Merge pull request #48 from dvklopfenstein/dvk

added aummarize script

makefile

@@ -5,6 +5,9 @@ install:
 
 py:
 	find src -name \*.py
+
+e:
+	find src/pmidcite/eutils -name \*.py
 
 t:
 	find src/tests -regextype posix-extended -regex ".*[a-z]+.py"
@@ -113,3 +116,6 @@ clean:
 clobber_tmp:
 	rm -rf ./icite
 	rm -rf ./src/tests/icite
+
+clobber:
+	make -f makefile clobber_tmp clobber_dist

src/bin/summarize_papers.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+"""Summarize NIH citation data for requested papers from the commandline or in files"""
+
+__copyright__ = "Copyright (C) 2022-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
+
+from pmidcite.cli.summarize_papers import SummarizePapersCli # get_argparser
+from pmidcite.cfg import get_cfgparser
+
+
+def main():
+    """Summarize NIH citation data for requested papers from the commandline or in files"""
+    SummarizePapersCli(get_cfgparser(prt=None)).cli()
+
+if __name__ == '__main__':
+    main()
+
+# Copyright (C) 2022-present, DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/cli/summarize_papers.py

@@ -0,0 +1,75 @@
+"""Summarize NIH citation data for requested papers from the commandline or in files"""
+
+from sys import stdout
+from argparse import ArgumentParser
+from pmidcite.cli.utils import prt_loc_rcfile
+from pmidcite.cli.utils import get_files_exists
+from pmidcite.summarize_papers import SummarizePapers
+
+__copyright__ = "Copyright (C) 2022-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
+
+
+class SummarizePapersCli:
+    """Summarize NIH citation data for requested papers from the commandline or in files"""
+
+    def __init__(self, cfg):
+        self.cfg = cfg
+
+    def get_argparser(self):
+        """Argument parser for summarizing the citations on set(s) of papers"""
+        parser = ArgumentParser(
+            description="Summarize NIH's citation on a set(s) of papers",
+            add_help=False)
+        ##cfg = self.cfg
+        # https://docs.python.org/3/library/argparse.html
+        # https://docs.python.org/3/library/argparse.html#action
+        # - PMIDs ----------------------------------------------------------------------------
+        parser.add_argument(
+            '-h', '--help', action='store_true',
+            help='print this help message and exit (also --help)')
+        parser.add_argument(
+            'files', metavar='FILES', type=str, nargs='*',
+            help='File(s) containing NIH citation data for numerous papers with PMIDs')
+        ##parser.add_argument(
+        ##    '-i', '--infile', nargs='*',
+        ##    help='Files containing NIH citation data for numerous papers with PMIDs')
+        ##parser.add_argument(
+        ##    '-o', '--outfile',
+        ##    help='Write current citation report to an ASCII text file.')
+        ##parser.add_argument(
+        ##    '-f', '--force_write', action='store_true',
+        ##    help='if an existing outfile file exists, overwrite it.')
+
+        self.cfg.get_nihgrouper().add_arguments(parser)
+        ##parser.add_argument(
+        ##    '--md', action='store_true',
+        ##    help='Print using markdown table format.')
+        parser.add_argument(
+            '--print-rcfile', action='store_true',
+            help='Print the location of the pmidcite configuration file (env var: PMIDCITECONF)')
+        return parser
+
+
+    def cli(self):
+        """Run citation summary on a set(s) of PMIDs"""
+        argparser = self.get_argparser()
+        args = argparser.parse_args()
+        print('ARGS CITE SUMMARY ../pmidcite/src/pmidcite/cli/summarize_papers.py', args)
+        if args.print_rcfile:
+            prt_loc_rcfile(self.cfg, stdout)
+            return
+        files = get_files_exists(args.files)
+        if args.help or not files:
+            argparser.print_help()
+            print('\nHelp message printed because: -h or --help == True')
+            return
+        ##self._run(args, argparser)
+        nih_grouper = self.cfg.get_nihgrouper()
+        for filename in files:
+            sumpap = SummarizePapers.from_file(filename, nih_grouper)
+            print(sumpap.str_oneline())
+        return
+
+
+# Copyright (C) 2022-present, DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/cli/utils.py

