notes

from now on I will focus on using seaborn. should be more than enoough for simple EDA purpose



In [1]:

    
import pandas as pd
import seaborn as sns

%matplotlib inline

prepare data



In [2]:

    
df = pd.read_csv('ex2data1.txt', names=['exam1', 'exam2', 'admitted'])
print(df.shape)
df.head()



In [3]:

    
df.describe()

seaborn



In [7]:

    
sns.set(context="notebook", style="darkgrid", palette=sns.color_palette("RdBu", 2))

sns.lmplot('exam1', 'exam2', hue='admitted', data=df, 
           size=6, 
           fit_reg=False, 
           scatter_kws={"s": 50}
          )









    Out[7]:





<seaborn.axisgrid.FacetGrid at 0x115491da0>



In [ ]:

	exam1	exam2	admitted
0	34.623660	78.024693	0
1	30.286711	43.894998	0
2	35.847409	72.902198	0
3	60.182599	86.308552	1
4	79.032736	75.344376	1

	exam1	exam2	admitted
count	100.000000	100.000000	100.000000
mean	65.644274	66.221998	0.600000
std	19.458222	18.582783	0.492366
min	30.058822	30.603263	0.000000
25%	50.919511	48.179205	0.000000
50%	67.032988	67.682381	1.000000
75%	80.212529	79.360605	1.000000
max	99.827858	98.869436	1.000000