This Notebook uses a .csv file to create visualisations of references to Classical authors across a corpus of texts, divided by author and separated by language of source text and gender of author.

The below cells import the DF and the libraries

import pandas as pd
data = pd.read_csv("datathesisaug2023.csv")
data

	Title	Year	References to Galen	References to Hippocrates	References to Aristotle	Page Count	Percentage Galen	Percentage Hippocrates	Percentage Aristotle	Gender	Language of Source	Link to Source
0	The byrth of mankynde	1540	2	11	0	176	1.13	6.25	0.00	m	English	https://quod.lib.umich.edu/e/eebo2/A10887.0001...
1	Erreurs populaires	1578	41	60	30	227	18.06	26.43	13.21	m	French	https://play.google.com/books/reader?id=AffngP...
2	Trois livres appartenans	1582	94	108	47	923	10.18	11.70	5.09	m	French	https://play.google.com/books/reader?id=q8pEAA...
3	The Happy Delivery of Women	1612	41	64	16	118	31.74	54.23	13.55	m	English	https://quod.lib.umich.edu/e/eebo/A02362.0001....
4	Observations diverses	1617	1	2	0	540	0.18	0.37	0.00	f	French	https://archive.org/details/observationsdive01...
5	The womans doctour	1652	46	31	0	270	17.03	11.48	0.00	m	English	https://quod.lib.umich.edu/e/eebo/A39862.0001....
6	Directory for midwives	1652	21	48	5	250	8.40	19.20	2.00	m	English	https://quod.lib.umich.edu/e/eebo/A69832.0001....
7	The midwives book	1671	20	36	10	418	4.78	8.61	2.39	f	English	https://quod.lib.umich.edu/e/eebo2/A93039.0001...
8	Diseases of Women	1672	5	40	2	437	1.14	9.15	0.45	m	English	https://quod.lib.umich.edu/e/eebo2/A88969.0001...
9	A general treatise	1696	6	5	0	256	2.30	1.35	0.00	m	English	https://quod.lib.umich.edu/e/eebo/A53915.0001....
10	The compleat midwife’s practice enlarged	1698	16	11	0	351	4.55	3.13	0.00	m	English	https://quod.lib.umich.edu/e/eebo/A53913.0001....
11	Companion	1699	2	3	1	111	1.80	2.70	0.90	m	English	https://quod.lib.umich.edu/e/eebo/A31042.0001....
12	A Treatise on the Theory and Practice of Midwi...	1752	9	16	0	454	1.98	3.52	0.00	m	English	https://play.google.com/books/reader?id=UvM3AQ...
13	Avis au Peuple Sur sa Santé	1762	0	0	0	569	0.00	0.00	0.00	m	French	https://www.gutenberg.org/cache/epub/61258/pg6...
14	Dictionnaire portatif de santé	1762	4	2	0	427	0.93	0.46	0.00	m	French	https://play.google.com/books/reader?id=Z42cBX...
15	Abrégé de l’art des accouchemens	1789	0	0	0	208	0.00	0.00	0.00	f	French	https://play.google.com/books/reader?id=ychEAA...

import numpy as np
import matplotlib.pyplot as plt

The below code takes the data from the frame and outputs it across the corpus.

import numpy as np
import matplotlib.pyplot as plt

# Assuming data and other necessary variables are defined

x = np.array(data["Year"])

y1 = np.array(data["Percentage Aristotle"])
color1 = "blue"  # Choose a color for Aristotle's data

plt.scatter(x, y1, color=color1)  # Set scatter dots color to color1
z1 = np.polyfit(x, y1, 2)
p1 = np.poly1d(z1)
plt.plot(x, p1(x), label="Aristotle", color=color1)
plt.legend()

y2 = np.array(data["Percentage Galen"])
color2 = "orange"  # Choose a color for Galen's data

plt.scatter(x, y2, color=color2)  # Set scatter dots color to color2
z2 = np.polyfit(x, y2, 2)
p2 = np.poly1d(z2)
plt.plot(x, p2(x), label="Galen", color=color2)
plt.legend()

y3 = np.array(data["Percentage Hippocrates"])
color3 = "green"  # Choose a color for Hippocrates's data

plt.scatter(x, y3, color=color3)  # Set scatter dots color to color3
z3 = np.polyfit(x, y3, 2)
p3 = np.poly1d(z3)
plt.plot(x, p3(x), label="Hippocrates", color=color3)
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends of References over Time")
plt.savefig('ClassicalGraphs/Corpus.png', dpi=100, bbox_inches='tight')
plt.show()

