10a_earthquake_alternative_methods-balanced.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.preprocessing import (\n",
    "    LabelEncoder, OneHotEncoder, MinMaxScaler\n",
    "    )\n",
    "from sklearn.metrics import (\n",
    "    precision_score, recall_score, roc_auc_score, f1_score, confusion_matrix, accuracy_score\n",
    "    )\n",
    "\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "quake_frame = pd.read_csv('data/consolidated_data.csv')\n",
    "\n",
    "quake_frame.drop(['id', 'Unnamed: 0', 'place', 'time', 'updated'], inplace=True, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['sonic boom', 'earthquake', 'quarry blast', 'explosion',\n",
       "       'nuclear explosion', 'mine collapse', 'other event',\n",
       "       'chemical explosion', 'rock burst', 'ice quake', 'rockslide',\n",
       "       'Rock Slide', 'landslide', 'quarry', 'building collapse',\n",
       "       'mining explosion', 'sonicboom', 'acoustic noise', 'not reported',\n",
       "       'experimental explosion', 'collapse', 'meteorite',\n",
       "       'induced or triggered event', 'volcanic eruption', 'eq'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quake_frame.type.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "natural_quakes = ['earthquake']\n",
    "quake_frame['simple_label'] = quake_frame['type'].apply(lambda x: x not in natural_quakes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.027042808333236575"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(quake_frame['simple_label'])/len(quake_frame.index)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simple model, no imputation\n",
    "\n",
    "We'll start this off with a simple model, just a Random Forest for two classes that takes only rows that have no nans in them. Let's see how many we get.  \n",
    "Then we'll split the data 80/20 and run training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "latitude           0\n",
       "longitude          0\n",
       "depth              0\n",
       "mag                0\n",
       "magType            0\n",
       "nst                0\n",
       "gap                0\n",
       "dmin               0\n",
       "rms                0\n",
       "net                0\n",
       "type               0\n",
       "horizontalError    0\n",
       "depthError         0\n",
       "magError           0\n",
       "magNst             0\n",
       "status             0\n",
       "locationSource     0\n",
       "magSource          0\n",
       "simple_label       0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quake_frame.dropna(inplace=True)\n",
    "quake_frame.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1227408"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(quake_frame)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.03523522740604591"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(quake_frame['simple_label'])/len(quake_frame.index)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>37.361674</td>\n",
       "      <td>4.841731</td>\n",
       "      <td>0.000</td>\n",
       "      <td>35.964167</td>\n",
       "      <td>37.573000</td>\n",
       "      <td>38.817000</td>\n",
       "      <td>62.030667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>-119.557707</td>\n",
       "      <td>10.027502</td>\n",
       "      <td>-179.098</td>\n",
       "      <td>-122.701333</td>\n",
       "      <td>-120.558833</td>\n",
       "      <td>-118.150167</td>\n",
       "      <td>179.661500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>depth</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>6.016756</td>\n",
       "      <td>7.922880</td>\n",
       "      <td>-3.882</td>\n",
       "      <td>1.816000</td>\n",
       "      <td>4.413000</td>\n",
       "      <td>7.830000</td>\n",
       "      <td>211.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mag</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>1.258097</td>\n",
       "      <td>0.694405</td>\n",
       "      <td>-2.500</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>1.180000</td>\n",
       "      <td>1.670000</td>\n",
       "      <td>5.840000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nst</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>17.010182</td>\n",
       "      <td>13.671235</td>\n",
       "      <td>0.000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>22.000000</td>\n",
       "      <td>276.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>gap</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>121.032150</td>\n",
       "      <td>65.767724</td>\n",
       "      <td>0.000</td>\n",
       "      <td>72.000000</td>\n",
       "      <td>105.000000</td>\n",
       "      <td>153.000000</td>\n",
       "      <td>360.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dmin</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>0.078264</td>\n",
       "      <td>0.342578</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.017120</td>\n",
       "      <td>0.037840</td>\n",
