stock_price_wavelet_denoising_ann.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Importing needed packages"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this project, we use several packages. The version of each packages we use are listed below. \n",
    "\n",
    "- yfinance==0.1.74\n",
    "- tensorflow==2.9.1\n",
    "- scikit-learn==1.2.1\n",
    "- PyWavelets==1.1.1\n",
    "- pandas==1.0.5\n",
    "- numpy==1.23.1\n",
    "- matplotlib==3.2.2\n",
    "- keras==2.9.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "FydciQMDpJyW"
   },
   "outputs": [],
   "source": [
    "import math\n",
    "import yfinance as yf\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import pywt\n",
    "from pywt import wavedec\n",
    "from pywt import waverec\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "import matplotlib.pyplot as plt\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "z8aJs2otiPgy"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import r2_score\n",
    "from sklearn.metrics import mean_absolute_error\n",
    "from sklearn.metrics import mean_absolute_percentage_error\n",
    "from sklearn.metrics import mean_squared_error"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UUv8HmH76FYg"
   },
   "source": [
    "# Getting stock's data and pre-processing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 255
    },
    "id": "0UHqyw-Eply5",
    "outputId": "e5cd13fa-7408-4ce5-f9d9-20f941275069"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[*********************100%***********************]  1 of 1 completed\n"
     ]
    },
    {
     "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>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2020-03-31</th>\n",
       "      <td>63.900002</td>\n",
       "      <td>65.622498</td>\n",
       "      <td>63.000000</td>\n",
       "      <td>63.572498</td>\n",
       "      <td>62.428360</td>\n",
       "      <td>197002000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-01</th>\n",
       "      <td>61.625000</td>\n",
       "      <td>62.180000</td>\n",
       "      <td>59.782501</td>\n",
       "      <td>60.227501</td>\n",
       "      <td>59.143562</td>\n",
       "      <td>176218400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-02</th>\n",
       "      <td>60.084999</td>\n",
       "      <td>61.287498</td>\n",
       "      <td>59.224998</td>\n",
       "      <td>61.232498</td>\n",
       "      <td>60.130470</td>\n",
       "      <td>165934000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-03</th>\n",
       "      <td>60.700001</td>\n",
       "      <td>61.424999</td>\n",
       "      <td>59.742500</td>\n",
       "      <td>60.352501</td>\n",
       "      <td>59.266312</td>\n",
       "      <td>129880000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-04-06</th>\n",
       "      <td>62.724998</td>\n",
       "      <td>65.777496</td>\n",
       "      <td>62.345001</td>\n",
       "      <td>65.617500</td>\n",
       "      <td>64.436554</td>\n",
       "      <td>201820400</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Open       High        Low      Close  Adj Close     Volume\n",
       "Date                                                                        \n",
       "2020-03-31  63.900002  65.622498  63.000000  63.572498  62.428360  197002000\n",
       "2020-04-01  61.625000  62.180000  59.782501  60.227501  59.143562  176218400\n",
       "2020-04-02  60.084999  61.287498  59.224998  61.232498  60.130470  165934000\n",
       "2020-04-03  60.700001  61.424999  59.742500  60.352501  59.266312  129880000\n",
       "2020-04-06  62.724998  65.777496  62.345001  65.617500  64.436554  201820400"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#getting Apple Inc. stock data from yfinance for April 1st,2020 throgh March 31st,2022\n",
    "stock = 'AAPL' #stock's ticker\n",
    "stock_data = yf.download(stock, start='2020-04-01', end='2022-04-01')\n",
    "stock_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "qrgX98P5Ov9-"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Date\n",
       "2020-03-31     63.572498\n",
       "2020-04-01     60.227501\n",
       "2020-04-02     61.232498\n",
       "2020-04-03     60.352501\n",
       "2020-04-06     65.617500\n",
       "                 ...    \n",
       "2022-03-25    174.720001\n",
       "2022-03-28    175.600006\n",