The below code creates the output for the individual authors.

x = np.array(data["Year"])

y1 = np.array(data["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,2)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

plt.ylabel("References to Aristotle Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends of References over Time")
plt.savefig('ClassicalGraphs/Aristotle.png', dpi=100, bbox_inches='tight')

x = np.array(data["Year"])

y1 = np.array(data["Percentage Galen"])
plt.scatter(x,y1, color=color2)
z1=np.polyfit(x,y1,2)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Galen", color = "orange")
plt.legend()

plt.ylabel("References to Galen Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends of References over Time")
plt.savefig('ClassicalGraphs/Galen.png', dpi=100, bbox_inches='tight')

x = np.array(data["Year"])

y1 = np.array(data["Percentage Hippocrates"])
plt.scatter(x,y1, color=color3)
z1=np.polyfit(x,y1,2)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Hipporates", color = "green")
plt.legend()

plt.ylabel("References to Hippocrates Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends of References over Time")
plt.savefig('ClassicalGraphs/Hippocrates.png', dpi=100, bbox_inches='tight')

Next, we create the output for the composite graph by language of the source

langue = data[data['Language of Source'] == 'French']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

y2 = np.array(langue["Percentage Galen"])
plt.scatter(x,y2, color=color2)
z2=np.polyfit(x,y2,1)
p2=np.poly1d(z2)
plt.plot(x, p2(x), label = "Galen", color = "orange")
plt.legend()

y3 = np.array(langue["Percentage Hippocrates"])
plt.scatter(x,y3, color=color3)
z3=np.polyfit(x,y3,1)
p3=np.poly1d(z3)
plt.plot(x, p3(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends French authors")
plt.savefig('ClassicalGraphs/French.png', dpi=100, bbox_inches='tight')

langue = data[data['Language of Source'] == 'French']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends French authors")
plt.savefig('ClassicalGraphs/AristotleFrench.png', dpi=100, bbox_inches='tight')

langue = data[data['Language of Source'] == 'French']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Galen"])
plt.scatter(x,y1, color=color2)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Galen", color = "orange")
plt.legend()

plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends French authors")
plt.savefig('ClassicalGraphs/GalenFrench.png', dpi=100, bbox_inches='tight')

langue = data[data['Language of Source'] == 'French']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Hippocrates"])
plt.scatter(x,y1, color=color3)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Hippocrates", color = "green")
plt.legend()

plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends French authors")
plt.savefig('ClassicalGraphs/HippocratesFrench.png', dpi=100, bbox_inches='tight')

Next, we do the same for the English sources, first the composite, then individual

langue = data[data['Language of Source'] == 'English']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

y2 = np.array(langue["Percentage Galen"])
plt.scatter(x,y2, color=color2)
z2=np.polyfit(x,y2,1)
p2=np.poly1d(z2)
plt.plot(x, p2(x), label = "Galen", color = "orange")
plt.legend()

y3 = np.array(langue["Percentage Hippocrates"])
plt.scatter(x,y3, color=color3)
z3=np.polyfit(x,y3,1)
p3=np.poly1d(z3)
plt.plot(x, p3(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends English authors")
plt.savefig('ClassicalGraphs/English.png', dpi=100, bbox_inches='tight')

langue = data[data['Language of Source'] == 'English']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends English authors")
plt.savefig('ClassicalGraphs/AristotleEnglish.png', dpi=100, bbox_inches='tight')

langue = data[data['Language of Source'] == 'English']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Galen"])
plt.scatter(x,y1, color=color2)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Galen", color = "orange")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends English authors")
plt.savefig('ClassicalGraphs/GalenEnglish.png', dpi=100, bbox_inches='tight')

langue = data[data['Language of Source'] == 'English']

x = np.array(langue["Year"])

y1 = np.array(langue["Percentage Hippocrates"])
plt.scatter(x,y1, color=color3)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends English authors")
plt.savefig('ClassicalGraphs/HippocratesEnglish.png', dpi=100, bbox_inches='tight')

