# This example script uses the "erddapy" python package to download data from ONC ERDDAP server.
# More information on how to use the erddapy package to download data using python: https://github.com/ioos/erddapy

# Installing erddapy in conda
# conda install --channel conda-forge erddapy

# Installing erddapy using pip
# pip install erddapy

from erddapy import ERDDAP
import pandas as pd

erddap_server = ERDDAP(
  server='http://dap.onc.uvic.ca/erddap', # ONC ERDDAP server
)

# Fetch total number of datasets on the server
df = pd.read_csv(erddap_server.get_search_url(response='csv', search_for='all'))
print(
    f'ONC currently hosts {len(set(df["tabledap"].dropna()))} '
    f'tabledap, {len(set(df["griddap"].dropna()))} '
    f'griddap, and {len(set(df["wms"].dropna()))} wms endpoints.'
)

# Searching for datasets
# The following parameter list will search for all datasets available between 2015 and 2017 with temperature as a variable.
params = {
    'standard_name': 'temperature',
    'min_time': '2015-01-01T00:00:00Z',
    'max_time': '2017-12-31T00:00:00Z'
}
search_url = erddap_server.get_search_url(response='csv', **params)
print(pd.read_csv(search_url)['Dataset ID'].values)

# Fetch metadata of a particular dataset
metadata_url = erddap_server.get_info_url(dataset_id="scalar_1206500", response='csv')
metadata = pd.read_csv(metadata_url)
metadata.head()

# Fetch all data categories from the server
category_url = erddap_server.get_categorize_url(categorize_by='standard_name', response='csv')
pd.read_csv(category_url)['Category']

# Downloading a dataset
server_url = ERDDAP(
    server='http://dap.onc.uvic.ca/erddap',
    protocol='tabledap',
    response='csv',
)

server_url.dataset_id = "scalar_118170"
server_url.constraints = {
    'time>=': '2012-05-24T00:00:00Z',
    'time<=': '2012-05-29T00:00:00Z'
}
server_url.variables = [
    'latitude',
    'longitude',
    'temperature',
    'time'
]

data_url = server_url.get_download_url()

df = server_url.to_pandas(
    index_col='time (UTC)',
    parse_dates=True,
).dropna()

df.head()

# To fetch all variables in a dataset, do not define the variable parameters for the url object
# Clear workspace before executing next code block
server_url = ERDDAP(
    server='http://dap.onc.uvic.ca/erddap',
    protocol='tabledap',
    response='csv',
)

server_url.dataset_id = "scalar_118170"
server_url.constraints = {
    'time>=': '2012-05-24T00:00:00Z',
    'time<=': '2012-05-29T00:00:00Z'
}
data_url = server_url.get_download_url()

df = server_url.to_pandas(
    index_col='time (UTC)',
    parse_dates=True,
)
df.head()

# Plot data
import matplotlib.pyplot as plt
import matplotlib.dates as mdates

fig, ax = plt.subplots(figsize=(17, 2))
cs = ax.scatter(df.index, df['temperature (K)'], s=1)
ax.invert_yaxis()
ax.set_xlim(df.index[0], df.index[-1])
xfmt = mdates.DateFormatter('%H:%Mh\n%d-%b')
ax.xaxis.set_major_formatter(xfmt)
ax.set_ylabel('Temperature ($^\circ$K)');

% Load portion of dataset from ONC ERDDAP server load(urlwrite('http://dap.onc.uvic.ca/erddap/tabledap/SaanichInlet_BPS_WLFLNTU2474.mat?timeseries_id,profile_id,time,latitude,longitude,chlorophyll,turbidity,depth&time>=2015-01-02T00:00:00Z&time<=2015-01-03T00:00:00Z', 'test.mat'));

% Load metadata for dataset from ONC ERDDAP server and review portions of the response
load(urlwrite('http://dap.onc.uvic.ca/erddap/info/SaanichInlet_BPS_WLFLNTU2474/index.mat', 'meta.mat'));

response.Attribute_Name

% Get the device name attribute from the response object
for i=1:length(response.Attribute_Name)
if strcmp(strtrim(response.Attribute_Name(i,: - ) ),'deviceName')
response.Value(i,: - )
end
end

% Get units attribute from the response object
j=1;
for i=1:length(response.Attribute_Name)
if strcmp(strtrim(response.Attribute_Name(i,: -) ),'units')
units(j,: - ) =response.Value(i,: -) ;
j=j+1;
end
end
units

% Investigate some of the dataset contents
length(SaanichInlet_BPS_WLFLNTU2474.chlorophyll)
SaanichInlet_BPS_WLFLNTU2474.chlorophyll(1:10)
max(SaanichInlet_BPS_WLFLNTU2474.turbidity)
min(SaanichInlet_BPS_WLFLNTU2474.turbidity)

% Chlorophyll plots - vs time, depth and turbidity
plot(SaanichInlet_BPS_WLFLNTU2474.time, SaanichInlet_BPS_WLFLNTU2474.chlorophyll)
datetick
xlabel('Time')
ylabel('Chlorophyll')

plot(SaanichInlet_BPS_WLFLNTU2474.chlorophyll,SaanichInlet_BPS_WLFLNTU2474.depth,'.')
ylabel('Depth')
xlabel('Chlorophyll')
axis ij

scatter(SaanichInlet_BPS_WLFLNTU2474.chlorophyll, SaanichInlet_BPS_WLFLNTU2474.turbidity)
xlabel('Chlorphyll')
ylabel('Turbidity')

# This example script uses the "rerddap" R package to download data from ONC ERDDAP server.
# More information on how to use the erddapy package to download data using python: https://cran.r-project.org/web/packages/rerddap/rerddap.pdf

# Install packages
# install.packages("rerddap")
# install.packages("tidyverse")

library(rerddap)
library(tidyverse)

erddap_server <- "http://dap.onc.uvic.ca/erddap/"

all_datasets <- ed_datasets(which = "tabledap", url = erddap_server)
head(all_datasets)

# Get metadata of a particular dataset
info("scalar_118170", url = erddap_server)

# Download a subset of a dataset using different parameters

# Subset over time
data_susbet1 <- tabledap("scalar_118170", 'time>=2012-05-23', 'time<=2012-05-29', url = erddap_server)

# Subset by variable name
data_susbet2 <- tabledap("scalar_118170", fields = c("time", "temperature"),
                         'time>=2012-05-23', 'time<=2012-05-29', url = erddap_server)

# Download complete dataset with no filters
data <- tabledap("scalar_118170", url = erddap_server)

# Plot the data
# Convert to date time before plotting
data_subset2$date <- paste(substr(data_subset2$time,1,10),substr(data_subset2$time,12,19),sep=" ")
data_subset2$date <- as.POSIXct(data_subset2$date,format="%Y-%m-%d %H:%M:%S",tz="UTC")

with(data_subset2, plot(date, temperature, type = "l", 
                        col = "blue", xlab = "Date", ylab = "Temperature (K)", xaxt = "n"))
axis(1, data_subset2$date, format(data_subset2$date, "%b %d"), cex.axis = .7)