Dropbox (Smithsonian)/idigbio_ferns/Untitled.ipynb

Taxon Matching - dealing with unmatched taxa.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import pandas as pd",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "unmatched = pd.read_csv('data/taxonomy_matching/no_matches.tsv', sep='\\t')\nunmatched.head()",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 2,
          "data": {
            "text/plain": "  idigbio_genus idigbio_species                 idigbio_sciname  idigbio_count\n0           NaN             NaN      abies balsamea f. hudsonia              1\n1           NaN             NaN  abies balsamea var. macrocarpa              1\n2           NaN             NaN     abies homolepis 'prostrata'              1\n3           NaN             NaN                     abies nigra              1\n4           NaN             NaN                 acacia acuifera              1",
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>idigbio_genus</th>\n      <th>idigbio_species</th>\n      <th>idigbio_sciname</th>\n      <th>idigbio_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>abies balsamea f. hudsonia</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>abies balsamea var. macrocarpa</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>abies homolepis 'prostrata'</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>abies nigra</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>acacia acuifera</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def split_sciname(row):\n    sciname_split = row['idigbio_sciname'].split(' ')\n    if len(sciname_split) == 2:\n        row['split_genus'] = sciname_split[0].capitalize()\n        row['split_species'] = sciname_split[1]\n    return row",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "unmatched = unmatched.apply(split_sciname, axis='columns')\nunmatched.head()",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 4,
          "data": {
            "text/plain": "   idigbio_count idigbio_genus                 idigbio_sciname  \\\n0              1           NaN      abies balsamea f. hudsonia   \n1              1           NaN  abies balsamea var. macrocarpa   \n2              1           NaN     abies homolepis 'prostrata'   \n3              1           NaN                     abies nigra   \n4              1           NaN                 acacia acuifera   \n\n  idigbio_species split_genus split_species  \n0             NaN         NaN           NaN  \n1             NaN         NaN           NaN  \n2             NaN         NaN           NaN  \n3             NaN       Abies         nigra  \n4             NaN      Acacia      acuifera  ",
            "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>idigbio_count</th>\n      <th>idigbio_genus</th>\n      <th>idigbio_sciname</th>\n      <th>idigbio_species</th>\n      <th>split_genus</th>\n      <th>split_species</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>NaN</td>\n      <td>abies balsamea f. hudsonia</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>NaN</td>\n      <td>abies balsamea var. macrocarpa</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>1</td>\n      <td>NaN</td>\n      <td>abies homolepis 'prostrata'</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1</td>\n      <td>NaN</td>\n      <td>abies nigra</td>\n      <td>NaN</td>\n      <td>Abies</td>\n      <td>nigra</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>1</td>\n      <td>NaN</td>\n      <td>acacia acuifera</td>\n      <td>NaN</td>\n      <td>Acacia</td>\n      <td>acuifera</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.8",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Dropbox (Smithsonian)/idigbio_ferns/Untitled.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}