       "2022-03-29    178.960007\n",
       "2022-03-30    177.770004\n",
       "2022-03-31    174.610001\n",
       "Name: Close, Length: 506, dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#in this project, we use only closing price to train and test the model\n",
    "#in that case, we only need closing price data\n",
    "\n",
    "#taking closing price data\n",
    "stock_price = stock_data['Close']\n",
    "stock_price"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "5o7-opKQzPFd"
   },
   "outputs": [],
   "source": [
    "train_size = 0.8 #train:test ratio is 4:1\n",
    "\n",
    "#splitting the training and test data\n",
    "train = stock_price[:round(len(stock_price)*train_size)]\n",
    "test = stock_price[round(len(stock_price)*train_size):]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Za7WufS26Y0N"
   },
   "source": [
    "# Denoising using Discrete Wavelet Transform and Inverse Discrete Wavelet Transform"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "#initiate wavelet type and wavelet decomposition level variables\n",
    "level = 2 #wavelet transform decomposition level\n",
    "wavelet = 'db2' #wavelet type. here we choose wavelet Daubechies 2 (db2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "id": "YX55nOi-Vobs"
   },
   "outputs": [],
   "source": [
    "#making function for calculating mean absolute deviation for thresholding\n",
    "def mad(d, axis=None):\n",
    "    \"\"\" Mean absolute deviation of a signal \"\"\"\n",
    "    return np.mean(np.absolute(d - np.mean(d, axis)), axis)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "#wavelet denoising consists of three parts: decomposition, thresholding, reconstruction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "id": "Padqo2xrp0pb"
   },
   "outputs": [],
   "source": [
    "#decompositon/Discrete Wavelet Transform\n",
    "level = int(level)\n",
    "wavelet = wavelet\n",
    "coeff = wavedec(train, wavelet, level=level)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "tyoi_MMFmOBy"
   },
   "outputs": [],
   "source": [
    "#thresholding\n",
    "sigma = mad(coeff[-level])/0.6745\n",
    "threshold = sigma * np.sqrt(2*np.log(len(train)))\n",
    "coeff[1:] = (pywt.threshold(i, value=threshold, mode=\"soft\") for i in coeff[1:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "id": "74ut6JasQJz0"
   },
   "outputs": [],
   "source": [
    "#reconstruction/Inverse Discrete Wavelet Transform\n",
    "denoised = waverec(coeff, wavelet)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "4UmU4YkJd2nd"
   },
   "outputs": [],
   "source": [
    "train = train.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "if len(train)!=len(denoised):\n",
    "    denoised = denoised[:-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "id": "jvPts0OIWO24"
   },
   "outputs": [],
   "source": [
    "train ['denoised'] = denoised"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 514
    },
    "id": "WerkqFG2tW8Q",
    "outputId": "542de60f-c37b-4d15-9c31-0d977e69a25f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x23f26cd8a00>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#plotting the actual stock price data and the denoised data\n",
    "plt.figure(figsize=(15, 8))\n",
    "plt.title('Training data')\n",
    "plt.plot(train['Date'], train['Close'])\n",
    "plt.plot(train['Date'], denoised)\n",
    "plt.xlabel('Date')\n",
    "plt.ylabel('Price ($)')\n",
    "plt.legend(['Actual data', 'Denoised data'], loc='best')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2hjdRXf16kLW"
   },
   "source": [
    "# Building ANN Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "id": "ybkAdAuzJyiC"
   },
   "outputs": [],
   "source": [
    "train = pd.DataFrame(train['denoised'])\n",
    "test_df = pd.DataFrame(test)\n",
    "test_df = test_df.reset_index()\n",
    "test = pd.DataFrame(test_df['Close'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "zigL21k-bC12"
   },
   "outputs": [],
   "source": [
    "#Feature Scaling\n",
    "sc = MinMaxScaler(feature_range = (0, 1))\n",
    "train_scaled = sc.fit_transform(train.values.reshape(-1,1))\n",
    "test_scaled = sc.fit_transform(test.values.reshape(-1,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "id": "v9C1hPQScjeh"
   },
   "outputs": [],
   "source": [
    "#dividing each of training and testing data into input and output data for model training and testing\n",
