The Re-Vowelization of American Baby Names

import pandas as pd
import matplotlib as mpl

import mplstyle
import mplstyle.styles.simple
mplstyle.set(mplstyle.styles.simple)
original_colors = mplstyle.get("axes.color_cycle")
mplstyle.set({
    "figure.figsize": (10, 8),
    "lines.markersize": 0,
    "axes.color_cycle": original_colors[:2]
})
base_style = mplstyle.get()

# The baby name data can be downloaded from this link:
# https://github.com/jsvine/babynames/raw/master/data/babynames.csv.bz2
# 
# More information on the data and sourcing here:
# https://github.com/jsvine/babynames/
DATA_PATH = "/Users/jsvine/Dropbox/babynames/data/babynames.csv.bz2"

# Read the data into a pandas DataFrame
names = pd.read_csv(DATA_PATH, compression="bz2")

# Make order of sexes explicit, and lengthen variable names
sexes = ["Female", "Male"]
names["sex"] = names["sex"].apply(lambda x: "Male" if x == "M" else "Female")

# Calculate ranges useful for chart axes
years = names["year"].unique()
n_years = names["year"].max() - names["year"].min()
decades = [ 1880 + x * 10 for x in 
    range(n_years / 10 + 1) ]
decimals = [ float(x)/10 for x in range(11) ]
percentages = [ "%d%%" % (x * 100) for x in decimals ]

# Return a new DataFrame with only the 
# top `n` names per year and sex
def top_n(n):
    grouped = names.groupby(["year", "sex"])
    return grouped.apply(lambda x: x[:n]).reset_index(drop=True)

# Helper function to set axes to sane defaults
def adjust_axes(ax):
    ax.set_ylim(0, 1)
    ax.set_xlim(years[0], years[-1] + 1)
    ax.set_yticks(decimals)
    ax.set_yticklabels(percentages)
    ax.set_xticks(decades)
    ax.legend(sexes)
    ax.set_xlabel("\nYear")

# Add vowel data to each row
VOWELS = "AEIOU"
names["len"] = names["name"].apply(len)
names["vowels"] = names["name"].apply(lambda x: sum(let in VOWELS for let in x.upper()))
names["starts_with_vowel"] = names["name"].apply(lambda x: x[0] in VOWELS)

def plot_vowel_rate(df):
    get_vowel_rate = lambda x: float(sum(x["vowels"])) / sum(x["len"])
    grouped = df.groupby(["year", "sex"])
    per_group = grouped.size()[0]
    vowel_rate = grouped.apply(get_vowel_rate).unstack()[sexes]
    
    ax = vowel_rate.plot(grid=True, alpha=0.5)
    adjust_axes(ax)
    
    ax.set_title("Vowels, as a Percentage of All Letters, in the\n%d Most Popular Boy/Girl Baby Names, Over Time\n" % per_group)
    ax.set_ylabel("Vowel Percentage\n")

plot_vowel_rate(top_n(100))

def plot_first_vowel(df, **kwargs):
    grouped = df.groupby(["year", "sex"])
    per_group = grouped.size()[0]
    first_vowel = grouped["starts_with_vowel"].mean().unstack()
    
    ax = first_vowel.plot(grid=True, alpha=0.5, **kwargs)
    adjust_axes(ax)
    ax.set_title("Names Starting With a Vowel, as a Percentage\nof the %d Most Popular Boy/Girl Names, Over Time\n" % per_group)
    ax.set_ylabel("Percentage of Names Starting With a Vowel\n")

plot_first_vowel(top_n(100))

plot_first_vowel(top_n(20), drawstyle="steps")

plot_first_vowel(top_n(10), drawstyle="steps")

# Helper function for simple equality queries
def select(df, **kwargs):
    conds = [ df[k] == v for k,v in kwargs.iteritems() ]
    product = reduce(lambda m, x: m * x, conds, True)
    return df[product]

# Helpers for displaying Markdown
from IPython.display import HTML
from markdown import markdown
md = lambda x: HTML(markdown(x))

def name_list(names):
    format_name = lambda x: "__%s__" % x if x[0] in VOWELS else x
    front = u", ".join(map(format_name, names.values[:-1]))
    back = ", and " + format_name(names.values[-1])
    return front + back

md("""
In 1945, in the middle of this vowel valley, the top 10 female baby names were: %s.

In 2012, at vowelization's latest peak, they were: %s.

In 1880, they were: %s.
""" % tuple(name_list(select(top_n(10), 
        year=year, 
        sex="Female")["name"])
    for year in (1945, 2012, 1880)
))

def plot_first_letter(df, let, max_y=0.3, **kwargs):
    let_0 = lambda name: name[0] == let
    grouped = df.groupby("year")
    per_group = grouped.size().iget(0)
    first_vowel = grouped["name"].apply(lambda x: sum(map(let_0, x)) * 1. / per_group)
    ax = first_vowel.plot(grid=True, **kwargs)
    ax.set_ylim(0, max_y)
    ax.set_yticks(decimals[:4])
    ax.set_yticklabels([])
    ax.set_xlim(years[0], years[-1])
    ax.set_xticks([])
    ax.set_xlabel("")

def plot_first_letter_sm(n, abc = "ABCDEFGHIJKLMNOPQRSTUVQXYZ", **kwargs):
    df = top_n(n)
    dfs = [ df ] + [ select(df, sex=sex) for sex in sexes ]
    mplstyle.set({"figure.figsize": (8, 15)})
    mpl.pyplot.subplots_adjust(hspace=0.25, wspace=0.1)
    colors = ["#333333"] + original_colors[:2]
    for i in range(len(abc)):
        for j in range(len(dfs)):
            ax = mpl.pyplot.subplot(26, 3, i*len(dfs) + j + 1)
            plot_first_letter(dfs[j], abc[i], 
                ax=ax, 
                color=(colors)[j],
                alpha=0.5,
                **kwargs)
            ax.set_ylabel(abc[i] if not j else "", rotation=0)
    top_center = mpl.pyplot.subplot(26, 3, 2)
    top_center.set_title("Percentage of Top %d Baby Names,\n%d-%d, Starting With the Letter...\n" % 
        (n, years[0], years[-1]))
    top_right = mpl.pyplot.subplot(26, 3, 3)
    top_right.yaxis.tick_right()
    top_right.set_yticklabels([ percentages[0], "", "", percentages[3] ])
    last_row = (len(abc) - 1) * 3 + 1
    labels = ["Either Sex"] + sexes
    for i in range(len(labels)):
        mpl.pyplot.subplot(26, 3, last_row + i).set_xlabel(labels[i])
    mplstyle.reset(base_style)

plot_first_letter_sm(100, VOWELS)

plot_first_letter_sm(20, VOWELS)

plot_first_letter_sm(100)