{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Time Series regression - MLP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading required package: daltoolbox\n",
      "\n",
      "Registered S3 method overwritten by 'quantmod':\n",
      "  method            from\n",
      "  as.zoo.data.frame zoo \n",
      "\n",
      "\n",
      "Attaching package: ‘daltoolbox’\n",
      "\n",
      "\n",
      "The following object is masked from ‘package:base’:\n",
      "\n",
      "    transform\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# DAL ToolBox\n",
    "# version 1.01.727\n",
    "\n",
    "source(\"https://raw.githubusercontent.com/cefet-rj-dal/daltoolbox/main/jupyter.R\")\n",
    "\n",
    "#loading DAL\n",
    "load_library(\"daltoolbox\") "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Series for studying"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A matrix: 3 × 10 of type dbl</caption>\n",
       "<thead>\n",
       "\t<tr><th scope=col>t9</th><th scope=col>t8</th><th scope=col>t7</th><th scope=col>t6</th><th scope=col>t5</th><th scope=col>t4</th><th scope=col>t3</th><th scope=col>t2</th><th scope=col>t1</th><th scope=col>t0</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><td>0.0000000</td><td>0.2474040</td><td>0.4794255</td><td>0.6816388</td><td>0.8414710</td><td>0.9489846</td><td>0.9974950</td><td>0.9839859</td><td>0.9092974</td><td>0.7780732</td></tr>\n",
       "\t<tr><td>0.2474040</td><td>0.4794255</td><td>0.6816388</td><td>0.8414710</td><td>0.9489846</td><td>0.9974950</td><td>0.9839859</td><td>0.9092974</td><td>0.7780732</td><td>0.5984721</td></tr>\n",
       "\t<tr><td>0.4794255</td><td>0.6816388</td><td>0.8414710</td><td>0.9489846</td><td>0.9974950</td><td>0.9839859</td><td>0.9092974</td><td>0.7780732</td><td>0.5984721</td><td>0.3816610</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A matrix: 3 × 10 of type dbl\n",
       "\\begin{tabular}{llllllllll}\n",
       " t9 & t8 & t7 & t6 & t5 & t4 & t3 & t2 & t1 & t0\\\\\n",
       "\\hline\n",
       "\t 0.0000000 & 0.2474040 & 0.4794255 & 0.6816388 & 0.8414710 & 0.9489846 & 0.9974950 & 0.9839859 & 0.9092974 & 0.7780732\\\\\n",
       "\t 0.2474040 & 0.4794255 & 0.6816388 & 0.8414710 & 0.9489846 & 0.9974950 & 0.9839859 & 0.9092974 & 0.7780732 & 0.5984721\\\\\n",
       "\t 0.4794255 & 0.6816388 & 0.8414710 & 0.9489846 & 0.9974950 & 0.9839859 & 0.9092974 & 0.7780732 & 0.5984721 & 0.3816610\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A matrix: 3 × 10 of type dbl\n",
       "\n",
       "| t9 | t8 | t7 | t6 | t5 | t4 | t3 | t2 | t1 | t0 |\n",
       "|---|---|---|---|---|---|---|---|---|---|\n",
       "| 0.0000000 | 0.2474040 | 0.4794255 | 0.6816388 | 0.8414710 | 0.9489846 | 0.9974950 | 0.9839859 | 0.9092974 | 0.7780732 |\n",
       "| 0.2474040 | 0.4794255 | 0.6816388 | 0.8414710 | 0.9489846 | 0.9974950 | 0.9839859 | 0.9092974 | 0.7780732 | 0.5984721 |\n",
       "| 0.4794255 | 0.6816388 | 0.8414710 | 0.9489846 | 0.9974950 | 0.9839859 | 0.9092974 | 0.7780732 | 0.5984721 | 0.3816610 |\n",
       "\n"
      ],
      "text/plain": [
       "     t9        t8        t7        t6        t5        t4        t3       \n",
       "[1,] 0.0000000 0.2474040 0.4794255 0.6816388 0.8414710 0.9489846 0.9974950\n",
       "[2,] 0.2474040 0.4794255 0.6816388 0.8414710 0.9489846 0.9974950 0.9839859\n",
       "[3,] 0.4794255 0.6816388 0.8414710 0.9489846 0.9974950 0.9839859 0.9092974\n",
       "     t2        t1        t0       \n",
       "[1,] 0.9839859 0.9092974 0.7780732\n",
       "[2,] 0.9092974 0.7780732 0.5984721\n",
       "[3,] 0.7780732 0.5984721 0.3816610"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "data(sin_data)\n",
    "ts <- ts_data(sin_data$y, 10)\n",
    "ts_head(ts, 3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAMAAADKOT/pAAADAFBMVEUAAAABAQECAgIDAwME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",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 420
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "library(ggplot2)\n",
    "plot_ts(x=sin_data$x, y=sin_data$y) + theme(text = element_text(size=16))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### data sampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "samp <- ts_sample(ts, test_size = 5)\n",
    "io_train <- ts_projection(samp$train)\n",
    "io_test <- ts_projection(samp$test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### data preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "preproc <- ts_norm_gminmax()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "model <- ts_mlp(ts_norm_gminmax(), input_size=4, size=4, decay=0)\n",
    "model <- fit(model, x=io_train$input, y=io_train$output)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Evaluation of adjustment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "1.11558705263708e-05"
      ],
      "text/latex": [
       "1.11558705263708e-05"
      ],
      "text/markdown": [
       "1.11558705263708e-05"
      ],
      "text/plain": [
       "[1] 1.115587e-05"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "adjust <- predict(model, io_train$input)\n",
    "adjust <- as.vector(adjust)\n",
    "output <- as.vector(io_train$output)\n",