       "      <td>0.079990</td>\n",
       "      <td>141.160000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>rms</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>0.097118</td>\n",
       "      <td>0.195847</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.030000</td>\n",
       "      <td>0.060000</td>\n",
       "      <td>0.130000</td>\n",
       "      <td>64.290000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>horizontalError</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>0.801039</td>\n",
       "      <td>2.296862</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.270000</td>\n",
       "      <td>0.410000</td>\n",
       "      <td>0.720000</td>\n",
       "      <td>194.584100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>depthError</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>2.773763</td>\n",
       "      <td>6.903563</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.490000</td>\n",
       "      <td>0.770000</td>\n",
       "      <td>1.460000</td>\n",
       "      <td>725.300000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>magError</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>0.158215</td>\n",
       "      <td>0.132854</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.090000</td>\n",
       "      <td>0.140000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>6.110000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>magNst</th>\n",
       "      <td>1227408.0</td>\n",
       "      <td>12.685281</td>\n",
       "      <td>17.846407</td>\n",
       "      <td>0.000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>14.000000</td>\n",
       "      <td>430.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     count        mean        std      min         25%  \\\n",
       "latitude         1227408.0   37.361674   4.841731    0.000   35.964167   \n",
       "longitude        1227408.0 -119.557707  10.027502 -179.098 -122.701333   \n",
       "depth            1227408.0    6.016756   7.922880   -3.882    1.816000   \n",
       "mag              1227408.0    1.258097   0.694405   -2.500    0.800000   \n",
       "nst              1227408.0   17.010182  13.671235    0.000    8.000000   \n",
       "gap              1227408.0  121.032150  65.767724    0.000   72.000000   \n",
       "dmin             1227408.0    0.078264   0.342578    0.000    0.017120   \n",
       "rms              1227408.0    0.097118   0.195847    0.000    0.030000   \n",
       "horizontalError  1227408.0    0.801039   2.296862    0.000    0.270000   \n",
       "depthError       1227408.0    2.773763   6.903563    0.000    0.490000   \n",
       "magError         1227408.0    0.158215   0.132854    0.000    0.090000   \n",
       "magNst           1227408.0   12.685281  17.846407    0.000    4.000000   \n",
       "\n",
       "                        50%         75%         max  \n",
       "latitude          37.573000   38.817000   62.030667  \n",
       "longitude       -120.558833 -118.150167  179.661500  \n",
       "depth              4.413000    7.830000  211.000000  \n",
       "mag                1.180000    1.670000    5.840000  \n",
       "nst               13.000000   22.000000  276.000000  \n",
       "gap              105.000000  153.000000  360.000000  \n",
       "dmin               0.037840    0.079990  141.160000  \n",
       "rms                0.060000    0.130000   64.290000  \n",
       "horizontalError    0.410000    0.720000  194.584100  \n",
       "depthError         0.770000    1.460000  725.300000  \n",
       "magError           0.140000    0.200000    6.110000  \n",
       "magNst             8.000000   14.000000  430.000000  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quake_frame.describe().transpose()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Alright, this changes the proportions slightly, but not too bad. If anything, one might suggest that at least the mild increase in proportion of non-earthquakes offsets the reduced dataset a little.  \n",
    "Okay, so the problematic values are no longer there, that's something.  \n",
    "Let's try this.  \n",
    "We'll start by mixing up the data frame, then encoding all the categories numerically and splitting it sklearn style."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "quake_frame = quake_frame.sample(frac=1, random_state=42).reset_index(drop=True)\n",
    "\n",
    "le = LabelEncoder()\n",
    "\n",
    "cat_columns = ['magType', 'net', 'status', 'locationSource', 'magSource']\n",
    "\n",
    "for cat in cat_columns:\n",
    "    quake_frame = pd.concat([quake_frame,\n",
    "                             pd.get_dummies(quake_frame[cat], prefix=cat)],\n",
    "                            axis=1)\n",
    "\n",
    "scale_cols = ['latitude', 'longitude', 'depth', 'mag', 'nst', 'gap', 'dmin', 'rms', 'horizontalError',\n",
    " 'depthError', 'magError', 'magNst']\n",
    "\n",
    "scaler = MinMaxScaler()\n",
    "\n",
    "quake_frame[scale_cols] = scaler.fit_transform(quake_frame[scale_cols])\n",
