Add growth graph (#227)

* Add Publication per Year figure: creation in make_md.py and display in README.md

* adjust image path

* Add README to commit

* add numpy and matplotlib to CI env

* remove versions from numpy in requirements file

* remove latex rendering in plot for testing

* Add figure to top

* Adjust figure file paths

* Center the images

* Add dark and brigh version and make relative sizes

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Small fix in make_md

---------

Co-authored-by: Claudius Krause <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

README.md

@@ -5,6 +5,8 @@
 [![download](https://img.shields.io/badge/download-review-blue.svg)](https://iml-wg.github.io/HEPML-LivingReview/assets/hepml_review.pdf)
 [![github](https://badges.aleen42.com/src/github.svg)](https://github.com/iml-wg/HEPML-LivingReview)
 
+<p align="center"><img src="docs/assets/per_year.png" width="75%", alt="Publications per Year"></p>
+
 The purpose of this note is to collect references for modern machine learning as applied to particle physics. A minimal number of categories is chosen in order to be as useful as possible. Note that papers may be referenced in more than one category. The fact that a paper is listed in this document does not endorse or validate its content - that is for the community (and for peer-review) to decide. Furthermore, the classification here is a best attempt and may have flaws - please let us know if (a) we have missed a paper you think should be included, (b) a paper has been misclassified, or (c) a citation for a paper is not correct or if the journal information is now available. In order to be as useful as possible, this document will continue to evolve so please check back before you write your next paper. If you find this review helpful, please consider citing it using ```\cite{hepmllivingreview}``` in `HEPML.bib`.
 
 This review was built with the help of the HEP-ML community, the [INSPIRE REST API](https://github.com/inspirehep/rest-api-doc), and the moderators Benjamin Nachman, Matthew Feickert, Claudius Krause, and Ramon Winterhalder.

docs/index.md

@@ -27,6 +27,9 @@ const expandElements = shouldExpand => {
 [![download](https://img.shields.io/badge/download-review-blue.svg)](https://iml-wg.github.io/HEPML-LivingReview/assets/hepml_review.pdf)
 [![github](https://badges.aleen42.com/src/github.svg)](https://github.com/iml-wg/HEPML-LivingReview)
 
+<p align="center"><img src="assets/per_year.png#only-light" width="75%", alt="Publications per Year"></p>
+<p align="center"><img src="assets/dark_per_year.png#only-dark" width="75%", alt="Publications per Year"></p>
+
 
 <a class="md-button" onClick="expandElements(true)">Expand all sections</a>
 <a class="md-button" onClick="expandElements(false)">Collapse all sections</a>

make_md.py

@@ -1,12 +1,12 @@
 import os
 from dataclasses import dataclass
-from datetime import datetime
+from datetime import date, datetime
 
 import requests
 
 update_journal = False
 update_recent = False
-
+update_plot = False
 
 myfile = open("HEPML.tex", encoding="utf8")
 myfile_readme = open("README.md","w", encoding="utf8")
@@ -28,6 +28,13 @@
     file.write("[![download](https://img.shields.io/badge/download-review-blue.svg)](https://iml-wg.github.io/HEPML-LivingReview/assets/hepml_review.pdf)\n[![github](https://badges.aleen42.com/src/github.svg)](https://github.com/iml-wg/HEPML-LivingReview)\n\n")
 
