"
144 | ]
145 | },
146 | "execution_count": 7,
147 | "metadata": {},
148 | "output_type": "execute_result"
149 | }
150 | ],
151 | "source": [
152 | "spatial_chunk = 4096\n",
153 | "compressor = Zstd(level=1)\n",
154 | "encoding = {\n",
155 | " \"analysed_sst\": {\n",
156 | " \"chunks\": (1, spatial_chunk, spatial_chunk),\n",
157 | " \"compressor\": compressor,\n",
158 | " },\n",
159 | " \"sea_ice_fraction\": {\n",
160 | " \"chunks\": (1, spatial_chunk, spatial_chunk),\n",
161 | " \"compressor\": compressor,\n",
162 | " },\n",
163 | "}\n",
164 | "ds.to_zarr(v2_output, mode=\"w\", consolidated=True, zarr_format=2, encoding=encoding)"
165 | ]
166 | },
167 | {
168 | "cell_type": "markdown",
169 | "metadata": {},
170 | "source": [
171 | "## Inspect Zarr V2 store"
172 | ]
173 | },
174 | {
175 | "cell_type": "markdown",
176 | "metadata": {},
177 | "source": [
178 | "First, let's look at the structure of Zarr arrays using zarr's `Group.tree()` method"
179 | ]
180 | },
181 | {
182 | "cell_type": "code",
183 | "execution_count": 8,
184 | "metadata": {},
185 | "outputs": [
186 | {
187 | "data": {
188 | "text/html": [
189 | "/\n",
190 | "├── analysed_sst (1, 17999, 36000) float64\n",
191 | "├── lat (17999,) float32\n",
192 | "├── lon (36000,) float32\n",
193 | "├── sea_ice_fraction (1, 17999, 36000) float64\n",
194 | "├── spatial_ref () int64\n",
195 | "└── time (1,) int32\n",
196 | "
\n"
197 | ],
198 | "text/plain": [
199 | "\u001b[1m/\u001b[0m\n",
200 | "├── \u001b[1manalysed_sst\u001b[0m (1, 17999, 36000) float64\n",
201 | "├── \u001b[1mlat\u001b[0m (17999,) float32\n",
202 | "├── \u001b[1mlon\u001b[0m (36000,) float32\n",
203 | "├── \u001b[1msea_ice_fraction\u001b[0m (1, 17999, 36000) float64\n",
204 | "├── \u001b[1mspatial_ref\u001b[0m () int64\n",
205 | "└── \u001b[1mtime\u001b[0m (1,) int32\n"
206 | ]
207 | },
208 | "execution_count": 8,
209 | "metadata": {},
210 | "output_type": "execute_result"
211 | }
212 | ],
213 | "source": [
214 | "root = zarr.open_group(v2_output)\n",
215 | "root.tree()"
216 | ]
217 | },
218 | {
219 | "cell_type": "markdown",
220 | "metadata": {},
221 | "source": [
222 | "Second, let's look at what's actually recorded in the Zarr metadata using the consolidated metadata at the root of the Zarr store.\n",
223 | "\n",
224 | "In order to match valid JSON, we convert the nan fill_value entries to \"nan\".\n",
225 | "\n",
226 | "### Key observations\n",
227 | "\n",
228 | "- For each array, metadata is stored under '.zattrs'\n",
229 | "- All arrays contain a `.zattrs/standard_name`\n",
230 | "- The root group specifies that the metadata follows CF conventions, which should be validated.\n",
231 | "- `.zattrs/_ARRAY_DIMENSIONS` for `lat`, `lon`, and `time` contains a list with only the the name of the array, indicating that they are coordinates variables.\n",
232 | "- `.zattrs/_ARRAY_DIMENSIONS` for `spatial_ref` contains an empty list, indicating that it is an auxiliary coordinate.\n",
233 | "- `.zattrs/_ARRAY_DIMENSIONS` for `analysed_sst`, `sea_ice_fraction` contain a list referring to other arrays, indicating that they are data variables rather than coordinate variables.\n",
234 | "- `.zattrs/grid_mapping` for `analysed_sst`, `sea_ice_fraction` is `\"spatial_ref\"` indicating that CRS information is included in that auxiliary variable's metadata.\n",
235 | "- `spatial_ref/.zattrs` contains the OGC WKT for the CRS.\n"
236 | ]
237 | },
238 | {
239 | "cell_type": "code",
240 | "execution_count": 9,
241 | "metadata": {},
242 | "outputs": [
243 | {
244 | "data": {
245 | "text/html": [
246 | ""
262 | ]
263 | },
264 | "metadata": {},
265 | "output_type": "display_data"
266 | },
267 | {
268 | "data": {