    "\n",
    "x_cols = ['latitude', 'longitude', 'depth', 'mag', 'nst', 'gap', 'dmin', 'rms', 'horizontalError', 'depthError',\n",
    " 'magError', 'magNst', 'magType_Mb', 'magType_Md', 'magType_Ml', 'magType_Unknown', 'magType_ma', 'magType_mb',\n",
    " 'magType_mc', 'magType_md', 'magType_me', 'magType_mh', 'magType_ml', 'magType_mlg', 'magType_mlr', 'magType_mw',\n",
    " 'net_av', 'net_ci', 'net_hv', 'net_ismpkansas', 'net_ld', 'net_mb', 'net_nc', 'net_nm', 'net_nn', 'net_pr',\n",
    " 'net_se', 'net_uu', 'net_uw', 'status_automatic', 'status_manual', 'status_reviewed', 'locationSource_av',\n",
    " 'locationSource_ci', 'locationSource_hv', 'locationSource_ismp', 'locationSource_ld', 'locationSource_mb',\n",
    " 'locationSource_nc', 'locationSource_nm', 'locationSource_nn', 'locationSource_pr', 'locationSource_se',\n",
    " 'locationSource_uu', 'locationSource_uw', 'magSource_av', 'magSource_ci', 'magSource_hv', 'magSource_ismp',\n",
    " 'magSource_ld', 'magSource_mb', 'magSource_nc', 'magSource_nm', 'magSource_nn', 'magSource_pr', 'magSource_se',\n",
    " 'magSource_uu', 'magSource_uw']\n",
    "\n",
    "y_col = ['simple_label']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['latitude',\n",
       " 'longitude',\n",
       " 'depth',\n",
       " 'mag',\n",
       " 'nst',\n",
       " 'gap',\n",
       " 'dmin',\n",
       " 'rms',\n",
       " 'horizontalError',\n",
       " 'depthError',\n",
       " 'magError',\n",
       " 'magNst',\n",
       " 'magType_Mb',\n",
       " 'magType_Md',\n",
       " 'magType_Ml',\n",
       " 'magType_Unknown',\n",
       " 'magType_ma',\n",
       " 'magType_mb',\n",
       " 'magType_mc',\n",
       " 'magType_md',\n",
       " 'magType_me',\n",
       " 'magType_mh',\n",
       " 'magType_ml',\n",
       " 'magType_mlg',\n",
       " 'magType_mlr',\n",
       " 'magType_mw',\n",
       " 'net_av',\n",
       " 'net_ci',\n",
       " 'net_hv',\n",
       " 'net_ismpkansas',\n",
       " 'net_ld',\n",
       " 'net_mb',\n",
       " 'net_nc',\n",
       " 'net_nm',\n",
       " 'net_nn',\n",
       " 'net_pr',\n",
       " 'net_se',\n",
       " 'net_uu',\n",
       " 'net_uw',\n",
       " 'status_automatic',\n",
       " 'status_manual',\n",
       " 'status_reviewed',\n",
       " 'locationSource_av',\n",
       " 'locationSource_ci',\n",
       " 'locationSource_hv',\n",
       " 'locationSource_ismp',\n",
       " 'locationSource_ld',\n",
       " 'locationSource_mb',\n",
       " 'locationSource_nc',\n",
       " 'locationSource_nm',\n",
       " 'locationSource_nn',\n",
       " 'locationSource_pr',\n",
       " 'locationSource_se',\n",
       " 'locationSource_uu',\n",
       " 'locationSource_uw',\n",
       " 'magSource_av',\n",
       " 'magSource_ci',\n",
       " 'magSource_hv',\n",
       " 'magSource_ismp',\n",
       " 'magSource_ld',\n",
       " 'magSource_mb',\n",
       " 'magSource_nc',\n",
       " 'magSource_nm',\n",
       " 'magSource_nn',\n",
       " 'magSource_pr',\n",
       " 'magSource_se',\n",
       " 'magSource_uu',\n",
       " 'magSource_uw',\n",
       " 'simple_label']"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_cols + y_col"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "43248"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(quake_frame['simple_label'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Try oversampling with GAN\n",
    "\n",
    "Using the **ND Dial: Imbalanced Algorithms** repository at https://github.com/dialnd/imbalanced-algorithms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from imbalanced_algorithms.gan import GAN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# required to re-train if necessary\n",
    "# import tensorflow as tf\n",
    "# gan.close()\n",
    "# tf.reset_default_graph()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:215: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:319: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:320: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
      "\n",
      "WARNING:tensorflow:\n",
      "The TensorFlow contrib module will not be included in TensorFlow 2.0.\n",
      "For more information, please see:\n",
      "  * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md\n",
      "  * https://github.com/tensorflow/addons\n",
      "  * https://github.com/tensorflow/io (for I/O related ops)\n",
      "If you depend on functionality not listed there, please file an issue.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:83: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/anaconda3/envs/earthquake37/lib/python3.7/site-packages/tensorflow_core/python/ops/nn_impl.py:183: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:356: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:364: The name tf.train.AdamOptimizer is deprecated. Please use tf.compat.v1.train.AdamOptimizer instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:230: The name tf.global_variables_initializer is deprecated. Please use tf.compat.v1.global_variables_initializer instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:233: The name tf.InteractiveSession is deprecated. Please use tf.compat.v1.InteractiveSession instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:235: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.\n",
