diff --git a/docs/ag3/ag3.0.ipynb b/docs/ag3/ag3.0.ipynb index d588184..643651d 100644 --- a/docs/ag3/ag3.0.ipynb +++ b/docs/ag3/ag3.0.ipynb @@ -122,7 +122,298 @@ "remove-input" ] }, - "outputs": [], + "outputs": [ + { + "data": { + "application/javascript": [ + "(function(root) {\n", + " function now() {\n", + " return new Date();\n", + " }\n", + "\n", + " const force = true;\n", + "\n", + " if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n", + " root._bokeh_onload_callbacks = [];\n", + " root._bokeh_is_loading = undefined;\n", + " }\n", + "\n", + "const JS_MIME_TYPE = 'application/javascript';\n", + " const HTML_MIME_TYPE = 'text/html';\n", + " const EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n", + " const CLASS_NAME = 'output_bokeh rendered_html';\n", + "\n", + " /**\n", + " * Render data to the DOM node\n", + " */\n", + " function render(props, node) {\n", + " const script = document.createElement(\"script\");\n", + " node.appendChild(script);\n", + " }\n", + "\n", + " /**\n", + " * Handle when an output is cleared or removed\n", + " */\n", + " function handleClearOutput(event, handle) {\n", + " function drop(id) {\n", + " const view = Bokeh.index.get_by_id(id)\n", + " if (view != null) {\n", + " view.model.document.clear()\n", + " Bokeh.index.delete(view)\n", + " }\n", + " }\n", + "\n", + " const cell = handle.cell;\n", + "\n", + " const id = cell.output_area._bokeh_element_id;\n", + " const server_id = cell.output_area._bokeh_server_id;\n", + "\n", + " // Clean up Bokeh references\n", + " if (id != null) {\n", + " drop(id)\n", + " }\n", + "\n", + " if (server_id !== undefined) {\n", + " // Clean up Bokeh references\n", + " const cmd_clean = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n", + " cell.notebook.kernel.execute(cmd_clean, {\n", + " iopub: {\n", + " output: function(msg) {\n", + " const id = msg.content.text.trim()\n", + " drop(id)\n", + " }\n", + " }\n", + " });\n", + " // Destroy server and session\n", + " const cmd_destroy = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n", + " cell.notebook.kernel.execute(cmd_destroy);\n", + " }\n", + " }\n", + "\n", + " /**\n", + " * Handle when a new output is added\n", + " */\n", + " function handleAddOutput(event, handle) {\n", + " const output_area = handle.output_area;\n", + " const output = handle.output;\n", + "\n", + " // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n", + " if ((output.output_type != \"display_data\") || (!Object.prototype.hasOwnProperty.call(output.data, EXEC_MIME_TYPE))) {\n", + " return\n", + " }\n", + "\n", + " const toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n", + "\n", + " if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n", + " toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n", + " // store reference to embed id on output_area\n", + " output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n", + " }\n", + " if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n", + " const bk_div = document.createElement(\"div\");\n", + " bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n", + " const script_attrs = bk_div.children[0].attributes;\n", + " for (let i = 0; i < script_attrs.length; i++) {\n", + " toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n", + " toinsert[toinsert.length - 1].firstChild.textContent = bk_div.children[0].textContent\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", + " function register_renderer(events, OutputArea) {\n", + "\n", + " function append_mime(data, metadata, element) {\n", + " // create a DOM node to render to\n", + " const 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", + " const props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n", + " render(props, toinsert[toinsert.length - 1]);\n", + " element.append(toinsert);\n", + " return toinsert\n", + " }\n", + "\n", + " /* Handle when an output is cleared or removed */\n", + " events.on('clear_output.CodeCell', handleClearOutput);\n", + " events.on('delete.Cell', handleClearOutput);\n", + "\n", + " /* Handle when a new output is added */\n", + " events.on('output_added.OutputArea', handleAddOutput);\n", + "\n", + " /**\n", + " * Register the mime type and append_mime function with output_area\n", + " */\n", + " OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n", + " /* Is output safe? */\n", + " safe: true,\n", + " /* Index of renderer in `output_area.display_order` */\n", + " index: 0\n", + " });\n", + " }\n", + "\n", + " // register the mime type if in Jupyter Notebook environment and previously unregistered\n", + " if (root.Jupyter !