better paths for plot missing data

workflow/notebooks/.ipynb_checkpoints/test_path.py-checkpoint.ipynb

@@ -0,0 +1,35 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "print(os.getcwd())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

workflow/notebooks/.ipynb_checkpoints/treetime.py-checkpoint.ipynb

@@ -0,0 +1,175 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Treetime Analysis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Module Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from Bio import Phylo\n",
+    "from treetime.utils import parse_dates\n",
+    "import pandas"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Input File Paths"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../../results/iqtree/assembly/iqtree.core-chromosome.filter0.treefile\n",
+      "../../results/treetime/assembly/metadata.tsv\n"
+     ]
+    }
+   ],
+   "source": [
+    "'''\n",
+    "tree_path = str(snakemake.input.tree)\n",
+    "aln_path = str(snakemake.input.snp_aln)\n",
+    "metadata_path = str(snakemake.input.metadata)\n",
+    "treetime_path = str(snakemake.output.treetime)\n",
+    "'''\n",
+    "\n",
+    "tree_path = \"../../results/iqtree/assembly/iqtree.core-chromosome.filter0.treefile\"\n",
+    "metadata_path = \"../../results/treetime/assembly/metadata.tsv\"\n",
+    "print(tree_path)\n",
+    "print(metadata_path)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Constants and Variables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "name_column = \"Accession\"\n",
+    "dates_column = \"BioSampleCollectionDate\"\n",
+    "attribute = \"BioSampleBiovar\"\n",
+    "missing_data = \"?\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Parse Dates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                             Accession BioSampleGeographicLocation  \\\n",
+      "0  GCA_009669545.1_ASM966954v1_genomic                         USA   \n",
+      "1  GCA_009669555.1_ASM966955v1_genomic                         USA   \n",
+      "2  GCA_009669565.1_ASM966956v1_genomic                         USA   \n",
+      "3                            Reference                         USA   \n",
+      "\n",
+      "   BioSampleCollectionDate  \n",
+      "0                     2000  \n",
+      "1                     2000  \n",
+      "2                     2000  \n",
+      "3                     2000  \n"
+     ]
+    }
+   ],
+   "source": [
+    "states = pandas.read_csv(metadata_path, sep='\\t')\n",
+    "if name_column in states.columns:\n",
+    "    taxon_name = name_column\n",
+    "if attribute in states.columns:\n",
+    "    attr = attribute\n",
+    "\n",
+    "# Get tips names\n",
+    "tree = Phylo.read(tree_path, \"nexus\")\n",
+    "tree_tip_names = [t.name for t in tree.get_terminals()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'treetime_path' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-12-3803fc66c3c7>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtreetime_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"w\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mfile\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m     \u001b[0;34m...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'treetime_path' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "with open(treetime_path, \"w\") as file:\n",
+    "    ..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}