    "ev_adjust <- evaluate(model, output, adjust)\n",
    "ev_adjust$mse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Prediction of test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<dl>\n",
       "\t<dt>$values</dt>\n",
       "\t\t<dd><style>\n",
       ".list-inline {list-style: none; margin:0; padding: 0}\n",
       ".list-inline>li {display: inline-block}\n",
       ".list-inline>li:not(:last-child)::after {content: \"\\00b7\"; padding: 0 .5ex}\n",
       "</style>\n",
       "<ol class=list-inline><li>0.412118485241757</li><li>0.173889485380434</li><li>-0.0751511204618093</li><li>-0.319519193622274</li><li>-0.54402111088937</li></ol>\n",
       "</dd>\n",
       "\t<dt>$prediction</dt>\n",
       "\t\t<dd><style>\n",
       ".list-inline {list-style: none; margin:0; padding: 0}\n",
       ".list-inline>li {display: inline-block}\n",
       ".list-inline>li:not(:last-child)::after {content: \"\\00b7\"; padding: 0 .5ex}\n",
       "</style>\n",
       "<ol class=list-inline><li>0.417930383863916</li><li>0.184270190591257</li><li>-0.0590592888553944</li><li>-0.300328614290653</li><li>-0.522706739711133</li></ol>\n",
       "</dd>\n",
       "\t<dt>$smape</dt>\n",
       "\t\t<dd>0.0827306326137497</dd>\n",
       "\t<dt>$mse</dt>\n",
       "\t\t<dd>0.000244613000904878</dd>\n",
       "\t<dt>$R2</dt>\n",
       "\t\t<dd>0.997887264876547</dd>\n",
       "\t<dt>$metrics</dt>\n",
       "\t\t<dd><table class=\"dataframe\">\n",
       "<caption>A data.frame: 1 × 3</caption>\n",
       "<thead>\n",
       "\t<tr><th scope=col>mse</th><th scope=col>smape</th><th scope=col>R2</th></tr>\n",
       "\t<tr><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><td>0.000244613</td><td>0.08273063</td><td>0.9978873</td></tr>\n",
       "</tbody>\n",
       "</table>\n",
       "</dd>\n",
       "</dl>\n"
      ],
      "text/latex": [
       "\\begin{description}\n",
       "\\item[\\$values] \\begin{enumerate*}\n",
       "\\item 0.412118485241757\n",
       "\\item 0.173889485380434\n",
       "\\item -0.0751511204618093\n",
       "\\item -0.319519193622274\n",
       "\\item -0.54402111088937\n",
       "\\end{enumerate*}\n",
       "\n",
       "\\item[\\$prediction] \\begin{enumerate*}\n",
       "\\item 0.417930383863916\n",
       "\\item 0.184270190591257\n",
       "\\item -0.0590592888553944\n",
       "\\item -0.300328614290653\n",
       "\\item -0.522706739711133\n",
       "\\end{enumerate*}\n",
       "\n",
       "\\item[\\$smape] 0.0827306326137497\n",
       "\\item[\\$mse] 0.000244613000904878\n",
       "\\item[\\$R2] 0.997887264876547\n",
       "\\item[\\$metrics] A data.frame: 1 × 3\n",
       "\\begin{tabular}{lll}\n",
       " mse & smape & R2\\\\\n",
       " <dbl> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t 0.000244613 & 0.08273063 & 0.9978873\\\\\n",
       "\\end{tabular}\n",
       "\n",
       "\\end{description}\n"
      ],
      "text/markdown": [
       "$values\n",
       ":   1. 0.412118485241757\n",
       "2. 0.173889485380434\n",
       "3. -0.0751511204618093\n",
       "4. -0.319519193622274\n",
       "5. -0.54402111088937\n",
       "\n",
       "\n",
       "\n",
       "$prediction\n",
       ":   1. 0.417930383863916\n",
       "2. 0.184270190591257\n",
       "3. -0.0590592888553944\n",
       "4. -0.300328614290653\n",
       "5. -0.522706739711133\n",
       "\n",
       "\n",
       "\n",
       "$smape\n",
       ":   0.0827306326137497\n",
       "$mse\n",
       ":   0.000244613000904878\n",
       "$R2\n",
       ":   0.997887264876547\n",
       "$metrics\n",
       ":   \n",
       "A data.frame: 1 × 3\n",
       "\n",
       "| mse &lt;dbl&gt; | smape &lt;dbl&gt; | R2 &lt;dbl&gt; |\n",
       "|---|---|---|\n",
       "| 0.000244613 | 0.08273063 | 0.9978873 |\n",
       "\n",
       "\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "$values\n",
       "[1]  0.41211849  0.17388949 -0.07515112 -0.31951919 -0.54402111\n",
       "\n",
       "$prediction\n",
       "[1]  0.41793038  0.18427019 -0.05905929 -0.30032861 -0.52270674\n",
       "\n",
       "$smape\n",
       "[1] 0.08273063\n",
       "\n",
       "$mse\n",
       "[1] 0.000244613\n",
       "\n",
       "$R2\n",
       "[1] 0.9978873\n",
       "\n",
       "$metrics\n",
       "          mse      smape        R2\n",
       "1 0.000244613 0.08273063 0.9978873\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "prediction <- predict(model, x=io_test$input[1,], steps_ahead=5)\n",
    "prediction <- as.vector(prediction)\n",
    "output <- as.vector(io_test$output)\n",
    "ev_test <- evaluate(model, output, prediction)\n",
    "ev_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plot results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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\nBwAAoIj/ASrDmW9kZDUIAAAAAElFTkSuQmCC",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 420
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "yvalues <- c(io_train$output, io_test$output)\n",
    "plot_ts_pred(y=yvalues, yadj=adjust, ypre=prediction) + theme(text = element_text(size=16))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "4.4.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}