python简单可视化

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

df = pd.read_csv('Recommendation System.csv')

df.head()

df.columns = (['user_id','item_id',"rating","timestamp"])

df.head()

movie_titles = pd.read_csv("Movie_Id_Titles")
movie_titles.head()

df = pd.merge(df,movie_titles,on='item_id')  #类似于inner join

df.sort_values('item_id').head()

df.head()

df.groupby("title")['rating'].mean().sort_values(ascending=False).head()    #排名前五的电影

title
Marlene Dietrich: Shadow and Light (1996)     5.0
Prefontaine (1997)                            5.0
Santa with Muscles (1996)                     5.0
Star Kid (1997)                               5.0
Someone Else's America (1995)                 5.0
Name: rating, dtype: float64

df.groupby("title")['rating'].count().sort_values(ascending=False).head()   #等级评论前五的电影

title
Star Wars (1977)             583
Contact (1997)               509
Fargo (1996)                 508
Return of the Jedi (1983)    507
Liar Liar (1997)             485
Name: rating, dtype: int64

ratings = pd.DataFrame(df.groupby("title")['rating'].mean())
ratings.head()

ratings["rating_counts"]= pd.DataFrame(df.groupby("title")['rating'].count())

ratings.head()

seaborn的displot()集合了matplotlib的hist()与核函数估计kdeplot的功能，增加了rugplot分布观测条显示与利用scipy库fit拟合参数分布的新颖用途。

核密度估计是在概率论中用来估计未知的密度函数，属于非参数检验方法之一。由于核密度估计方法不利用有关数据分布的先验知识，对数据分布不附加任何假定，是一种从数据样本本身出发研究数据分布特征的方法，因而，在统计学理论和应用领域均受到高度的重视。

sns.distplot(ratings["rating_counts"])

<matplotlib.axes._subplots.AxesSubplot at 0x2a6bc5a3710>

# plt.figure(figsize=(20,10))
sns.distplot(ratings["rating"],bins=50)  #分箱

<matplotlib.axes._subplots.AxesSubplot at 0x2a6bcda9da0>

sns.distplot( (ratings['rating']*ratings['rating_counts'] ) )

<matplotlib.axes._subplots.AxesSubplot at 0x2a6bcec49b0>

plt.figure(figsize=(10,7))
sns.jointplot(x='rating',y="rating_counts",data=ratings,alpha=.5)

df.head()

数据透视表：

https://www.cnblogs.com/Yanjy-OnlyOne/p/11195621.html

movie_mat = df.pivot_table(values='rating',index='user_id',columns = 'title')

movie_mat.head()

5 rows × 1664 columns