import seaborn as sns
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
def sinplot(flip=1):
x = np.linspace(0, 14, 100)
for i in range(1, 7):
plt.plot(x, np.sin(x + i * .5) * (7 - i) * flip)
sinplot()
sns.set()#用seaborn默认参数组合
sinplot()
5种主题风格
sns.set_style("whitegrid")
data = np.random.normal(size=(20, 6)) + np.arange(6) / 2
sns.boxplot(data=data)
#f, ax = plt.subplots()
sns.violinplot(data)
sns.despine(offset=10)#offset:图与轴线距离
sns.set_style("whitegrid")
sns.boxplot(data=data, palette="deep")
sns.despine(left=True)#左轴隐藏
with sns.axes_style("darkgrid"):#with打开风格,with内是darkgrid风格
plt.subplot(211)
sinplot()
plt.subplot(212)
sinplot(-1)
sns.set()
sns.set_context("paper")# paper, talk,poster
plt.figure(figsize=(8, 6))
sinplot()
sns.set_context("notebook", font_scale=1.5, rc={"lines.linewidth": 2.5})#指定坐标字体大小
sinplot()
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
sns.set(rc={"figure.figsize": (6, 6)})
current_palette = sns.color_palette()
sns.palplot(current_palette)
6个默认的颜色循环主题: deep, muted, pastel, bright, dark, colorblind
当你有六个以上的分类要区分时,最简单的方法就是在一个圆形的颜色空间中画出均匀间隔的颜色(这样的色调会保持亮度和饱和度不变)。这是大多数的当他们需要使用比当前默认颜色循环中设置的颜色更多时的默认方案。
最常用的方法是使用hls的颜色空间,这是RGB值的一个简单转换。
sns.palplot(sns.color_palette("hls", 8))#传出来8种颜色
data = np.random.normal(size=(20, 8)) + np.arange(8) / 2
sns.boxplot(data=data,palette=sns.color_palette("hls", 8))
l-亮度 lightness
s-饱和 saturation
sns.palplot(sns.hls_palette(8, l=.7, s=.9))
sns.palplot(sns.color_palette("Paired",8))#成对颜色相近调色板
kcd包含了一套众包努力的针对随机RGB色的命名。产生了954个可以随时通过xdcd_rgb字典中调用的命名颜色。
plt.plot([0, 1], [0, 1], sns.xkcd_rgb["pale red"], lw=3)
plt.plot([0, 1], [0, 2], sns.xkcd_rgb["medium green"], lw=3)
plt.plot([0, 1], [0, 3], sns.xkcd_rgb["denim blue"], lw=3)
colors = ["windows blue", "amber", "greyish", "faded green", "dusty purple"]
sns.palplot(sns.xkcd_palette(colors))
色彩随数据变换,比如数据越来越重要则颜色越来越深
sns.palplot(sns.color_palette("Blues"))
sns.palplot(sns.color_palette("BuGn_r"))
色调线性变换
sns.palplot(sns.color_palette("cubehelix", 8))
sns.palplot(sns.cubehelix_palette(8, start=.5, rot=-.75))
sns.palplot(sns.cubehelix_palette(8, start=.75, rot=-.150))
sns.palplot(sns.light_palette("green"))
sns.palplot(sns.dark_palette("purple"))
sns.palplot(sns.light_palette("navy", reverse=True))
x, y = np.random.multivariate_normal([0, 0], [[1, -.5], [-.5, 1]], size=300).T
pal = sns.dark_palette("green", as_cmap=True)
sns.kdeplot(x, y, cmap=pal);
sns.palplot(sns.light_palette((210, 90, 60), input="husl"))
%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")))
x = np.random.normal(size=100)
sns.distplot(x,kde=False)
sns.distplot(x, bins=20, kde=False)
x = np.random.gamma(6, size=200)
sns.distplot(x, kde=False, fit=stats.gamma)
mean, cov = [0, 1], [(1, .5), (.5, 1)]
data = np.random.multivariate_normal(mean, cov, 200)
df = pd.DataFrame(data, columns=["x", "y"])
df
sns.jointplot(x="x", y="y", 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")
iris = sns.load_dataset("iris")
sns.pairplot(iris)
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(color_codes=True)
np.random.seed(sum(map(ord, "regression")))
tips = sns.load_dataset("tips")
tips.head()
regplot()和lmplot()都可以绘制回归关系,推荐regplot()
sns.regplot(x="total_bill", y="tip", data=tips)
sns.lmplot(x="total_bill", y="tip", data=tips);
sns.regplot(data=tips,x="size",y="tip")
sns.regplot(x="size", y="tip", data=tips, x_jitter=.05)
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="whitegrid", color_codes=True)
np.random.seed(sum(map(ord, "categorical")))
titanic = sns.load_dataset("titanic")
tips = sns.load_dataset("tips")
iris = sns.load_dataset("iris")
sns.stripplot(x="day", y="total_bill", data=tips);
sns.stripplot(x="day", y="total_bill", data=tips, jitter=True)
sns.swarmplot(x="day", y="total_bill", data=tips)
sns.swarmplot(x="day", y="total_bill", hue="sex",data=tips)
sns.swarmplot(x="total_bill", y="day", hue="time", data=tips);
IQR即统计学概念四分位距,第一/四分位与第三/四分位之间的距离
N = 1.5IQR 如果一个值>Q3+N或 < Q1-N,则为离群点
sns.boxplot(x="day", y="total_bill", hue="time", data=tips);
sns.violinplot(x="total_bill", y="day", hue="time", data=tips);
sns.violinplot(x="day", y="total_bill", hue="sex", data=tips, split=True);
sns.violinplot(x="day", y="total_bill", data=tips, inner=None)
