Exploratory Data Analysis of Game of Thrones Dataset

Game_of_Thrones.py

# Future Imports
from __future__ import absolute_import
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals

# Data Cleaning
from pandas import read_csv
import numpy as np

# Data Visualization
import matplotlib.pyplot as plt
%matplotlib inline

# Time
import time

def timeit(method):
    ''' To check the execution time
        Parameter
        ---------
        method: function
        Return
        ---------
        float number
    '''
    def timed(*args, **kw):
        ts = time.time()
        result = method(*args, **kw)
        te = time.time()
        if 'log_time' in kw:
            name = kw.get('log_name', method.__name__.upper())
            kw['log_time'][name] = int((te - ts) * 1000)
        else:
            print('%r  %2.2f ms' % \
                  (method.__name__, (te - ts) * 1000))
        return result
    return timed
  
@timeit
def dataframe(name):
    ''' Creates the dataframe
        Parameters
        ----------
        method: string
        Return
        ----------
        dataframe
    '''
    try:
        filepath = './'+ name +'.csv'
        if name == 'battles':
            return read_csv(filepath)
        elif name == 'character-deaths':
            return read_csv(filepath)
        elif name == 'character-predictions':
            return read_csv(filepath)
    except IOError:
        raise 'File does not exists'
#     return (battles, character_deaths, character_predictions) 
    
battles = dataframe('battles')
character_deaths = dataframe('character-deaths')
character_predictions = dataframe('character-predictions')

battles = battles[['name', 'year', 'battle_number', 'attacker_king', 'defender_king', \
         'attacker_outcome', 'major_death', 'major_capture', 'attacker_size', 'defender_size']]

battles.groupby('attacker_outcome').count()

#Plots
@timeit
def plots(dataframe):
    ''' Creates bar charts for the columns
        Parameter
        ---------
        method: dataframe
        Return
        ---------
        None
    '''
  dataframe.groupby('attacker_outcome')[['attacker_size', 'defender_size']].sum().plot(kind='bar')
  plt.xlabel('')
  dataframe.groupby('attacker_king')[['attacker_size', 'defender_size']].sum().plot(kind='bar')
  plt.xlabel('')
  plt.ylabel('Army Size')
  dataframe.groupby('attacker_king')[['attacker_outcome']].count().plot(kind='barh')
  plt.ylabel('')
  plt.xlabel('Wins')
  dataframe[dataframe.attacker_outcome == 'loss'].groupby('defender_king')[['defender_king']].count().plot(kind='barh')
  plt.xlabel('wins')
  plt.ylabel('')
  dataframe.groupby('attacker_king')[['battle_number']].sum().plot(kind='barh')
  plt.xlabel('Battle Count')
  plt.ylabel('')
  dataframe[dataframe.attacker_king == 'Joffrey/Tommen Baratheon'].groupby \
  ('attacker_king')[['attacker_size']].sum()

plots(battles)

# Battles fought by Joffrey/Tommen
battles[battles.attacker_king == 'Joffrey/Tommen Baratheon'][['name']]