{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "tH3lvFAXfjGz"
   },
   "outputs": [],
   "source": [
    "# import libraries \n",
    "\n",
    "import pandas as pd \n",
    "\n",
    "from sklearn.model_selection import train_test_split \n",
    "\n",
    "from sklearn.linear_model import LinearRegression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "O0ob0P0RftvC"
   },
   "outputs": [],
   "source": [
    "# column headers \n",
    "\n",
    "_headers = ['CIC0', 'SM1', 'GATS1i', 'NdsCH', 'Ndssc', 'MLOGP', 'response'] \n",
    "\n",
    "# read in data \n",
    "\n",
    "df = pd.read_csv('../Dataset/qsar_fish_toxicity.csv', names=_headers, sep=';') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 194
    },
    "colab_type": "code",
    "id": "RbFPJeOKfvFx",
    "outputId": "20b9e550-bcb8-49c7-a589-f08b9cd48754"
   },
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "wS62XTnDf1VC"
   },
   "outputs": [],
   "source": [
    "# Let's split our data \n",
    "\n",
    "features = df.drop('response', axis=1).values \n",
    "\n",
    "labels = df[['response']].values \n",
    "\n",
    " \n",
    "\n",
    "X_train, X_eval, y_train, y_eval = train_test_split(features, labels, test_size=0.2, random_state=0) \n",
    "\n",
    "X_val, X_test, y_val, y_test = train_test_split(X_eval, y_eval, random_state=0) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "h2BBicmsf5Gi"
   },
   "outputs": [],
   "source": [
    "model = LinearRegression() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "Sbmn6Wfif6sa",
    "outputId": "819c811a-ec55-46a7-a4b2-a6c20facaecc"
   },
   "outputs": [],
   "source": [
    "model.fit(X_train, y_train) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "j52nxGrLf_Y6"
   },
   "outputs": [],
   "source": [
    "y_pred = model.predict(X_val) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "dboYPiDhgAzS",
    "outputId": "354432d9-670c-4d5e-96ba-62b79733f930"
   },
   "outputs": [],
   "source": [
    "r2 = model.score(X_val, y_val) \n",
    "\n",
    "print('R^2 score: {}'.format(r2)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 194
    },
    "colab_type": "code",
    "id": "KWhxdfXmgZPk",
    "outputId": "f0602638-2383-4df3-8286-9225ca272cb0"
   },
   "outputs": [],
   "source": [
    "_ys = pd.DataFrame(dict(actuals=y_val.reshape(-1), predicted=y_pred.reshape(-1))) \n",
    "\n",
    "_ys.head() "
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise6_02.ipynb",
   "provenance": []
  },
  "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": 1
}