269 | "application/javascript": "(function(root) {\n function now() {\n return new Date();\n }\n\n const force = true;\n const py_version = '3.6.3'.replace('rc', '-rc.').replace('.dev', '-dev.');\n const reloading = false;\n const Bokeh = root.Bokeh;\n\n // Set a timeout for this load but only if we are not already initializing\n if (typeof (root._bokeh_timeout) === \"undefined\" || (force || !root._bokeh_is_initializing)) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks;\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, js_modules, js_exports, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n if (js_modules == null) js_modules = [];\n if (js_exports == null) js_exports = {};\n\n root._bokeh_onload_callbacks.push(callback);\n\n if (root._bokeh_is_loading > 0) {\n // Don't load bokeh if it is still initializing\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n } else if (js_urls.length === 0 && js_modules.length === 0 && Object.keys(js_exports).length === 0) {\n // There is nothing to load\n run_callbacks();\n return null;\n }\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n window._bokeh_on_load = on_load\n\n function on_error(e) {\n const src_el = e.srcElement\n console.error(\"failed to load \" + (src_el.href || src_el.src));\n }\n\n const skip = [];\n if (window.requirejs) {\n window.requirejs.config({'packages': {}, 'paths': {}, 'shim': {}});\n root._bokeh_is_loading = css_urls.length + 0;\n } else {\n root._bokeh_is_loading = css_urls.length + js_urls.length + js_modules.length + Object.keys(js_exports).length;\n }\n\n const existing_stylesheets = []\n const links = document.getElementsByTagName('link')\n for (let i = 0; i < links.length; i++) {\n const link = links[i]\n if (link.href != null) {\n existing_stylesheets.push(link.href)\n }\n }\n for (let i = 0; i < css_urls.length; i++) {\n const url = css_urls[i];\n const escaped = encodeURI(url)\n if (existing_stylesheets.indexOf(escaped) !== -1) {\n on_load()\n continue;\n }\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error;\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n } var existing_scripts = []\n const scripts = document.getElementsByTagName('script')\n for (let i = 0; i < scripts.length; i++) {\n var script = scripts[i]\n if (script.src != null) {\n existing_scripts.push(script.src)\n }\n }\n for (let i = 0; i < js_urls.length; i++) {\n const url = js_urls[i];\n const escaped = encodeURI(url)\n if (skip.indexOf(escaped) !== -1 || existing_scripts.indexOf(escaped) !== -1) {\n if (!window.requirejs) {\n on_load();\n }\n continue;\n }\n const element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n for (let i = 0; i < js_modules.length; i++) {\n const url = js_modules[i];\n const escaped = encodeURI(url)\n if (skip.indexOf(escaped) !== -1 || existing_scripts.indexOf(escaped) !== -1) {\n if (!window.requirejs) {\n on_load();\n }\n continue;\n }\n var element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n element.type = \"module\";\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n for (const name in js_exports) {\n const url = js_exports[name];\n const escaped = encodeURI(url)\n if (skip.indexOf(escaped) >= 0 || root[name] != null) {\n if (!window.requirejs) {\n on_load();\n }\n continue;\n }\n var element = document.createElement('script');\n element.onerror = on_error;\n element.async = false;\n element.type = \"module\";\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n element.textContent = `\n import ${name} from \"${url}\"\n window.${name} = ${name}\n window._bokeh_on_load()\n `\n document.head.appendChild(element);\n }\n if (!js_urls.length && !js_modules.length) {\n on_load()\n }\n };\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n const js_urls = [\"https://cdn.holoviz.org/panel/1.6.1/dist/bundled/reactiveesm/es-module-shims@^1.10.0/dist/es-module-shims.