fix: enhance get_papers() to handle cases with missing papers (#80)

Update the get_papers() method to support returning a list of not found paper IDs. When the return_not_found parameter is set to True, the method now returns a tuple containing both a list of found papers and a list of not found IDs.This enhancement addresses the issue where handling of missing papers was not clear.
danielnsilva · Jan 7, 2024 · 3c59a83 · 3c59a83
1 parent 4c94f2f
commit 3c59a83
Show file tree

Hide file tree

Showing 7 changed files with 664 additions and 14 deletions.
diff --git a/semanticscholar/AsyncSemanticScholar.py b/semanticscholar/AsyncSemanticScholar.py
@@ -1,5 +1,6 @@
 import re
-from typing import List, Literal
+from typing import List, Literal, Tuple, Union
+import warnings
 
 from semanticscholar.ApiRequester import ApiRequester
 from semanticscholar.Author import Author
@@ -121,8 +122,9 @@ async def get_paper(
     async def get_papers(
                 self,
                 paper_ids: List[str],
-                fields: list = None
-            ) -> List[Paper]:
+                fields: list = None,
+                return_not_found: bool = False
+            ) -> Union[List[Paper], Tuple[List[Paper], List[str]]]:
         '''Get details for multiple papers at once
 
         :calls: `POST /paper/batch <https://api.semanticscholar.org/api-docs/\
@@ -138,8 +140,13 @@ async def get_papers(
             - biorxiv.org
 
         :param list fields: (optional) list of the fields to be returned.
-        :returns: papers data
-        :rtype: :class:`List` of :class:`semanticscholar.Paper.Paper`
+        :param bool return_not_found: (optional) flag to include not found IDs\
+            in the return, except for IDs in URL:<url> format.
+        :returns: papers data, and optionally list of IDs not found.
+        :rtype: :class:`List` of :class:`semanticscholar.Paper.Paper`\
+            or :class:`Tuple`[:class:`List` of\
+            :class:`semanticscholar.Paper.Paper`,\
+            :class:`List` of :class:`str`]
         :raises: BadQueryParametersException: if no paper was found.
         '''
 
@@ -160,9 +167,36 @@ async def get_papers(
 
         data = await self._requester.get_data_async(
             url, parameters, self.auth_header, payload)
-        papers = [Paper(item) for item in data]
-
-        return papers
+        papers = [Paper(item) for item in data if item is not None]
+
+        prefix_mapping = {
+            'ARXIV': 'ArXiv',
+            'MAG': 'MAG',
+            'ACL': 'ACL',
+            'PMID': 'PubMed',
+            'PMCID': 'PubMedCentral',
+            'CorpusId': 'CorpusId'
+        }
+        prefix_mapping = {v.lower(): k for k, v in prefix_mapping.items()}
+
+        found_ids = set()
+        for paper in papers:
+            found_ids.add(paper.paperId)
+            if paper.externalIds:
+                for prefix, value in paper.externalIds.items():
+                    if prefix.lower() in prefix_mapping:
+                        found_ids.add(
+                            f'{prefix_mapping[prefix.lower()]}:{value}')
+                    else:
+                        found_ids.add(f'{value}')        
+        found_ids = {id.lower() for id in found_ids}  
+
+        not_found_ids = [id for id in paper_ids if id.lower() not in found_ids]
+
+        if not_found_ids:
+            warnings.warn(f"IDs not found: {not_found_ids}")
+
+        return papers if not return_not_found else (papers, not_found_ids)
 
     async def get_paper_authors(
                 self,

diff --git a/semanticscholar/SemanticScholar.py b/semanticscholar/SemanticScholar.py
@@ -1,4 +1,4 @@
-from typing import List, Literal
+from typing import List, Literal, Tuple, Union
 import asyncio
 import nest_asyncio
 
@@ -105,8 +105,9 @@ def get_paper(
     def get_papers(
                 self,
                 paper_ids: List[str],
-                fields: list = None
-            ) -> List[Paper]:
+                fields: list = None,
+                return_not_found: bool = False
+            ) -> Union[List[Paper], Tuple[List[Paper], List[str]]]:
         '''Get details for multiple papers at once
 
         :calls: `POST /paper/batch <https://api.semanticscholar.org/api-docs/\
@@ -122,16 +123,22 @@ def get_papers(
             - biorxiv.org
 
