", line 1468, in predict_proba
return super()._predict_proba_lr(X)
File "/usr/local/lib/python3.8/site-packages/sklearn/linear_model/_base.py", line 321, in _predict_proba_lr
prob = self.decision_function(X)
File "/usr/local/lib/python3.8/site-packages/sklearn/linear_model/_base.py", line 286, in decision_function
raise ValueError("X has %d features per sample; expecting %d"
ValueError: X has 93 features per sample; expecting 95
Ok. Thanks.
My recent submission seems to be taking too long… no error messages from evaluation status.
Submission number:123436.
Could you have a look please?
Can you please resubmit that one? Sometimes the page fails to update and we are looking into fixing it, sorry for the inconvenience
All good now. Thanks!