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-3.6.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.6.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.6.3.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.6.3.min.js\", \"https://cdn.holoviz.org/panel/1.6.1/dist/panel.min.js\"];\n const js_modules = [];\n const js_exports = {};\n const css_urls = [];\n const inline_js = [ function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {} // ensure no trailing comma for IE\n ];\n\n function run_inline_js() {\n if ((root.Bokeh !== undefined) || (force === true)) {\n for (let i = 0; i < inline_js.length; i++) {\n try {\n inline_js[i].call(root, root.Bokeh);\n } catch(e) {\n if (!reloading) {\n throw e;\n }\n }\n }\n // Cache old bokeh versions\n if (Bokeh != undefined && !reloading) {\n var NewBokeh = root.Bokeh;\n if (Bokeh.versions === undefined) {\n Bokeh.versions = new Map();\n }\n if (NewBokeh.version !== Bokeh.version) {\n Bokeh.versions.set(NewBokeh.version, NewBokeh)\n }\n root.Bokeh = Bokeh;\n }\n } else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n root._bokeh_failed_load = true;\n }\n root._bokeh_is_initializing = false\n }\n\n function load_or_wait() {\n // Implement a backoff loop that tries to ensure we do not load multiple\n // versions of Bokeh and its dependencies at the same time.\n // In recent versions we use the root._bokeh_is_initializing flag\n // to determine whether there is an ongoing attempt to initialize\n // bokeh, however for backward compatibility we also try to ensure\n // that we do not start loading a newer (Panel>=1.0 and Bokeh>3) version\n // before older versions are fully initialized.\n if (root._bokeh_is_initializing && Date.now() > root._bokeh_timeout) {\n // If the timeout and bokeh was not successfully loaded we reset\n // everything and try loading again\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_is_initializing = false;\n root._bokeh_onload_callbacks = undefined;\n root._bokeh_is_loading = 0\n console.log(\"Bokeh: BokehJS was loaded multiple times but one version failed to initialize.\");\n load_or_wait();\n } else if (root._bokeh_is_initializing || (typeof root._bokeh_is_initializing === \"undefined\" && root._bokeh_onload_callbacks !== undefined)) {\n setTimeout(load_or_wait, 100);\n } else {\n root._bokeh_is_initializing = true\n root._bokeh_onload_callbacks = []\n const bokeh_loaded = root.Bokeh != null && (root.Bokeh.version === py_version || (root.Bokeh.versions !== undefined && root.Bokeh.versions.has(py_version)));\n if (!reloading && !bokeh_loaded) {\n if (root.Bokeh) {\n root.Bokeh = undefined;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n }\n load_libs(css_urls, js_urls, js_modules, js_exports, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n }\n // Give older versions of the autoload script a head-start to ensure\n // they initialize before we start loading newer version.\n setTimeout(load_or_wait, 100)\n}(window));",
270 | "application/vnd.holoviews_load.v0+json": ""
271 | },
272 | "metadata": {},
273 | "output_type": "display_data"
274 | },
275 | {
276 | "data": {
277 | "application/javascript": "\nif ((window.PyViz === undefined) || (window.PyViz instanceof HTMLElement)) {\n window.PyViz = {comms: {}, comm_status:{}, kernels:{}, receivers: {}, plot_index: []}\n}\n\n\n function JupyterCommManager() {\n }\n\n JupyterCommManager.prototype.register_target = function(plot_id, comm_id, msg_handler) {\n if (window.comm_manager || ((window.Jupyter !