‘’’
另一篇博客:https://blog.csdn.net/weixin_40924580/article/details/82809484 有关于使用matplotlib查看titanic数据特征的方法
‘’’
数据下载——保存——导入
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
sns.set_style('darkgrid')
# names = ['mpg','cylinders','displacement','horsepower','weight','acceleration','model_year','origin','car_name']
# df =pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data',sep='\s+',names=names)
# df.to_csv("H:/seaborn2.csv")
df = pd.read_csv('H:/seaborn2.csv')
df['maker'] = df.car_name.map(lambda x:x.split()[0]) #以空格分割,取第一个
df.origin = df.origin.map({1:'Americ',2:'Europe',3:'Asia'})
df.applymap(lambda x:np.nan if x=='?' else x).dropna()
# sns.factorplot(data=df,x="model_year",y="mpg",col="origin") #!1 按照origin维度取值不同画图
# sns.factorplot(data=df,x="model_year",y="mpg",col="origin",kind = 'bar') #!2 柱状图
# sns.factorplot("model_year",data=df,col="origin",kind = 'count') #!3 对某一列根据origin计数
# g = sns.FacetGrid(df,col='origin') #!4 并查看分布
# g.map(sns.distplot,'mpg')
# g = sns.FacetGrid(df, col="origin") #!5散点图
# g.map(plt.scatter, "horsepower", "mpg")
# g = sns.FacetGrid(df, col="origin") #!6 画图同时包含回归
# g.map(sns.regplot, "displacement", "mpg")
# plt.xlim(0, 250)
# plt.ylim(0, 60)
# df['tons'] = (df.weight/2000).astype(int) #! 7密度绘图
# g = sns.FacetGrid(df, col="origin", row="tons")
# g.map(sns.kdeplot, "displacement", "mpg")
# plt.xlim(0, 250)
# plt.ylim(0, 60)
# sns.jointplot("mpg", "weight", data=df, kind='kde') #!8联合绘图
# sns.jointplot("mpg", "weight", data=df, kind='reg') #!9联合绘图加回归
# g = sns.JointGrid(x="weight", y="mpg", data=df) #!10多项式联合回归,"order"
# g.plot_joint(sns.regplot, order=2)
# g.plot_marginals(sns.distplot)