Convert csv to netcdf

Question

I am trying to convert a CSV file to netCDF4 through Python, but I find it hard to understand how I can store information from the .csv table format to netCDF. My main problem is how to declare variables from columns to netCDF4 working format? Everything that I found usually extracts information from netCDF4 in .csv or ASCII. I presented sample data, code sample, and my errors for declaring corresponding arrays. Any help would be greatly appreciated.

The following is an example table below:

Station Name    Country  Code   Lat Lon mn.yr   temp1   temp2   temp3   hpa 
Somewhere   US  12340   35.52   23.358  1.19    -8.3    -13.1   -5  69.5
Somewhere   US  12340           2.1971  -10.7   -13.9   -7.9    27.9
Somewhere   US  12340           3.1971  -8.4    -13 -4.3    90.8

My sample code is:

#! / usr / bin / env python

import scipy
import numpy
import netCDF4
import csv

from numpy import arange, dtype 

#Declare empty arrays

v1 = []
v2 = []
v3 = []
v4 = []

# Open the csv file and declare a variable for arrays for each header

f = open('station_data.csv', 'r').readlines()

for line in f[1:]:
    fields = line.split(',')
    v1.append(fields[0]) #station
    v2.append(fields[1])#country
    v3.append(int(fields[2]))#code
    v4.append(float(fields[3]))#lat
    v5.append(float(fields[3]))#lon
#more variables included but this is just an abridged list
print v1
print v2
print v3
print v4

#convert to netcdf4 framework, which works like netcdf

ncout = netCDF4.Dataset('station_data.nc','w') 

# latitude and longitude. Enable NaN for Missing Numbers

lats_out = -25.0 + 5.0*arange(v4,dtype='float32')
lons_out = -125.0 + 5.0*arange(v5,dtype='float32')

# output.

press_out = 900. + arange(v4*v5,dtype='float32') # 1d array
press_out.shape = (v4,v5) # reshape to 2d array
temp_out = 9. + 0.25*arange(v4*v5,dtype='float32') # 1d array
temp_out.shape = (v4,v5) # reshape to 2d array

# create lat and lon sizes.

ncout.createDimension('latitude',v4)
ncout.createDimension('longitude',v5)

# .

lats = ncout.createVariable('latitude',dtype('float32').char,('latitude',))
lons = ncout.createVariable('longitude',dtype('float32').char,('longitude',))

# var. , .

lats.units = 'degrees_north'
lons.units = 'degrees_east'

# vars.

lats[:] = lats_out
lons[:] = lons_out

#

press = ncout.createVariable('pressure',dtype('float32').char,('latitude','longitude'))
temp = ncout.createVariable('temperature',dtype('float32').char,'latitude','longitude'))

# .

press.units =  'hPa'
temp.units = 'celsius'

# .

press[:] = press_out
temp[:] = temp_out

ncout.close()
f.close()

:

Traceback (most recent call last):
  File "station_data.py", line 33, in <module>
    v4.append(float(fields[3]))#lat
ValueError: could not convert string to float: 

Answer 1

, , Lat. csv, , .. fields[3], "". ValueError. , :

def str_to_float(str):
    try:
        number = float(str)
    except ValueError:
        number = 0.0
# you can assign an appropriate value instead of 0.0 which suits your requirement
    return number

float :

v4.append(str_to_float(fields[3]))

Answer 2

xarray, python, , netcdf. , :

import pandas as pd
import xarray as xr

url = 'http://www.cpc.ncep.noaa.gov/products/precip/CWlink/'

ao_file = url + 'daily_ao_index/monthly.ao.index.b50.current.ascii'
nao_file = url + 'pna/norm.nao.monthly.b5001.current.ascii'

kw = dict(sep='\s*', parse_dates={'dates': [0, 1]},
          header=None, index_col=0, squeeze=True, engine='python')

# read into Pandas Series
s1 = pd.read_csv(ao_file, **kw)
s2 = pd.read_csv(nao_file, **kw)

s1.name='AO'
s2.name='NAO'

# concatenate two Pandas Series into a Pandas DataFrame
df=pd.concat([s1, s2], axis=1)

# create xarray Dataset from Pandas DataFrame
xds = xr.array.Dataset.from_dataframe(df)

# add variable attribute metadata
xds['AO'].attrs={'units':'1', 'long_name':'Arctic Oscillation'}
xds['NAO'].attrs={'units':'1', 'long_name':'North Atlantic Oscillation'}

# add global attribute metadata
xds.attrs={'Conventions':'CF-1.0', 'title':'AO and NAO', 'summary':'Arctic and North Atlantic Oscillation Indices'}

# save to netCDF
xds.to_netcdf('/usgs/data2/notebook/data/ao_and_nao.nc')

ncdump -h ao_and_nao.nc :

netcdf ao_and_nao {
dimensions:
        dates = 782 ;
variables:
        double dates(dates) ;
                dates:units = "days since 1950-01-06 00:00:00" ;
                dates:calendar = "proleptic_gregorian" ;
        double NAO(dates) ;
                NAO:units = "1" ;
                NAO:long_name = "North Atlantic Oscillation" ;
        double AO(dates) ;
                AO:units = "1" ;
                AO:long_name = "Arctic Oscillation" ;

// global attributes:
                :title = "AO and NAO" ;
                :summary = "Arctic and North Atlantic Oscillation Indices" ;
                :Conventions = "CF-1.0" ;

, xarray pip, Anaconda Python Distribution, Anaconda.org/conda-forge, :

conda install -c conda-forge xarray

Answer 3

xarray - , , iris , CF-, , .

AO/NOA:

http://nbviewer.ipython.org/gist/ocefpaf/c66a7d0b967664ee4f5c

(. " CF-" .)