      "\n",
      "WARNING:tensorflow:From /Users/eikegermann/Repos/earthquake/imbalanced_algorithms/gan.py:235: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "gan = GAN(num_epochs=200,\n",
    "          batch_size=3000,\n",
    "          d_hidden_dim=(768, 512, 384, 256),\n",
    "          g_hidden_dim=(1024, 768, 512, 384, 256, 128),\n",
    "          n_input=len(x_cols + y_col),  # Number of columns in quake_frame\n",
    "          stddev=0.15,  # standard deviation for initialization noise\n",
    "          d_learning_rate=0.001,\n",
    "          g_learning_rate=0.00075,\n",
    "          pretrain=False,\n",
    "          random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch: 1 loss_d_real: 0.0062 loss_d_fake: 0.0039 loss_g: 25.2442\n",
      "Epoch: 2 loss_d_real: 0.0423 loss_d_fake: 0.0309 loss_g: 16.1519\n",
      "Epoch: 3 loss_d_real: 0.8026 loss_d_fake: 0.1224 loss_g: 7.9913\n",
      "Epoch: 4 loss_d_real: 0.0121 loss_d_fake: 0.1841 loss_g: 3.0552\n",
      "Epoch: 5 loss_d_real: 0.0025 loss_d_fake: 0.0237 loss_g: 3.9146\n",
      "Epoch: 6 loss_d_real: 0.0114 loss_d_fake: 0.0094 loss_g: 5.0364\n",
      "Epoch: 7 loss_d_real: 0.0037 loss_d_fake: 0.0073 loss_g: 5.5310\n",
      "Epoch: 8 loss_d_real: 0.0052 loss_d_fake: 0.0086 loss_g: 5.8310\n",
      "Epoch: 9 loss_d_real: 0.0024 loss_d_fake: 0.0065 loss_g: 6.0723\n",
      "Epoch: 10 loss_d_real: 0.0106 loss_d_fake: 0.0070 loss_g: 6.1712\n",
      "Epoch: 11 loss_d_real: 0.0047 loss_d_fake: 0.0046 loss_g: 6.2245\n",
      "Epoch: 12 loss_d_real: 0.0056 loss_d_fake: 0.0092 loss_g: 6.1081\n",
      "Epoch: 13 loss_d_real: 0.0084 loss_d_fake: 0.0058 loss_g: 6.3621\n",
      "Epoch: 14 loss_d_real: 0.0079 loss_d_fake: 0.0046 loss_g: 6.5224\n",
      "Epoch: 15 loss_d_real: 0.0032 loss_d_fake: 0.0793 loss_g: 3.9845\n",
      "Epoch: 16 loss_d_real: 0.0108 loss_d_fake: 0.0170 loss_g: 5.7102\n",
      "Epoch: 17 loss_d_real: 0.0116 loss_d_fake: 0.1843 loss_g: 3.7036\n",
      "Epoch: 18 loss_d_real: 0.5428 loss_d_fake: 0.0476 loss_g: 4.9540\n",
      "Epoch: 19 loss_d_real: 0.2583 loss_d_fake: 0.1858 loss_g: 3.3853\n",
      "Epoch: 20 loss_d_real: 0.2939 loss_d_fake: 0.1300 loss_g: 3.6424\n",
      "Epoch: 21 loss_d_real: 0.2700 loss_d_fake: 0.1844 loss_g: 2.8556\n",
      "Epoch: 22 loss_d_real: 0.4580 loss_d_fake: 0.2984 loss_g: 4.3818\n",
      "Epoch: 23 loss_d_real: 0.8092 loss_d_fake: 0.0220 loss_g: 5.2051\n",
      "Epoch: 24 loss_d_real: 0.1199 loss_d_fake: 0.2934 loss_g: 2.2133\n",
      "Epoch: 25 loss_d_real: 0.1664 loss_d_fake: 0.5701 loss_g: 2.3376\n",
      "Epoch: 26 loss_d_real: 0.1748 loss_d_fake: 0.0787 loss_g: 4.5935\n",
      "Epoch: 27 loss_d_real: 0.0414 loss_d_fake: 0.3536 loss_g: 2.0105\n",
      "Epoch: 28 loss_d_real: 0.0722 loss_d_fake: 0.1579 loss_g: 2.7275\n",
      "Epoch: 29 loss_d_real: 0.8876 loss_d_fake: 0.1194 loss_g: 2.6834\n",
      "Epoch: 30 loss_d_real: 0.7509 loss_d_fake: 0.2288 loss_g: 2.1638\n",
      "Epoch: 31 loss_d_real: 0.1183 loss_d_fake: 0.5602 loss_g: 1.7028\n",
      "Epoch: 32 loss_d_real: 0.2815 loss_d_fake: 0.5176 loss_g: 1.4582\n",
      "Epoch: 33 loss_d_real: 1.4330 loss_d_fake: 0.0680 loss_g: 4.9896\n",
      "Epoch: 34 loss_d_real: 0.3330 loss_d_fake: 0.3750 loss_g: 1.7045\n",
      "Epoch: 35 loss_d_real: 0.7636 loss_d_fake: 0.2091 loss_g: 2.6146\n",
      "Epoch: 36 loss_d_real: 0.6866 loss_d_fake: 0.2108 loss_g: 2.1345\n",
      "Epoch: 37 loss_d_real: 0.2896 loss_d_fake: 0.2844 loss_g: 1.9864\n",
      "Epoch: 38 loss_d_real: 0.2099 loss_d_fake: 0.3167 loss_g: 2.1826\n",
      "Epoch: 39 loss_d_real: 0.6989 loss_d_fake: 0.2792 loss_g: 2.1181\n",
      "Epoch: 40 loss_d_real: 0.0947 loss_d_fake: 0.4064 loss_g: 1.7860\n",
      "Epoch: 41 loss_d_real: 0.2027 loss_d_fake: 0.5090 loss_g: 1.2555\n",
      "Epoch: 42 loss_d_real: 0.0169 loss_d_fake: 1.4392 loss_g: 0.8460\n",
      "Epoch: 43 loss_d_real: 0.3395 loss_d_fake: 0.3512 loss_g: 1.5684\n",
      "Epoch: 44 loss_d_real: 0.7590 loss_d_fake: 0.0894 loss_g: 3.0568\n",
      "Epoch: 45 loss_d_real: 0.1343 loss_d_fake: 0.3318 loss_g: 1.7554\n",
      "Epoch: 46 loss_d_real: 0.0342 loss_d_fake: 0.4162 loss_g: 1.7393\n",
      "Epoch: 47 loss_d_real: 0.5204 loss_d_fake: 0.1687 loss_g: 2.5253\n",
      "Epoch: 48 loss_d_real: 0.1713 loss_d_fake: 0.1898 loss_g: 2.2610\n",
      "Epoch: 49 loss_d_real: 0.5464 loss_d_fake: 0.0559 loss_g: 4.0016\n",
      "Epoch: 50 loss_d_real: 0.1507 loss_d_fake: 0.4767 loss_g: 1.4429\n",
      "Epoch: 51 loss_d_real: 0.0644 loss_d_fake: 0.2147 loss_g: 2.1540\n",
      "Epoch: 52 loss_d_real: 0.1245 loss_d_fake: 0.0856 loss_g: 3.0732\n",
      "Epoch: 53 loss_d_real: 0.4334 loss_d_fake: 0.0627 loss_g: 3.4660\n",
      "Epoch: 54 loss_d_real: 0.2792 loss_d_fake: 0.6407 loss_g: 1.1602\n",
