18-12-8-可视化库Seaborn学习笔记（三：Var）

 案例

#!/usr/bin/python
# -*- coding: UTF-8 -*-
# %matplotlib inline
import numpy as np
import pandas as pd
from scipy import stats, integrate
import matplotlib.pyplot as plt

import seaborn as sns
sns.set(color_codes=True)
# np.random.seed(sum(map(ord, "distributions")))#随机数种子 

x = np.random.normal(size=100)
sns.distplot(x,kde=False)

sns.distplot(x, bins=20, kde=False)

sns.distplot(x, bins=40, kde=False)

数据分布情况-加上曲线

x = np.random.gamma(6, size=200)
sns.distplot(x, kde=False, fit=stats.gamma)

 根据均值和协方差生成数据

mean, cov = [0, 1], [(1, .5), (.5, 1)]
data = np.random.multivariate_normal(mean, cov, 200)
df = pd.DataFrame(data, columns=["x", "y"])
print(df)
'''
            x         y
0   -0.966779  1.224554
1    1.326123  0.467515
2   -1.233853  0.459449
3   -0.877749  0.512031
......
'''

观测两个变量之间的分布关系最好用散点图

mean, cov = [0, 1], [(1, .5), (.5, 1)]
data = np.random.multivariate_normal(mean, cov, 200)
df = pd.DataFrame(data, columns=["x", "y"])
sns.jointplot(x="x", y="y", data=df);

mean, cov = [0, 1], [(1, .5), (.5, 1)]
data = np.random.multivariate_normal(mean, cov, 200)
df = pd.DataFrame(data, columns=["x", "y"])
sns.jointplot(x="x", y="y", kind="hex",data=df);

x, y = np.random.multivariate_normal(mean, cov, 1000).T
with sns.axes_style("white"):
    sns.jointplot(x=x, y=y, kind="hex", color="k")

案例：鸢尾花特征散点分布

iris = sns.load_dataset("iris")
sns.pairplot(iris)