条件筛选1-4题（30 天 Pandas 挑战）

1. 相关知识点

1.1 query条件或查询

# |或
world.query('`area`>= 3000000 | `population`>=25000000')[['name','population','area']]

1.2 query条件与查询

# &与
products.query('`low_fats`=="Y" & `recyclable`=="Y"')[['product_id']]

1.3 存在查询及列名修改

customers=customers.query(f'`id` not in {order_list}')
customers=customers.rename(columns={'name':'Customers'})

1.4 条件查询，相等

new_views=views[views['author_id']==views['viewer_id']]

1.5 删除重复值

new_views.drop_duplicates(keep='first',inplace=True)

1.6 排序

new_views.sort_values(by='author_id',inplace=True)

2. 题目

2.1 大的国家

import pandas as pd

def big_countries(world: pd.DataFrame) -> pd.DataFrame:
    world_new=world.query('`area`>= 3000000 | `population`>=25000000')[['name','population','area']]
    return world_new

2.2 可回收且低脂的产品

import pandas as pd

def find_products(products: pd.DataFrame) -> pd.DataFrame:
    return products.query('`low_fats`=="Y" & `recyclable`=="Y"')[['product_id']]

2.3 从不订购的客户

import pandas as pd

def find_customers(customers: pd.DataFrame, orders: pd.DataFrame) -> pd.DataFrame:
    order_list=orders['customerId'].to_list()
    customers=customers.query(f'`id` not in {order_list}')
    customers=customers.rename(columns={'name':'Customers'})
    return customers[['Customers']]

2.4 文章浏览 I

import pandas as pd

def article_views(views: pd.DataFrame) -> pd.DataFrame:
    new_views=views[views['author_id']==views['viewer_id']][['author_id']].drop_duplicates().sort_values(by='author_id').rename(columns={'author_id':'id'})
    # new_views=views[views['author_id']==views['viewer_id']][['author_id']]
    # new_views.drop_duplicates(keep='first',inplace=True)
    # new_views.sort_values(by='author_id',inplace=True)
    # new_views.columns=['id']
    return new_views