    "\n",
    "window_size = 60\n",
    "\n",
    "X_train, y_train = [], []\n",
    "\n",
    "for i in range(len(train_scaled)-window_size):\n",
    "  a = train_scaled[i:(i+window_size), 0]\n",
    "  X_train.append(a)\n",
    "  y_train.append(train_scaled[i+window_size, 0])\n",
    "\n",
    "X_train = np.array(X_train)\n",
    "y_train = np.array(y_train)\n",
    "\n",
    "X_test, y_test = [], []\n",
    "\n",
    "for i in range(len(test)-window_size):\n",
    "  a = test_scaled[i:(i+window_size), 0]\n",
    "  X_test.append(a)\n",
    "  y_test.append(test_scaled[i+window_size, 0])\n",
    "\n",
    "X_test = np.array(X_test)\n",
    "y_test = np.array(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "id": "MY2xAbNze-8F"
   },
   "outputs": [],
   "source": [
    "#reshaping\n",
    "X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)\n",
    "X_test = X_test.reshape(X_test.shape[0], X_test.shape[1], 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "id": "PW1uP2mlNYX3"
   },
   "outputs": [],
   "source": [
    "#initiate hyperparameter values\n",
    "batch = 1\n",
    "epochs = 15\n",
    "neuron = 40"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "uCIPPrCR-FCt",
    "outputId": "f17ac6f7-9146-4b9e-e9a2-7c143a25fbe0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " lstm (LSTM)                 (None, 60, 60)            14880     \n",
      "                                                                 \n",
      " lstm_1 (LSTM)               (None, 40)                16160     \n",
      "                                                                 \n",
      " dense (Dense)               (None, 1)                 41        \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 31,081\n",
      "Trainable params: 31,081\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "#building ANN model\n",
    "model = keras.Sequential()\n",
    "model.add(layers.LSTM(window_size, return_sequences=True, input_shape=(window_size, 1)))\n",
    "model.add(layers.LSTM(neuron, return_sequences=False))\n",
    "model.add(layers.Dense(1))\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "raQV-BjK-NRU",
    "outputId": "cae5ac41-3728-4c3a-a9b3-550ec524b77d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/15\n",
      "345/345 [==============================] - 17s 34ms/step - loss: 0.0086\n",
      "Epoch 2/15\n",
      "345/345 [==============================] - 9s 27ms/step - loss: 0.0028\n",
      "Epoch 3/15\n",
      "345/345 [==============================] - 12s 34ms/step - loss: 0.0023\n",
      "Epoch 4/15\n",
      "345/345 [==============================] - 10s 28ms/step - loss: 0.0012\n",
      "Epoch 5/15\n",
      "345/345 [==============================] - 10s 30ms/step - loss: 0.0015\n",
      "Epoch 6/15\n",
      "345/345 [==============================] - 11s 32ms/step - loss: 9.3110e-04\n",
      "Epoch 7/15\n",
      "345/345 [==============================] - 10s 30ms/step - loss: 0.0010\n",
      "Epoch 8/15\n",
      "345/345 [==============================] - 9s 27ms/step - loss: 8.4576e-04\n",
      "Epoch 9/15\n",
      "345/345 [==============================] - 11s 32ms/step - loss: 7.0237e-04\n",
      "Epoch 10/15\n",
      "345/345 [==============================] - 11s 32ms/step - loss: 5.5496e-04\n",
      "Epoch 11/15\n",
      "345/345 [==============================] - 10s 30ms/step - loss: 4.8921e-04\n",
      "Epoch 12/15\n",
      "345/345 [==============================] - 10s 28ms/step - loss: 4.1993e-04\n",
      "Epoch 13/15\n",
      "345/345 [==============================] - 9s 26ms/step - loss: 3.5672e-04\n",
      "Epoch 14/15\n",
      "345/345 [==============================] - 11s 32ms/step - loss: 4.1915e-04\n",
      "Epoch 15/15\n",
      "345/345 [==============================] - 9s 27ms/step - loss: 3.2413e-04\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x23f28197eb0>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#training model\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "model.fit(X_train, y_train, batch_size=batch, epochs=epochs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "lNVYAqlCoRY-",
    "outputId": "19ab4d84-741a-4df1-f27a-30d605c96f64"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2/2 [==============================] - 1s 16ms/step\n"
     ]
    }
   ],
   "source": [
    "pred = model.predict(X_test)\n",
