#!/usr/bin/env python
# coding: utf-8

# # Assess time series extraction methods for a large gridded dataset (CFSR)

# In[1]:


get_ipython().run_line_magic('matplotlib', 'inline')
import xarray as xr
import pandas as pd


# ### Specify time range and location for extracted time series

# In[2]:


start = '2017-01-01'
stop = '2017-03-01'
lon0 = -71.6+360
lat0 = 41.55


# ### Extract time series using xarray from HSDS dataset

# In[3]:


# use URL for 12 month dataset
url_hsds = 'http://149.165.156.174:5101/home/rsignell/tmp2m_2017.nc'
ds_hsds = xr.open_dataset(url_hsds, engine='h5netcdf', decode_cf=False)

# next two lines are to add back in missing units
ds_hsds['time'].attrs['units']='seconds since 1970-01-01 00:00'
ds_hsds = xr.decode_cf(ds_hsds)

loc_hsds = ds_hsds.sel(longitude=lon0, latitude=lat0, method='nearest')
d_hsds = loc_hsds.sel(time=slice(start,stop))
get_ipython().run_line_magic('time', "d_hsds['TMP_2maboveground'].plot();")


# In[4]:


import h5pyd
f = h5pyd.File(url_hsds,'r')
ds = f['TMP_2maboveground']
ds.chunks


# ### Extract time series using xarray from concatenated netcdf file via OPeNDAP

# In[5]:


url_dap = 'http://js-170-55.jetstream-cloud.org/thredds/dodsC/data/CFSR/2017/tmp2m_2months.nc'
ds_dap = xr.open_dataset(url_dap)
loc_dap = ds_dap.sel(longitude=lon0, latitude=lat0, method='nearest')
d_dap = loc_dap.sel(time=slice(start,stop))

get_ipython().run_line_magic('time', "d_dap['TMP_2maboveground'].plot();")


# ### Extract time series using xarray from grib aggregation via OPeNDAP

# In[7]:


url_dap_grb2 = 'http://js-170-55.jetstream-cloud.org/thredds/dodsC/grib/CFSr_v2/tmp2m/Best'
ds_dap_grb2 = xr.open_dataset(url_dap_grb2)
loc_dap_grb2 = ds_dap_grb2.sel(lon=lon0, lat=lat0, method='nearest')
d_dap_grb2 = loc_dap_grb2.sel(time=slice(start,stop))
get_ipython().run_line_magic('time', "d_dap_grb2['Temperature_height_above_ground'].plot();")


# ### Extract time series using from grib aggregation using NCSS (NetCDF Subset Service)

# In[8]:


url = ('https://js-170-55.jetstream-cloud.org/thredds'
       '/ncss/grib/CFSr_v2/tmp2m/Best?var=Temperature_height_above_ground&'
       'latitude={}&longitude={}&time_start={}T01%3A00%3A00Z&time_end={}T00%3A00%3A00Z&'
       'vertCoord=&accept=csv'.format(lat0,lon0,start,stop))
get_ipython().run_line_magic('time', "df = pd.read_csv(url, parse_dates=True, index_col='time')")
df['Temperature_height_above_ground[unit="K"]'].plot()