Single server

.github/workflows/tests.yml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
         os: [windows-latest, ubuntu-latest, macos-latest]
       fail-fast: false
 

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.4.0
+  rev: v4.5.0
   hooks:
     - id: trailing-whitespace
     - id: check-ast
@@ -20,7 +20,7 @@ repos:
     language_version: python3
 
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v1.5.1
+  rev: v1.6.0
   hooks:
   - id: mypy
     exclude: docs/source/conf.py

gliderpy/fetchers.py

@@ -12,13 +12,12 @@
 
 from gliderpy.servers import (
     server_parameter_rename,
-    server_select,
     server_vars,
 )
 
 OptionalStr = Optional[str]
 
-# This defaults to the IOOS glider DAC.
+# Defaults to the IOOS glider DAC.
 _server = "https://gliders.ioos.us/erddap"
 
 
@@ -36,16 +35,15 @@ def standardise_df(df, dataset_url):
 class GliderDataFetcher:
     """
     Args:
-        server: a glider ERDDAP server URL
+        server: A glider ERDDAP server URL.
 
     Attributes:
-        dataset_id: a dataset unique id.
-        constraints: download constraints, default
+        dataset_id: A dataset unique id.
+        constraints: Download constraints, defaults same as query.
 
     """
 
     def __init__(self, server=_server):
-        server = server_select(server)
         self.server = server
         self.fetcher = ERDDAP(
             server=server,
@@ -61,9 +59,14 @@ def to_pandas(self):
 
         :return: pandas dataframe with datetime UTC as index
         """
-        if type(self.datasets) is pd.Series:
+        if self.fetcher.dataset_id:
+            df = self.fetcher.to_pandas(
+                index_col="time (UTC)",
+                parse_dates=True,
+            )
+        elif not self.fetcher.dataset_id and self.datasets is not None:
             df_all = []
-            for dataset_id in self.datasets:
+            for dataset_id in self.datasets["Dataset ID"]:
                 self.fetcher.dataset_id = dataset_id
                 df = self.fetcher.to_pandas(
                     index_col="time (UTC)",
@@ -73,20 +76,26 @@ def to_pandas(self):
                 df = standardise_df(df, dataset_url)
                 df_all.append(df)
             return pd.concat(df_all)
+        else:
+            raise ValueError(
+                f"Must provide a {self.fetcher.dataset_id} or `query` terms to download data.",
+            )
 
-        if not self.fetcher.dataset_id:
-            return None
-
-        df = self.fetcher.to_pandas(
-            index_col="time (UTC)",
-            parse_dates=True,
-        )
-        # Standardize variable names
+        # Standardize variable names.
         dataset_url = self.fetcher.get_download_url().split("?")[0]
         df = standardise_df(df, dataset_url)
         return df
 
-    def query(self, min_lat, max_lat, min_lon, max_lon, min_time, max_time):
+    def query(
+        self,
+        min_lat,
+        max_lat,
+        min_lon,
+        max_lon,
+        min_time,
+        max_time,
+        delayed=False,
+    ):
         """
         Takes user supplied geographical and time constraints and adds them to the query
 
@@ -106,7 +115,7 @@ def query(self, min_lat, max_lat, min_lon, max_lon, min_time, max_time):
             "longitude>=": min_lon,
             "longitude<=": max_lon,
         }
-        if not self.fetcher.dataset_id:
+        if not self.datasets:
             url = self.fetcher.get_search_url(
                 search_for="glider",
                 response="csv",
@@ -117,27 +126,24 @@ def query(self, min_lat, max_lat, min_lon, max_lon, min_time, max_time):
                 min_time=min_time,
                 max_time=max_time,
             )
+            self.query_url = url
             try:
                 data = urlopen(url)
             except httpx.HTTPError as err:
                 raise Exception(
                     f"Error, no datasets found in supplied range. Try relaxing your constraints: {self.fetcher.constraints}",
                 ) from err
                 return None
-            df = pd.read_csv(data)
-            self.datasets = df["Dataset ID"]
-            return df[["Title", "Institution", "Dataset ID"]]
-
-        return self
-
-    def platform(self, platform):
-        """
-
-        :param platform: platform and deployment id from ifremer
-        :return: search query with platform constraint applied
-        """
-        self.fetcher.constraints["platform_deployment="] = platform
-        return self
+            df = pd.read_csv(data)[["Title", "Institution", "Dataset ID"]]
+            if not delayed:
+                df = df.loc[~df["Dataset ID"].str.endswith("delayed")]
+                info_urls = [
+                    self.fetcher.get_info_url(dataset_id=dataset_id, response="html")
+                    for dataset_id in df["Dataset ID"]
+                ]
+                df["info_url"] = info_urls
+            self.datasets = df
+        return self.datasets
 
 
 class DatasetList:
@@ -146,7 +152,7 @@ class DatasetList:
 
     Attributes:
         e: an ERDDAP server instance
-        TODO: search_terms: A list of terms to search the server for. Multiple terms will be combined as AND
+        TODO: search_terms: A list of terms to search the server for. Multiple terms will be combined as "AND."
 