== undefined) && (Jupyter.notebook.kernel != null))) {\n var comm_manager = window.comm_manager || Jupyter.notebook.kernel.comm_manager;\n comm_manager.register_target(comm_id, function(comm) {\n comm.on_msg(msg_handler);\n });\n } else if ((plot_id in window.PyViz.kernels) && (window.PyViz.kernels[plot_id])) {\n window.PyViz.kernels[plot_id].registerCommTarget(comm_id, function(comm) {\n comm.onMsg = msg_handler;\n });\n } else if (typeof google != 'undefined' && google.colab.kernel != null) {\n google.colab.kernel.comms.registerTarget(comm_id, (comm) => {\n var messages = comm.messages[Symbol.asyncIterator]();\n function processIteratorResult(result) {\n var message = result.value;\n console.log(message)\n var content = {data: message.data, comm_id};\n var buffers = []\n for (var buffer of message.buffers || []) {\n buffers.push(new DataView(buffer))\n }\n var metadata = message.metadata || {};\n var msg = {content, buffers, metadata}\n msg_handler(msg);\n return messages.next().then(processIteratorResult);\n }\n return messages.next().then(processIteratorResult);\n })\n }\n }\n\n JupyterCommManager.prototype.get_client_comm = function(plot_id, comm_id, msg_handler) {\n if (comm_id in window.PyViz.comms) {\n return window.PyViz.comms[comm_id];\n } else if (window.comm_manager || ((window.Jupyter !== undefined) && (Jupyter.notebook.kernel != null))) {\n var comm_manager = window.comm_manager || Jupyter.notebook.kernel.comm_manager;\n var comm = comm_manager.new_comm(comm_id, {}, {}, {}, comm_id);\n if (msg_handler) {\n comm.on_msg(msg_handler);\n }\n } else if ((plot_id in window.PyViz.kernels) && (window.PyViz.kernels[plot_id])) {\n var comm = window.PyViz.kernels[plot_id].connectToComm(comm_id);\n comm.open();\n if (msg_handler) {\n comm.onMsg = msg_handler;\n }\n } else if (typeof google != 'undefined' && google.colab.kernel != null) {\n var comm_promise = google.colab.kernel.comms.open(comm_id)\n comm_promise.then((comm) => {\n window.PyViz.comms[comm_id] = comm;\n if (msg_handler) {\n var messages = comm.messages[Symbol.asyncIterator]();\n function processIteratorResult(result) {\n var message = result.value;\n var content = {data: message.data};\n var metadata = message.metadata || {comm_id};\n var msg = {content, metadata}\n msg_handler(msg);\n return messages.next().then(processIteratorResult);\n }\n return messages.next().then(processIteratorResult);\n }\n })\n var sendClosure = (data, metadata, buffers, disposeOnDone) => {\n return comm_promise.then((comm) => {\n comm.send(data, metadata, buffers, disposeOnDone);\n });\n };\n var comm = {\n send: sendClosure\n };\n }\n window.PyViz.comms[comm_id] = comm;\n return comm;\n }\n window.PyViz.comm_manager = new JupyterCommManager();\n \n\n\nvar JS_MIME_TYPE = 'application/javascript';\nvar HTML_MIME_TYPE = 'text/html';\nvar EXEC_MIME_TYPE = 'application/vnd.holoviews_exec.v0+json';\nvar CLASS_NAME = 'output';\n\n/**\n * Render data to the DOM node\n */\nfunction render(props, node) {\n var div = document.createElement(\"div\");\n var script = document.createElement(\"script\");\n node.appendChild(div);\n node.appendChild(script);\n}\n\n/**\n * Handle when a new output is added\n */\nfunction handle_add_output(event, handle) {\n var output_area = handle.output_area;\n var output = handle.output;\n if ((output.data == undefined) || (!output.data.hasOwnProperty(EXEC_MIME_TYPE))) {\n return\n }\n var id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n var toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n if (id !== undefined) {\n var nchildren = toinsert.length;\n var html_node = toinsert[nchildren-1].children[0];\n html_node.innerHTML = output.data[HTML_MIME_TYPE];\n var scripts = [];\n var nodelist = html_node.querySelectorAll(\"script\");\n for (var i in nodelist) {\n if (nodelist.hasOwnProperty(i)) {\n scripts.push(nodelist[i])\n }\n }\n\n scripts.forEach( function (oldScript) {\n var newScript = document.createElement(\"script\");\n var attrs = [];\n var nodemap = oldScript.attributes;\n for (var j in nodemap) {\n if (nodemap.hasOwnProperty(j)) {\n attrs.push(nodemap[j])\n }\n }\n attrs.forEach(function(attr) { newScript.setAttribute(attr.name, attr.value) });\n newScript.appendChild(document.createTextNode(oldScript.innerHTML));\n oldScript.parentNode.replaceChild(newScript, oldScript);\n });\n if (JS_MIME_TYPE in output.data) {\n toinsert[nchildren-1].children[1].textContent = output.data[JS_MIME_TYPE];\n }\n output_area._hv_plot_id = id;\n if ((window.Bokeh !