import pandas as pd
import numpy as np
import seaborn as sns

# allow plots to appear in the notebook
%matplotlib inline

df = pd.read_table('http://people.sc.fsu.edu/~jburkardt/datasets/regression/x01.txt', sep='\s+', skiprows=33, names=['id','brain','body'], index_col='id')
df.head()

df.describe()

# only keep rows in which the body weight is less than 200
df = df[df.body < 200]
df.shape

sns.lmplot(x='body', y='brain', data=df, ci=None, fit_reg=False)
sns.plt.xlim(-10, 200)
sns.plt.ylim(-10, 250)

sns.lmplot(x='body', y='brain', data=df, ci=None)
sns.plt.xlim(-10, 200)
sns.plt.ylim(-10, 250)

# set a random seed for reproducibility
np.random.seed(12345)

# randomly assign every row to either sample 1 or sample 2
df['sample'] = np.random.randint(1, 3, len(df))
df.head()

# col='sample' subsets the data by sample and creates two separate plots
sns.lmplot(x='body', y='brain', data=df, ci=None, col='sample')
sns.plt.xlim(-10, 200)
sns.plt.ylim(-10, 250)

# hue='sample' subsets the data by sample and creates a single plot
sns.lmplot(x='body', y='brain', data=df, ci=None, hue='sample')
sns.plt.xlim(-10, 200)
sns.plt.ylim(-10, 250)

sns.lmplot(x='body', y='brain', data=df, ci=None, col='sample', order=8)
sns.plt.xlim(-10, 200)
sns.plt.ylim(-10, 250)

sns.lmplot(x='body', y='brain', data=df, ci=None, col='sample', order=2)
sns.plt.xlim(-10, 200)
sns.plt.ylim(-10, 250)