    "pred = sc.inverse_transform(pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "id": "ueysomcIJK4S"
   },
   "outputs": [],
   "source": [
    "y_test = y_test.reshape(len(y_test), 1)\n",
    "y_test = sc.inverse_transform(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "gmoJzGikr7_L",
    "outputId": "e3f8ec47-27dd-41d3-e6a4-49545e3c218d"
   },
   "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>Date</th>\n",
       "      <th>Close</th>\n",
       "      <th>predictions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>2022-02-02</td>\n",
       "      <td>175.839996</td>\n",
       "      <td>176.970062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>2022-02-03</td>\n",
       "      <td>172.899994</td>\n",
       "      <td>176.031036</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>2022-02-04</td>\n",
       "      <td>172.389999</td>\n",
       "      <td>172.494308</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>2022-02-07</td>\n",
       "      <td>171.660004</td>\n",
       "      <td>172.236557</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>2022-02-08</td>\n",
       "      <td>174.830002</td>\n",
       "      <td>172.527161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>2022-02-09</td>\n",
       "      <td>176.279999</td>\n",
       "      <td>176.650452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>2022-02-10</td>\n",
       "      <td>172.119995</td>\n",
       "      <td>178.732452</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>2022-02-11</td>\n",
       "      <td>168.639999</td>\n",
       "      <td>172.515045</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>2022-02-14</td>\n",
       "      <td>168.880005</td>\n",
       "      <td>167.564743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>2022-02-15</td>\n",
       "      <td>172.789993</td>\n",
       "      <td>168.637161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>2022-02-16</td>\n",
       "      <td>172.550003</td>\n",
       "      <td>174.257965</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>2022-02-17</td>\n",
       "      <td>168.880005</td>\n",
       "      <td>174.599518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>2022-02-18</td>\n",
       "      <td>167.300003</td>\n",
       "      <td>168.930710</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>73</th>\n",
       "      <td>2022-02-22</td>\n",
       "      <td>164.320007</td>\n",
       "      <td>166.416580</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>2022-02-23</td>\n",
       "      <td>160.070007</td>\n",
       "      <td>164.134171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75</th>\n",
       "      <td>2022-02-24</td>\n",
       "      <td>162.740005</td>\n",
       "      <td>160.500183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>2022-02-25</td>\n",
       "      <td>164.850006</td>\n",
       "      <td>162.432663</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77</th>\n",
       "      <td>2022-02-28</td>\n",
       "      <td>165.119995</td>\n",
       "      <td>165.526123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78</th>\n",
       "      <td>2022-03-01</td>\n",
       "      <td>163.199997</td>\n",
       "      <td>166.337067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79</th>\n",
       "      <td>2022-03-02</td>\n",
       "      <td>166.559998</td>\n",
       "      <td>163.996307</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>2022-03-03</td>\n",
       "      <td>166.229996</td>\n",
       "      <td>166.307373</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>81</th>\n",
       "      <td>2022-03-04</td>\n",
       "      <td>163.169998</td>\n",
       "      <td>166.967865</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>2022-03-07</td>\n",
       "      <td>159.300003</td>\n",
       "      <td>163.780075</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>2022-03-08</td>\n",
       "      <td>157.440002</td>\n",
       "      <td>159.747192</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84</th>\n",
       "      <td>2022-03-09</td>\n",
       "      <td>162.949997</td>\n",
       "      <td>157.973312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>2022-03-10</td>\n",
       "      <td>158.520004</td>\n",
       "      <td>162.240585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>86</th>\n",
