train-2007.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from scipy.stats import pearsonr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1105, 195)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "selected_columns = [0, 1, 2, 3, 6, 10, 11, 12, 15, 19, 20, 21, 24, 28, 29, 30, 33, 37, 38, 39, 42, 46, 47, 48, 51, 55, 56, 57, 60, 64, 65, 66, 69, 73, 74, 75, 78]\n",
    "train_df = pd.read_csv(\"PDBbind_refined07-core07.csv\", usecols=selected_columns)\n",
    "test_df = pd.read_csv(\"PDBbind_core07.csv\", usecols=selected_columns)\n",
    "len(train_df), len(test_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "param_grid = {\"n_estimators\": [500], \"max_features\": [i for i in range(2, len(selected_columns), 1)]}\n",
    "regressor = RandomForestRegressor(oob_score=True, random_state=1, verbose=False)\n",
    "model = GridSearchCV(estimator=regressor, n_jobs=-1, param_grid=param_grid, verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=None, error_score='raise',\n",
       "       estimator=RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n",
       "           max_features='auto', max_leaf_nodes=None,\n",
       "           min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "           min_samples_leaf=1, min_samples_split=2,\n",
       "           min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=1,\n",
       "           oob_score=True, random_state=1, verbose=False, warm_start=False),\n",
       "       fit_params=None, iid=True, n_jobs=-1,\n",
       "       param_grid={'n_estimators': [500], 'max_features': [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36]},\n",
       "       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',\n",
       "       scoring=None, verbose=False)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(train_df[train_df.columns[1:]].values, train_df[\"pbindaff\"].values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n",
       "           max_features=2, max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "           min_impurity_split=None, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           n_estimators=500, n_jobs=1, oob_score=True, random_state=1,\n",
       "           verbose=False, warm_start=False)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = model.best_estimator_\n",
    "clf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(0.9765735491381653, 0.0) (0.7803930295798895, 3.224784234670014e-41)\n"
     ]
    }
   ],
   "source": [
    "train_r = pearsonr(train_df[\"pbindaff\"].values, clf.predict(train_df[train_df.columns[1:]].values))\n",
    "test_r = pearsonr(test_df[\"pbindaff\"].values, clf.predict(test_df[test_df.columns[1:]].values))\n",
    "\n",
    "print(train_r, test_r)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['RFScore-v1_07']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Save the model\n",
    "joblib.dump(clf, \"RFScore-v1_07\")"
   ]
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}