{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "df = pd.read_parquet(\"fraud-cleaned-sample.parquet\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train/test split\n",
    "\n",
    "We're using time-series data, so we'll split based on time."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "first = df['timestamp'].min()\n",
    "last = df['timestamp'].max()\n",
    "cutoff = first + ((last - first) * 0.7)\n",
    "\n",
    "df = df.copy()\n",
    "\n",
    "train = df[df['timestamp'] <= cutoff]\n",
    "test = df[df['timestamp'] > cutoff]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cloudpickle as cp\n",
    "feature_pipeline = cp.load(open('feature_pipeline.sav', 'rb'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn import model_selection\n",
    "\n",
    "rfc = RandomForestClassifier(n_estimators=16, max_depth=8, random_state=404, class_weight=\"balanced_subsample\")\n",
    "\n",
    "svecs = feature_pipeline.fit_transform(train)\n",
    "rfc.fit(svecs, train[\"label\"])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "\n",
    "predictions = rfc.predict(feature_pipeline.fit_transform(test))\n",
    "print(classification_report(test.label.values, predictions))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from mlworkflows import plot\n",
    "df, chart = plot.binary_confusion_matrix(test[\"label\"], predictions)\n",
    "chart"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Save the trained model as a pipeline stage"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from mlworkflows import util\n",
    "util.serialize_to(rfc, \"rfc.sav\")"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}