# Import required modules
import pandas as pd
from ggplot import *
%matplotlib inline

# Set ipython's max row display
pd.set_option('display.max_row', 1000)

# Set iPython's max column width to 50
pd.set_option('display.max_columns', 50)

# Load the dataset
df = pd.read_csv('5kings_battles_v1.csv')

# View the top five observations
df.head()

# View the bottom five observations
df.tail()

# Count the number of observations for each value
df['year'].value_counts()

# Count the number of observations for each value, then make a bar plot
df['region'].value_counts().plot(kind='bar')

# Count the number of observations for each value, then make a bar plot
df['attacker_outcome'].value_counts().plot(kind='bar')

# Count the number of observations for each value, then make a bar plot
df['battle_type'].value_counts().plot(kind='bar')

# Count the number of observations for each value, then make a bar plot
df['attacker_king'].value_counts().plot(kind='bar')

# Count the number of observations for each value, then make a bar plot
df['defender_king'].value_counts().plot(kind='bar')

war_action = df['attacker_king'].value_counts() + df['defender_king'].value_counts()
war_action.fillna(1).plot(kind='bar')

# Create a ggplot scatter plot of attacker_size against defender_size (if not NaN), 
# with the color of each dot being determined by the outcome of the battle
ggplot(aes(x='attacker_size', y='defender_size', colour='attacker_outcome'), 
       data=df[df['attacker_size'].notnull() & df['defender_size'].notnull() & df['attacker_outcome'].notnull()]) + \
    geom_point()