 
+# neccessary in testing since readme and out file are at different locations.
+# once merged to master, link can point to file on master branch for both
+myfile_readme.write('<p align="center"><img src="docs/assets/per_year.png" width="75%", alt="Publications per Year"></p>\n\n')
+myfile_out.write('<p align="center"><img src="assets/per_year.png#only-light" width="75%", alt="Publications per Year"></p>\n')
+myfile_out.write('<p align="center"><img src="assets/dark_per_year.png#only-dark" width="75%", alt="Publications per Year"></p>\n\n')
+
+
 for file in myfile_readme,myfile_about:
     file.write(r"The purpose of this note is to collect references for modern machine learning as applied to particle physics. A minimal number of categories is chosen in order to be as useful as possible. Note that papers may be referenced in more than one category. The fact that a paper is listed in this document does not endorse or validate its content - that is for the community (and for peer-review) to decide. Furthermore, the classification here is a best attempt and may have flaws - please let us know if (a) we have missed a paper you think should be included, (b) a paper has been misclassified, or (c) a citation for a paper is not correct or if the journal information is now available. In order to be as useful as possible, this document will continue to evolve so please check back before you write your next paper. If you find this review helpful, please consider citing it using ```\cite{hepmllivingreview}``` in `HEPML.bib`.")
     file.write("\n\nThis review was built with the help of the HEP-ML community, the [INSPIRE REST API](https://github.com/inspirehep/rest-api-doc), and the moderators Benjamin Nachman, Matthew Feickert, Claudius Krause, and Ramon Winterhalder.\n\n")
@@ -171,21 +178,25 @@ def convert_from_bib(myline):
             paper=f" [[DOI](https://doi.org/{myentry_dict['doi']})]"
         elif "url" in myentry_dict:
             paper=f" [[url]({myentry_dict['url']})]"
+        YEARS_FOR_PLOT.append(year)
         return "["+myentry_dict["title"]+"](https://arxiv.org/abs/"+myentry_dict["eprint"]+")"+paper+year
     elif "doi" in myentry_dict:
         year=""
         if "year" in myentry_dict:
             year = f" ({myentry_dict['year']})"
+            YEARS_FOR_PLOT.append(year)
         return "["+myentry_dict["title"]+"](https://doi.org/"+myentry_dict["doi"]+")"+year
     elif "url" in myentry_dict:
         year=""
         if "year" in myentry_dict:
             year = f" ({myentry_dict['year']})"
+            YEARS_FOR_PLOT.append(year)
         return "["+myentry_dict["title"]+"]("+myentry_dict["url"]+")"+year
     else:
         year=""
         if "year" in myentry_dict:
             year = f" ({myentry_dict['year']})"
+            YEARS_FOR_PLOT.append(year)
         return myentry_dict["title"]+year
     return myline
 
@@ -209,6 +220,7 @@ def write_to_files(*args,readme=myfile_readme,webpage=myfile_out,add_header=Fals
             webpage.write("\n??? example "+"\""+split[-1].strip()+"\"\n\n")
 
 itemize_counter = 0
+YEARS_FOR_PLOT = []
 for line in myfile:
 
     if "author" in line:
@@ -275,6 +287,37 @@ def write_to_files(*args,readme=myfile_readme,webpage=myfile_out,add_header=Fals
                     write_to_files(header+line.split(r"\item")[1]+"\n\n")
                 pass
 
+if update_plot:
+    import matplotlib.pyplot as plt
+    import numpy as np
+    names =["per_year.png", "dark_per_year.png"]
+    for name in names:
+        if name == "dark_per_year.png":
+            plt.style.use('dark_background')
+        #plt.rcParams.update({"text.usetex": True,
+        #                     "font.family": "Helvetica"})
+        min_year = 2000
+        clean_list = []
+        for entry in YEARS_FOR_PLOT:
+            clean_list.append(int(entry.replace(" (", "").replace(")", "")))
+        years, counts = np.unique(clean_list, return_counts=True)
+        plt.figure(figsize=(6,4))
+        plt.bar(years, counts, zorder=5)
+        plt.title(r"Number of HEP-ML Papers by Year", fontsize=16)
+        plt.xlabel(r"Year", fontsize=12)
+        plt.ylabel(r"Number of Papers", fontsize=12)
+        plt.xlim(min_year, years.max()+1)
+        plt.grid(axis='y', zorder=0)
+        labels = np.arange(min_year, years.max()+1)
+        plt.gca().set_xticks(labels, [str(lbl) for lbl in labels], rotation=90, ha='center')
+        plt.xticks(rotation=90)
+        plt.tight_layout()
+        plt.gca().text(0.02, 0.98, f'As of {date.today().strftime("%d.%m.%Y")}',
+                    verticalalignment='top', horizontalalignment='left',
+                    transform=plt.gca().transAxes)
+        plt.savefig(f'docs/assets/{name}', transparent=True)
+
+
 def get_year_month(period_months=3):
     month_up = datetime.now().month
     year = datetime.now().year

requirements.txt

@@ -1,4 +1,6 @@
+matplotlib
 mkdocs~=1.4.3
 mkdocs-material~=9.1.14
 mkdocs-material-extensions~=1.1.1
+numpy
 requests~=2.27