      "Epoch: 55 loss_d_real: 0.4359 loss_d_fake: 0.2108 loss_g: 2.3262\n",
      "Epoch: 56 loss_d_real: 0.4015 loss_d_fake: 0.1746 loss_g: 2.2463\n",
      "Epoch: 57 loss_d_real: 0.1312 loss_d_fake: 0.6388 loss_g: 0.8554\n",
      "Epoch: 58 loss_d_real: 0.4835 loss_d_fake: 0.3455 loss_g: 1.4783\n",
      "Epoch: 59 loss_d_real: 0.1003 loss_d_fake: 0.5276 loss_g: 1.0733\n",
      "Epoch: 60 loss_d_real: 0.4441 loss_d_fake: 0.4064 loss_g: 1.3091\n",
      "Epoch: 61 loss_d_real: 0.3610 loss_d_fake: 0.3755 loss_g: 1.4670\n",
      "Epoch: 62 loss_d_real: 0.1512 loss_d_fake: 0.3844 loss_g: 1.5197\n",
      "Epoch: 63 loss_d_real: 0.0670 loss_d_fake: 0.3169 loss_g: 1.5533\n",
      "Epoch: 64 loss_d_real: 0.0510 loss_d_fake: 0.3925 loss_g: 1.4997\n",
      "Epoch: 65 loss_d_real: 7.2893 loss_d_fake: 0.0112 loss_g: 13.1921\n",
      "Epoch: 66 loss_d_real: 0.2888 loss_d_fake: 0.3429 loss_g: 1.3269\n",
      "Epoch: 67 loss_d_real: 0.2681 loss_d_fake: 0.2088 loss_g: 1.8484\n",
      "Epoch: 68 loss_d_real: 0.2217 loss_d_fake: 0.1338 loss_g: 2.2303\n",
      "Epoch: 69 loss_d_real: 0.5878 loss_d_fake: 0.2446 loss_g: 1.8285\n",
      "Epoch: 70 loss_d_real: 0.5545 loss_d_fake: 0.2489 loss_g: 1.8545\n",
      "Epoch: 71 loss_d_real: 0.4494 loss_d_fake: 0.3792 loss_g: 1.4690\n",
      "Epoch: 72 loss_d_real: 0.2791 loss_d_fake: 0.4177 loss_g: 1.5653\n",
      "Epoch: 73 loss_d_real: 0.1660 loss_d_fake: 0.2790 loss_g: 1.6682\n",
      "Epoch: 74 loss_d_real: 0.1883 loss_d_fake: 0.2488 loss_g: 1.7730\n",
      "Epoch: 75 loss_d_real: 0.5376 loss_d_fake: 0.1441 loss_g: 2.8606\n",
      "Epoch: 76 loss_d_real: 0.8816 loss_d_fake: 0.1894 loss_g: 1.8934\n",
      "Epoch: 77 loss_d_real: 3.0166 loss_d_fake: 0.2661 loss_g: 6.2931\n",
      "Epoch: 78 loss_d_real: 0.4125 loss_d_fake: 0.3217 loss_g: 1.3598\n",
      "Epoch: 79 loss_d_real: 0.5176 loss_d_fake: 0.3997 loss_g: 1.2535\n",
      "Epoch: 80 loss_d_real: 0.4271 loss_d_fake: 0.2637 loss_g: 1.5972\n",
      "Epoch: 81 loss_d_real: 2.4638 loss_d_fake: 0.0877 loss_g: 4.6360\n",
      "Epoch: 82 loss_d_real: 0.1655 loss_d_fake: 0.4223 loss_g: 1.1138\n",
      "Epoch: 83 loss_d_real: 1.0525 loss_d_fake: 0.1788 loss_g: 1.9076\n",
      "Epoch: 84 loss_d_real: 0.6327 loss_d_fake: 0.3740 loss_g: 1.2135\n",
      "Epoch: 85 loss_d_real: 0.4568 loss_d_fake: 0.5272 loss_g: 1.1142\n",
      "Epoch: 86 loss_d_real: 0.5825 loss_d_fake: 0.3698 loss_g: 1.2267\n",
      "Epoch: 87 loss_d_real: 0.5245 loss_d_fake: 0.3661 loss_g: 1.2309\n",
      "Epoch: 88 loss_d_real: 0.3083 loss_d_fake: 0.6388 loss_g: 0.9930\n",
      "Epoch: 89 loss_d_real: 0.4660 loss_d_fake: 0.4107 loss_g: 1.2100\n",
      "Epoch: 90 loss_d_real: 0.2687 loss_d_fake: 0.3974 loss_g: 1.2222\n",
      "Epoch: 91 loss_d_real: 0.4925 loss_d_fake: 0.2847 loss_g: 1.5859\n",
      "Epoch: 92 loss_d_real: 0.1248 loss_d_fake: 0.3170 loss_g: 1.4288\n",
      "Epoch: 93 loss_d_real: 0.1495 loss_d_fake: 0.1919 loss_g: 1.9202\n",
      "Epoch: 94 loss_d_real: 0.1020 loss_d_fake: 0.3131 loss_g: 1.4832\n",
      "Epoch: 95 loss_d_real: 0.2499 loss_d_fake: 0.2804 loss_g: 1.7200\n",
      "Epoch: 96 loss_d_real: 0.0994 loss_d_fake: 0.3376 loss_g: 1.5687\n",
      "Epoch: 97 loss_d_real: 0.3519 loss_d_fake: 0.0882 loss_g: 3.3912\n",
      "Epoch: 98 loss_d_real: 0.0985 loss_d_fake: 0.4333 loss_g: 1.4978\n",
      "Epoch: 99 loss_d_real: 0.1491 loss_d_fake: 0.0848 loss_g: 2.9536\n",
      "Epoch: 100 loss_d_real: 0.2688 loss_d_fake: 0.1189 loss_g: 2.5992\n",
      "Epoch: 101 loss_d_real: 1.5217 loss_d_fake: 0.0701 loss_g: 3.5201\n",
      "Epoch: 102 loss_d_real: 0.1264 loss_d_fake: 0.3991 loss_g: 1.1846\n",
      "Epoch: 103 loss_d_real: 0.1827 loss_d_fake: 0.2435 loss_g: 1.6170\n",
      "Epoch: 104 loss_d_real: 0.0984 loss_d_fake: 0.1823 loss_g: 1.9429\n",
      "Epoch: 105 loss_d_real: 0.1078 loss_d_fake: 0.1175 loss_g: 2.3663\n",
      "Epoch: 106 loss_d_real: 0.0488 loss_d_fake: 0.1645 loss_g: 2.2319\n",
      "Epoch: 107 loss_d_real: 0.3275 loss_d_fake: 0.2452 loss_g: 2.2126\n",
      "Epoch: 108 loss_d_real: 0.3325 loss_d_fake: 0.3049 loss_g: 2.0560\n",
      "Epoch: 109 loss_d_real: 0.1852 loss_d_fake: 0.2425 loss_g: 2.0767\n",
      "Epoch: 110 loss_d_real: 0.6002 loss_d_fake: 0.1738 loss_g: 2.3457\n",
      "Epoch: 111 loss_d_real: 0.5067 loss_d_fake: 0.0875 loss_g: 2.9454\n",
      "Epoch: 112 loss_d_real: 0.2186 loss_d_fake: 0.2454 loss_g: 1.8948\n",
      "Epoch: 113 loss_d_real: 0.2324 loss_d_fake: 0.1826 loss_g: 2.1883\n",
      "Epoch: 114 loss_d_real: 0.6485 loss_d_fake: 0.1909 loss_g: 2.4957\n",
      "Epoch: 115 loss_d_real: 0.6770 loss_d_fake: 0.0637 loss_g: 4.0695\n",
      "Epoch: 116 loss_d_real: 0.2159 loss_d_fake: 0.1760 loss_g: 2.5308\n",
      "Epoch: 117 loss_d_real: 0.2884 loss_d_fake: 0.2514 loss_g: 2.0436\n",
      "Epoch: 118 loss_d_real: 0.7007 loss_d_fake: 0.0517 loss_g: 6.8326\n",
      "Epoch: 119 loss_d_real: 1.4398 loss_d_fake: 0.1669 loss_g: 2.3106\n",
      "Epoch: 120 loss_d_real: 0.3851 loss_d_fake: 0.2957 loss_g: 1.9973\n",
