A GPTC model to classify American news as right- or left-leaning
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

85 lines
1.9 KiB

import gptc
states = [
"Alabama",
"Alaska",
"Arizona",
"Arkansas",
"California",
"Colorado",
"Connecticut",
"Delaware",
"Florida",
"Georgia",
"Hawaii",
"Idaho",
"Illinois",
"Indiana",
"Iowa",
"Kansas",
"Kentucky",
"Louisiana",
"Maine",
"Maryland",
"Massachusetts",
"Michigan",
"Minnesota",
"Mississippi",
"Missouri",
"Montana",
"Nebraska",
"Nevada",
"New Hampshire",
"New Jersey",
"New Mexico",
"New York",
"North Carolina",
"North Dakota",
"Ohio",
"Oklahoma",
"Oregon",
"Pennsylvania",
"Rhode Island",
"South Carolina",
"South Dakota",
"Tennessee",
"Texas",
"Utah",
"Vermont",
"Virginia",
"Washington",
"West Virginia",
"Wisconsin",
"Wyoming",
]
with open("model.gptc", "rb") as f:
model = gptc.deserialize(f)
classified_states = []
for state in states:
classified_states.append((state, model.get(state),))
classified_states.sort(key=lambda x: x[1]["left"])
longest = max([len(state) for state in states])
print("# State Analysis")
print()
print("""This is an analysis of which states are mentioned more in right- or left-
leaning American news sources. Results do not necessarily correlate with the
political views of residents of the states; for example, the predominantly
liberal state of Oregon is mentioned more in right-leaning sources than in
left-leaning ones.""")
print()
print("| State | Left | Right |")
print("+----------------+-------+-------+")
for state, data in classified_states:
percent_right = f"{round(data['right']*1000)/10}%"
percent_left = f"{round(data['left']*1000)/10}%"
state_padding = " "*(longest - len(state))
print(f"| {state}{state_padding} | {percent_left} | {percent_right} |")
print("+----------------+-------+-------+")
print("| State | Left | Right |")