update catalog

eco4cast · Oct 27, 2024 · cfdc553 · cfdc553
1 parent 1b13c2a
commit cfdc553
Show file tree

Hide file tree

Showing 176 changed files with 1,288 additions and 1,118 deletions.
diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/collection.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/collection.json
@@ -8,21 +8,6 @@
   ],
   "type": "Collection",
   "links": [
-    {
-      "rel": "item",
-      "type": "application/json",
-      "href": "./models/tg_tbats.json"
-    },
-    {
-      "rel": "item",
-      "type": "application/json",
-      "href": "./models/tg_temp_lm.json"
-    },
-    {
-      "rel": "item",
-      "type": "application/json",
-      "href": "./models/tg_temp_lm_all_sites.json"
-    },
     {
       "rel": "item",
       "type": "application/json",
@@ -113,6 +98,21 @@
       "type": "application/json",
       "href": "./models/tg_randfor.json"
     },
+    {
+      "rel": "item",
+      "type": "application/json",
+      "href": "./models/tg_tbats.json"
+    },
+    {
+      "rel": "item",
+      "type": "application/json",
+      "href": "./models/tg_temp_lm.json"
+    },
+    {
+      "rel": "item",
+      "type": "application/json",
+      "href": "./models/tg_temp_lm_all_sites.json"
+    },
     {
       "rel": "parent",
       "type": "application/json",

diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/USGSHABs1.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/USGSHABs1.json
@@ -17,7 +17,8 @@
   "properties": {
     "title": "USGSHABs1",
     "description": "All summaries for the Daily_Chlorophyll_a variable for the USGSHABs1 model. Information for the model is provided as follows: NA.\n                                    The model predicts this variable at the following sites: BLWA, TOMB, FLNT.\n                                    Summaries are the forecasts statistics of the raw forecasts (i.e., mean, median, confidence intervals)",
-    "datetime": "2024-10-23T00:00:00Z",
+    "datetime": "2024-02-05",
+    "updated": "2024-07-02",
     "start_datetime": "2023-11-12T00:00:00Z",
     "end_datetime": "2024-03-09T00:00:00Z",
     "providers": [
@@ -197,7 +198,7 @@
       "type": "application/x-parquet",
       "title": "Database Access for Daily Chlorophyll_a",
       "href": "s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=USGSHABs1?endpoint_override=sdsc.osn.xsede.org",
-      "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=USGSHABs1?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n"
+      "description": "Use `R` or `Python` code for remote access to the database. This code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=USGSHABs1?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n### Python\n\n```# Use code below\n\n\nimport ibis\n\n       con = ibis.duckdbf.connect()\n\n\n       con.raw_sql(f'''\n\n       CREATE OR REPLACE SECRET secret (\n\n       TYPE S3,\n\n       ENDPOINT 'sdsc.osn.xsede.org',\n\n       URL_STYLE 'path'\n\n\n       );/n\n       '''\n\n\n       path = \"s3:///project_id=neon4cast/duration=P1D/variable=chla/model_id=USGSHABs1\"\ncon.read_parquet(path + \"/**\")"
     }
   }
 }
diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/cb_prophet.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/cb_prophet.json
@@ -23,7 +23,8 @@
   "properties": {
     "title": "cb_prophet",
     "description": "All summaries for the Daily_Chlorophyll_a variable for the cb_prophet model. Information for the model is provided as follows: The Prophet model is an empirical model, specifically a non-linear regression model that includes\nseasonality effects (Taylor & Letham, 2018). The model relies on Bayesian estimation with an additive\nwhite noise error term.\n                                    The model predicts this variable at the following sites: BARC, BLWA, CRAM, FLNT, LIRO, PRLA, PRPO, SUGG, TOMB.\n                                    Summaries are the forecasts statistics of the raw forecasts (i.e., mean, median, confidence intervals)",
-    "datetime": "2024-10-23T00:00:00Z",
+    "datetime": "2024-02-06",
+    "updated": "2024-02-07",
     "start_datetime": "2023-11-14T00:00:00Z",
     "end_datetime": "2024-03-10T00:00:00Z",
     "providers": [
@@ -209,7 +210,7 @@
       "type": "application/x-parquet",
       "title": "Database Access for Daily Chlorophyll_a",