      "Epoch: 121 loss_d_real: 0.5399 loss_d_fake: 0.0263 loss_g: 4.1438\n",
      "Epoch: 122 loss_d_real: 0.2657 loss_d_fake: 0.0674 loss_g: 3.2427\n",
      "Epoch: 123 loss_d_real: 0.5650 loss_d_fake: 0.1344 loss_g: 2.4682\n",
      "Epoch: 124 loss_d_real: 0.0708 loss_d_fake: 0.0836 loss_g: 2.7607\n",
      "Epoch: 125 loss_d_real: 0.0404 loss_d_fake: 0.0687 loss_g: 3.0071\n",
      "Epoch: 126 loss_d_real: 0.1279 loss_d_fake: 0.0377 loss_g: 4.4257\n",
      "Epoch: 127 loss_d_real: 0.9104 loss_d_fake: 0.0854 loss_g: 3.7856\n",
      "Epoch: 128 loss_d_real: 0.6804 loss_d_fake: 0.3562 loss_g: 1.4237\n",
      "Epoch: 129 loss_d_real: 0.4392 loss_d_fake: 0.2587 loss_g: 1.6238\n",
      "Epoch: 130 loss_d_real: 0.3001 loss_d_fake: 0.2333 loss_g: 1.6867\n",
      "Epoch: 131 loss_d_real: 0.0873 loss_d_fake: 0.1200 loss_g: 2.3495\n",
      "Epoch: 132 loss_d_real: 0.1989 loss_d_fake: 1.0288 loss_g: 0.9350\n",
      "Epoch: 133 loss_d_real: 0.2641 loss_d_fake: 0.2122 loss_g: 1.8024\n",
      "Epoch: 134 loss_d_real: 0.3525 loss_d_fake: 0.4407 loss_g: 1.1660\n",
      "Epoch: 135 loss_d_real: 0.3452 loss_d_fake: 0.5792 loss_g: 1.1027\n",
      "Epoch: 136 loss_d_real: 0.4181 loss_d_fake: 0.2756 loss_g: 1.5826\n",
      "Epoch: 137 loss_d_real: 0.5121 loss_d_fake: 0.5236 loss_g: 1.0452\n",
      "Epoch: 138 loss_d_real: 0.4402 loss_d_fake: 0.2204 loss_g: 1.8160\n",
      "Epoch: 139 loss_d_real: 0.6201 loss_d_fake: 0.4173 loss_g: 1.2581\n",
      "Epoch: 140 loss_d_real: 0.4440 loss_d_fake: 0.4891 loss_g: 1.0438\n",
      "Epoch: 141 loss_d_real: 0.4893 loss_d_fake: 0.4318 loss_g: 1.1955\n",
      "Epoch: 142 loss_d_real: 0.4628 loss_d_fake: 0.4294 loss_g: 1.1832\n",
      "Epoch: 143 loss_d_real: 0.4133 loss_d_fake: 0.3320 loss_g: 1.4583\n",
      "Epoch: 144 loss_d_real: 0.4104 loss_d_fake: 0.4536 loss_g: 1.2059\n",
      "Epoch: 145 loss_d_real: 0.5377 loss_d_fake: 0.4532 loss_g: 1.0921\n",
      "Epoch: 146 loss_d_real: 0.7241 loss_d_fake: 0.2631 loss_g: 1.6633\n",
      "Epoch: 147 loss_d_real: 0.3860 loss_d_fake: 0.2642 loss_g: 1.5856\n",
      "Epoch: 148 loss_d_real: 0.4587 loss_d_fake: 0.3573 loss_g: 1.3128\n",
      "Epoch: 149 loss_d_real: 0.4395 loss_d_fake: 0.3987 loss_g: 1.4576\n",
      "Epoch: 150 loss_d_real: 0.3355 loss_d_fake: 0.3337 loss_g: 1.3750\n",
      "Epoch: 151 loss_d_real: 0.4556 loss_d_fake: 0.3236 loss_g: 1.3999\n",
      "Epoch: 152 loss_d_real: 0.4563 loss_d_fake: 0.3859 loss_g: 1.2924\n",
      "Epoch: 153 loss_d_real: 0.6050 loss_d_fake: 0.3564 loss_g: 1.3601\n",
      "Epoch: 154 loss_d_real: 0.5755 loss_d_fake: 0.4101 loss_g: 1.1666\n",
      "Epoch: 155 loss_d_real: 0.3352 loss_d_fake: 0.5490 loss_g: 1.0318\n",
      "Epoch: 156 loss_d_real: 0.4493 loss_d_fake: 0.4864 loss_g: 1.1257\n",
      "Epoch: 157 loss_d_real: 0.4833 loss_d_fake: 0.4559 loss_g: 1.1508\n",
      "Epoch: 158 loss_d_real: 0.3709 loss_d_fake: 0.3078 loss_g: 1.4534\n",
      "Epoch: 159 loss_d_real: 0.5799 loss_d_fake: 0.5741 loss_g: 1.1013\n",
      "Epoch: 160 loss_d_real: 0.3489 loss_d_fake: 0.4180 loss_g: 1.1885\n",
      "Epoch: 161 loss_d_real: 0.7045 loss_d_fake: 0.4382 loss_g: 1.1208\n",
      "Epoch: 162 loss_d_real: 0.8665 loss_d_fake: 0.3508 loss_g: 1.6884\n",
      "Epoch: 163 loss_d_real: 0.8580 loss_d_fake: 0.3218 loss_g: 1.4115\n",
      "Epoch: 164 loss_d_real: 0.3304 loss_d_fake: 0.3539 loss_g: 1.5644\n",
      "Epoch: 165 loss_d_real: 0.6233 loss_d_fake: 0.4762 loss_g: 1.0300\n",
      "Epoch: 166 loss_d_real: 0.5058 loss_d_fake: 0.4540 loss_g: 1.0878\n",
      "Epoch: 167 loss_d_real: 0.3667 loss_d_fake: 0.4035 loss_g: 1.2412\n",
      "Epoch: 168 loss_d_real: 0.5425 loss_d_fake: 0.1946 loss_g: 1.9212\n",
      "Epoch: 169 loss_d_real: 0.7242 loss_d_fake: 0.1136 loss_g: 3.0622\n",
      "Epoch: 170 loss_d_real: 1.0917 loss_d_fake: 0.3483 loss_g: 1.3062\n",
      "Epoch: 171 loss_d_real: 0.2223 loss_d_fake: 0.3008 loss_g: 1.4250\n",
      "Epoch: 172 loss_d_real: 0.1011 loss_d_fake: 0.1295 loss_g: 2.2655\n",
      "Epoch: 173 loss_d_real: 0.5047 loss_d_fake: 0.3261 loss_g: 1.8653\n",
      "Epoch: 174 loss_d_real: 0.6572 loss_d_fake: 0.3766 loss_g: 1.3257\n",
      "Epoch: 175 loss_d_real: 0.3682 loss_d_fake: 0.4633 loss_g: 1.0339\n",
      "Epoch: 176 loss_d_real: 0.3356 loss_d_fake: 0.3394 loss_g: 1.3981\n",
      "Epoch: 177 loss_d_real: 0.6406 loss_d_fake: 0.4325 loss_g: 1.1289\n",
      "Epoch: 178 loss_d_real: 0.4169 loss_d_fake: 0.5770 loss_g: 0.9326\n",
      "Epoch: 179 loss_d_real: 0.3402 loss_d_fake: 0.4970 loss_g: 1.0076\n",
      "Epoch: 180 loss_d_real: 0.3952 loss_d_fake: 0.4991 loss_g: 1.0081\n",
      "Epoch: 181 loss_d_real: 0.6439 loss_d_fake: 0.4683 loss_g: 1.0328\n",
      "Epoch: 182 loss_d_real: 1.7829 loss_d_fake: 0.1706 loss_g: 3.4190\n",
      "Epoch: 183 loss_d_real: 0.3726 loss_d_fake: 0.5537 loss_g: 0.9371\n",
      "Epoch: 184 loss_d_real: 0.5316 loss_d_fake: 0.4691 loss_g: 1.0193\n",
      "Epoch: 185 loss_d_real: 0.6356 loss_d_fake: 0.3953 loss_g: 1.1694\n",
      "Epoch: 186 loss_d_real: 0.4048 loss_d_fake: 0.4868 loss_g: 1.0052\n",
