"Who are the scientists who oppose Trump’s travel ban?" supplement

census_disciplines.csv

discipline_analysis.py

from collections import Counter

import json
import csv

if __name__ == "__main__":
    # Load all of US Census's academic disciplines
    disciplines = []; discipline_color = {};
    with open('census_disciplines.csv', 'rb') as csvfile:
        reader = csv.reader(csvfile)
        for i, row in enumerate(reader):
            disciplines.append(row[0].lower())
            # These different colors correspond to broad category
            # the census assigns to a discipline
            if i < 93:
                discipline_color[row[0].lower()] = "#a6cee3"
            elif i < 119:
                discipline_color[row[0].lower()] = "#1f78b4"
            elif i < 135:
                discipline_color[row[0].lower()] = "#b2df8a"
            elif i < 148:
                discipline_color[row[0].lower()] = "#33a02c"
            else:
                discipline_color[row[0].lower()] = "#fb9a99"
    print "number of disciplines: {0}".format(len(disciplines))

    # Read people JSON
    with open("signatures.json", "rb") as f:
        data = json.loads(f.read().decode("utf-8"))

        areas_count = Counter()

        for i, person in enumerate(data["data"]):
            title = person[2]
  
            # Look for discipline matches
            for discipline in disciplines:
                if title.lower().count(discipline) > 0:
                    areas_count[discipline.title()] += 1


    writer = csv.writer(open("discipline_counts.csv", 'w'))
    writer.writerow(['id', 'value', 'color'])
    for area, count in areas_count.most_common():
        writer.writerow([area.encode('utf-8'), count, discipline_color[area.lower()]])