@@ -1,7 +1,7 @@
 """Read a file created by pmidcite and write simple text file of PMIDs"""
 
-__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein. All rights reserved."
-__author__ = "DV Klopfenstein"
+__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
 
 from os.path import exists
 from os.path import split
@@ -48,6 +48,16 @@ def get_all(pmid_list, fin_pmids, top_cit_ref=None):
                 print('  MISSING: {FILE}'.format(FILE=fin))
     return pmids
 
+def get_files_exists(files, prt=None):
+    """Get the files that exist"""
+    ret = []
+    for filename in files:
+        if exists(filename):
+            ret.append(filename)
+        elif prt:
+            prt.write(f'**WARNING: FILE NOT EXIST({filename})\n')
+    return ret
+
 def _read_pmids(fin, top_cit_ref):
     """Read PMIDs from a file. One PMID per line."""
     pmids = []
@@ -125,5 +135,12 @@ def _get_outfile_resolved(outfile, append_outfile):
         return append_outfile
     return None
 
+def prt_loc_rcfile(cfg, prt=stdout):
+    """Print location of configuration file"""
+    prt.write('\n**NOTE FROM ARG(--print-rcfile):\n')
+    cfg.prt_cfgfile()
+    prt.write('\n')
+
+
 
-# Copyright (C) 2019-present DV Klopfenstein. All rights reserved.
+# Copyright (C) 2019-present DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/eutils/cmds/efetch.py

@@ -1,8 +1,8 @@
 """Fetch items and write"""
 # https://www.ncbi.nlm.nih.gov/books/NBK25499/#chapter4.EFetch
 
-__author__ = 'DV Klopfenstein'
-__copyright__ = "Copyright (C) 2016-present DV Klopfenstein. All rights reserved."
+__author__ = 'DV Klopfenstein, PhD'
+__copyright__ = "Copyright (C) 2016-present DV Klopfenstein, PhD. All rights reserved."
 __license__ = "GPL"
 
 import sys
@@ -17,7 +17,7 @@ class EFetch(CommandBase):
     #### def __init__(self, retmax=10000, rettype='medline', retmode='text', batch_size=100, **kws):
     def __init__(self, rettype='medline', retmode='text', batch_size=100, **kws):
         kws_base = {k:v for k, v in kws.items() if k in CommandBase.exp_kws}
-        print('FFFFFFFFFFFFFFFFFFFF', kws_base)
+        ##print('FFFFFFFFFFFFFFFFFFFF', kws_base)
         super(EFetch, self).__init__(**kws_base)
 
     def efetch_and_write(self, ostrm, database, webenv, querykey, num_fetches):
@@ -29,7 +29,7 @@ def efetch_and_write(self, ostrm, database, webenv, querykey, num_fetches):
         for start in range(0, num_fetches, self.batch_size):
             ## msg = msg_fmt.format(querykey, database, self.batch_size, start, self.desc)
             ## sys.stdout.write(msg)
-            print('SSSSSSSSSSSSSSSSSSSSSSSTART:', start)
+            ## print('SSSSSSSSSSSSSSSSSSSSSSSTART:', start)
             txt = self.efetch_txt(start, self.batch_size, database, webenv, querykey)
 
             if txt is not None:
@@ -73,4 +73,4 @@ def efetch_txt(self, start, retmax, database, webenv, querykey):
             sys.stdout.write("  querykey:   {}\n".format(querykey))
 
 
-# Copyright (C) 2016-present DV Klopfenstein. All rights reserved.
+# Copyright (C) 2016-present DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/icite/dnldr/pmid_dnlder.py

@@ -1,8 +1,8 @@
 """Given a PubMed ID (PMID), download a list of publications which cite and reference it"""
 # https://icite.od.nih.gov/api
 