       "      <td>2022-03-11</td>\n",
       "      <td>154.729996</td>\n",
       "      <td>160.707809</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87</th>\n",
       "      <td>2022-03-14</td>\n",
       "      <td>150.619995</td>\n",
       "      <td>156.862701</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>88</th>\n",
       "      <td>2022-03-15</td>\n",
       "      <td>155.089996</td>\n",
       "      <td>153.418106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>89</th>\n",
       "      <td>2022-03-16</td>\n",
       "      <td>159.589996</td>\n",
       "      <td>154.729813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>90</th>\n",
       "      <td>2022-03-17</td>\n",
       "      <td>160.619995</td>\n",
       "      <td>158.726212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>91</th>\n",
       "      <td>2022-03-18</td>\n",
       "      <td>163.979996</td>\n",
       "      <td>161.557693</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>2022-03-21</td>\n",
       "      <td>165.380005</td>\n",
       "      <td>164.682297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>93</th>\n",
       "      <td>2022-03-22</td>\n",
       "      <td>168.820007</td>\n",
       "      <td>166.374756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94</th>\n",
       "      <td>2022-03-23</td>\n",
       "      <td>170.210007</td>\n",
       "      <td>169.451279</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>2022-03-24</td>\n",
       "      <td>174.070007</td>\n",
       "      <td>171.264160</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>2022-03-25</td>\n",
       "      <td>174.720001</td>\n",
       "      <td>175.301163</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>2022-03-28</td>\n",
       "      <td>175.600006</td>\n",
       "      <td>176.296478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>2022-03-29</td>\n",
       "      <td>178.960007</td>\n",
       "      <td>176.603806</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>2022-03-30</td>\n",
       "      <td>177.770004</td>\n",
       "      <td>180.680756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>2022-03-31</td>\n",
       "      <td>174.610001</td>\n",
       "      <td>179.269791</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Date       Close  predictions\n",
       "60  2022-02-02  175.839996   176.970062\n",
       "61  2022-02-03  172.899994   176.031036\n",
       "62  2022-02-04  172.389999   172.494308\n",
       "63  2022-02-07  171.660004   172.236557\n",
       "64  2022-02-08  174.830002   172.527161\n",
       "65  2022-02-09  176.279999   176.650452\n",
       "66  2022-02-10  172.119995   178.732452\n",
       "67  2022-02-11  168.639999   172.515045\n",
       "68  2022-02-14  168.880005   167.564743\n",
       "69  2022-02-15  172.789993   168.637161\n",
       "70  2022-02-16  172.550003   174.257965\n",
       "71  2022-02-17  168.880005   174.599518\n",
       "72  2022-02-18  167.300003   168.930710\n",
       "73  2022-02-22  164.320007   166.416580\n",
       "74  2022-02-23  160.070007   164.134171\n",
       "75  2022-02-24  162.740005   160.500183\n",
       "76  2022-02-25  164.850006   162.432663\n",
       "77  2022-02-28  165.119995   165.526123\n",
       "78  2022-03-01  163.199997   166.337067\n",
       "79  2022-03-02  166.559998   163.996307\n",
       "80  2022-03-03  166.229996   166.307373\n",
       "81  2022-03-04  163.169998   166.967865\n",
       "82  2022-03-07  159.300003   163.780075\n",
       "83  2022-03-08  157.440002   159.747192\n",
       "84  2022-03-09  162.949997   157.973312\n",
       "85  2022-03-10  158.520004   162.240585\n",
       "86  2022-03-11  154.729996   160.707809\n",
       "87  2022-03-14  150.619995   156.862701\n",
       "88  2022-03-15  155.089996   153.418106\n",
       "89  2022-03-16  159.589996   154.729813\n",
       "90  2022-03-17  160.619995   158.726212\n",
       "91  2022-03-18  163.979996   161.557693\n",
       "92  2022-03-21  165.380005   164.682297\n",
       "93  2022-03-22  168.820007   166.374756\n",
       "94  2022-03-23  170.210007   169.451279\n",
       "95  2022-03-24  174.070007   171.264160\n",
       "96  2022-03-25  174.720001   175.301163\n",
       "97  2022-03-28  175.600006   176.296478\n",
       "98  2022-03-29  178.960007   176.603806\n",