      "Epoch: 187 loss_d_real: 0.5599 loss_d_fake: 0.5012 loss_g: 0.9780\n",
      "Epoch: 188 loss_d_real: 0.5213 loss_d_fake: 0.4946 loss_g: 0.9756\n",
      "Epoch: 189 loss_d_real: 0.6126 loss_d_fake: 0.4466 loss_g: 1.0410\n",
      "Epoch: 190 loss_d_real: 0.5425 loss_d_fake: 0.4504 loss_g: 1.0575\n",
      "Epoch: 191 loss_d_real: 0.5421 loss_d_fake: 0.4694 loss_g: 1.0317\n",
      "Epoch: 192 loss_d_real: 0.5560 loss_d_fake: 0.4448 loss_g: 1.1049\n",
      "Epoch: 193 loss_d_real: 0.6193 loss_d_fake: 0.4114 loss_g: 1.1188\n",
      "Epoch: 194 loss_d_real: 0.5747 loss_d_fake: 0.4648 loss_g: 1.0632\n",
      "Epoch: 195 loss_d_real: 0.5489 loss_d_fake: 0.4677 loss_g: 1.0230\n",
      "Epoch: 196 loss_d_real: 0.5028 loss_d_fake: 0.4944 loss_g: 0.9988\n",
      "Epoch: 197 loss_d_real: 0.6374 loss_d_fake: 0.5128 loss_g: 1.1179\n",
      "Epoch: 198 loss_d_real: 0.5661 loss_d_fake: 0.4519 loss_g: 1.0702\n",
      "Epoch: 199 loss_d_real: 0.5663 loss_d_fake: 0.4322 loss_g: 1.0787\n",
      "Epoch: 200 loss_d_real: 0.5448 loss_d_fake: 0.4890 loss_g: 0.9771\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<imbalanced_algorithms.gan.GAN at 0x1a21914978>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gan.fit(quake_frame.loc[quake_frame['simple_label'] == True, x_cols + y_col].values, display_step=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "synth_samples = pd.DataFrame(gan.sample(round((len(quake_frame.index) - sum(quake_frame['simple_label']))/2)), columns = x_cols + y_col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We'll have to help out a little and round the one-hot-encoded values to make them properly encoded."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "one_hot_cols = ['magType_Mb',\n",
    " 'magType_Md',\n",
    " 'magType_Ml',\n",
    " 'magType_Unknown',\n",
    " 'magType_ma',\n",
    " 'magType_mb',\n",
    " 'magType_mc',\n",
    " 'magType_md',\n",
    " 'magType_me',\n",
    " 'magType_mh',\n",
    " 'magType_ml',\n",
    " 'magType_mlg',\n",
    " 'magType_mlr',\n",
    " 'magType_mw',\n",
    " 'net_av',\n",
    " 'net_ci',\n",
    " 'net_hv',\n",
    " 'net_ismpkansas',\n",
    " 'net_ld',\n",
    " 'net_mb',\n",
    " 'net_nc',\n",
    " 'net_nm',\n",
    " 'net_nn',\n",
    " 'net_pr',\n",
    " 'net_se',\n",
    " 'net_uu',\n",
    " 'net_uw',\n",
    " 'status_automatic',\n",
    " 'status_manual',\n",
    " 'status_reviewed',\n",
    " 'locationSource_av',\n",
    " 'locationSource_ci',\n",
    " 'locationSource_hv',\n",
    " 'locationSource_ismp',\n",
    " 'locationSource_ld',\n",
    " 'locationSource_mb',\n",
    " 'locationSource_nc',\n",
    " 'locationSource_nm',\n",
    " 'locationSource_nn',\n",
    " 'locationSource_pr',\n",
    " 'locationSource_se',\n",
    " 'locationSource_uu',\n",
    " 'locationSource_uw',\n",
    " 'magSource_av',\n",
    " 'magSource_ci',\n",
    " 'magSource_hv',\n",
    " 'magSource_ismp',\n",
    " 'magSource_ld',\n",
    " 'magSource_mb',\n",
    " 'magSource_nc',\n",
    " 'magSource_nm',\n",
    " 'magSource_nn',\n",
    " 'magSource_pr',\n",
    " 'magSource_se',\n",
    " 'magSource_uu',\n",
    " 'magSource_uw',\n",
    " 'simple_label']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "synth_samples[one_hot_cols] = synth_samples[one_hot_cols].apply(round).astype('int')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>depth</th>\n",
       "      <th>mag</th>\n",
       "      <th>nst</th>\n",
       "      <th>gap</th>\n",
       "      <th>dmin</th>\n",
       "      <th>rms</th>\n",
       "      <th>horizontalError</th>\n",
       "      <th>depthError</th>\n",
       "      <th>...</th>\n",
       "      <th>magSource_ld</th>\n",
       "      <th>magSource_mb</th>\n",
       "      <th>magSource_nc</th>\n",
       "      <th>magSource_nm</th>\n",
       "      <th>magSource_nn</th>\n",
       "      <th>magSource_pr</th>\n",
       "      <th>magSource_se</th>\n",
       "      <th>magSource_uu</th>\n",
       "      <th>magSource_uw</th>\n",
       "      <th>simple_label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.635341</td>\n",
       "      <td>0.173858</td>\n",
       "      <td>0.023625</td>\n",
       "      <td>0.523611</td>\n",
       "      <td>0.070972</td>\n",
       "      <td>0.196466</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.029123</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.080656</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.627177</td>\n",
       "      <td>0.165113</td>\n",
       "      <td>0.013989</td>\n",
       "      <td>0.534554</td>\n",
       "      <td>0.056572</td>\n",
       "      <td>0.317007</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.033753</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.086150</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.647575</td>\n",
       "      <td>0.179874</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.564497</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.300294</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.011607</td>\n",