-__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein. All rights reserved."
-__author__ = "DV Klopfenstein"
+__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
 
 from os.path import exists
 from os.path import join
@@ -53,7 +53,8 @@ def _dnld_icites(self, pmid2foutpy):
             for nih_dict in nihdicts:
                 s_wrpy(pmid2foutpy[nih_dict['pmid']], nih_dict)
             s_get_group = self.nihgrouper.get_group
-            return [NIHiCiteEntry(d, s_get_group(d['nih_percentile'])) for d in nihdicts]
+            # pylint: disable=line-too-long
+            return [NIHiCiteEntry.from_jsondct(d, s_get_group(d['nih_percentile'])) for d in nihdicts]
         return []
 
     def get_icite(self, pmid):
@@ -63,7 +64,7 @@ def get_icite(self, pmid):
             nih_dict = self.api.dnld_nihdict(pmid)
             if nih_dict:
                 self._wrpy(file_pmid, nih_dict)
-                return NIHiCiteEntry(
+                return NIHiCiteEntry.from_jsondct(
                     nih_dict,
                     self.nihgrouper.get_group(nih_dict['nih_percentile']))
         return self.loader.load_icite(file_pmid)  # NIHiCiteEntry
@@ -99,4 +100,4 @@ def _load_icites(self, pmids, pmid2py):
         return nihentries_loaded
 
 
-# Copyright (C) 2019-present DV Klopfenstein. All rights reserved.
+# Copyright (C) 2019-present DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/icite/dnldr/pmid_dnlder_only.py

@@ -1,8 +1,8 @@
 """Given a PubMed ID (PMID), download a list of publications which cite and reference it"""
 # https://icite.od.nih.gov/api
 
-__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein. All rights reserved."
-__author__ = "DV Klopfenstein"
+__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
 
 from pmidcite.icite.dnldr.pmid_dnlder_base import NIHiCiteDownloaderBase
 from pmidcite.icite.entry import NIHiCiteEntry
@@ -24,17 +24,18 @@ def _dnld_icites(self, pmids):
         nihdicts = self.api.dnld_nihdicts(pmids)
         if nihdicts:
             s_get_group = self.nihgrouper.get_group
-            return [NIHiCiteEntry(d, s_get_group(d['nih_percentile'])) for d in nihdicts]
+            # pylint: disable=line-too-long
+            return [NIHiCiteEntry.from_jsondct(d, s_get_group(d['nih_percentile'])) for d in nihdicts]
         return []
 
     def get_icite(self, pmid):
         """Load or download NIH iCite data for requested PMID"""
         nih_dict = self.api.dnld_nihdict(pmid)
         if nih_dict:
-            return NIHiCiteEntry(
+            return NIHiCiteEntry.from_jsondct(
                 nih_dict,
                 self.nihgrouper.get_group(nih_dict['nih_percentile']))
         return None
 
 
-# Copyright (C) 2019-present DV Klopfenstein. All rights reserved.
+# Copyright (C) 2019-present DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/icite/dnldr/pmid_loader.py

@@ -1,7 +1,7 @@
 """Given a PubMed ID (PMID), return a list of publications which cite it"""
 
-__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein. All rights reserved."
-__author__ = "DV Klopfenstein"
+__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
 
 from sys import stdout
 from os.path import join
@@ -64,7 +64,8 @@ def load_icite(self, file_pmid):
             mod = module_from_spec(spec)
             spec.loader.exec_module(mod)
             ## print('LLLLLLLLLLLLL load_icite', file_pmid)
-            return NIHiCiteEntry(mod.ICITE, self.nih_grouper.get_group(mod.ICITE['nih_percentile']))
+            # pylint: disable=line-too-long
+            return NIHiCiteEntry.from_jsondct(mod.ICITE, self.nih_grouper.get_group(mod.ICITE['nih_percentile']))
         return None
 
     def load_pmid(self, pmid):
@@ -84,4 +85,4 @@ def _get_pmids_linked(self, icites_top):
         ## return pmids_linked
 
 
-# Copyright (C) 2019-present DV Klopfenstein. All rights reserved.
+# Copyright (C) 2019-present DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/icite/entry.py

@@ -1,8 +1,8 @@
 """Holds NIH iCite data for one PubMed ID (PMID)"""
 # https://icite.od.nih.gov/api
 
-__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein. All rights reserved."
-__author__ = "DV Klopfenstein"
+__copyright__ = "Copyright (C) 2019-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
 
 from sys import stdout
 
@@ -56,19 +56,25 @@ class NIHiCiteEntry:
         author1='authors',
         title='title')
 
