charfreq.py

# Title: charfreq.py
# Author: Michael Gard
# Date Created: 8/14/16
# Description: Given the plain text resume "pt_MG_Resume.txt", output a barplot in Seaborn representing individual character frequency. Colors of the bars are determined by creating one "color bucket" per each of the 26 characters. Higher frequencies get darker colors

import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
import string

def make_heat_palette(vals, pal):
    maxindex = len(vals) - 1
    minv = min(vals)
    maxv = max(vals)
    denom = float(maxv - minv)
    return [pal[int(((x - minv) / denom) * maxindex)] for x in vals]

results = {c: 0 for c in string.uppercase}

with open("pt_MG_Resume.txt") as f:
    for line in f:
        for i in line.upper():
            if i in results:
                results[i] += 1

chars = results.keys()
freqs = results.values()
red_pal = sns.color_palette("Reds", len(freqs))
custom_pal = make_heat_palette(freqs, red_pal)

sns.barplot(chars, freqs, palette=custom_pal)
plt.title('Character Frequency of MG Resume')
plt.xlabel('Character')
plt.ylabel('Frequency')

sns.plt.show()