== undefined) {\n", + " const events = require('base/js/events');\n", + " const OutputArea = require('notebook/js/outputarea').OutputArea;\n", + "\n", + " if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n", + " register_renderer(events, OutputArea);\n", + " }\n", + " }\n", + " if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n", + " root._bokeh_timeout = Date.now() + 5000;\n", + " root._bokeh_failed_load = false;\n", + " }\n", + "\n", + " const NB_LOAD_WARNING = {'data': {'text/html':\n", + " \"
\\n\"+\n", + " \"

\\n\"+\n", + " \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n", + " \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n", + " \"

\\n\"+\n", + " \"\\n\"+\n", + " \"\\n\"+\n", + " \"from bokeh.resources import INLINE\\n\"+\n", + " \"output_notebook(resources=INLINE)\\n\"+\n", + " \"\\n\"+\n", + " \"
\"}};\n", + "\n", + " function display_loaded() {\n", + " const el = document.getElementById(null);\n", + " if (el != null) {\n", + " el.textContent = \"BokehJS is loading...\";\n", + " }\n", + " if (root.Bokeh !== undefined) {\n", + " if (el != null) {\n", + " el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n", + " }\n", + " } else if (Date.now() < root._bokeh_timeout) {\n", + " setTimeout(display_loaded, 100)\n", + " }\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, callback) {\n", + " if (css_urls == null) css_urls = [];\n", + " if (js_urls == null) js_urls = [];\n", + "\n", + " root._bokeh_onload_callbacks.push(callback);\n", + " if (root._bokeh_is_loading > 0) {\n", + " console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n", + " return null;\n", + " }\n", + " if (js_urls == null || js_urls.length === 0) {\n", + " run_callbacks();\n", + " return null;\n", + " }\n", + " console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", + " root._bokeh_is_loading = css_urls.length + js_urls.length;\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", + "\n", + " function on_error(url) {\n", + " console.error(\"failed to load \" + url);\n", + " }\n", + "\n", + " for (let i = 0; i < css_urls.length; i++) {\n", + " const url = css_urls[i];\n", + " const element = document.createElement(\"link\");\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\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", + " }\n", + "\n", + " for (let i = 0; i < js_urls.length; i++) {\n", + " const url = js_urls[i];\n", + " const element = document.createElement('script');\n", + " element.onload = on_load;\n", + " element.onerror = on_error.bind(null, url);\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", + " };\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.bokeh.org/bokeh/release/bokeh-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.3.0.min.js\"];\n", + " const css_urls = [];\n", + "\n", + " const inline_js = [ function(Bokeh) {\n", + " Bokeh.set_log_level(\"info\");\n", + " },\n", + "function(Bokeh) {\n", + " }\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", + " inline_js[i].call(root, root.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", + " } else if (force !== true) {\n", + " const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n", + " cell.output_area.append_execute_result(NB_LOAD_WARNING)\n", + " }\n", + " }\n", + "\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", + " run_inline_js();\n", + " } else {\n", + " load_libs(css_urls, js_urls, function() {\n", + " console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n", + " run_inline_js();\n", + " });\n", + " }\n", + "}(window));" + ], + "application/vnd.bokehjs_load.v0+json": "(function(root) {\n function now() {\n return new Date();\n }\n\n const force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\n\n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n const NB_LOAD_WARNING = {'data': {'text/html':\n \"
\\n\"+\n \"

\\n\"+\n \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n \"

\\n\"+\n \"\\n\"+\n \"\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"\\n\"+\n \"