-    def __init__(self, icite_dct, nih_group):
-        self.pmid = icite_dct['pmid']
-        self.dct = icite_dct
+    def __init__(self, pmid=None, dct=None):
+        self.pmid = pmid
+        self.dct = dct
+
+    @classmethod
+    def from_jsondct(cls, icite_dct, nih_group_num):
+        """Construct NIHiCiteEntry from jsondct downloaded from NIH using Entrez utils"""
+        cls_dct = icite_dct
         nih_perc = icite_dct['nih_percentile']
-        self.dct['nih_group'] = nih_group  # 0 - 5
+        cls_dct['nih_group'] = nih_group_num  # 0 - 5
         # pylint: disable=line-too-long
-        self.dct['num_auth'] = len(icite_dct['authors'])
-        self.dct['num_clin'] = len(icite_dct['cited_by_clin'])
-        self.dct['num_cite'] = len(icite_dct['cited_by'])
-        num_cites_all = len(set(self.dct['cited_by_clin']).union(self.dct['cited_by']))
-        self.dct['num_cites_all'] = num_cites_all
-        self.dct['nih_perc'] = round(nih_perc) if nih_perc is not None else 110 + num_cites_all
-        self.dct['num_refs'] = len(icite_dct['references'])
+        cls_dct['num_auth'] = len(icite_dct['authors'])
+        cls_dct['num_clin'] = len(icite_dct['cited_by_clin'])
+        cls_dct['num_cite'] = len(icite_dct['cited_by'])
+        num_cites_all = len(set(cls_dct['cited_by_clin']).union(cls_dct['cited_by']))
+        cls_dct['num_cites_all'] = num_cites_all
+        cls_dct['nih_perc'] = round(nih_perc) if nih_perc is not None else 110 + num_cites_all
+        cls_dct['num_refs'] = len(icite_dct['references'])
+        return cls(icite_dct['pmid'], cls_dct)
 
     ## TBD:
     ## def __eq__(self, rhs):
@@ -222,4 +228,4 @@ def __lt__(self, rhs):
         return self.pmid < rhs.pmid
 
 
-# Copyright (C) 2019-present DV Klopfensteinr,. All rights reserved.
+# Copyright (C) 2019-present DV Klopfenstein, PhD. All rights reserved.

src/pmidcite/icite/nih_grouper.py

@@ -11,11 +11,22 @@ class NihGrouper:
 
     ntobj = namedtuple('NtNihGroup', 'val txt')
 
+    group_chrs = ['0', '1', '2', '3', '4', 'i']
+
     def __init__(self, group1_min=2.1, group2_min=15.7, group3_min=83.9, group4_min=97.5):
         self.min1 = group1_min
         self.min2 = group2_min
         self.min3 = group3_min
         self.min4 = group4_min
+        #print(f'group1_min: {group1_min}')
+        #print(f'group2_min: {group2_min}')
+        #print(f'group3_min: {group3_min}')
+        #print(f'group4_min: {group4_min}')
+
+    def str_group(self, nih_percentile):
+        """Get chr representing group number"""
+        group_num = self.get_group(nih_percentile)
+        return 'i' if group_num == 5 else str(group_num)
 
     def get_group(self, nih_percentile):
         """Assign group numbers to the NIH percentile values using the 68-95-99.7 rule"""

src/pmidcite/scripts/summarize_papers.py

@@ -0,0 +1,15 @@
+"""Summarize NIH citation data for requested papers from the commandline or in files"""
+
+__copyright__ = "Copyright (C) 2022-present, DV Klopfenstein, PhD. All rights reserved."
+__author__ = "DV Klopfenstein, PhD"
+
+from pmidcite.cli.summarize_papers import SummarizePapersCli # get_argparser
+from pmidcite.cfg import get_cfgparser
+
+
+def main():
+    """Summarize NIH citation data for requested papers from the commandline or in files"""
+    SummarizePapersCli(get_cfgparser(prt=None)).cli()
+
+
+# Copyright (C) 2022-present, DV Klopfenstein, PhD. All rights reserved.