sns.swarmplot(x="day", y="total_bill", data=tips, color="w", alpha=.5)
sns.barplot(x="sex", y="survived", hue="class", data=titanic);
sns.pointplot(x="sex", y="survived", hue="class", data=titanic);
sns.pointplot(x="class", y="survived", hue="sex", data=titanic,
palette={"male": "g", "female": "m"},
markers=["^", "o"], linestyles=["-", "--"]);
sns.boxplot(data=iris,orient="h");
sns.factorplot(x="day", y="total_bill", hue="smoker", data=tips)
sns.factorplot(x="day", y="total_bill", hue="smoker", data=tips, kind="bar")
sns.factorplot(x="day", y="total_bill", hue="smoker",
col="time", data=tips, kind="swarm")
sns.factorplot(x="time", y="total_bill", hue="smoker",
col="day", data=tips, kind="box", size=4, aspect=.5)
Parameters:
x,y,hue 数据集变量 变量名
date 数据集 数据集名
row,col 更多分类变量进行平铺显示 变量名
col_wrap 每行的最高平铺数 整数
estimator 在每个分类中进行矢量到标量的映射 矢量
ci 置信区间 浮点数或None
n_boot 计算置信区间时使用的引导迭代次数 整数
units 采样单元的标识符,用于执行多级引导和重复测量设计 数据变量或向量数据
order, hue_order 对应排序列表 字符串列表
row_order, col_order 对应排序列表 字符串列表
kind : 可选:point 默认, bar 柱形图, count 频次, box 箱体, violin 提琴, strip 散点,swarm 分散点 size 每个面的高度(英寸) 标量 aspect 纵横比 标量 orient 方向 “v”/“h” color 颜色 matplotlib颜色 palette 调色板 seaborn颜色色板或字典 legend hue的信息面板 True/False legend_out 是否扩展图形,并将信息框绘制在中心右边 True/False share{x,y} 共享轴线 True/False
%matplotlib inline
import numpy as np
import pandas as pd
import seaborn as sns
from scipy import stats
import matplotlib as mpl
import matplotlib.pyplot as plt
sns.set(style="ticks")
np.random.seed(sum(map(ord, "axis_grids")))
tips = sns.load_dataset("tips")
tips.head()
g = sns.FacetGrid(tips, col="time")
g = sns.FacetGrid(tips, col="time")
g.map(plt.hist, "tip");
g = sns.FacetGrid(tips, col="sex", hue="smoker")
g.map(plt.scatter, "total_bill", "tip", alpha=.7)
g.add_legend();
g = sns.FacetGrid(tips, row="smoker", col="time", margin_titles=True)
g.map(sns.regplot, "size", "total_bill", color=".1", fit_reg=False, x_jitter=.1);
g = sns.FacetGrid(tips, col="day", size=4, aspect=.5)
g.map(sns.barplot, "sex", "total_bill");
from pandas import Categorical
ordered_days = tips.day.value_counts().index
print (ordered_days)
ordered_days = Categorical(['Thur', 'Fri', 'Sat', 'Sun'])
g = sns.FacetGrid(tips, row="day", row_order=ordered_days,
size=1.7, aspect=4,)
g.map(sns.boxplot, "total_bill");
pal = dict(Lunch="seagreen", Dinner="gray")
g = sns.FacetGrid(tips, hue="time", palette=pal, size=5)
g.map(plt.scatter, "total_bill", "tip", s=50, alpha=.7, linewidth=.5, edgecolor="white")
g.add_legend();
g = sns.FacetGrid(tips, hue="sex", palette="Set1", size=5, hue_kws={"marker": ["^", "v"]})
g.map(plt.scatter, "total_bill", "tip", s=100, linewidth=.5, edgecolor="white")
g.add_legend();
with sns.axes_style("white"):
g = sns.FacetGrid(tips, row="sex", col="smoker", margin_titles=True, size=2.5)
g.map(plt.scatter, "total_bill", "tip", color="#334488", edgecolor="white", lw=.5);
g.set_axis_labels("Total bill (US Dollars)", "Tip");
g.set(xticks=[10, 30, 50], yticks=[2, 6, 10]);
g.fig.subplots_adjust(wspace=.02, hspace=.02);
#g.fig.subplots_adjust(left = 0.125,right = 0.5,bottom = 0.1,top = 0.9, wspace=.02, hspace=.02)
iris = sns.load_dataset("iris")
g = sns.PairGrid(iris)
g.map(plt.scatter);
g = sns.PairGrid(iris)
g.map_diag(plt.hist)
g.map_offdiag(plt.scatter);
g = sns.PairGrid(iris, hue="species")
g.map_diag(plt.hist)
g.map_offdiag(plt.scatter)
g.add_legend();
g = sns.PairGrid(iris, vars=["sepal_length", "sepal_width"], hue="species")
g.map(plt.scatter);
g = sns.PairGrid(tips, hue="size", palette="GnBu_d")
g.map(plt.scatter, s=50, edgecolor="white")
g.add_legend();
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np;
np.random.seed(0)
import seaborn as sns;
sns.set()
uniform_data = np.random.rand(3, 3)
print (uniform_data)
heatmap = sns.heatmap(uniform_data)
ax = sns.heatmap(uniform_data, vmin=0.2, vmax=0.5)
normal_data = np.random.randn(3, 3)
print (normal_data)
ax = sns.heatmap(normal_data, center=0)
flights = sns.load_dataset("flights")
flights.head()
flights = flights.pivot("month", "year", "passengers")
print (flights)
ax = sns.heatmap(flights)
ax = sns.heatmap(flights, annot=True,fmt="d")
ax = sns.heatmap(flights, linewidths=.5)
ax = sns.heatmap(flights, cmap="YlGnBu")
ax = sns.heatmap(flights, cbar=False)