%matplotlib inline

import csv
from collections import Counter
import pandas as pd

names = {
    "female": [],
    "male": []
}
with open("extract_trustee.csv") as a:
    reader = csv.reader(a)
    for row in reader:
        # ignore rows that aren't two records long
        if len(row) != 2:
            continue
        name = row[1].lower().split(" ") # split the name by spaces
        # if there's only one field then ignore the name
        if len(name) <= 1:
            continue
        # if the second name string (usually surname) is less that 2 characters ignore the row
        if len(name[1]) <= 2:
            continue
        # if there are non-alpha characters (numbers, symbols) then ignore the row
        if not name[1].isalpha():
            continue
        name[1] = name[1].title() # get the first name (assuming name[0] is a title)
        # if the first word is one of these titles it's a female name
        if name[0] in ["miss", "mrs", "ms", "dame"]:
            names["female"].append(name[1])
        # if the first word is one of these titles it's a male name
        elif name[0] in ["mr", "sir"]:
            names["male"].append(name[1])

print(names["female"][0:10])
print(names["male"][0:10])

['Felicity', 'Tessa', 'Elizabeth', 'Julie', 'Rosemary', 'Catherine', 'Eileen', 'Christa', 'Roberta', 'Beverley']
['Oliver', 'Kenneth', 'Neil', 'Keith', 'John', 'Herschel', 'Alex', 'David', 'Christopher', 'Daniel']

female = Counter(names["female"])
male = Counter(names["male"])

female_names = len(female)
male_names = len(male)
all_names = female_names + male_names
female_people = len(list(female.elements()))
male_people = len(list(male.elements()))
all_people = female_people + male_people

print("Female: {:,.0f} (from {:,.0f} people)".format(
    female_names,
    female_people,
))
print("Male: {:,.0f} (from {:,.0f} people)".format(
    male_names,
    male_people,
))
print("{:,.1f} % of names are female, {:,.1f} of people in sample".format(
    (female_names / all_names) * 100,
    (female_people / all_people) * 100
))

weighting = ((male_people / 0.489) - male_people) / female_people
print("Use a weighting of {:,.3f} to bring female population to 51.1% of sample".format(
    weighting
))

# 100 = X + Y
# X = male
# Y = female
# Z = female weighted
# X / (X + Y) = 0.520
# X / (X + Z) = 0.489
# X = 0.489 * (X + Z)
# X / 0.489 = X + Z
# Z = (X / 0.489) - X

Female: 15,367 (from 335,237 people)
Male: 16,085 (from 363,296 people)
48.9 % of names are female, 48.0 of people in sample
Use a weighting of 1.132 to bring female population to 51.1% of sample

female_df = pd.DataFrame.from_dict(female, orient='index')
female_df.columns = ["female"]

male_df = pd.DataFrame.from_dict(male, orient='index')
male_df.columns = ["male"]

female_df = (female_df * weighting).round(0)

both = pd.concat([female_df, male_df], join='outer', axis=1).fillna(0)
both.loc[:, "total"] = both.loc[:, "female"] + both.loc[:, "male"]
both.loc[:, "female_pc"] = both.loc[:, "female"] / both.loc[:, "total"]
both.loc[:, "male_pc"] = both.loc[:, "male"] / both.loc[:, "total"]
both.sort_values("total", ascending=False, inplace=True)

both[0:10]

both[-10:]

shared = both[(both["male"] > 30) & (both["female"] > 30)].sort_values("female_pc", ascending=False)
print(len(shared))
shared

23

shared[["female_pc", "male_pc"]].multiply(100).iloc[::-1].plot(kind="barh", stacked=True, figsize=(8, 8))

<matplotlib.axes._subplots.AxesSubplot at 0x23fe0924e80>