拓端tecdat|python编程代写对NOAA天气数据格式转换

转换NOAA天气数据文件“ .fly”为Pandas DataFrame

 获取数据 ftp://ftp.ncdc.noaa.gov/pub/data/ghcn/daily

In [1]:

import  matplotlib.pyplot  as  plt 
import  pandas  as  pd 
import  numpy  as  np 
import  re 
import  ftplib

% matplotlib notebook

In [2]:

# download data from FTP

def  download_file_from_ftp ( FTP_SERVER , FTP_PATH , FILENAME ): 
    with  ftplib . FTP ( FTP_SERVER )  as  ftp : 
        ftp . login () 
        ftp . cwd ( FTP_PATH ) 
        with  open ( FILENAME ,  'wb' )  as  f : 
            ftp . retrbinary ( 'RETR '  +  FILENAME ,  f . write )

查询站ID

In [3]:

def  get_station_ID ( station_to_find ,  filename ): 
    for  line  in  open ( filename ): 
        if  station_to_find  in  line : 
            line_with_station = line 
            station_ID = re . split ( " " , line_with_station )[ 0 ] 
            return  station_ID 
    return  None 
# warning, it is slow, download it only once 
download_file_from_ftp ( "ftp.ncdc.noaa.gov" , "/pub/data/ghcn/daily" ,  "ghcnd-stations.txt" )

station_to_find = "GUANGZHOU"  # USE CAPS 
station_ID = get_station_ID ( station_to_find ,  "ghcnd-stations.txt" )

下载天气数据

In [4]:

weather_data_filename = station_ID + '.dly'

# warning, it is slow, download it only once 
download_file_from_ftp ( "ftp.ncdc.noaa.gov" ,  "/pub/data/ghcn/daily/all" ,  weather_data_filename )

将.fly转换为pandas Dataframe

In [7]:

df = convert_dly_to_dataframe ( weather_data_filename ) 
df . head ()

Out[7]: