I noticed your run script was hardcoded to use spritzer. As discussed in class, spritzer is not really for serious evaluation, but intended only for testing your source code.
Your code works with the hard-coded spritzer test set.
I stole the command from the run script to run it with the benchmark I asked for in the assignment - this is how I got the error
Running your code on the test200 benchmark gives me an error
dietz@jelly:~/datasci/code2/team1$ python ef_ranking_document_generate.py ../all.test200.cbor.outlines ...test200.cbor.paragraphs output-test200.run notenhanced Gathered Pages Gathered Paragraphs Gathered Regular Queries ^CTraceback (most recent call last): File "ef_ranking_document_generate.py", line 81, in
temp_list.append(bm25_instance.bm25_score(query, document))
I noticed your run script was hardcoded to use spritzer. As discussed in class, spritzer is not really for serious evaluation, but intended only for testing your source code.
Your code works with the hard-coded spritzer test set.
I stole the command from the run script to run it with the benchmark I asked for in the assignment - this is how I got the error