diff --git a/README.md b/README.md index 0230e72..c39aaa8 100644 --- a/README.md +++ b/README.md @@ -37,3 +37,10 @@ The [Makefile](./Makefile) contains targets to apply a consistent formatting to ## Citations from Google Scholar Alerts As an initial step and to get a higher coverage, citations are extracted from Google Scholar Alert e-mails received April 2016 to date. See [gscholar_alerts](./gscholar_alerts/). + +## Plotting the Data + +A Python script for plotting citations over time is included in this repository. + + +
_Fig 1: Plot of Common Crawl citations in Google Scholar as of July 29th 2024_
diff --git a/plot-data.py b/plot-data.py new file mode 100644 index 0000000..f549c17 --- /dev/null +++ b/plot-data.py @@ -0,0 +1,83 @@ +#!/usr/bin/env python3 + +import pandas as pd +import matplotlib.pyplot as plt +import jsonlines +import sys +import argparse + +# Usage: +# ./plot-data.py \ +# --title "Common Crawl Google Scholar Citations per Year" \ +# --groupby "year" \ +# --xlabel "Year" \ +# --ylabel "N Citations" \ +# --output "citations-by-year.png" \ +# --format "jsonl" \ +# < data.jsonl + +# Alternatively for CSV data as input: +# ./plot-data.py \ +# --title "Common Crawl Google Scholar Citations per Year" \ +# --groupby "year" \ +# --xlabel "Year" \ +# --ylabel "N Citations" \ +# --output "citations-by-year.png" \ +# --format "csv" \ +# --transparent \ +# < data.csv + +parser = argparse.ArgumentParser() +parser.add_argument('--title', default='Graph Title') +parser.add_argument('--xlabel', default='X Label') +parser.add_argument('--ylabel', default='Y Label') +parser.add_argument('--output', default='output.png') +parser.add_argument('--groupby', default='year') +parser.add_argument('--transparent', action='store_true', help='Save plot with transparent background') +parser.add_argument('--format', choices=['jsonl', 'csv'], default='jsonl', help='input data format') + +args = parser.parse_args() + +outputfile = args.output +ccblue = '#3287c5' + +if args.format == 'jsonl': + data = [] + with jsonlines.Reader(sys.stdin) as reader: + for obj in reader: + data.append(obj) + df = pd.DataFrame(data) + +elif args.format == 'csv': + df = pd.read_csv(sys.stdin) + +# # debug: verify df structure +# print("DataFrame columns:", df.columns) +# print("DataFrame head:\n", df.head()) + +plt.figure(figsize=(20, 12)) +bars = plt.bar(df['year'].astype(str), df['count'], color=ccblue) + +for bar in bars: + yval = bar.get_height() + plt.text(bar.get_x() + bar.get_width()/2.0, yval, int(yval), va='bottom', ha='center') + +plt.title(args.title) +plt.xlabel(args.xlabel) +plt.ylabel(args.ylabel) +plt.xticks() +plt.grid(False) + +ax = plt.gca() +ax.patch.set_alpha(0) +plt.gcf().patch.set_alpha(0 if args.transparent else 1) + +for spine in ax.spines.values(): + spine.set_visible(False) + +ax.tick_params(left=False, bottom=False) + +plt.savefig(outputfile, transparent=args.transparent, dpi=320, bbox_inches='tight') + +print(f"Total rows: {len(df)}") +print(f"Plot saved to {outputfile}") diff --git a/plot.html b/plot.html new file mode 100644 index 0000000..007939a --- /dev/null +++ b/plot.html @@ -0,0 +1,126 @@ + + + + +
+
Citations by Year
+ + + + + +
+
+
Google Scholar Citations by Year
+
Plot of Common Crawl citations in Google Scholar as of July 29th 2024
+
+
+
+ + + diff --git a/plots/citations-by-year-jul-2024.csv b/plots/citations-by-year-jul-2024.csv new file mode 100644 index 0000000..ce4a4e0 --- /dev/null +++ b/plots/citations-by-year-jul-2024.csv @@ -0,0 +1,13 @@ +count,year +30,2012 +80,2013 +160,2014 +190,2015 +330,2016 +440,2017 +533,2018 +710,2019 +977,2020 +1105,2021 +1266,2022 +1777,2023 diff --git a/plots/citations-by-year.png b/plots/citations-by-year.png new file mode 100644 index 0000000..ae4a0bd Binary files /dev/null and b/plots/citations-by-year.png differ