\"}};\n\n function display_loaded() {\n const el = document.getElementById(null);\n if (el != null) {\n el.textContent = \"BokehJS is loading...\";\n }\n if (root.Bokeh !== undefined) {\n if (el != null) {\n el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n }\n } else if (Date.now() < root._bokeh_timeout) {\n setTimeout(display_loaded, 100)\n }\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, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls == null || js_urls.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = css_urls.length + js_urls.length;\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\n function on_error(url) {\n console.error(\"failed to load \" + url);\n }\n\n for (let i = 0; i < css_urls.length; i++) {\n const url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\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 }\n\n for (let i = 0; i < js_urls.length; i++) {\n const url = js_urls[i];\n const element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error.bind(null, url);\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 };\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.bokeh.org/bokeh/release/bokeh-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-gl-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-widgets-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-tables-3.3.0.min.js\", \"https://cdn.bokeh.org/bokeh/release/bokeh-mathjax-3.3.0.min.js\"];\n const css_urls = [];\n\n const inline_js = [ function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\nfunction(Bokeh) {\n }\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 inline_js[i].call(root, root.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 } else if (force !== true) {\n const cell = $(document.getElementById(null)).parents('.cell').data().cell;\n cell.output_area.append_execute_result(NB_LOAD_WARNING)\n }\n }\n\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(css_urls, js_urls, function() {\n console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));" + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "import malariagen_data\n", "ag3 = malariagen_data.Ag3()" @@ -282,7 +573,7 @@ " \n", " \n", " AG1000G-X\n", - " 297\n", + " 669\n", " \n", " \n", "\n", @@ -318,7 +609,7 @@ "AG1000G-MZ 74\n", "AG1000G-TZ 300\n", "AG1000G-UG 290\n", - "AG1000G-X 297" + "AG1000G-X 669" ] }, "execution_count": 3, @@ -346,7 +637,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -381,6 +672,7 @@ " \n", " \n", " \n", + " \n", " taxon\n", " arabiensis\n", " coluzzii\n", @@ -388,10 +680,10 @@ " gcx1\n", " gcx2\n", " gcx3\n", - " intermediate_arabiensis_gambiae\n", - " intermediate_gambiae_coluzzii\n", + " unassigned\n", " \n", " \n", + " study_id\n", " sample_set\n", " country\n", " year\n", @@ -402,12 +694,12 @@ " \n", " \n", " \n", - " \n", " \n", " \n", " \n", " \n", " AG1000G-AO\n", + " AG1000G-AO\n", " Angola\n", " 2009\n", " 0\n", @@ -417,20 +709,19 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-BF-1\n", " AG1000G-BF-A\n", " Burkina Faso\n", " 2012\n", " 0\n", " 82\n", - " 98\n", + " 99\n", " 0\n", " 0\n", " 0\n", " 0\n", - " 1\n", " \n", " \n", " AG1000G-BF-B\n", @@ -443,9 +734,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-BF-2\n", " AG1000G-BF-C\n", " Burkina Faso\n", " 2004\n", @@ -456,10 +747,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-CD\n", + " AG1000G-CD\n", " Democratic Republic of the Congo\n", " 2015\n", " 0\n", @@ -469,10 +760,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-CF\n", + " AG1000G-CF\n", " Central African Republic\n", " 1993\n", " 0\n", @@ -482,7 +773,6 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " 1994\n", @@ -493,10 +783,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-CI\n", + " AG1000G-CI\n", " Cote d'Ivoire\n", " 2012\n", " 0\n", @@ -506,9 +796,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-CM-1\n", " AG1000G-CM-A\n", " Cameroon\n", " 2009\n", @@ -519,9 +809,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-CM-2\n", " AG1000G-CM-B\n", " Cameroon\n", " 2005\n", @@ -532,9 +822,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-CM-3\n", " AG1000G-CM-C\n", " Cameroon\n", " 2013\n", @@ -545,10 +835,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-FR\n", + " AG1000G-FR\n", " Mayotte\n", " 2011\n", " 0\n", @@ -558,9 +848,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-GA-1\n", " AG1000G-GA-A\n", " Gabon\n", " 2000\n", @@ -571,10 +861,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-GH\n", + " AG1000G-GH\n", " Ghana\n", " 2012\n", " 0\n", @@ -584,9 +874,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-GM-1\n", " AG1000G-GM-A\n", " Gambia, The\n", " 2011\n", @@ -597,22 +887,22 @@ " 6\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-GM-2\n", " AG1000G-GM-B\n", " Gambia, The\n", - " 2012\n", + " 2006\n", " 0\n", - " 2\n", " 0\n", - " 9\n", - " 20\n", " 0\n", + " 9\n", + " 22\n", " 0\n", " 0\n", " \n", " \n", + " AG1000G-GM-3\n", " AG1000G-GM-C\n", " Gambia, The\n", " 2012\n", @@ -623,20 +913,19 @@ " 172\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-GN-ML\n", " AG1000G-GN-A\n", " Guinea\n", " 2012\n", " 0\n", - " 3\n", - " 40\n", + " 4\n", + " 41\n", + " 0\n", " 0\n", - " 1\n", " 0\n", " 0\n", - " 1\n", " \n", " \n", " AG1000G-GN-B\n", @@ -644,27 +933,26 @@ " 2012\n", " 0\n", " 7\n", - " 83\n", + " 84\n", " 0\n", " 0\n", " 0\n", " 0\n", - " 1\n", " \n", " \n", " Mali\n", " 2012\n", " 0\n", - " 28\n", + " 27\n", " 65\n", " 0\n", " 0\n", " 0\n", - " 0\n", - " 1\n", + " 2\n", " \n", " \n", " AG1000G-GQ\n", + " AG1000G-GQ\n", " Equatorial Guinea\n", " 2002\n", " 0\n", @@ -674,10 +962,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-GW\n", + " AG1000G-GW\n", " Guinea-Bissau\n", " 2010\n", " 0\n", @@ -687,44 +975,42 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-KE\n", + " AG1000G-KE\n", " Kenya\n", - " 2012\n", - " 10\n", + " 2000\n", " 0\n", " 0\n", + " 19\n", " 0\n", " 0\n", - " 54\n", " 0\n", " 0\n", " \n", " \n", - " 2000\n", + " 2007\n", + " 3\n", " 0\n", " 0\n", - " 19\n", - " 0\n", " 0\n", " 0\n", " 0\n", " 0\n", " \n", " \n", - " 2007\n", - " 3\n", - " 0\n", - " 0\n", + " 2012\n", + " 10\n", " 0\n", " 0\n", " 0\n", " 0\n", + " 54\n", " 0\n", " \n", " \n", + " AG1000G-ML-1\n", " AG1000G-ML-A\n", " Mali\n", " 2014\n", @@ -735,9 +1021,9 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", + " AG1000G-ML-2\n", " AG1000G-ML-B\n", " Mali\n", " 2004\n", @@ -748,10 +1034,10 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-MW\n", + " AG1000G-MW\n", " Malawi\n", " 2015\n", " 41\n", @@ -761,27 +1047,25 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", " AG1000G-MZ\n", + " AG1000G-MZ\n", " Mozambique\n", - " 2004\n", + " 2003\n", " 0\n", " 0\n", - " 71\n", - " 0\n", + " 3\n", " 0\n", " 0\n", " 0\n", " 0\n", " \n", " \n", - " 2003\n", + " 2004\n", " 0\n", " 0\n", - " 3\n", - " 0\n", + " 71\n", " 0\n", " 0\n", " 0\n", @@ -789,6 +1073,7 @@ " \n", " \n", " AG1000G-TZ\n", + " AG1000G-TZ\n", " Tanzania\n", " 2012\n", " 87\n", @@ -798,32 +1083,30 @@ " 0\n", " 0\n", " 0\n", - " 0\n", " \n", " \n", - " 2015\n", - " 137\n", + " 2013\n", + " 1\n", " 0\n", " 32\n", " 0\n", " 0\n", - " 1\n", - " 0\n", + " 10\n", " 0\n", " \n", " \n", - " 2013\n", - " 1\n", + " 2015\n", + " 137\n", " 0\n", " 32\n", " 0\n", " 0\n", - " 10\n", - " 0\n", + " 1\n", " 0\n", " \n", " \n", " AG1000G-UG\n", + " AG1000G-UG\n", " Uganda\n", " 2012\n", " 82\n", @@ -833,163 +1116,255 @@ " 0\n", " 0\n", " 1\n", + " \n", + " \n", + " AG1000G-X\n", + " AG1000G-X\n", + " Lab Cross\n", + " -1\n", + " 0\n", + " 0\n", + " 0\n", " 0\n", + " 0\n", + " 0\n", + " 297\n", " \n", " \n", "\n", "" ], "text/plain": [ - "taxon arabiensis coluzzii \\\n", - "sample_set country year \n", - "AG1000G-AO Angola 2009 0 81 \n", - "AG1000G-BF-A Burkina Faso 2012 0 82 \n", - "AG1000G-BF-B Burkina Faso 2014 3 53 \n", - "AG1000G-BF-C Burkina Faso 2004 0 0 \n", - "AG1000G-CD Democratic Republic of the Congo 2015 0 0 \n", - "AG1000G-CF Central African Republic 1993 0 5 \n", - " 1994 0 13 \n", - "AG1000G-CI Cote d'Ivoire 2012 0 80 \n", - "AG1000G-CM-A Cameroon 2009 0 0 \n", - "AG1000G-CM-B Cameroon 2005 0 7 \n", - "AG1000G-CM-C Cameroon 2013 2 19 \n", - "AG1000G-FR Mayotte 2011 0 0 \n", - "AG1000G-GA-A Gabon 2000 0 0 \n", - "AG1000G-GH Ghana 2012 0 64 \n", - "AG1000G-GM-A Gambia, The 2011 0 0 \n", - "AG1000G-GM-B Gambia, The 2012 0 2 \n", - "AG1000G-GM-C Gambia, The 2012 0 0 \n", - "AG1000G-GN-A Guinea 2012 0 3 \n", - "AG1000G-GN-B Guinea 2012 0 7 \n", - " Mali 2012 0 28 \n", - "AG1000G-GQ Equatorial Guinea 2002 0 0 \n", - "AG1000G-GW Guinea-Bissau 2010 0 0 \n", - "AG1000G-KE Kenya 2012 10 0 \n", - " 2000 0 0 \n", - " 2007 3 0 \n", - "AG1000G-ML-A Mali 2014 0 27 \n", - "AG1000G-ML-B Mali 2004 2 36 \n", - "AG1000G-MW Malawi 2015 41 0 \n", - "AG1000G-MZ Mozambique 2004 0 0 \n", - " 2003 0 0 \n", - "AG1000G-TZ Tanzania 2012 87 0 \n", - " 2015 137 0 \n", - " 2013 1 0 \n", - "AG1000G-UG Uganda 2012 82 0 \n", + "taxon arabiensis \\\n", + "study_id sample_set country year \n", + "AG1000G-AO AG1000G-AO Angola 2009 0 \n", + "AG1000G-BF-1 AG1000G-BF-A Burkina Faso 2012 0 \n", + " AG1000G-BF-B Burkina Faso 2014 3 \n", + "AG1000G-BF-2 AG1000G-BF-C Burkina Faso 2004 0 \n", + "AG1000G-CD AG1000G-CD Democratic Republic of the Congo 2015 0 \n", + "AG1000G-CF AG1000G-CF Central African Republic 1993 0 \n", + " 1994 0 \n", + "AG1000G-CI AG1000G-CI Cote d'Ivoire 2012 0 \n", + "AG1000G-CM-1 AG1000G-CM-A Cameroon 2009 0 \n", + "AG1000G-CM-2 AG1000G-CM-B Cameroon 2005 0 \n", + "AG1000G-CM-3 AG1000G-CM-C Cameroon 2013 2 \n", + "AG1000G-FR AG1000G-FR Mayotte 2011 0 \n", + "AG1000G-GA-1 AG1000G-GA-A Gabon 2000 0 \n", + "AG1000G-GH AG1000G-GH Ghana 2012 0 \n", + "AG1000G-GM-1 AG1000G-GM-A Gambia, The 2011 0 \n", + "AG1000G-GM-2 AG1000G-GM-B Gambia, The 2006 0 \n", + "AG1000G-GM-3 AG1000G-GM-C Gambia, The 2012 0 \n", + "AG1000G-GN-ML AG1000G-GN-A Guinea 2012 0 \n", + " AG1000G-GN-B Guinea 2012 0 \n", + " Mali 2012 0 \n", + "AG1000G-GQ AG1000G-GQ Equatorial Guinea 2002 0 \n", + "AG1000G-GW AG1000G-GW Guinea-Bissau 2010 0 \n", + "AG1000G-KE AG1000G-KE Kenya 2000 0 \n", + " 2007 3 \n", + " 2012 10 \n", + "AG1000G-ML-1 AG1000G-ML-A Mali 2014 0 \n", + "AG1000G-ML-2 AG1000G-ML-B Mali 2004 2 \n", + "AG1000G-MW AG1000G-MW Malawi 2015 41 \n", + "AG1000G-MZ AG1000G-MZ Mozambique 2003 0 \n", + " 2004 0 \n", + "AG1000G-TZ AG1000G-TZ Tanzania 2012 87 \n", + " 2013 1 \n", + " 2015 137 \n", + "AG1000G-UG AG1000G-UG Uganda 2012 82 \n", + "AG1000G-X AG1000G-X Lab Cross -1 0 \n", + "\n", + "taxon coluzzii \\\n", + "study_id sample_set country year \n", + "AG1000G-AO AG1000G-AO Angola 2009 81 \n", + "AG1000G-BF-1 AG1000G-BF-A Burkina Faso 2012 82 \n", + " AG1000G-BF-B Burkina Faso 2014 53 \n", + "AG1000G-BF-2 AG1000G-BF-C Burkina Faso 2004 0 \n", + "AG1000G-CD AG1000G-CD Democratic Republic of the Congo 2015 0 \n", + "AG1000G-CF AG1000G-CF Central African Republic 1993 5 \n", + " 1994 13 \n", + "AG1000G-CI AG1000G-CI Cote d'Ivoire 2012 80 \n", + "AG1000G-CM-1 AG1000G-CM-A Cameroon 2009 0 \n", + "AG1000G-CM-2 AG1000G-CM-B Cameroon 2005 7 \n", + "AG1000G-CM-3 AG1000G-CM-C Cameroon 2013 19 \n", + "AG1000G-FR AG1000G-FR Mayotte 2011 0 \n", + "AG1000G-GA-1 AG1000G-GA-A Gabon 2000 0 \n", + "AG1000G-GH AG1000G-GH Ghana 2012 64 \n", + "AG1000G-GM-1 AG1000G-GM-A Gambia, The 2011 0 \n", + "AG1000G-GM-2 AG1000G-GM-B Gambia, The 2006 0 \n", + "AG1000G-GM-3 AG1000G-GM-C Gambia, The 2012 0 \n", + "AG1000G-GN-ML AG1000G-GN-A Guinea 2012 4 \n", + " AG1000G-GN-B Guinea 2012 7 \n", + " Mali 2012 27 \n", + "AG1000G-GQ AG1000G-GQ Equatorial Guinea 2002 0 \n", + "AG1000G-GW AG1000G-GW Guinea-Bissau 2010 0 \n", + "AG1000G-KE AG1000G-KE Kenya 2000 0 \n", + " 2007 0 \n", + " 2012 0 \n", + "AG1000G-ML-1 AG1000G-ML-A Mali 2014 27 \n", + "AG1000G-ML-2 AG1000G-ML-B Mali 2004 36 \n", + "AG1000G-MW AG1000G-MW Malawi 2015 0 \n", + "AG1000G-MZ AG1000G-MZ Mozambique 2003 0 \n", + " 2004 0 \n", + "AG1000G-TZ AG1000G-TZ Tanzania 2012 0 \n", + " 2013 0 \n", + " 2015 0 \n", + "AG1000G-UG AG1000G-UG Uganda 2012 0 \n", + "AG1000G-X AG1000G-X Lab Cross -1 0 \n", + "\n", + "taxon gambiae \\\n", + "study_id sample_set country year \n", + "AG1000G-AO AG1000G-AO Angola 2009 0 \n", + "AG1000G-BF-1 AG1000G-BF-A Burkina Faso 2012 99 \n", + " AG1000G-BF-B Burkina Faso 2014 46 \n", + "AG1000G-BF-2 AG1000G-BF-C Burkina Faso 2004 13 \n", + "AG1000G-CD AG1000G-CD Democratic Republic of the Congo 2015 76 \n", + "AG1000G-CF AG1000G-CF Central African Republic 1993 2 \n", + " 1994 53 \n", + "AG1000G-CI AG1000G-CI Cote d'Ivoire 2012 0 \n", + "AG1000G-CM-1 AG1000G-CM-A Cameroon 2009 303 \n", + "AG1000G-CM-2 AG1000G-CM-B Cameroon 2005 90 \n", + "AG1000G-CM-3 AG1000G-CM-C Cameroon 2013 23 \n", + "AG1000G-FR AG1000G-FR Mayotte 2011 23 \n", + "AG1000G-GA-1 AG1000G-GA-A Gabon 2000 69 \n", + "AG1000G-GH AG1000G-GH Ghana 2012 36 \n", + "AG1000G-GM-1 AG1000G-GM-A Gambia, The 2011 0 \n", + "AG1000G-GM-2 AG1000G-GM-B Gambia, The 2006 0 \n", + "AG1000G-GM-3 AG1000G-GM-C Gambia, The 2012 2 \n", + "AG1000G-GN-ML AG1000G-GN-A Guinea 2012 41 \n", + " AG1000G-GN-B Guinea 2012 84 \n", + " Mali 2012 65 \n", + "AG1000G-GQ AG1000G-GQ Equatorial Guinea 2002 10 \n", + "AG1000G-GW AG1000G-GW Guinea-Bissau 2010 8 \n", + "AG1000G-KE AG1000G-KE Kenya 2000 19 \n", + " 2007 0 \n", + " 2012 0 \n", + "AG1000G-ML-1 AG1000G-ML-A Mali 2014 33 \n", + "AG1000G-ML-2 AG1000G-ML-B Mali 2004 33 \n", + "AG1000G-MW AG1000G-MW Malawi 2015 0 \n", + "AG1000G-MZ AG1000G-MZ Mozambique 2003 3 \n", + " 2004 71 \n", + "AG1000G-TZ AG1000G-TZ Tanzania 2012 0 \n", + " 2013 32 \n", + " 2015 32 \n", + "AG1000G-UG AG1000G-UG Uganda 2012 207 \n", + "AG1000G-X AG1000G-X Lab Cross -1 0 \n", "\n", - "taxon gambiae gcx1 gcx2 gcx3 \\\n", - "sample_set country year \n", - "AG1000G-AO Angola 2009 0 0 0 0 \n", - "AG1000G-BF-A Burkina Faso 2012 98 0 0 0 \n", - "AG1000G-BF-B Burkina Faso 2014 46 0 0 0 \n", - "AG1000G-BF-C Burkina Faso 2004 13 0 0 0 \n", - "AG1000G-CD Democratic Republic of the Congo 2015 76 0 0 0 \n", - "AG1000G-CF Central African Republic 1993 2 0 0 0 \n", - " 1994 53 0 0 0 \n", - "AG1000G-CI Cote d'Ivoire 2012 0 0 0 0 \n", - "AG1000G-CM-A Cameroon 2009 303 0 0 0 \n", - "AG1000G-CM-B Cameroon 2005 90 0 0 0 \n", - "AG1000G-CM-C Cameroon 2013 23 0 0 0 \n", - "AG1000G-FR Mayotte 2011 23 0 0 0 \n", - "AG1000G-GA-A Gabon 2000 69 0 0 0 \n", - "AG1000G-GH Ghana 2012 36 0 0 0 \n", - "AG1000G-GM-A Gambia, The 2011 0 68 6 0 \n", - "AG1000G-GM-B Gambia, The 2012 0 9 20 0 \n", - "AG1000G-GM-C Gambia, The 2012 2 0 172 0 \n", - "AG1000G-GN-A Guinea 2012 40 0 1 0 \n", - "AG1000G-GN-B Guinea 2012 83 0 0 0 \n", - " Mali 2012 65 0 0 0 \n", - "AG1000G-GQ Equatorial Guinea 2002 10 0 0 0 \n", - "AG1000G-GW Guinea-Bissau 2010 8 93 0 0 \n", - "AG1000G-KE Kenya 2012 0 0 0 54 \n", - " 2000 19 0 0 0 \n", - " 2007 0 0 0 0 \n", - "AG1000G-ML-A Mali 2014 33 0 0 0 \n", - "AG1000G-ML-B Mali 2004 33 0 0 0 \n", - "AG1000G-MW Malawi 2015 0 0 0 0 \n", - "AG1000G-MZ Mozambique 2004 71 0 0 0 \n", - " 2003 3 0 0 0 \n", - "AG1000G-TZ Tanzania 2012 0 0 0 0 \n", - " 2015 32 0 0 1 \n", - " 2013 32 0 0 10 \n", - "AG1000G-UG Uganda 2012 207 0 0 0 \n", + "taxon gcx1 gcx2 \\\n", + "study_id sample_set country year \n", + "AG1000G-AO AG1000G-AO Angola 2009 0 0 \n", + "AG1000G-BF-1 AG1000G-BF-A Burkina Faso 2012 0 0 \n", + " AG1000G-BF-B Burkina Faso 2014 0 0 \n", + "AG1000G-BF-2 AG1000G-BF-C Burkina Faso 2004 0 0 \n", + "AG1000G-CD AG1000G-CD Democratic Republic of the Congo 2015 0 0 \n", + "AG1000G-CF AG1000G-CF Central African Republic 1993 0 0 \n", + " 1994 0 0 \n", + "AG1000G-CI AG1000G-CI Cote d'Ivoire 2012 0 0 \n", + "AG1000G-CM-1 AG1000G-CM-A Cameroon 2009 0 0 \n", + "AG1000G-CM-2 AG1000G-CM-B Cameroon 2005 0 0 \n", + "AG1000G-CM-3 AG1000G-CM-C Cameroon 2013 0 0 \n", + "AG1000G-FR AG1000G-FR Mayotte 2011 0 0 \n", + "AG1000G-GA-1 AG1000G-GA-A Gabon 2000 0 0 \n", + "AG1000G-GH AG1000G-GH Ghana 2012 0 0 \n", + "AG1000G-GM-1 AG1000G-GM-A Gambia, The 2011 68 6 \n", + "AG1000G-GM-2 AG1000G-GM-B Gambia, The 2006 9 22 \n", + "AG1000G-GM-3 AG1000G-GM-C Gambia, The 2012 0 172 \n", + "AG1000G-GN-ML AG1000G-GN-A Guinea 2012 0 0 \n", + " AG1000G-GN-B Guinea 2012 0 0 \n", + " Mali 2012 0 0 \n", + "AG1000G-GQ AG1000G-GQ Equatorial Guinea 2002 0 0 \n", + "AG1000G-GW AG1000G-GW Guinea-Bissau 2010 93 0 \n", + "AG1000G-KE AG1000G-KE Kenya 2000 0 0 \n", + " 2007 0 0 \n", + " 2012 0 0 \n", + "AG1000G-ML-1 AG1000G-ML-A Mali 2014 0 0 \n", + "AG1000G-ML-2 AG1000G-ML-B Mali 2004 0 0 \n", + "AG1000G-MW AG1000G-MW Malawi 2015 0 0 \n", + "AG1000G-MZ AG1000G-MZ Mozambique 2003 0 0 \n", + " 2004 0 0 \n", + "AG1000G-TZ AG1000G-TZ Tanzania 2012 0 0 \n", + " 2013 0 0 \n", + " 2015 0 0 \n", + "AG1000G-UG AG1000G-UG Uganda 2012 0 0 \n", + "AG1000G-X AG1000G-X Lab Cross -1 0 0 \n", "\n", - "taxon intermediate_arabiensis_gambiae \\\n", - "sample_set country year \n", - "AG1000G-AO Angola 2009 0 \n", - "AG1000G-BF-A Burkina Faso 2012 0 \n", - "AG1000G-BF-B Burkina Faso 2014 0 \n", - "AG1000G-BF-C Burkina Faso 2004 0 \n", - "AG1000G-CD Democratic Republic of the Congo 2015 0 \n", - "AG1000G-CF Central African Republic 1993 0 \n", - " 1994 0 \n", - "AG1000G-CI Cote d'Ivoire 2012 0 \n", - "AG1000G-CM-A Cameroon 2009 0 \n", - "AG1000G-CM-B Cameroon 2005 0 \n", - "AG1000G-CM-C Cameroon 2013 0 \n", - "AG1000G-FR Mayotte 2011 0 \n", - "AG1000G-GA-A Gabon 2000 0 \n", - "AG1000G-GH Ghana 2012 0 \n", - "AG1000G-GM-A Gambia, The 2011 0 \n", - "AG1000G-GM-B Gambia, The 2012 0 \n", - "AG1000G-GM-C Gambia, The 2012 0 \n", - "AG1000G-GN-A Guinea 2012 0 \n", - "AG1000G-GN-B Guinea 2012 0 \n", - " Mali 2012 0 \n", - "AG1000G-GQ Equatorial Guinea 2002 0 \n", - "AG1000G-GW Guinea-Bissau 2010 0 \n", - "AG1000G-KE Kenya 2012 0 \n", - " 2000 0 \n", - " 2007 0 \n", - "AG1000G-ML-A Mali 2014 0 \n", - "AG1000G-ML-B Mali 2004 0 \n", - "AG1000G-MW Malawi 2015 0 \n", - "AG1000G-MZ Mozambique 2004 0 \n", - " 2003 0 \n", - "AG1000G-TZ Tanzania 2012 0 \n", - " 2015 0 \n", - " 2013 0 \n", - "AG1000G-UG Uganda 2012 1 \n", + "taxon gcx3 \\\n", + "study_id sample_set country year \n", + "AG1000G-AO AG1000G-AO Angola 2009 0 \n", + "AG1000G-BF-1 AG1000G-BF-A Burkina Faso 2012 0 \n", + " AG1000G-BF-B Burkina Faso 2014 0 \n", + "AG1000G-BF-2 AG1000G-BF-C Burkina Faso 2004 0 \n", + "AG1000G-CD AG1000G-CD Democratic Republic of the Congo 2015 0 \n", + "AG1000G-CF AG1000G-CF Central African Republic 1993 0 \n", + " 1994 0 \n", + "AG1000G-CI AG1000G-CI Cote d'Ivoire 2012 0 \n", + "AG1000G-CM-1 AG1000G-CM-A Cameroon 2009 0 \n", + "AG1000G-CM-2 AG1000G-CM-B Cameroon 2005 0 \n", + "AG1000G-CM-3 AG1000G-CM-C Cameroon 2013 0 \n", + "AG1000G-FR AG1000G-FR Mayotte 2011 0 \n", + "AG1000G-GA-1 AG1000G-GA-A Gabon 2000 0 \n", + "AG1000G-GH AG1000G-GH Ghana 2012 0 \n", + "AG1000G-GM-1 AG1000G-GM-A Gambia, The 2011 0 \n", + "AG1000G-GM-2 AG1000G-GM-B Gambia, The 2006 0 \n", + "AG1000G-GM-3 AG1000G-GM-C Gambia, The 2012 0 \n", + "AG1000G-GN-ML AG1000G-GN-A Guinea 2012 0 \n", + " AG1000G-GN-B Guinea 2012 0 \n", + " Mali 2012 0 \n", + "AG1000G-GQ AG1000G-GQ Equatorial Guinea 2002 0 \n", + "AG1000G-GW AG1000G-GW Guinea-Bissau 2010 0 \n", + "AG1000G-KE AG1000G-KE Kenya 2000 0 \n", + " 2007 0 \n", + " 2012 54 \n", + "AG1000G-ML-1 AG1000G-ML-A Mali 2014 0 \n", + "AG1000G-ML-2 AG1000G-ML-B Mali 2004 0 \n", + "AG1000G-MW AG1000G-MW Malawi 2015 0 \n", + "AG1000G-MZ AG1000G-MZ Mozambique 2003 0 \n", + " 2004 0 \n", + "AG1000G-TZ AG1000G-TZ Tanzania 2012 0 \n", + " 2013 10 \n", + " 2015 1 \n", + "AG1000G-UG AG1000G-UG Uganda 2012 0 \n", + "AG1000G-X AG1000G-X Lab Cross -1 0 \n", "\n", - "taxon intermediate_gambiae_coluzzii \n", - "sample_set country year \n", - "AG1000G-AO Angola 2009 0 \n", - "AG1000G-BF-A Burkina Faso 2012 1 \n", - "AG1000G-BF-B Burkina Faso 2014 0 \n", - "AG1000G-BF-C Burkina Faso 2004 0 \n", - "AG1000G-CD Democratic Republic of the Congo 2015 0 \n", - "AG1000G-CF Central African Republic 1993 0 \n", - " 1994 0 \n", - "AG1000G-CI Cote d'Ivoire 2012 0 \n", - "AG1000G-CM-A Cameroon 2009 0 \n", - "AG1000G-CM-B Cameroon 2005 0 \n", - "AG1000G-CM-C Cameroon 2013 0 \n", - "AG1000G-FR Mayotte 2011 0 \n", - "AG1000G-GA-A Gabon 2000 0 \n", - "AG1000G-GH Ghana 2012 0 \n", - "AG1000G-GM-A Gambia, The 2011 0 \n", - "AG1000G-GM-B Gambia, The 2012 0 \n", - "AG1000G-GM-C Gambia, The 2012 0 \n", - "AG1000G-GN-A Guinea 2012 1 \n", - "AG1000G-GN-B Guinea 2012 1 \n", - " Mali 2012 1 \n", - "AG1000G-GQ Equatorial Guinea 2002 0 \n", - "AG1000G-GW Guinea-Bissau 2010 0 \n", - "AG1000G-KE Kenya 2012 0 \n", - " 2000 0 \n", - " 2007 0 \n", - "AG1000G-ML-A Mali 2014 0 \n", - "AG1000G-ML-B Mali 2004 0 \n", - "AG1000G-MW Malawi 2015 0 \n", - "AG1000G-MZ Mozambique 2004 0 \n", - " 2003 0 \n", - "AG1000G-TZ Tanzania 2012 0 \n", - " 2015 0 \n", - " 2013 0 \n", - "AG1000G-UG Uganda 2012 0 " + "taxon unassigned \n", + "study_id sample_set country year \n", + "AG1000G-AO AG1000G-AO Angola 2009 0 \n", + "AG1000G-BF-1 AG1000G-BF-A Burkina Faso 2012 0 \n", + " AG1000G-BF-B Burkina Faso 2014 0 \n", + "AG1000G-BF-2 AG1000G-BF-C Burkina Faso 2004 0 \n", + "AG1000G-CD AG1000G-CD Democratic Republic of the Congo 2015 0 \n", + "AG1000G-CF AG1000G-CF Central African Republic 1993 0 \n", + " 1994 0 \n", + "AG1000G-CI AG1000G-CI Cote d'Ivoire 2012 0 \n", + "AG1000G-CM-1 AG1000G-CM-A Cameroon 2009 0 \n", + "AG1000G-CM-2 AG1000G-CM-B Cameroon 2005 0 \n", + "AG1000G-CM-3 AG1000G-CM-C Cameroon 2013 0 \n", + "AG1000G-FR AG1000G-FR Mayotte 2011 0 \n", + "AG1000G-GA-1 AG1000G-GA-A Gabon 2000 0 \n", + "AG1000G-GH AG1000G-GH Ghana 2012 0 \n", + "AG1000G-GM-1 AG1000G-GM-A Gambia, The 2011 0 \n", + "AG1000G-GM-2 AG1000G-GM-B Gambia, The 2006 0 \n", + "AG1000G-GM-3 AG1000G-GM-C Gambia, The 2012 0 \n", + "AG1000G-GN-ML AG1000G-GN-A Guinea 2012 0 \n", + " AG1000G-GN-B Guinea 2012 0 \n", + " Mali 2012 2 \n", + "AG1000G-GQ AG1000G-GQ Equatorial Guinea 2002 0 \n", + "AG1000G-GW AG1000G-GW Guinea-Bissau 2010 0 \n", + "AG1000G-KE AG1000G-KE Kenya 2000 0 \n", + " 2007 0 \n", + " 2012 0 \n", + "AG1000G-ML-1 AG1000G-ML-A Mali 2014 0 \n", + "AG1000G-ML-2 AG1000G-ML-B Mali 2004 0 \n", + "AG1000G-MW AG1000G-MW Malawi 2015 0 \n", + "AG1000G-MZ AG1000G-MZ Mozambique 2003 0 \n", + " 2004 0 \n", + "AG1000G-TZ AG1000G-TZ Tanzania 2012 0 \n", + " 2013 0 \n", + " 2015 0 \n", + "AG1000G-UG AG1000G-UG Uganda 2012 1 \n", + "AG1000G-X AG1000G-X Lab Cross -1 297 " ] }, - "execution_count": 4, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -997,7 +1372,7 @@ "source": [ "df_samples = ag3.sample_metadata(sample_sets=\"3.0\")\n", "df_summary = df_samples.pivot_table(\n", - " index=[\"sample_set\", \"country\", \"year\"], \n", + " index=[\"study_id\",\"sample_set\", \"country\", \"year\"], \n", " columns=[\"taxon\"],\n", " values=\"sample_id\", \n", " aggfunc=len,\n", diff --git a/docs/ag3/ag3.1.ipynb b/docs/ag3/ag3.1.ipynb index 35650aa..3ad8938 100644 --- a/docs/ag3/ag3.1.ipynb +++ b/docs/ag3/ag3.1.ipynb @@ -25,7 +25,10 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use).\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", + "\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.2.ipynb b/docs/ag3/ag3.2.ipynb index 807186c..68ef0bf 100644 --- a/docs/ag3/ag3.2.ipynb +++ b/docs/ag3/ag3.2.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use).\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.3.ipynb b/docs/ag3/ag3.3.ipynb index 25fd7fe..e5f648d 100644 --- a/docs/ag3/ag3.3.ipynb +++ b/docs/ag3/ag3.3.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use).\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.4.ipynb b/docs/ag3/ag3.4.ipynb index 6683c85..5a44453 100644 --- a/docs/ag3/ag3.4.ipynb +++ b/docs/ag3/ag3.4.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use).\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.5.ipynb b/docs/ag3/ag3.5.ipynb index dbc572b..c646752 100644 --- a/docs/ag3/ag3.5.ipynb +++ b/docs/ag3/ag3.5.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use).\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.6.ipynb b/docs/ag3/ag3.6.ipynb index 24e4e00..739591a 100644 --- a/docs/ag3/ag3.6.ipynb +++ b/docs/ag3/ag3.6.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use). \n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.7.ipynb b/docs/ag3/ag3.7.ipynb index 5094a9b..2fa98c4 100644 --- a/docs/ag3/ag3.7.ipynb +++ b/docs/ag3/ag3.7.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use).\n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n", diff --git a/docs/ag3/ag3.8.ipynb b/docs/ag3/ag3.8.ipynb index cc05bfe..06ca690 100644 --- a/docs/ag3/ag3.8.ipynb +++ b/docs/ag3/ag3.8.ipynb @@ -25,7 +25,9 @@ "source": [ "## Terms of use\n", "\n", - "Please note that, unless otherwise stated, all data on this release are subject to a publication embargo, described further in the [_Anopheles gambiae_ genomic surveillance project terms of use](https://www.malariagen.net/data/terms-use/anopheles-gambiae-genomic-surveillance-project-terms-use). \n", + "Data from this project will be made publicly available before journal publication. Unless otherwise stated, analyses of project data are ongoing and publications are in preparation by project partners, and it is not permitted to use project data for publication (including any type of communication with the general public) without prior permission from the originating partner studies. \n", + "\n", + "Although malaria is generally an endemic rather than an epidemic disease, and the focus of this project is on surveillance of disease vectors rather than pathogens, our data terms of use build on MalariaGEN's approach to data sharing, and adopt norms which have been established for rapid sharing of pathogen genomic data during disease outbreaks. The primary rationale for this approach is that malaria remains a public health emergency, where ethically appropriate and rapid sharing of genomic surveillance data can help to detect and respond to biological threats such as new forms of insecticide resistance, and to adapt malaria vector control strategies to different settings and changing circumstances.\n", "\n", "The publication embargo for all data on this release will expire on the **17th of November 2025**. \n", "\n",