def calculate_overall_ranking(self, raw_queries, settings):
api = API()
mean_ap_whole = []
mean_ap_doc = []
queries = self.__raw_queries_to_queries(raw_queries)
settings["mode"] = Mode.without_importance_to_sections
settings_sec = copy.deepcopy(settings)
settings_sec["mode"] = Mode.importance_to_sections
for i, query in enumerate(queries):
progressBar(i, len(queries))
ranked_papers_whole = api.get_papers({"whole-document": query["search_query"]}, settings)
ranked_papers_sec = api.get_papers({query["imrad"]: query["search_query"]}, settings_sec)
relevant_paper = [api.get_paper(reference["paper_id"]) for reference in query["references"]]
ap_whole = self.average_precision(ranked_papers_whole, relevant_paper)
ap_doc = self.average_precision(ranked_papers_sec, relevant_paper)
mean_ap_whole.append(ap_whole)
mean_ap_doc.append(ap_doc)
result_whole = sum(mean_ap_whole) / len(mean_ap_whole)
result_doc = sum(mean_ap_doc) / len(mean_ap_doc)
print()
print("{} & {} & {}".format(Mode.without_importance_to_sections.name.replace("_", " "), len(mean_ap_whole),
round(result_whole, 4)))
print("{} & {} & {}".format(Mode.importance_to_sections.name.replace("_", " "), len(mean_ap_doc),
round(result_doc, 4)))
def calculate_ranking_sections(self, raw_queries, settings):
api = API()
mean_ap_intro, mean_ap_background, mean_ap_methods, mean_ap_result, mean_ap_discussion = [], [], [], [], []
queries = self.__raw_queries_to_queries(raw_queries)
for i, query in enumerate(queries):
progressBar(i, len(queries))
relevant_paper = [api.get_paper(reference["paper_id"]) for reference in query["references"]]
ranked_papers_intro = api.get_papers({IMRaDType.INTRODUCTION.name: query["search_query"]}, settings)
ranked_papers_background = api.get_papers({IMRaDType.BACKGROUND.name: query["search_query"]}, settings)
ranked_papers_methods = api.get_papers({IMRaDType.METHODS.name: query["search_query"]}, settings)
ranked_papers_result = api.get_papers({IMRaDType.RESULTS.name: query["search_query"]}, settings)
ranked_papers_discussion = api.get_papers({IMRaDType.DISCUSSION.name: query["search_query"]}, settings)
ap_intro = self.average_precision(ranked_papers_intro, relevant_paper)
ap_background = self.average_precision(ranked_papers_background, relevant_paper)
ap_methods = self.average_precision(ranked_papers_methods, relevant_paper)
ap_result = self.average_precision(ranked_papers_result, relevant_paper)
ap_discussion = self.average_precision(ranked_papers_discussion, relevant_paper)
mean_ap_intro.append(ap_intro)
mean_ap_background.append(ap_background)
mean_ap_methods.append(ap_methods)
mean_ap_result.append(ap_result)
mean_ap_discussion.append(ap_discussion)
print()
print("{} & {} & {}".format(Mode.only_introduction.name.replace("_", " "),
len(mean_ap_intro), sum(mean_ap_intro) / len(mean_ap_intro)))
print("{} & {} & {}".format(Mode.only_background.name.replace("_", " "),
len(mean_ap_background), sum(mean_ap_background) / len(mean_ap_background)))
print("{} & {} & {}".format(Mode.only_methods.name.replace("_", " "),
len(mean_ap_methods), sum(mean_ap_methods) / len(mean_ap_methods)))
print("{} & {} & {}".format(Mode.only_results.name.replace("_", " "),
len(mean_ap_result), sum(mean_ap_result) / len(mean_ap_result)))
print("{} & {} & {}".format(Mode.only_discussion.name.replace("_", " "),
len(mean_ap_discussion), sum(mean_ap_discussion) / len(mean_ap_discussion)))
def test_simple_ranking(self):
queries = {
IMRaDType.INTRODUCTION.name: "aaa",
IMRaDType.BACKGROUND: "",
IMRaDType.METHODS.name: "aaa bbb ccc ddd eee fff",
IMRaDType.RESULTS.name: "",
IMRaDType.DISCUSSION.name: "",
"whole-document": "ggg aaa ccc"
}
settings = {
**{
"importance_sections": False
},
**TF.get_default_config()
}
api = API()
ret = api.get_papers(queries, settings)
self.assertGreater(len(ret), 0)