       "href": "s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=cb_prophet?endpoint_override=sdsc.osn.xsede.org",
-      "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=cb_prophet?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n"
+      "description": "Use `R` or `Python` code for remote access to the database. This code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=cb_prophet?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n### Python\n\n```# Use code below\n\n\nimport ibis\n\n       con = ibis.duckdbf.connect()\n\n\n       con.raw_sql(f'''\n\n       CREATE OR REPLACE SECRET secret (\n\n       TYPE S3,\n\n       ENDPOINT 'sdsc.osn.xsede.org',\n\n       URL_STYLE 'path'\n\n\n       );/n\n       '''\n\n\n       path = \"s3:///project_id=neon4cast/duration=P1D/variable=chla/model_id=cb_prophet\"\ncon.read_parquet(path + \"/**\")"
     }
   }
 }
diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/climatology.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/climatology.json
@@ -24,7 +24,8 @@
   "properties": {
     "title": "climatology",
     "description": "All summaries for the Daily_Chlorophyll_a variable for the climatology model. Information for the model is provided as follows: Historical DOY mean and sd.  Assumes normal distribution.\n                                    The model predicts this variable at the following sites: BARC, BLWA, FLNT, SUGG, TOMB, CRAM, LIRO, PRPO, PRLA, TOOK, USGS-01427510, USGS-01463500, USGS-05543010, USGS-05553700, USGS-05558300, USGS-05586300, USGS-14181500, USGS-14211010, USGS-14211720.\n                                    Summaries are the forecasts statistics of the raw forecasts (i.e., mean, median, confidence intervals)",
-    "datetime": "2024-10-23T00:00:00Z",
+    "datetime": "2024-08-22",
+    "updated": "2024-08-23",
     "start_datetime": "2023-01-02T00:00:00Z",
     "end_datetime": "2024-09-26T00:00:00Z",
     "providers": [
@@ -220,7 +221,7 @@
       "type": "application/x-parquet",
       "title": "Database Access for Daily Chlorophyll_a",
       "href": "s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=climatology?endpoint_override=sdsc.osn.xsede.org",
-      "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=climatology?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n"
+      "description": "Use `R` or `Python` code for remote access to the database. This code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=climatology?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n### Python\n\n```# Use code below\n\n\nimport ibis\n\n       con = ibis.duckdbf.connect()\n\n\n       con.raw_sql(f'''\n\n       CREATE OR REPLACE SECRET secret (\n\n       TYPE S3,\n\n       ENDPOINT 'sdsc.osn.xsede.org',\n\n       URL_STYLE 'path'\n\n\n       );/n\n       '''\n\n\n       path = \"s3:///project_id=neon4cast/duration=P1D/variable=chla/model_id=climatology\"\ncon.read_parquet(path + \"/**\")"
     }
   }
 }
diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/persistenceRW.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/persistenceRW.json
@@ -24,7 +24,8 @@
   "properties": {
     "title": "persistenceRW",
     "description": "All summaries for the Daily_Chlorophyll_a variable for the persistenceRW model. Information for the model is provided as follows: Random walk from the fable package with ensembles used to represent uncertainty.\n                                    The model predicts this variable at the following sites: LIRO, PRLA, PRPO, SUGG, TOMB, TOOK, BARC, BLWA, CRAM, FLNT.\n                                    Summaries are the forecasts statistics of the raw forecasts (i.e., mean, median, confidence intervals)",
-    "datetime": "2024-10-23T00:00:00Z",
+    "datetime": "2024-08-22",
+    "updated": "2024-08-23",
     "start_datetime": "2023-11-15T00:00:00Z",
     "end_datetime": "2024-09-25T00:00:00Z",
     "providers": [
@@ -211,7 +212,7 @@
       "type": "application/x-parquet",
       "title": "Database Access for Daily Chlorophyll_a",
       "href": "s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=persistenceRW?endpoint_override=sdsc.osn.xsede.org",
-      "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=persistenceRW?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n"
