convert csv to netcdf

Question

I am trying to convert a .csv file to a netCDF4 via Python but I am having trouble figuring out how I can store information from a .csv table format into a netCDF. My main concern is how do we declare the variables from the columns into a workable netCDF4 format? Everything I have found is normally extracting information from a netCDF4 to a .csv or ASCII. I have provided the sample data, sample code, and my errors for declaring the appropriate arrays. Any help would be much appreciated.

The sample table is 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 csv file and declare variable for arrays for each heading

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 that works as a netcdf

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

# latitudes and longitudes. Include 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 data.

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 the lat and lon dimensions.

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

# Define the coordinate variables. They will hold the coordinate information

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

# Assign units attributes to coordinate var data. This attaches a text attribute to each of the coordinate variables, containing the units.

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

# write data to coordinate vars.

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

# create the pressure and temperature variables

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

# set the units attribute.

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

# write data to variables.

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

ncout.close()
f.close()

error:

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

This is a perfect job for xarray, a python package that has a dataset object representing the netcdf common data model. Here's an example you can try:

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.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')

Then running ncdump -h ao_and_nao.nc produces:

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" ;

Note that you can install xarray using pip, but if you are using the Anaconda Python Distribution, you can install it from the Anaconda.org/conda-forge channel by using:

conda install -c conda-forge xarray