数据处理练习

题目来自高级编程课程

给定一个csv文件，完成以下两题：

对应代码如下：

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

anascombe = pd.read_csv( 'anscombe.csv')

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

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

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

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

print(anascombe.groupby( 'dataset').corr())

dataset_names = [ 'I', 'II', 'III', 'IV']

for i in dataset_names:

n = len(anascombe[anascombe.dataset == i])

is_train = np.random.rand(n) < 0.7

train = anascombe[anascombe.dataset == i][is_train].reset_index( drop = True)

test = anascombe[anascombe.dataset == i][ ~is_train].reset_index( drop = True)

lin_model = smf.ols( 'y ~ x', train).fit()

print(lin_model.summary())

g = sns.FacetGrid(anascombe, col = 'dataset')

g.map(plt.scatter, 'x', 'y')

plt.show()

程序命令行输出：

dataset
I      9.0
II     9.0
III    9.0
IV     9.0
Name: x, dtype: float64
dataset
I      7.500909
II     7.500909
III    7.500000
IV     7