       "      <td>0.004658</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.644466</td>\n",
       "      <td>0.178558</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.566991</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.281617</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.002728</td>\n",
       "      <td>0.008632</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.630248</td>\n",
       "      <td>0.172529</td>\n",
       "      <td>0.025024</td>\n",
       "      <td>0.523802</td>\n",
       "      <td>0.078192</td>\n",
       "      <td>0.180035</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.024942</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.075458</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 69 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   latitude  longitude     depth       mag       nst       gap  dmin  \\\n",
       "0  0.635341   0.173858  0.023625  0.523611  0.070972  0.196466   0.0   \n",
       "1  0.627177   0.165113  0.013989  0.534554  0.056572  0.317007   0.0   \n",
       "2  0.647575   0.179874  0.000000  0.564497  0.000000  0.300294   0.0   \n",
       "3  0.644466   0.178558  0.000000  0.566991  0.000000  0.281617   0.0   \n",
       "4  0.630248   0.172529  0.025024  0.523802  0.078192  0.180035   0.0   \n",
       "\n",
       "        rms  horizontalError  depthError  ...  magSource_ld  magSource_mb  \\\n",
       "0  0.029123         0.000000    0.080656  ...             0             0   \n",
       "1  0.033753         0.000000    0.086150  ...             0             0   \n",
       "2  0.000000         0.011607    0.004658  ...             0             0   \n",
       "3  0.000000         0.002728    0.008632  ...             0             0   \n",
       "4  0.024942         0.000000    0.075458  ...             0             0   \n",
       "\n",
       "   magSource_nc  magSource_nm  magSource_nn  magSource_pr  magSource_se  \\\n",
       "0             0             0             0             0             0   \n",
       "1             0             0             0             0             0   \n",
       "2             1             0             0             0             0   \n",
       "3             1             0             0             0             0   \n",
       "4             0             0             0             0             0   \n",
       "\n",
       "   magSource_uu  magSource_uw  simple_label  \n",
       "0             0             0             1  \n",
       "1             0             0             1  \n",
       "2             0             0             1  \n",
       "3             0             0             1  \n",
       "4             0             0             1  \n",
       "\n",
       "[5 rows x 69 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "synth_samples.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_length = int(np.round(len(quake_frame.index) * 0.8))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_X = pd.concat([quake_frame.loc[:train_length, x_cols], synth_samples[x_cols]])\n",
    "train_y = pd.concat([quake_frame.loc[:train_length, y_col], synth_samples[y_col]])\n",
    "\n",
    "valid_X = quake_frame.loc[train_length:, x_cols]\n",
    "valid_y = quake_frame.loc[train_length:, y_col]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "n_estim = 100\n",
    "\n",
    "rfc = RandomForestClassifier(n_estimators=n_estim,\n",
    "                             class_weight='balanced',\n",
    "                             random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight='balanced',\n",
       "                       criterion='gini', max_depth=None, max_features='auto',\n",
       "                       max_leaf_nodes=None, max_samples=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=100,\n",
       "                       n_jobs=None, oob_score=False, random_state=42, verbose=0,\n",
       "                       warm_start=False)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc.fit(train_X, np.ravel(train_y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "preds = pd.DataFrame(rfc.predict(valid_X), columns=['predictions'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Precision:  0.9710533027288957\n",
      "Recall:  0.8742824339839265\n",
      "ROC score:  0.9366618528779634\n",
      "F1 score:  0.9201304978250362\n",
      "Accuracy score:  0.9946146764324879\n"
     ]
    }
   ],
   "source": [
    "prec = precision_score(valid_y, preds)\n",
    "reca = recall_score(valid_y, preds)\n",
    "roc = roc_auc_score(valid_y, preds)\n",
    "f1 = f1_score(valid_y, preds)\n",
    "acc = accuracy_score(valid_y, preds)\n",
    "conf_mat = confusion_matrix(valid_y, preds)\n",
    "\n",
    "print(\"Precision: \", prec)\n",
    "print(\"Recall: \", reca)\n",
    "print(\"ROC score: \", roc)\n",
    "print(\"F1 score: \", f1)\n",
    "print(\"Accuracy score: \", acc)"
   ]
  },
  {
   "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}