Seaborn - 03 单变量分析绘图

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")))

拿到数据，首先看数据的分布情况/单变量单特征分析

x = np.random.normal(size=100)
sns.distplot(x,kde=False)   #直方图/柱形图，kde：是否要做核密度估计

x = np.random.normal(size=100)
#sns.distplot(x,kde=False)
sns.distplot(x, bins=20, kde=False)  #在x轴分为20份

1  数据分布情况

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
4   -1.682080  2.193876
..        ...       ...
195  0.415857  0.815041
196 -0.141024  0.214063
197 -1.879956  0.599829
198 -1.056075 -0.086185
199 -0.786835  2.789600

[200 rows x 2 columns]

2  观测两个变量之间的分布关系最好用散点图

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

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,kind="reg",color='g',stat_func=sci.pearsonr) # 显示皮尔逊相关系数，stat_func=sci.pearsonr必不可少
plt.show()

统计学三大相关系数之皮尔森（pearson）相关系数 https://blog.csdn.net/AlexMerer/article/details/74908435

http://seaborn.pydata.org/generated/seaborn.JointGrid.html#seaborn.JointGrid

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

mean, cov = [0, 1], [(1, .5), (.5, 1)]

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",stat_func=sci.pearsonr)
# 透过hex图，可以区分，那些点颜色更深，分布的点更多。更浅，分布的点更少

plt.show()

import seaborn as sns

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

对角线上：单变量分布情况

别的位置：两两之间关系的散点图