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

# # Demo with esgf search for CMIP6 at DKRZ site (Subset + Average)
# 
# ESGF Node at DKRZ: https://esgf-data.dkrz.de/search/cmip6-dkrz/

# ## Use esgf search at DKRZ ... no distributed search
# 
# 
# 
# Using ``esgf-pyclient``: 
# https://esgf-pyclient.readthedocs.io/en/latest/notebooks/examples/search.html

# In[ ]:


from pyesgf.search import SearchConnection
conn = SearchConnection('http://esgf-data.dkrz.de/esg-search',
                        distrib=False)


# **Search only CMIP6 files locally available at DKRZ**

# In[ ]:


ctx = conn.new_context(project='CMIP6', data_node='esgf3.dkrz.de', latest=True, replica=False)
ctx.hit_count


# Select only one dataset

# In[ ]:


results = ctx.search(
    institution_id='MPI-M',
    source_id='MPI-ESM1-2-HR',
    experiment_id='historical', 
    variable='tas', 
    frequency='day',
    variant_label='r1i1p1f1'
)
len(results)


# In[ ]:


ds = results[0]
ds.json


# Get a dataset identifier used by rook

# In[ ]:


dataset_id = ds.json['instance_id']
dataset_id


# Time range

# In[ ]:


f"{ds.json['datetime_start']}/{ds.json['datetime_stop']})"


# Bounding Box: (West, Sout, East, North)

# In[ ]:


f"({ds.json['west_degrees']}, {ds.json['south_degrees']},{ds.json['east_degrees']}, {ds.json['west_degrees']}, {ds.json['north_degrees']})"


# Size in GB

# In[ ]:


f"{ds.json['size'] / 1024 / 1024 / 1024} GB"


# ## Use Rook to run subset + average

# In[ ]:


import os
os.environ['ROOK_URL'] = 'http://rook.dkrz.de/wps'
os.environ['ROOK_MODE'] = 'async'

from rooki import operators as ops


# Run subset workflow
# 
# http://bboxfinder.com/

# In[ ]:


bbox_africa = "-23.906250,-35.746512,63.632813,37.996163"


subset = ops.Subset(
            ops.Input(
                'tas', [dataset_id]
            ),
            time="1850-01-01/1850-12-31",
            area=bbox_africa,
        )
wf = ops.Average(subset, dims="time")

resp = wf.orchestrate()
resp.ok


# ### The outputs are available as a Metalink document
# https://github.com/metalink-dev

# Metalink URL

# In[ ]:


resp.url


# Number of files

# In[ ]:


resp.num_files


# Total size in MB

# In[ ]:


resp.size_in_mb


# Download URLs

# In[ ]:


resp.download_urls()


# Download and open with xarray

# In[ ]:


ds_0 = resp.datasets()[0]
ds_0


# ### Provenance
# 
# Provenance information is given using the *PROV* standard.
# https://pypi.org/project/prov/

# Provenance: URL to json document

# In[ ]:


resp.provenance()


# Provenance Plot

# In[ ]:


from IPython.display import Image
Image(resp.provenance_image())