Starting Trend Analysis of Baby names

import matplotlib.pyplot as plt
import matplotlib.style as sty
import os
import re
import pandas as pd
import numpy as np
import matplotlib
from sys import exit
import csv
#an easy way to get all the imports installed is by just installing Anaconda (especially true for windows users)


class BabyNameAnalyzer:
    """Anaylze SSA baby name HTML files -- Use with a web scraper for maximum effectiveness"""

    def __init__(self):
        sty.use('ggplot')
        self.namedict = {}
        self.boyrankings = {}
        self.girlrankings = {}
        self.extractNames()
        self.organizeNames()

    def extractNames(self):
        """Extract the names from the Python Google class html files

        (in this example run the program from that directory)
        """
        for root, dirs, files in os.walk(os.path.dirname(os.path.realpath(__file__))):
            patt = re.compile(r'<tr align="right">\s*<td>(\d{1,4})<\/td>\s*<td>([A-Z][a-z]+?)<\/td>\s*<td>([A-Z][a-z]+?)<\/td>')
            for file in files:
                year = file[4:-5]
                self.namedict[year] = []
                if file[-4:] == "html":
                    myfile = open(os.path.join(root, file))
                    htmlText = myfile.read()
                    found = re.findall(patt,htmlText)
                    myfile.close()
                    [self.namedict[year].append(find) for find in found]

    def nameDumpCSV(self):
        """Organize the names into CSV for both girls and boys"""
        with open("boybabynames.csv","wb") as csvfile:
            fieldnames = ['name', 'year', 'rank']
            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
            writer.writeheader()

            for key,values in self.boyrankings.items():
                for value in values:
                    writer.writerow({'name': key, 'year': value[0], 'rank': value[1]})
        csvfile.close()
        with open("girlbabynames.csv","wb") as csvfile:
            fieldnames = ['name', 'year', 'rank']
            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
            writer.writeheader()

            for key,values in self.girlrankings.items():
                for value in values:
                    writer.writerow({'name': key, 'year': value[0], 'rank': value[1]})
        csvfile.close()


    def trendName(self):
        """Given a gender and name create a matplotlib line graph mapping the rankings over the years"""
        namedf = pd.read_csv('babynames.csv', index_col=1)
        namedf.plot()
        plt.show()


def main():

    bna = BabyNameAnalyzer()
    #bna.nameDumpCSV()
    bna.trendName()

if __name__ == '__main__':
  main()