         :param list fields: (optional) list of the fields to be returned.
-        :returns: papers data
-        :rtype: :class:`List` of :class:`semanticscholar.Paper.Paper`
+        :param bool return_not_found: (optional) flag to include not found IDs\
+            in the return, except for IDs in URL:<url> format.
+        :returns: papers data, and optionally list of IDs not found.
+        :rtype: :class:`List` of :class:`semanticscholar.Paper.Paper`\
+            or :class:`Tuple`[:class:`List` of\
+            :class:`semanticscholar.Paper.Paper`,\
+            :class:`List` of :class:`str`]
         :raises: BadQueryParametersException: if no paper was found.
         '''
 
         loop = asyncio.get_event_loop()
         papers = loop.run_until_complete(
             self._AsyncSemanticScholar.get_papers(
                 paper_ids=paper_ids,
-                fields=fields
+                fields=fields,
+                return_not_found=return_not_found
                 )
         )
 

diff --git a/tests/data/test_get_papers_not_found_warning.yaml b/tests/data/test_get_papers_not_found_warning.yaml
@@ -0,0 +1,140 @@
+interactions:
+- request:
+    body: '{"ids": ["CorpusId:211530585", "CorpusId:470667", "10.2139/ssrn.2250500",
+      "0f40b1f08821e22e859c6050916cec3667778613"]}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '118'
+      content-type:
+      - application/json
+      host:
+      - api.semanticscholar.org
+      user-agent:
+      - python-httpx/0.26.0
+    method: POST
+    uri: https://api.semanticscholar.org/graph/v1/paper/batch?fields=abstract,authors,citationCount,citationStyles,corpusId,externalIds,fieldsOfStudy,influentialCitationCount,isOpenAccess,journal,openAccessPdf,paperId,publicationDate,publicationTypes,publicationVenue,referenceCount,s2FieldsOfStudy,title,url,venue,year
+  response:
+    content: '[null, {"paperId": "c31c87c591a25c64fbaa82e8ac6a81831b6ac7ce", "externalIds":
+      {"MAG": "2096684396", "DOI": "10.2139/ssrn.288970", "CorpusId": 470667}, "corpusId":
+      470667, "publicationVenue": null, "url": "https://www.semanticscholar.org/paper/c31c87c591a25c64fbaa82e8ac6a81831b6ac7ce",
+      "title": "How Much Should We Trust Differences-in-Differences Estimates?", "abstract":
+      "Most Difference-in-Difference (DD) papers rely on many years of data and focus
+      on serially correlated outcomes. Yet almost all these papers ignore the bias
+      in the estimated standard errors that serial correlation introduce4s. This is
+      especially troubling because the independent variable of interest in DD estimation
+      (e.g., the passage of law) is itself very serially correlated, which will exacerbate
+      the bias in standard errors. To illustrate the severity of this issue, we randomly
+      generate placebo laws in state-level data on female wages from the Current Population
+      Survey. For each law, we use OLS to compute the DD estimate of its ''effect''
+      as well as the standard error for this estimate. The standard errors are severely
+      biased: with about 20 years of data, DD estimation finds an ''effect'' significant
+      at the 5% level of up to 45% of the placebo laws. Two very simple techniques
+      can solve this problem for large sample sizes. The first technique consists
+      in collapsing the data and ignoring the time-series variation altogether; the
+      second technique is to estimate standard errors while allowing for an arbitrary
+      covariance structure between time periods. We also suggest a third technique,
+      based on randomization inference testing methods, which works well irrespective
+      of sample size. This technique uses the empirical distribution of estimated
+      effects for placebo laws to form the test distribution.", "venue": "", "year":
+      2001, "referenceCount": 30, "citationCount": 10207, "influentialCitationCount":
+      564, "isOpenAccess": true, "openAccessPdf": {"url": "http://papers.nber.org/papers/w8841.pdf",
+      "status": "BRONZE"}, "fieldsOfStudy": ["Psychology", "Economics", "Mathematics"],
+      "s2FieldsOfStudy": [{"category": "Psychology", "source": "external"}, {"category":
+      "Economics", "source": "external"}, {"category": "Mathematics", "source": "external"},
+      {"category": "Economics", "source": "s2-fos-model"}], "publicationTypes": ["Review"],
+      "publicationDate": "2001-10-01", "journal": {"name": "Experimental & Empirical
+      Studies eJournal"}, "citationStyles": {"bibtex": "@Article{Bertrand2001HowMS,\n
+      author = {Marianne Bertrand and E. Duflo and S. Mullainathan},\n journal = {Experimental
+      & Empirical Studies eJournal},\n title = {How Much Should We Trust Differences-in-Differences
+      Estimates?},\n year = {2001}\n}\n"}, "authors": [{"authorId": "81141608", "name":
+      "Marianne Bertrand"}, {"authorId": "2259683", "name": "E. Duflo"}, {"authorId":
+      "2062143", "name": "S. Mullainathan"}]}, {"paperId": "cb1ebd913c3724c599f6b276b14b5c6253da68f3",
