xuefliang

  library ( tidyverse ) library ( duckdb ) library ( arrow ) con <- dbConnect (   duckdb () ,   dbdir = "./甘肃省POI数据.duckdb" , # 数据库文件保存路径   read_only = FALSE ) poi <- tbl ( con , "poi" ) poi #查看列名 colnames ( poi ) dbGetQuery ( con , "PRAGMA table_info(poi)" ) |>   select ( name , type ) # 关闭数据库连接 dbDisconnect ( con , shutdown = TRUE ) poi |>   group_by ( 城市 ) |>   summarise ( n = n ()) |>   # show_query()   collect () jzdw <- read_parquet ( './jzdw_with_location_baidu.parquet' ) jzdw |> str () ###parquet文件延迟 wz <- tbl_file ( path = './接种单位位置.parquet' ) wz wz |>   group_by ( 接种单位所属区县名称 ) |>   summarise ( n = n ()) #DuckDB 加速的本地数据操作 library ( duckplyr ) df <- duckdb_tibble ( x = 1 : 3 , y = letters [ 1 : 3 ]) df |> group_by ( y ) |> summarise ( n = n ()) nyc = tbl (   con ,   "read_parquet('nyc-taxi/**/*.parquet', hive_partitioning = true)" ) nc...

 pip install apache-superset export SUPERSET_SECRET_KEY="yEi9YUsuZExpRAZuNV3XbSLcuCcZ7ytdPOA7CCQaLPQ6NxeSRdpJwNUz" export FLASK_APP=superset cat /etc/superset_config.py # 禁用不安全数据库连接的安全检查 PREVENT_UNSAFE_DB_CONNECTIONS = False # 或者，更精确地允许 SQLite 驱动 ALLOWED_DIALECTS = [     "sqlite",     # 其他你需要的驱动，如 'postgresql', 'mysql' 等 ] export SUPERSET_CONFIG_PATH=/etc/superset_config.py superset init superset db upgrade superset fab create-admin \--username admin \--firstname Superset \--lastname Admin \--email 360149345@qq.com \--password admin superset run -p 8088 \--with-threads \--reload \--debugger sqlite:////mnt/c/Users/Administrator/Downloads/database.sqlite/database.sqlite

  from datetime import datetime from datetime import timedelta , date import polars as pl import duckdb as dd import time as time_module from concurrent.futures import ThreadPoolExecutor , as_completed import threading # 初始化 uri = "oracle:// " dd . sql ( "attach 'ducklake:meta.ducklake' as lake;" ) # 如果表存在，先删除 dd . sql ( "DROP TABLE IF EXISTS lake.ods.jzjl;" ) # 创建 schema dd . sql ( "CREATE SCHEMA IF NOT EXISTS lake.ods;" ) # 线程安全的标志 first_batch_lock = threading . Lock () first_batch = True def worker ( current_date ):     """处理单个日期的数据"""     global first_batch         start_time = time_module . time ()     result = {         'date' : current_date ,         'status' : 'success' ,         'rows' : 0 ,         'elapsed' : 0 ,         'error' : None     }         try :   ...

  from datetime import datetime from datetime import timedelta , date import polars as pl import duckdb as dd import time as time_module #初始化 uri = "oracle:// " dd . sql ( "attach 'ducklake:meta.ducklake' as lake;" ) # 如果表存在，先删除 dd . sql ( "DROP TABLE IF EXISTS lake.ods.jzjl;" ) # 创建 schema dd . sql ( "CREATE SCHEMA IF NOT EXISTS lake.ods;" ) # 写数据 bdate = date ( year = 2026 , month = 1 , day = 1 ) edate = date ( year = 2026 , month = 1 , day = 3 ) first_batch = True for i in range (( edate - bdate ). days + 1 ):     start_time = time_module . time ()     current_date = bdate + timedelta ( days = i )         try :         next_date = current_date + timedelta ( days = 1 )         query = f """         SELECT * FROM inoc_jzjl         WHERE jz_sj >= TO_DATE(' { current_date } ', 'YYYY-MM-DD')         AN...

  update lg -- 更新数据 SET age = CAST (( date ( -- 格式化 jz_sj (取前10位日期部分进行处理) printf ( '%04d-%02d-%02d' , substr ( replace ( jz_sj , '/' , '-' ), 1 , 4 ), CAST ( substr ( replace ( jz_sj , '/' , '-' ), 6 , instr ( substr ( replace ( jz_sj , '/' , '-' ), 6 ), '-' ) - 1 ) AS INTEGER ), CAST ( substr ( replace ( jz_sj , '/' , '-' ), 6 + instr ( substr ( replace ( jz_sj , '/' , '-' ), 6 ), '-' )) AS INTEGER ) ) ) - julianday ( -- 格式化 csrq printf ( '%04d-%02d-%02d' , substr ( replace ( csrq , '/' , '-' ), 1 , 4 ), CAST ( substr ( replace ( csrq , '/' , '-' ), 6 , instr ( substr ( replace ( csrq , '/' , '-' ), 6 ), '-' ) - 1 ) AS INTEGER ), CAST ( substr ( replace ( csrq , '/' , '-' ), ...

  import polars as pl import polars.selectors as cs import duckdb con = duckdb . connect ( "/mnt/c/Users/Administrator/Downloads/流感肺炎/fy.db" ) # 获取所有表名 tables = con . execute ( "SHOW TABLES" ). pl () print ( tables ) # 查看 test 表的列信息 schema = con . execute ( "DESCRIBE test" ). pl () print ( schema ) # 读数据库表 test = con . execute ( """     SELECT * FROM test """ ). pl ( lazy = True ) # 比较慢 # test2 = pl.read_database("SELECT * FROM test", connection=con).lazy() test . collect_schema () # 关闭连接 con . close () ####################### import polars as pl import polars.selectors as cs import duckdb con = duckdb . connect ( "/mnt/c/Users/Administrator/Downloads/流感肺炎/fy.db" ) temp = (     pl . scan_csv (         "/mnt/c/Users/Administrator/Downloads/流感肺炎/接种.csv" , infer_schema = None     )     . rename ( lambda col : col . lower ())     . with_columns (         pl . col ( "csr...

  import polars as pl import polars.selectors as cs from typing import Optional , List jz = (     pl . read_excel (         "/mnt/c/Users/Administrator/Downloads/不达标乡镇管理儿童接种记录/jzjl(3).xlsx"     )     . rename ( lambda x : x . lower ())     . with_columns (         pl . col ( "jz_sj" ). str . to_datetime (). alias ( "jz_sj" ),         pl . col ( "csrq" ). str . to_date (). alias ( "csrq" ),     )     . sort ( "jz_sj" )     . with_columns ( pl . col ( "ym_bm" ). str . slice ( 0 , 2 ). alias ( "ym_dl" ))     . with_columns (         pl . col ( "grda_code" ). cum_count (). alias ( "jc" ). over ([ "grda_code" , "ym_dl" ])     )     . with_columns ( age = (( pl . date ( 2025 , 12 , 31 ) - pl . col ( "csrq" )). dt . total_days () / 30 )) ) def get_zero_dose_children (     jz_data : pl . ...