import numpy as np
import pandas as pd
import scipy
import scipy.stats
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.simplefilter('ignore',FutureWarning)
df = pd.read_csv('http://www-bcf.usc.edu/~gareth/ISL/College.csv')
college = df
df['Accept'].describe()
df[['Accept','F.Undergrad']].describe()
df['Name'] = df.iloc[:,0]
interested = df.columns
sns.pairplot(data=college[['Accept','F.Undergrad']])
college.columns
sns.pairplot(data=college[['Top10perc','Top25perc','Room.Board']]);
sns.scatterplot(x='Top10perc',y='Room.Board',data=college[['Top10perc','Top25perc','Room.Board']]);
sns.boxplot(y="Private", x="Outstate", data=college);
college['Elite'] = (college['Top10perc'] > 50)
college['Acceptance.Rate'] = college['Accept'] / college['Apps']
sns.distplot(college['Acceptance.Rate']);
sns.boxplot(x="Elite", y="Outstate", data=college);
sns.distplot(college['Outstate'], bins=6, kde = False, rug = True);