+      "externalIds": {"MAG": "2148197077", "DOI": "10.2139/ssrn.2250500", "CorpusId":
+      3142471}, "corpusId": 3142471, "publicationVenue": null, "url": "https://www.semanticscholar.org/paper/cb1ebd913c3724c599f6b276b14b5c6253da68f3",
+      "title": "The Miracle of Microfinance? Evidence from a Randomized Evaluation",
+      "abstract": "Microcredit has spread extremely rapidly since its beginnings in
+      the late 1970s, but whether and how much is helps the poor is the subject of
+      intense debate. This paper reports on the \u2026rst randomized evaluation of
+      the impact of introducing microcredit in a new market. Half of 104 slums in
+      Hyderabad, India were randomly selected for opening of an MFI branch while the
+      remainder were not. We show that the intervention increased total MFI borrow.",
+      "venue": "", "year": 2013, "referenceCount": 67, "citationCount": 2069, "influentialCitationCount":
+      240, "isOpenAccess": true, "openAccessPdf": {"url": "https://dspace.mit.edu/bitstream/1721.1/95941/1/Banerjee_The%20miracle.pdf",
+      "status": "GREEN"}, "fieldsOfStudy": ["Business", "Economics", "Geography"],
+      "s2FieldsOfStudy": [{"category": "Business", "source": "external"}, {"category":
+      "Economics", "source": "external"}, {"category": "Geography", "source": "external"},
+      {"category": "Economics", "source": "s2-fos-model"}], "publicationTypes": null,
+      "publicationDate": "2013-04-10", "journal": {"name": "ERN: Credit Risk (Topic)"},
+      "citationStyles": {"bibtex": "@Article{Duflo2013TheMO,\n author = {E. Duflo
+      and A. Banerjee and R. Glennerster and Cynthia Kinnan},\n journal = {ERN: Credit
+      Risk (Topic)},\n title = {The Miracle of Microfinance? Evidence from a Randomized
+      Evaluation},\n year = {2013}\n}\n"}, "authors": [{"authorId": "2259683", "name":
+      "E. Duflo"}, {"authorId": "2237651454", "name": "A. Banerjee"}, {"authorId":
+      "4249203", "name": "R. Glennerster"}, {"authorId": "31549526", "name": "Cynthia
+      Kinnan"}]}, {"paperId": "0f40b1f08821e22e859c6050916cec3667778613", "externalIds":
+      {"DOI": "10.1257/rct.1355", "CorpusId": 255313304}, "corpusId": 255313304, "publicationVenue":
+      null, "url": "https://www.semanticscholar.org/paper/0f40b1f08821e22e859c6050916cec3667778613",
+      "title": "Improving Third-Party Audits and Regulatory Compliance in India",
+      "abstract": "Researchers: Esther Duflo Michael Greenstone Nick Ryan Rohini Pande
+      Sector(s): Environment, Energy, and Climate Change, Political Economy and Governance,
+      Firms J-PAL office: J-PAL South Asia Location: Ahmedabad and Surat, Gujarat,
+      India Sample: 473 industrial plants Target group: Small and medium enterprises
+      Outcome of interest: Pollution Climate change mitigation Intervention type:
+      Audits Monetary incentives AEA RCT registration number: AEARCTR-0001355 Data:
+      Download from the AEA Partner organization(s): Evidence for Policy Design (EPoD),
+      Government of India, State of Gujarat Pollution Control Board (GPCB), Harvard
+      University Sustainability Science Program (SSP), International Growth Center
+      (IGC), International Initiative for Impact Evaluation (3ie), MIT Center for
+      Energy and Environmental Policy Research (CEEPR), National Science Foundation
+      (NSF)", "venue": "", "year": 2023, "referenceCount": 2, "citationCount": 0,
+      "influentialCitationCount": 0, "isOpenAccess": true, "openAccessPdf": null,
+      "fieldsOfStudy": null, "s2FieldsOfStudy": [{"category": "Environmental Science",
+      "source": "s2-fos-model"}, {"category": "Business", "source": "s2-fos-model"},
+      {"category": "Economics", "source": "s2-fos-model"}], "publicationTypes": null,
+      "publicationDate": null, "journal": null, "citationStyles": {"bibtex": "@Inproceedings{Duflo2023ImprovingTA,\n
+      author = {E. Duflo and M. Greenstone and Nick Ryan},\n title = {Improving Third-Party
+      Audits and Regulatory Compliance in India},\n year = {2023}\n}\n"}, "authors":
+      [{"authorId": "2259683", "name": "E. Duflo"}, {"authorId": "4711469", "name":
+      "M. Greenstone"}, {"authorId": "2071339188", "name": "Nick Ryan"}]}]
+
+      '
+    headers:
+      Access-Control-Allow-Origin:
+      - '*'
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6838'
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 07 Jan 2024 13:10:58 GMT
+      Via:
+      - 1.1 7d4cada96f0b733f4f539a3bab2e2d16.cloudfront.net (CloudFront)
+      X-Amz-Cf-Id:
+      - ZfUdxcWnU7jWhWD3wvruuhabseWM2DL2_zloBiqD2XQRc43X4DFujg==
+      X-Amz-Cf-Pop:
+      - GRU3-P4
+      X-Cache:
+      - Miss from cloudfront
+      x-amz-apigw-id:
+      - RK5jYHo-PHcEpeA=
+      x-amzn-Remapped-Connection:
+      - keep-alive
+      x-amzn-Remapped-Content-Length:
+      - '6838'
+      x-amzn-Remapped-Date:
+      - Sun, 07 Jan 2024 13:10:58 GMT
+      x-amzn-Remapped-Server:
+      - gunicorn
+      x-amzn-RequestId:
+      - 3d0d2ad9-f238-4f06-a98c-4fcce3eb2838
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1