Finally, we repeat for gender: composite and individual

Female authors

fem = data[data['Gender'] == 'f']

x = np.array(fem["Year"])
y1 = np.array(fem["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

y2 = np.array(fem["Percentage Galen"])
plt.scatter(x,y2, color=color2)
z2=np.polyfit(x,y2,1)
p2=np.poly1d(z2)
plt.plot(x, p2(x), label = "Galen", color = "orange")
plt.legend()

y3 = np.array(fem["Percentage Hippocrates"])
plt.scatter(x,y3, color=color3)
z3=np.polyfit(x,y3,1)
p3=np.poly1d(z3)
plt.plot(x, p3(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Female Authors")
plt.savefig('ClassicalGraphs/FemaleAuthors.png', dpi=100, bbox_inches='tight')

fem = data[data['Gender'] == 'f']

x = np.array(fem["Year"])
y1 = np.array(fem["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Female Authors")
plt.savefig('ClassicalGraphs/AristotleFemaleAuthors.png', dpi=100, bbox_inches='tight')

fem = data[data['Gender'] == 'f']

x = np.array(fem["Year"])
y1 = np.array(fem["Percentage Galen"])
plt.scatter(x,y1, color=color2)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Galen", color = "orange")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Female Authors")
plt.savefig('ClassicalGraphs/GalenFemaleAuthors.png', dpi=100, bbox_inches='tight')

fem = data[data['Gender'] == 'f']

x = np.array(fem["Year"])
y1 = np.array(fem["Percentage Hippocrates"])
plt.scatter(x,y1, color=color3)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Female Authors")
plt.savefig('ClassicalGraphs/HippocratesFemaleAuthors.png', dpi=100, bbox_inches='tight')

Male authors

fem = data[data['Gender'] == 'm']

x = np.array(fem["Year"])
y1 = np.array(fem["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

y2 = np.array(fem["Percentage Galen"])
plt.scatter(x,y2, color=color2)
z2=np.polyfit(x,y2,1)
p2=np.poly1d(z2)
plt.plot(x, p2(x), label = "Galen", color = "orange")
plt.legend()

y3 = np.array(fem["Percentage Hippocrates"])
plt.scatter(x,y3, color=color3)
z3=np.polyfit(x,y3,1)
p3=np.poly1d(z3)
plt.plot(x, p3(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Male Authors")
plt.savefig('ClassicalGraphs/MaleAuthors.png', dpi=100, bbox_inches='tight')

men = data[data['Gender'] == 'm']

x = np.array(men["Year"])
y1 = np.array(men["Percentage Aristotle"])
plt.scatter(x,y1, color=color1)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Aristotle", color = "blue")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Male Authors")
plt.savefig('ClassicalGraphs/AristotleMaleAuthors.png', dpi=100, bbox_inches='tight')

men = data[data['Gender'] == 'm']

x = np.array(men["Year"])
y1 = np.array(men["Percentage Galen"])
plt.scatter(x,y1, color=color2)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Galen", color = "orange")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Male Authors")
plt.savefig('ClassicalGraphs/GalenMaleAuthors.png', dpi=100, bbox_inches='tight')

men = data[data['Gender'] == 'm']

x = np.array(men["Year"])
y1 = np.array(men["Percentage Hippocrates"])
plt.scatter(x,y1, color=color3)
z1=np.polyfit(x,y1,1)
p1=np.poly1d(z1)
plt.plot(x, p1(x), label = "Hippocrates", color = "green")
plt.legend()

plt.ylabel("References Relative to Number of Pages in Text")
plt.xlabel("Year")
plt.title("Trends Male Authors")
plt.savefig('ClassicalGraphs/HippocratesMaleAuthors.png', dpi=100, bbox_inches='tight')