核密度图（直⽅图的拟合曲线）
核密度图可以看作是概率密度图，其纵轴可以粗略看做是数据出现的次数，与横轴围成的⾯积是⼀.
火龙果季节法⼀：aborn的kdeplot函数专门⽤于画核密度估计图.
import pandas as pd
import numpy as np
import matplotlib.pylab as plt自查报告格式
import os
import aborn as sns
## 有时候要FQ才能下载
# df = pd.read_csv("/lva86/datats/raw/master/mpg_ggplot2.csv")
# df.to_csv('../data/mpg_ggplot2.csv', index=Fal)
df = pd.read_csv('../data/mpg_ggplot2.csv')
print(df.info())
print(df.shape)
# Draw Plot
plt.figure(figsize=(16,10), dpi= 90) # dpi⽤于设置输出figure中所有字体的⼤⼩
# 将cyl列等于4的cty筛选出来做图
sns.kdeplot(df.loc[df['cyl'] == 4, "cty"], shade=True, color="g", label="Cyl=4", alpha=0.5)
sns.kdeplot(df.loc[df['cyl'] == 5, "cty"], shade=True, color="deeppink", label="Cyl=5", alpha=.5)
麦秋sns.kdeplot(df.loc[df['cyl'] == 6, "cty"], shade=True, color="dodgerblue", label="Cyl=6", alpha=.5)
sns.kdeplot(df.loc[df['cyl'] == 8, "cty"], shade=True, color="orange", label="Cyl=8", alpha=.5)
# Decoration
故意杀人罪辩护词
中白鹭plt.title('Density Plot of City Mileage by n_Cylinders', fontsize=22)
plt.legend()
plt.show()
View Code
永立潮头displot()是将直⽅图和核密度图综合，
import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import os
import aborn as sns
## 有时候要FQ才能下载
# df = pd.read_csv("/lva86/datats/raw/master/mpg_ggplot2.csv")
# df.to_csv('../data/mpg_ggplot2.csv', index=Fal)
df = pd.read_csv('../data/mpg_ggplot2.csv')
# distplot图是直⽅图hist()和核密度图kdeplot()图的合体，
# bins参数⽤于调节直⽅图的数量
# 官⽹链接：aborn.pydata/generated/aborn.distplot.html
# 参数解释：/a/158933070_718302
plt.figure(figsize=(16,10), dpi= 90)
sns.distplot(df.loc[df['cyl'] == 4, "cty"], color="g", label="Cyl=4", bins = 100 )
sns.distplot(df.loc[df['cyl'] == 5, "cty"], color="deeppink", label="Cyl=5", bins= 10 )
plt.legend()
plt.show()
View Code
给定⼀组连续值的数据，将它们分成若⼲⼩段，统计每个⼩段中数据的个数，并画出它们的直⽅图和拟合曲线.
法⼆：利⽤aborn中的包可以快速实现，这⾥的拟合曲线默认不是正态曲线，⽽是更好的拟合了数据的分布情况，但通过参数fit可以设置拟合正态曲线.
import aborn as sns
import matplotlib.pyplot as plt
import numpy as np
sns.t()
from sklearn import datats
from scipy.stats import norm
iris = datats.load_iris() # 载⼊鸢尾花数据集
x = iris.data[:,0] # 取narry中的第⼀列
sns.t_palette("hls") #设置所有图的颜⾊，使⽤hls⾊彩空间
# sns.distplot( x,color="r",bins=100,kde=True,)# hist=Fal)
# hist和kde参数默认都是True，分别⽤于控制是否展现直⽅图和拟合的曲线图大树怎么画
# fit可⽤于指定拟合正态分布，要导⼊from scipy.stats import norm
sns.distplot( x,bins=30, hist=True,kde_kws={'color': 'green', 'lw':3, 'label':'x'}, hist_kws={'color': 'red', 'alpha': 0.2}) plt.show()
View Code
法三：利⽤round()函数保留⼩数点后⼀位或两位，再groupby作图，但效果远不如第⼀种.
f_train['VAR00007'] = f_train['VAR00007'].apply( lambda x: round(x, 1))
f_train = upby(['VAR00007'])['VAR00007'].agg(['count']).ret_index()
书的英语怎么读
f_train.sort_values(['VAR00007'], )
ydata = f_train['VAR00007'].tolist()
x = f_train['count'].tolist()
ydata.sort(rever=Fal)
plt.scatter( ydata, x)
plt.show()
View Code