+      "description": "Use `R` or `Python` code for remote access to the database. This code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=persistenceRW?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n### Python\n\n```# Use code below\n\n\nimport ibis\n\n       con = ibis.duckdbf.connect()\n\n\n       con.raw_sql(f'''\n\n       CREATE OR REPLACE SECRET secret (\n\n       TYPE S3,\n\n       ENDPOINT 'sdsc.osn.xsede.org',\n\n       URL_STYLE 'path'\n\n\n       );/n\n       '''\n\n\n       path = \"s3:///project_id=neon4cast/duration=P1D/variable=chla/model_id=persistenceRW\"\ncon.read_parquet(path + \"/**\")"
     }
   }
 }
diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/procBlanchardMonod.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/procBlanchardMonod.json
@@ -21,7 +21,8 @@
   "properties": {
     "title": "procBlanchardMonod",
     "description": "All summaries for the Daily_Chlorophyll_a variable for the procBlanchardMonod model. Information for the model is provided as follows: NA.\n                                    The model predicts this variable at the following sites: BARC, CRAM, LIRO, PRLA, PRPO, SUGG, TOOK.\n                                    Summaries are the forecasts statistics of the raw forecasts (i.e., mean, median, confidence intervals)",
-    "datetime": "2024-10-23T00:00:00Z",
+    "datetime": "2024-02-05",
+    "updated": "2024-02-07",
     "start_datetime": "2023-11-13T00:00:00Z",
     "end_datetime": "2024-03-06T00:00:00Z",
     "providers": [
@@ -205,7 +206,7 @@
       "type": "application/x-parquet",
       "title": "Database Access for Daily Chlorophyll_a",
       "href": "s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=procBlanchardMonod?endpoint_override=sdsc.osn.xsede.org",
-      "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=procBlanchardMonod?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n"
+      "description": "Use `R` or `Python` code for remote access to the database. This code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=procBlanchardMonod?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n### Python\n\n```# Use code below\n\n\nimport ibis\n\n       con = ibis.duckdbf.connect()\n\n\n       con.raw_sql(f'''\n\n       CREATE OR REPLACE SECRET secret (\n\n       TYPE S3,\n\n       ENDPOINT 'sdsc.osn.xsede.org',\n\n       URL_STYLE 'path'\n\n\n       );/n\n       '''\n\n\n       path = \"s3:///project_id=neon4cast/duration=P1D/variable=chla/model_id=procBlanchardMonod\"\ncon.read_parquet(path + \"/**\")"
     }
   }
 }
diff --git a/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/procCTMIMonod.json b/catalog/summaries/Aquatics/Daily_Chlorophyll_a/models/procCTMIMonod.json
@@ -21,7 +21,8 @@
   "properties": {
     "title": "procCTMIMonod",
     "description": "All summaries for the Daily_Chlorophyll_a variable for the procCTMIMonod model. Information for the model is provided as follows: NA.\n                                    The model predicts this variable at the following sites: BARC, CRAM, LIRO, PRLA, PRPO, SUGG, TOOK.\n                                    Summaries are the forecasts statistics of the raw forecasts (i.e., mean, median, confidence intervals)",
-    "datetime": "2024-10-23T00:00:00Z",
+    "datetime": "2024-02-05",
+    "updated": "2024-02-07",
     "start_datetime": "2023-11-13T00:00:00Z",
     "end_datetime": "2024-03-06T00:00:00Z",
     "providers": [
@@ -205,7 +206,7 @@
       "type": "application/x-parquet",
       "title": "Database Access for Daily Chlorophyll_a",
       "href": "s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=procCTMIMonod?endpoint_override=sdsc.osn.xsede.org",
-      "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=procCTMIMonod?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n"
+      "description": "Use `R` or `Python` code for remote access to the database. This code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@/project_id=neon4cast/duration=P1D/variable=chla/model_id=procCTMIMonod?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n       \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n### Python\n\n```# Use code below\n\n\nimport ibis\n\n       con = ibis.duckdbf.connect()\n\n\n       con.raw_sql(f'''\n\n       CREATE OR REPLACE SECRET secret (\n\n       TYPE S3,\n\n       ENDPOINT 'sdsc.osn.xsede.org',\n\n       URL_STYLE 'path'\n\n\n       );/n\n       '''\n\n\n       path = \"s3:///project_id=neon4cast/duration=P1D/variable=chla/model_id=procCTMIMonod\"\ncon.read_parquet(path + \"/**\")"
     }
   }
 }