{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false,
    "nbsphinx": "hidden"
   },
   "outputs": [],
   "source": [
    "import skchem\n",
    "import pandas as pd\n",
    "pd.options.display.max_rows = pd.options.display.max_columns = 10"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pipelining"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**scikit-chem** expands on the scikit-learn `Pipeline` object to support filtering.  It is initialized using a list of Transformer objects."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pipeline = skchem.pipeline.Pipeline([\n",
    "        skchem.standardizers.ChemAxonStandardizer(keep_failed=True),\n",
    "        skchem.forcefields.UFF(),\n",
    "        skchem.filters.OrganicFilter(),\n",
    "        skchem.descriptors.MorganFeaturizer()])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The pipeline will apply each in turn to objects, using the the highest priority function that each object implements, according to the order `transform_filter` > `filter` > `transform`.\n",
    "\n",
    "For example, our pipeline can transform sodium acetate all the way to fingerprints:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "mol = skchem.Mol.from_smiles('CC(=O)[O-].[Na+]')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "morgan_fp_idx\n",
       "0       0\n",
       "1       0\n",
       "2       0\n",
       "3       0\n",
       "4       0\n",
       "       ..\n",
       "2043    0\n",
       "2044    0\n",
       "2045    0\n",
       "2046    0\n",
       "2047    0\n",
       "Name: MorganFeaturizer, dtype: uint8"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.transform_filter(mol)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It also works on collections of molecules:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "batch\n",
       "ethane                          <Mol: CC>\n",
       "propane                        <Mol: CCC>\n",
       "benzene                   <Mol: c1ccccc1>\n",
       "sodium acetate    <Mol: CC(=O)[O-].[Na+]>\n",
       "serine                <Mol: NC(CO)C(=O)O>\n",
       "Name: structure, dtype: object"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mols = skchem.read_smiles('https://archive.org/download/scikit-chem_example_files/example.smi', name_column=1); mols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "ChemAxonStandardizer: 100% (5 of 5) |##########################################| Elapsed Time: 0:00:04 Time: 0:00:04\n",
      "UFF: 100% (5 of 5) |###########################################################| Elapsed Time: 0:00:00 Time: 0:00:00\n",
      "OrganicFilter: 100% (5 of 5) |#################################################| Elapsed Time: 0:00:00 Time: 0:00:00\n",
      "MorganFeaturizer: 100% (5 of 5) |##############################################| Elapsed Time: 0:00:00 Time: 0:00:00\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>morgan_fp_idx</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>...</th>\n",
       "      <th>2043</th>\n",
       "      <th>2044</th>\n",
       "      <th>2045</th>\n",
       "      <th>2046</th>\n",
       "      <th>2047</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>batch</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>ethane</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>propane</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>benzene</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sodium acetate</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>serine</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 2048 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "morgan_fp_idx   0     1     2     3     4     ...   2043  2044  2045  2046  \\\n",
       "batch                                         ...                            \n",
       "ethane             0     0     0     0     0  ...      0     0     0     0   \n",
       "propane            0     0     0     0     0  ...      0     0     0     0   \n",
       "benzene            0     0     0     0     0  ...      0     0     0     0   \n",
       "sodium acetate     0     0     0     0     0  ...      0     0     0     0   \n",
       "serine             0     0     0     0     0  ...      0     0     1     0   \n",
       "\n",
       "morgan_fp_idx   2047  \n",
       "batch                 \n",
       "ethane             0  \n",
       "propane            0  \n",
       "benzene            0  \n",
       "sodium acetate     0  \n",
       "serine             0  \n",
       "\n",
       "[5 rows x 2048 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.transform_filter(mols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "celltoolbar": "Raw Cell Format",
  "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": "3.5.1"
  },
  "widgets": {
   "state": {},
   "version": "1.1.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}