企业官网建设流程全解析

importpandasaspd df=pd.read_csv('D:/workspace/pandas/PandasProject/data/LJdata.csv')df# 处理中文列名 ==》英文列名df.columns=['district','address','title','house_type','area','price','floor','build_time','direction','update_time','view_num','extra_info','link']df# 查看数据df.head()# 查看前5行df[:5]# 查看前5行df.info()# 查看详细信息df.describe()#默认只统计数字列(因为数字可以用四分法：最大小值均值等)df.describe(include='all')#可设置统计所有列df.shape# 查看形状 几行几列# 1.找到租金最高、最低的房子# sql版# select * from xx order by price desc/asc limit0,1 (是房子不是租金:不是select min('price')...)#万一有多个找多个# select max(price) from xxx# select * from xxx where price=(select max/min(price) from xxx)# pandas版# 先排序df.sort_values('price',ascending=False).head(1)#最高的一个df.nlargest(1,'price')df.sort_values('price',ascending=True).head(1)#最低的一个df.nsmallest(1,'price')# 万一有多个找多个df[df['price']==df['price'].max()]df[df['price']==df['price'].min()]# 2.找到最近新上的10套房房源# sql版# select * from xx order by update_time desc limit 0,10;# pandas版df.sort_values(['update_time'],ascending=False).head(10)# df.nlargest(10, 'update_time') #字符串无法使用此方法比大小# 3.查看所有更新时间 去重# sql版# select distinct update_from xxx# pandas版df['update_time'].drop_duplicates()# df['update_time'].unique()# 4.查看看房人数的平均值，最大值和最小值# sql版# select avg(view_num),max(view_num),min(view_num) from xxx# pandas版df['view_num'].mean()df['view_num'].max()df['view_num'].min()df['view_num'].describe()# 5.查看不同看房人数的房源数量# sql版# select view_num,count(*) as 'house_count' from xxx group by view_num# pandas版temp=df.groupby('view_num').agg({'view_num':'count'})temp.columns=['house_count']temp df.groupby(['view_num']).address.count()df.groupby(['view_num'])['address'].count()# 6.查看房租价格的分布，例如：平均值、标准差、中位数...# sql版# select avg(price),std(price),median(price) from xxx# pandas版df['price'].describe()df['price'].mean()df['price'].std()df['price'].median()# 7.找到看房人数最多的朝向# 思路：根据朝向分组 看房人数聚合# sql版# with temp as(select direction,sum(view_num) as sum_view from xx group by direction)# select * from temp order by sum_view desc limit 0,1;# pandas版temp=df.groupby('direction').agg({'view_num':'sum'})type(temp)# temp[布尔Series]：返回的是 DataFrame(与原temp结构相同,但只包含满足条件的行;此处是只保留布尔Series中为True对应的行)temp[temp['view_num']==temp['view_num'].max()]# 8.查找最受欢迎的房型# 按房型分组，看房人人数的总和# sql版# select house_type,sum(view_num) where from xxx group by house_type# pandas版temp=df.groupby('house_type').agg({'view_num':'count'})temp temp[temp['view_num']==temp['view_num'].max()]# 9.查找房子的平均租房价格(元/平米)# sql版# select avg(price/area) from xxx# pandas版df['price_per']=df['price']/df['area']df['price_per'].mean()# 或者df['price'].sum()/df['area'].sum()# 10.找到出租房源最多的小区# sql版# select district,count(*) as house_count from xxx group by district order by house_count desc limit 1# pandas版temp=df.groupby('district').agg({'district':'count'})temp temp[temp['district']==temp['district'].max()]