     """
 
@@ -166,6 +172,3 @@ def get_ids(self):
             return self.dataset_ids
         else:
             raise ValueError(f"The {self.e.server} does not supported this operation.")
-        # TODO: List the platform_deployment variable
-        # if self.e.server == "https://erddap.ifremer.fr/erddap":
-        #     platform_deployment

gliderpy/servers.py

@@ -4,69 +4,30 @@
 """
 
 
-server_alias = {
-    "National Glider Data Assembly Center": "https://gliders.ioos.us/erddap",
-    "NGDAC": "https://gliders.ioos.us/erddap",
-    "IOOS": "https://gliders.ioos.us/erddap",
-    "Ocean Observatories Initiative": "https://erddap.dataexplorer.oceanobservatories.org/erddap/index.html",
-    "OOI": "https://erddap.dataexplorer.oceanobservatories.org/erddap/index.html",
-    "Institut français de recherche pour l'exploitation de la mer": "https://www.ifremer.fr/erddap",
-    "ifremer": "https://www.ifremer.fr/erddap",
-    "ifremer.fr": "https://www.ifremer.fr/erddap",
-}
-
 server_vars = {
     "https://gliders.ioos.us/erddap": [
-        "pressure",
         "latitude",
         "longitude",
+        "pressure",
+        "profile_id",
         "salinity",
         "temperature",
         "time",
     ],
-    "http://www.ifremer.fr/erddap": [
-        "time",
-        "latitude",
-        "longitude",
-        "PSAL",
-        "TEMP",
-        "PRES",
-    ],
 }
 
 server_parameter_rename = {
-    "latitude (degrees_north)": "latitude",
-    "longitude (degrees_east)": "longitude",
-    "salinity (1)": "salinity",
-    "psal (psu)": "salinity",
     "ctdgv_m_glider_instrument_practical_salinity (1)": "salinity",
-    "temperature (celsius)": "temperature",
-    "temp (degree_celsius)": "temperature",
+    "ctdgv_m_glider_instrument_sci_water_pressure_dbar (dbar)": "pressure",
     "ctdgv_m_glider_instrument_sci_water_temp (deg_c)": "temperature",
+    "dataset_url": "dataset_url",
+    "latitude (degrees_north)": "latitude",
+    "longitude (degrees_east)": "longitude",
     "pres (decibar)": "pressure",
     "pressure (dbar)": "pressure",
-    "ctdgv_m_glider_instrument_sci_water_pressure_dbar (dbar)": "pressure",
-    "dataset_url": "dataset_url",
+    "profile_id": "profile_id",
+    "psal (psu)": "salinity",
+    "salinity (1)": "salinity",
+    "temp (degree_celsius)": "temperature",
+    "temperature (celsius)": "temperature",
 }
-
-
-def server_select(server_string):
-    """
-    Attempts to match the supplied string to a known ERDDAP server by address or alias
-    """
-    if server_string in server_vars:
-        # If string matches exactly, return unchanged
-        return server_string
-    for server in server_vars:
-        # If string contains base ERDDAP address, return base ERDDAP address
-        if server in server_string:
-            return server
-    for alias in server_alias:
-        # If string matches one of the aliases, return the corresponding ERDDAP address
-        if server_string.lower() == alias.lower():
-            return server_alias[alias]
-    # If the server is not recognised, print options of working servers and exit
-    raise ValueError(
-        "Supplied server/alias not recognised. Please use one of the following supported servers:\n"
-        f"{str(server_vars.keys())[10:-1]}",
-    )

notebooks/00-quick_intro.ipynb

@@ -19,7 +19,7 @@
     "```\n",
     "\n",
     "gliderpy aims to make querying and downloading glider data easier.\n",
-    "Here is how one would build a query using `erddapy`:"
+    "Here is how one would build a query using erddapy:"
    ]
   },
   {
@@ -43,6 +43,7 @@
     "    \"longitude\",\n",
     "    \"salinity\",\n",
     "    \"temperature\",\n",
+    "    \"profile_id\",\n",
     "    \"time\",\n",
     "]\n",
     "\n",
@@ -79,16 +80,18 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The variable names are standardised by gliderpy, making it easier to fetch from different data sources and comparing the results.\n",
+    "Much easier, right?\n",
+    "The variable names are standardized by gliderpy,\n",
+    "making it easier to fetch from different data sources and comparing the results.\n",
     "\n",
-    "`gliderpy` can subset the data on the server side by passing a geographic bounding box and time interval."
+    "The gliderpy library can subset the data on the server side by passing a geographic bounding box and time interval."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Multiple datasets\n",
+    "### Querying multiple datasets\n",
     "\n",
     "The most common use is to search all datasets for data that falls within the certain space-time bounds."
    ]
@@ -101,7 +104,16 @@
    "source": [
     "glider_grab = GliderDataFetcher()\n",
     "\n",
-    "glider_grab.query(10, 40, -90, 8, \"2010-01-01\", \"2013-06-02\")\n",
+    "df = glider_grab.query(10, 40, -90, 8, \"2010-01-01\", \"2013-06-02\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "df = glider_grab.to_pandas()\n",
     "df.head()"
    ]
@@ -112,7 +124,7 @@
    "source": [
     "### Dataset search\n",
     "\n",
-    "One can query all dataset_ids available."
+    "One can query all dataset_ids available in the server."
    ]
   },
   {
@@ -126,7 +138,7 @@
     "datasets = DatasetList()\n",
     "ds_ids = datasets.get_ids()\n",
     "\n",
-    "print(f\"found {len(ds_ids)} glider datasets on the server {datasets.e.server}\")"
+    "print(f\"found {len(ds_ids)} glider datasets on the server {datasets.e.server}.\")"
    ]
   }
  ],
@@ -146,7 +158,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.6"
   }
  },
  "nbformat": 4,