== undefined) && (id in Bokeh.index)) {\n window.PyViz.plot_index[id] = Bokeh.index[id];\n } else {\n window.PyViz.plot_index[id] = null;\n }\n } else if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n var bk_div = document.createElement(\"div\");\n bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n var script_attrs = bk_div.children[0].attributes;\n for (var i = 0; i < script_attrs.length; i++) {\n toinsert[toinsert.length - 1].childNodes[1].setAttribute(script_attrs[i].name, script_attrs[i].value);\n }\n // store reference to server id on output_area\n output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n }\n}\n\n/**\n * Handle when an output is cleared or removed\n */\nfunction handle_clear_output(event, handle) {\n var id = handle.cell.output_area._hv_plot_id;\n var server_id = handle.cell.output_area._bokeh_server_id;\n if (((id === undefined) || !(id in PyViz.plot_index)) && (server_id !== undefined)) { return; }\n var comm = window.PyViz.comm_manager.get_client_comm(\"hv-extension-comm\", \"hv-extension-comm\", function () {});\n if (server_id !== null) {\n comm.send({event_type: 'server_delete', 'id': server_id});\n return;\n } else if (comm !== null) {\n comm.send({event_type: 'delete', 'id': id});\n }\n delete PyViz.plot_index[id];\n if ((window.Bokeh !== undefined) & (id in window.Bokeh.index)) {\n var doc = window.Bokeh.index[id].model.document\n doc.clear();\n const i = window.Bokeh.documents.indexOf(doc);\n if (i > -1) {\n window.Bokeh.documents.splice(i, 1);\n }\n }\n}\n\n/**\n * Handle kernel restart event\n */\nfunction handle_kernel_cleanup(event, handle) {\n delete PyViz.comms[\"hv-extension-comm\"];\n window.PyViz.plot_index = {}\n}\n\n/**\n * Handle update_display_data messages\n */\nfunction handle_update_output(event, handle) {\n handle_clear_output(event, {cell: {output_area: handle.output_area}})\n handle_add_output(event, handle)\n}\n\nfunction register_renderer(events, OutputArea) {\n function append_mime(data, metadata, element) {\n // create a DOM node to render to\n var toinsert = this.create_output_subarea(\n metadata,\n CLASS_NAME,\n EXEC_MIME_TYPE\n );\n this.keyboard_manager.register_events(toinsert);\n // Render to node\n var props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n render(props, toinsert[0]);\n element.append(toinsert);\n return toinsert\n }\n\n events.on('output_added.OutputArea', handle_add_output);\n events.on('output_updated.OutputArea', handle_update_output);\n events.on('clear_output.CodeCell', handle_clear_output);\n events.on('delete.Cell', handle_clear_output);\n events.on('kernel_ready.Kernel', handle_kernel_cleanup);\n\n OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n safe: true,\n index: 0\n });\n}\n\nif (window.Jupyter !== undefined) {\n try {\n var events = require('base/js/events');\n var OutputArea = require('notebook/js/outputarea').OutputArea;\n if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n register_renderer(events, OutputArea);\n }\n } catch(err) {\n }\n}\n",
278 | "application/vnd.holoviews_load.v0+json": ""
279 | },
280 | "metadata": {},
281 | "output_type": "display_data"
282 | },
283 | {
284 | "data": {
285 | "application/vnd.holoviews_exec.v0+json": "",
286 | "text/html": [
287 | "\n",
288 | "
\n",
289 | "
\n",
509 | "
\n",
510 | "