jupyter练习

%matplotlib inline

import random

import numpy as np
import scipy as sp
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

import statsmodels.api as sm
import statsmodels.formula.api as smf

sns.set_context("talk")

anascombe = pd.read_csv('data/anscombe.csv')
anascombe.head()

	dataset	x	y
0	I	10.0	8.04
1	I	8.0	6.95
2	I	13.0	7.58
3	I	9.0	8.81
4	I	11.0	8.33

print(anascombe.groupby('dataset')['x'].mean())
print(anascombe.groupby('dataset')['x'].var())

dataset
I      9.0
II     9.0
III    9.0
IV     9.0
Name: x, dtype: float64
dataset
I      11.0
II     11.0
III    11.0
IV     11.0
Name: x, dtype: float64

print(anascombe.groupby('dataset')['y'].mean())
print(anascombe.groupby('dataset')['y'].var())

dataset
I      7.500909
II     7.500909
III    7.500000
IV     7.500909
Name: y, dtype: float64
dataset
I      4.127269
II     4.127629
III    4.122620
IV     4.123249
Name: y, dtype: float64

df = anascombe.groupby('dataset')['x']
X = []
for key, x in df:
    X.append(x.values)
df = anascombe.groupby('dataset')['y']
Y = []
for key, y in df:
    Y.append(y.values)
for i in range(0,len(X)):
    print(np.corrcoef(X[i],Y[i])[0][1])

0.81642051634484
0.8162365060002427
0.8162867394895982
0.816521