chore:formatting

paperscraper/arxiv/arxiv.py

@@ -1,10 +1,9 @@
 from typing import Dict, List, Union
 
+import arxiv
 import pandas as pd
 from tqdm import tqdm
 
-import arxiv
-
 from ..utils import dump_papers
 from .utils import get_query_from_keywords
 

paperscraper/get_dumps/utils/chemrxiv/utils.py

@@ -1,4 +1,5 @@
 """Misc utils to download chemRxiv dump"""
+
 import json
 import logging
 import os

paperscraper/impact.py

@@ -97,13 +97,15 @@ def calculate_fuzziness_score(row):
 
         # Prepare the final result
         results = [
-            row.to_dict()
-            if return_all
-            else {
-                "journal": row["journal"],
-                "factor": row["factor"],
-                "score": row["score"],
-            }
+            (
+                row.to_dict()
+                if return_all
+                else {
+                    "journal": row["journal"],
+                    "factor": row["factor"],
+                    "score": row["score"],
+                }
+            )
             for _, row in matched_df.iterrows()
         ]
 

paperscraper/plotting.py

@@ -304,8 +304,10 @@ def plot_single(
             plt.bar(ind, np.zeros((len(ind),)), color="k", bottom=bottom)
         )
 
-    plt.ylabel("Counts", size=17) if not logscale else plt.ylabel(
-        "Counts (log scale)", size=17
+    (
+        plt.ylabel("Counts", size=17)
+        if not logscale
+        else plt.ylabel("Counts (log scale)", size=17)
     )
     plt.xlabel("Years", size=17)
     plt.title(title_text, size=17)

paperscraper/pubmed/tests/test_pubmed.py

@@ -1,31 +1,34 @@
-from paperscraper.pubmed import get_and_dump_pubmed_papers, get_pubmed_papers
-from paperscraper.pubmed.utils import get_query_from_keywords_and_date
 import os
-import pytest
-from unittest.mock import patch
 import tempfile
+from unittest.mock import patch
+
+import pytest
+
+from paperscraper.pubmed import get_and_dump_pubmed_papers, get_pubmed_papers
+from paperscraper.pubmed.utils import get_query_from_keywords_and_date
 
-KEYWORDS = [['machine learning', 'deep learning'], ['zoology']]
+KEYWORDS = [["machine learning", "deep learning"], ["zoology"]]
 
 
 class TestPubMed:
 
     def test_get_and_dump_pubmed(self):
         with tempfile.TemporaryDirectory() as temp_dir:
-            output_filepath = os.path.join(temp_dir, 'tmp.jsonl')
+            output_filepath = os.path.join(temp_dir, "tmp.jsonl")
             get_and_dump_pubmed_papers(KEYWORDS, output_filepath=output_filepath)
             assert os.path.exists(output_filepath), "File was not created"
-
-    def test_email(self):
-        query = get_query_from_keywords_and_date(KEYWORDS, start_date='2020/07/20')
-        df = get_pubmed_papers(query, fields=['emails', 'title', 'authors'])
-        assert 'emails' in df.columns
 
-        query = get_query_from_keywords_and_date(KEYWORDS, end_date='2020/07/20')
-        df = get_pubmed_papers(query, fields=['emails', 'title', 'authors'])
-        assert 'emails' in df.columns
+    def test_email(self):
+        query = get_query_from_keywords_and_date(KEYWORDS, start_date="2020/07/20")
+        df = get_pubmed_papers(query, fields=["emails", "title", "authors"])
+        assert "emails" in df.columns
 
-        query = get_query_from_keywords_and_date(KEYWORDS, start_date='2020/07/10', end_date='2020/07/20')
-        df = get_pubmed_papers(query, fields=['emails', 'title', 'authors'])
-        assert 'emails' in df.columns
+        query = get_query_from_keywords_and_date(KEYWORDS, end_date="2020/07/20")
+        df = get_pubmed_papers(query, fields=["emails", "title", "authors"])
+        assert "emails" in df.columns
 
+        query = get_query_from_keywords_and_date(
+            KEYWORDS, start_date="2020/07/10", end_date="2020/07/20"
+        )
+        df = get_pubmed_papers(query, fields=["emails", "title", "authors"])
+        assert "emails" in df.columns

paperscraper/scholar/tests/test_scholar.py

@@ -1,8 +1,9 @@
+import functools
 import logging
+
 import pandas as pd
 import pytest
 from scholarly._proxy_generator import MaxTriesExceededException
-import functools
 
 from paperscraper.scholar import (
     get_and_dump_scholar_papers,
@@ -58,8 +59,8 @@ def test_basic_search(self):
                 ]
             ]
         )
-    
+
     @handle_scholar_exception
     def test_bad_search(self):
         results = get_scholar_papers("GT4SDfsdhfiobfpsdfbsdp")
-        assert len(results) == 0  
+        assert len(results) == 0

paperscraper/tests/test_dump.py

@@ -23,7 +23,7 @@ def setup_medrxiv(self):
     @pytest.fixture
     def setup_biorxiv(self):
         return lambda: biorxiv(max_retries=2)
-   
+
     @pytest.fixture
     def setup_chemrxiv(self):
         return chemrxiv
@@ -78,4 +78,5 @@ def test_arxiv_dumping(self):
 
     def test_dump_existence(self):
         from paperscraper.load_dumps import QUERY_FN_DICT
+
         assert len(QUERY_FN_DICT) > 2

paperscraper/tests/test_pdf.py

@@ -1,8 +1,8 @@
 import logging
 import os
+import shutil
 from pathlib import Path
 from unittest.mock import MagicMock, mock_open, patch
-import shutil
 
 import pytest
 

paperscraper/xrxiv/tests/test_xrxiv.py

@@ -1,24 +1,24 @@
-from paperscraper.xrxiv.xrxiv_query import XRXivQuery
-from paperscraper.get_dumps import medrxiv
 import os
 
+from paperscraper.get_dumps import medrxiv
+from paperscraper.xrxiv.xrxiv_query import XRXivQuery
 
-
-
-covid19 = ['COVID-19', 'SARS-CoV-2']
-ai = ['Artificial intelligence', 'Deep learning', 'Machine learning']
-mi = ['Medical imaging']
+covid19 = ["COVID-19", "SARS-CoV-2"]
+ai = ["Artificial intelligence", "Deep learning", "Machine learning"]
+mi = ["Medical imaging"]
 
 
 class TestXRXiv:
 
     def test_get_medrxiv(self):
-        medrxiv(begin_date="2020-05-01", end_date="2020-05-10", save_path='medrix_tmp_dump.jsonl')
-
+        medrxiv(
+            begin_date="2020-05-01",
+            end_date="2020-05-10",
+            save_path="medrix_tmp_dump.jsonl",
+        )
 
     def test_xriv_querier(self):
-        querier = XRXivQuery('medrix_tmp_dump.jsonl')
+        querier = XRXivQuery("medrix_tmp_dump.jsonl")
         query = [covid19, ai, mi]
-        querier.search_keywords(query, output_filepath='covid19_ai_imaging.jsonl')
-        assert os.path.exists('covid19_ai_imaging.jsonl')
-
+        querier.search_keywords(query, output_filepath="covid19_ai_imaging.jsonl")
+        assert os.path.exists("covid19_ai_imaging.jsonl")

paperscraper/xrxiv/xrxiv_query.py

@@ -1,4 +1,5 @@
 """Query dumps from bioRxiv and medRXiv."""
+
 import logging
 import sys
 from typing import List, Union