       "99  2022-03-30  177.770004   180.680756\n",
       "100 2022-03-31  174.610001   179.269791"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict = test_df[window_size:].copy()\n",
    "predict['predictions'] = pred\n",
    "predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>Date</th>\n",
       "      <th>Close</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2021-11-05</td>\n",
       "      <td>151.279999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2021-11-08</td>\n",
       "      <td>150.440002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2021-11-09</td>\n",
       "      <td>150.809998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2021-11-10</td>\n",
       "      <td>147.919998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2021-11-11</td>\n",
       "      <td>147.869995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>2022-03-25</td>\n",
       "      <td>174.720001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>2022-03-28</td>\n",
       "      <td>175.600006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>2022-03-29</td>\n",
       "      <td>178.960007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>2022-03-30</td>\n",
       "      <td>177.770004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>2022-03-31</td>\n",
       "      <td>174.610001</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>101 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          Date       Close\n",
       "0   2021-11-05  151.279999\n",
       "1   2021-11-08  150.440002\n",
       "2   2021-11-09  150.809998\n",
       "3   2021-11-10  147.919998\n",
       "4   2021-11-11  147.869995\n",
       "..         ...         ...\n",
       "96  2022-03-25  174.720001\n",
       "97  2022-03-28  175.600006\n",
       "98  2022-03-29  178.960007\n",
       "99  2022-03-30  177.770004\n",
       "100 2022-03-31  174.610001\n",
       "\n",
       "[101 rows x 2 columns]"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "id": "nE-v9zvKAT7T"
   },
   "outputs": [],
   "source": [
    "predict=predict.set_index('Date')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 497
    },
    "id": "msysoH-Qg3lZ",
    "outputId": "4d3eb7a4-085f-4d49-8071-46eeae9a8c77"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#plotting\n",
    "plt.figure(figsize=(16,8))\n",
    "plt.xlabel('Tanggal')\n",
    "plt.ylabel('Harga ($)')\n",
    "plt.plot(predict['Close'])\n",
    "plt.plot(predict['predictions'])\n",
    "plt.legend(['Actual', 'Prediction'], loc='best')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "id": "4LBPzsuWi3cC"
   },
   "outputs": [],
   "source": [
    "#making dataframe to save the error data\n",
    "errors = pd.DataFrame(index=['MSE','RMSE', 'MAE', 'MAPE', 'R2'], columns=['Value'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "id": "AAP-LCH_hprD"
   },
   "outputs": [],
   "source": [
    "#calculating errors\n",
    "mse = mean_squared_error(y_test, pred)\n",
    "errors['Value']['MSE'] = mse\n",
    "\n",
    "rmse = np.sqrt(mean_squared_error(y_test, pred))\n",
    "errors['Value']['RMSE'] = rmse\n",
    "\n",
    "mae = mean_absolute_error(y_test, pred)\n",
    "errors['Value']['MAE'] = mae\n",
    "\n",
    "mape = mean_absolute_percentage_error(y_test, pred)\n",
    "errors['Value']['MAPE'] = mape\n",
    "\n",
    "r2 = r2_score(y_test, pred)\n",
    "errors['Value']['R2'] = r2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "9BjiC7p49IrN",
    "outputId": "5cf0ac10-8fa2-47d1-f58f-5cc1aae7327b"
   },
   "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>Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>MSE</th>\n",
       "      <td>10.2855</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RMSE</th>\n",
       "      <td>3.20711</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MAE</th>\n",
       "      <td>2.68035</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MAPE</th>\n",
       "      <td>0.0162283</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>R2</th>\n",
       "      <td>0.78294</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Value\n",
       "MSE     10.2855\n",
       "RMSE    3.20711\n",
       "MAE     2.68035\n",
       "MAPE  0.0162283\n",
       "R2      0.78294"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "errors"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}