Merge pull request #12 from cicirello/i100-i1000-etc

Added i100, i1000, i10000 indexes

CHANGELOG.md

@@ -4,7 +4,7 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased] - 2022-06-30
+## [Unreleased] - 2022-07-16
 
 ### Added
 
@@ -19,6 +19,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### CI/CD
 
 
+## [2.1.0] - 2022-07-16
+
+### Added
+* Calculation of i100-index, i1000-index, and i10000-index, with inclusion in SVG for any of
+  these that are greater than 0.
+
+
 ## [2.0.0] - 2022-06-30
 
 **BREAKING CHANGES** Entry point has changed--now runs as a module rather than a script.

README.md

@@ -11,6 +11,7 @@ This command line utility does the following:
 * retrieves the first page of your Google Scholar profile;
 * parses from that page your total citations, your five-year citation count, your h-index, your i10-index, and the number of citations of your most-cited paper;
 * computes your g-index provided if it is less than 100 ([reason for limitation later](#respect-google-scholars-robotstxt));
+* computes your i100-index, i1000-index, and i10000-index ([doi:10.1007/s11192-020-03831-9](https://doi.org/10.1007/s11192-020-03831-9)), hiding any that are 0, and provided they are less than 100 ([reason for limitation later](#respect-google-scholars-robotstxt));
 * generates a JSON file summarizing these bibliometrics; and
 * generates one or more SVG images summarizing these bibliometrics.
 
@@ -50,12 +51,13 @@ Here is a sample of the JSON summary also generated by the utility:
 
 ```JSON
 {
-    "fiveYear": 376,
-    "g": 45,
+    "fiveYear": 364,
+    "g": 44,
     "h": 25,
     "i10": 33,
+    "i100": 3,
     "most": 228,
-    "total": 2064
+    "total": 2052
 }
 ```
 
@@ -162,8 +164,8 @@ py -m bibliometrics
 ## Respect Google Scholar's robots.txt
 
 If you use this utility, please respect Google Scholar's robots.txt. The reason that the
-g-index is only computed by this utility if it is less than 100 derives from Scholar's
-robots.txt. Here is the relevant excerpt:
+g-index (as well as i100-index, i1000-index, i10000-index) is only computed by this utility 
+if it is less than 100 derives from Scholar's robots.txt. Here is the relevant excerpt:
 
 ```robots.txt
 Allow: /citations?user=

bibliometrics.json

@@ -1,8 +1,9 @@
 {
-    "fiveYear": 376,
-    "g": 45,
+    "fiveYear": 364,
+    "g": 44,
     "h": 25,
     "i10": 33,
+    "i100": 3,
     "most": 228,
-    "total": 2064
+    "total": 2052
 }

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "bibliometrics"
-version = "2.0.0"
+version = "2.1.0"
 authors = [
   { name="Vincent A. Cicirello", email="development@cicirello.org" },
 ]
@@ -25,10 +25,14 @@ keywords = [
     "g-index",
     "h-index",
     "i10-index",
+    "i100-index",
+    "i1000-index",
+    "i10000-index",
     "journals",
     "publications",
     "researcher",
     "scholar",
+    "scientometrics",
     "SVG",
     "SVG generation",
 ]

src/bibliometrics/bibliometrics.py

@@ -86,6 +86,9 @@ def generateBibliometricsImage(metrics, colors, titleText) :
         ("Most-cited paper", "most"),
         ("h-index", "h"),
         ("i10-index", "i10"),
+        ("i100-index", "i100"),
+        ("i1000-index", "i1000"),
+        ("i10000-index", "i10000"),
         ("g-index", "g")
     ]
 
@@ -226,14 +229,20 @@ def parseBibliometrics(page) :
         return metrics
     i10 = page[startStat+1:endStat]
     metrics["i10"] = int(i10.strip())
-    g, most = calculateMostAndG(page)
+    g, most, i100, i1000, i10000 = calculate_additional(page)
     if g > 0 and g < 100 :
         metrics["g"] = g
     if most > 0 :
         metrics["most"] = most
+    if i100 > 0 and i100 < 100 :
+        metrics["i100"] = i100
+    if i1000 > 0 and i1000 < 100 :
+        metrics["i1000"] = i1000
+    if i10000 > 0 and i10000 < 100 :
+        metrics["i10000"] = i10000
     return metrics
 
-def calculateMostAndG(page) :
+def calculate_additional(page) :
     """Calculates the g-index and the most cited paper.
 
     Keyword arguments:
@@ -243,11 +252,14 @@ def calculateMostAndG(page) :
     if len(citesList) > 0 :
         citesList.sort(reverse=True)
         most = citesList[0]
+        i100 = sum(1 for x in citesList if x >= 100)
+        i1000 = sum(1 for x in citesList if x >= 1000)
+        i10000 = sum(1 for x in citesList if x >= 10000)
         for i in range(1, len(citesList)) :
             citesList[i] = citesList[i] + citesList[i-1]
         citesList = [ (i+1, x) for i, x in enumerate(citesList) ]
-        return max(y for y, x in citesList if x >= y*y), most
-    return 0, 0
+        return max(y for y, x in citesList if x >= y*y), most, i100, i1000, i10000
+    return 0, 0, 0, 0, 0
 
 def parseDataForG(page) :
     """Parses the cites per publication for calculating g-index

tests/tests.py

@@ -46,13 +46,17 @@ def test_parse(self) :
             self.assertEqual(33, metrics["i10"])
             self.assertEqual(44, metrics["g"])
             self.assertEqual(228, metrics["most"])
+            self.assertEqual(3, metrics["i100"])
+            self.assertFalse("i1000" in metrics)
+            self.assertFalse("i10000" in metrics)
 
     def test_generate_image(self) :
         metrics = {
             "total" : 2052,
             "fiveYear" : 364,
             "h" : 25,
             "i10" : 33,
+            "i100" : 3,
             "g" : 44,
             "most" : 228
         }
@@ -81,3 +85,4 @@ def test_generate_image(self) :
         if TestBibiometrics.printSampleImage :
             bib.outputImage(image, "images/bibliometrics2.svg")
             bib.outputImage(image2, "images/bibliometrics.svg")
+            bib.outputJSON("bibliometrics.json", metrics)