Read, Process, and Visualize Ambient Weather Station Data#

Motivation#

Within this notebook, we build the workflow to process data from the Ambient weather stations. We will also process the raw data, rename some fields, and write out the data to a netcdf file.

Imports#

from ambient_api.ambientapi import AmbientAPI
import numpy as np
from datetime import datetime
import time
import hvplot.pandas
import hvplot.xarray
from bokeh.models.formatters import DatetimeTickFormatter
import holoviews as hv
import pandas as pd
import panel as pn
import holoviews as hv
import xarray as xr
import os
from pathlib import Path
hv.extension('bokeh')

Setup Your Environment#

! export AMBIENT_ENDPOINT=https://api.ambientweather.net/v1
! export AMBIENT_API_KEY="b93528c5ad494a70bf4cf804b1fcf92df2ffddd530084ab7903fac42c235becd"
! export AMBIENT_APPLICATION_KEY="6f8a8d7706a744f28af53fca96ced84a0851269a01484942a97788c7c1d18992"

Call the API#

Now, we can call the API once we have our environment variables.

api = AmbientAPI()
devices = api.get_devices()

Setup Helper Functions and Metadata Fixes#

attrs_dict = {'tempf':{'standard_name': 'Temperature',
                       'units': 'degF'},
              'tempinf':{'standard_name': 'Temperature',
                         'units': 'degF'},
              'dewPoint': {'standard_name': 'Dewpoint Temperature',
                           'units': 'degF'},
              'dewPointin': {'standard_name': 'Dewpoint Temperature',
                             'units': 'degF'}}

variable_mapping = {'tempf':'outdoor_temperature',
                    'tempinf':'indoor_temperature',
                    'dewPoint':'outdoor_dewpoint',
                    'dewPointin':'indoor_dewpoint',
                    'date':'time'}


def process_station(device, attrs=attrs_dict, variable_mapping=variable_mapping):
    
    current_date = datetime.utcnow()
    # Read in the station data
    data = device.get_data(end_date = current_date)
    
    meta = device.info
    
    # Read into a pandas dataframe
    df = pd.DataFrame(data)
    
    # Format the times properly
    df['date'] = pd.to_datetime(df.date).astype('datetime64[ns]')

    # Sort the values and set the index to be the date
    df = df.sort_values('date')
    df = df.set_index('date')

    ds = df.to_xarray()

    # Add associated metadata
    for variable in attrs.keys():
        ds[variable].attrs = attrs[variable]
    
    # Rename the variables
    ds = ds.rename(variable_mapping)
        
    # Reshape the data
    ds = ds.expand_dims('station')
    ds['station'] = [meta['name']]
    ds['latitude'] = meta['coords']['coords']['lat']
    ds['longitude'] = meta['coords']['coords']['lon']
    
    ds = ds.sel(time=f"{current_date.year}-{current_date.month}-{current_date.day}")
    
    return ds

Run the Functions + Read our Data#

Read our data, and combine the datasets at the end into a single dataset.

dsets = []
for device in devices:
    try:
        dsets.append(process_station(device))
    except:
        pass
    time.sleep(5)
ds = xr.concat(dsets, dim='station')
---------------------------------------------------------------------------
StopIteration                             Traceback (most recent call last)
File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/site-packages/xarray/core/concat.py:254, in concat(objs, dim, data_vars, coords, compat, positions, fill_value, join, combine_attrs, create_index_for_new_dim)
    253 try:
--> 254     first_obj, objs = utils.peek_at(objs)
    255 except StopIteration as err:

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/site-packages/xarray/core/utils.py:199, in peek_at(iterable)
    198 gen = iter(iterable)
--> 199 peek = next(gen)
    200 return peek, itertools.chain([peek], gen)

StopIteration: 

The above exception was the direct cause of the following exception:

ValueError                                Traceback (most recent call last)
Cell In[6], line 8
      6         pass
      7     time.sleep(5)
----> 8 ds = xr.concat(dsets, dim='station')

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/site-packages/xarray/core/concat.py:256, in concat(objs, dim, data_vars, coords, compat, positions, fill_value, join, combine_attrs, create_index_for_new_dim)
    254     first_obj, objs = utils.peek_at(objs)
    255 except StopIteration as err:
--> 256     raise ValueError("must supply at least one object to concatenate") from err
    258 if compat not in set(_VALID_COMPAT) - {"minimal"}:
    259     raise ValueError(
    260         f"compat={compat!r} invalid: must be 'broadcast_equals', 'equals', 'identical', 'no_conflicts' or 'override'"
    261     )

ValueError: must supply at least one object to concatenate

Write out the Data File#

end_time = ds.isel(time=-1)
time_label = pd.to_datetime(end_time.time.values).strftime('%Y/%m/%d/ambient.a1.%Y%m%d.nc')
full_file = f'../../data/surface-meteorology/{time_label}'
full_path = Path(full_file)
if not os.path.exists(full_path.parent):
    os.makedirs(full_path.parent)
ds.to_netcdf(full_file)

Visualize the Variables#

formatter = DatetimeTickFormatter(hours="%d %b %Y \n %H:%M UTC")

variables = ['outdoor_temperature', 'outdoor_dewpoint', 'hourlyrainin', 'solarradiation']

panels = []
for variable in variables:
    panels.append(ds[variable].hvplot.line(x='time', by='station', xformatter=formatter))
hv.Layout(panels).cols(1)