python对NOAA天气数据格式转换

原文链接：http:///?p=7679  

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]:

	YEAR	MONTH	ELEMENT	VALUE1	VALUE2	VALUE3	VALUE4	VALUE5	VALUE6	VALUE7	...	VALUE22	VALUE23	VALUE24	VALUE25	VALUE26	VALUE27	VALUE28	VALUE29	VALUE30	VALUE31
0	1945	11	TAVG	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	107.0	NaN
1	1945	12	TAVG	123.0	136.0	152.0	144.0	146.0	189.0	219.0	...	179.0	146.0	128.0	107.0	104.0	112.0	122.0	127.0	129.0	156.0
2	1946	1	TAVG	150.0	150.0	123.0	117.0	112.0	121.0	125.0	...	146.0	153.0	173.0	196.0	211.0	212.0	218.0	201.0	156.0	131.0
3	1946	2	TAVG	114.0	112.0	147.0	181.0	195.0	192.0	149.0	...	201.0	196.0	231.0	226.0	221.0	229.0	240.0	NaN	NaN	NaN
4	1946	3	TAVG	237.0	162.0	142.0	133.0	183.0	187.0	160.0	...	183.0	192.0	205.0	216.0	223.0	238.0	207.0	195.0	233.0	228.0