Python數據可視化-seaborn

1  set_style( )  set( )

set_style( )是用來設置主題的，Seaborn有五個預設好的主題： darkgrid , whitegrid , dark , white ,和 ticks  默認： darkgrid

 

import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style("whitegrid")
plt.plot(np.arange(10))
plt.show()

 

 

set( )通過設置參數可以用來設置背景，調色板等，更加常用。

 

import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="white", palette="muted", color_codes=True)     #set( )設置主題，調色板更常用
plt.plot(np.arange(10))
plt.show()

 

 

 

2  distplot( )  kdeplot( )

distplot( )為hist加強版，kdeplot( )為密度曲線圖 

 

import matplotlib.pyplot as plt
import seaborn as sns
df_iris = pd.read_csv('../input/iris.csv')
fig, axes = plt.subplots(1,2)
sns.distplot(df_iris['petal length'], ax = axes[0], kde = True, rug = True)        # kde 密度曲線  rug 邊際毛毯
sns.kdeplot(df_iris['petal length'], ax = axes[1], shade=True)                     # shade  陰影
plt.show()

import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
sns.set( palette="muted", color_codes=True)
rs = np.random.RandomState(10)
d = rs.normal(size=100)
f, axes = plt.subplots(2, 2, figsize=(7, 7), sharex=True)
sns.distplot(d, kde=False, color="b", ax=axes[0, 0])
sns.distplot(d, hist=False, rug=True, color="r", ax=axes[0, 1])
sns.distplot(d, hist=False, color="g", kde_kws={"shade": True}, ax=axes[1, 0])
sns.distplot(d, color="m", ax=axes[1, 1])
plt.show()

3  箱型圖 boxplot( )

 

import matplotlib.pyplot as plt
import seaborn as sns
df_iris = pd.read_csv('../input/iris.csv')
sns.boxplot(x = df_iris['class'],y = df_iris['sepal width'])
plt.show()

 

import matplotlib.pyplot as plt
import seaborn as sns
tips = pd.read_csv('../input/tips.csv')
sns.set(style="ticks")                                     #設置主題
sns.boxplot(x="day", y="total_bill", hue="sex", data=tips, palette="PRGn")   #palette 調色板
plt.show()

 

 

4  聯合分布jointplot( )

tips = pd.read_csv('../input/tips.csv')   #右上角顯示相關系數
sns.jointplot("total_bill", "tip", tips)
plt.show()

tips = pd.read_csv('../input/tips.csv')
sns.jointplot("total_bill", "tip", tips, kind='reg')
plt.show()

 

5  熱點圖heatmap( )

 internal_chars = ['full_sq', 'life_sq', 'floor', 'max_floor', 'build_year', 'num_room', 'kitch_sq', 'state', 'price_doc']
corrmat = train[internal_chars].corr()

f, ax = plt.subplots(figsize=(10, 7))
plt.xticks(rotation='90')
sns.heatmap(corrmat, square=True, linewidths=.5, annot=True)
plt.show()

 

 

6  散點圖scatter( )

f, ax = plt.subplots(figsize=(10, 7))
plt.scatter(x=train['full_sq'], y=train['price_doc'], c='r')
plt.xlim(0,500)
plt.show()

 

7.pointplot畫出變量間的關系

grouped_df = train_df.groupby('floor')['price_doc'].aggregate(np.median).reset_index()

plt.figure(figsize=(12,8))

sns.pointplot(grouped_df.floor.values, grouped_df.price_doc.values, alpha=0.8, color=color[2])

plt.ylabel('Median Price', fontsize=12)

plt.xlabel('Floor number', fontsize=12)

plt.xticks(rotation='vertical') plt.show()

8 pairplot( )

import matplotlib.pyplot as plt
import seaborn as sns
data = pd.read_csv("../input/iris.csv")
sns.set()                        #使用默認配色
sns.pairplot(data,hue="class")   #hue 選擇分類列
plt.show()

 

 

import seaborn as sns
import matplotlib.pyplot as plt
iris = pd.read_csv('../input/iris.csv')
sns.pairplot(iris, vars=["sepal width", "sepal length"],hue='class',palette="husl")
plt.show()

 

9  FacetGrid( )

import seaborn as sns
import matplotlib.pyplot as plt
tips = pd.read_csv('../input/tips.csv')
g = sns.FacetGrid(tips, col="time",  row="smoker")
g = g.map(plt.hist, "total_bill",  color="r")
plt.show()

 

 

10  barplot( )

f, ax=plt.subplots(figsize=(12,20))

#orient='h'表示是水平展示的，alpha表示顏色的深淺程度
sns.barplot(y=group_df.sub_area.values, x=group_df.price_doc.values,orient='h', alpha=0.8, color='red')

#設置y軸、X軸的坐標名字與字體大小
plt.ylabel('price_doc', fontsize=16)
plt.xlabel('sub_area', fontsize=16)

#設置X軸的各列下標字體是水平的
plt.xticks(rotation='horizontal')

#設置Y軸下標的字體大小
plt.yticks(fontsize=15)
plt.show()

注：如果orient='v'表示成豎直顯示的話，一定要記得y=group_df.sub_area.values, x=group_df.price_doc.values調換一下坐標軸，否則報錯

 

11.bar圖

import matplotlib.pyplot as plt
import numpy as np
plt.rc('font', family='SimHei', size=13)

num = np.array([13325, 9403, 9227, 8651])
ratio = np.array([0.75, 0.76, 0.72, 0.75])
men = num * ratio
women = num * (1-ratio)
x = ['聊天','支付','團購\n優惠券','在線視頻']

width = 0.5
idx = np.arange(len(x))
plt.bar(idx, men, width, color='red', label='男性用戶')
plt.bar(idx, women, width, bottom=men, color='yellow', label='女性用戶')  #這一塊可是設置bottom,top，如果是水平放置的，可以設置right或者left。
plt.xlabel('應用類別')
plt.ylabel('男女分布')
plt.xticks(idx+width/2, x, rotation=40)
plt.legend()
plt.show()

 

 

 

 

來源：http://blog.csdn.net/qq_34264472/article/details/53814653

 也可以參考：http://seaborn.pydata.org/tutorial/distributions.html

知乎專欄關於seaborn的：https://zhuanlan.zhihu.com/p/27570774