questionso-Copy2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 Physical GPUs, 1 Logical GPUs\n",
      "1.47683495e-05\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# 0. 사용할 패키지 불러오기\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "# from keras.models import Sequential\n",
    "# from keras.layers import Dense, LSTM, Dropout, Conv2D, Reshape, TimeDistributed, Flatten, Conv1D,ConvLSTM2D, MaxPooling1D, BatchNormalization, Bidirectional, CuDNNLSTM\n",
    "# from keras.layers.core import Dense, Activation, Dropout\n",
    "# from keras import optimizers\n",
    "from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
    "from sklearn.metrics import mean_squared_error\n",
    "import tensorflow as tf\n",
    "import matplotlib.pyplot as plt\n",
    "# from keras import backend as K\n",
    "from keras.models import load_model\n",
    "import json\n",
    "import requests\n",
    "import os\n",
    "import pandas as pd\n",
    "import time\n",
    "import sys\n",
    "from tensorflow.keras import layers, optimizers, Sequential, metrics\n",
    "import datetime\n",
    "import tensorflow as tf\n",
    "\n",
    "gpus = tf.config.experimental.list_physical_devices('GPU')\n",
    "if gpus:\n",
    "  try:\n",
    "    # Currently, memory growth needs to be the same across GPUs\n",
    "    for gpu in gpus:\n",
    "      tf.config.experimental.set_memory_growth(gpu, True)\n",
    "    logical_gpus = tf.config.experimental.list_logical_devices('GPU')\n",
    "    print(len(gpus), \"Physical GPUs,\", len(logical_gpus), \"Logical GPUs\")\n",
    "  except RuntimeError as e:\n",
    "    # Memory growth must be set before GPUs have been initialized\n",
    "    print(e)\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "def create_dataset(signal_data, look_back=1):\n",
    "    dataX, dataY = [], []\n",
    "    for i in range(len(signal_data) - look_back):\n",
    "        dataX.append(signal_data[i:(i + look_back), :])\n",
    "        dataY.append(signal_data[i + look_back, -1])\n",
    "    return np.array(dataX), np.array(dataY)\n",
    "\n",
    "\n",
    "look_back = 20\n",
    "forecast = 20\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "stock = '모나미.csv'\n",
    "\n",
    "\n",
    "df = pd.read_csv(stock) #this file is stock data including 'Close' value\n",
    "signal_data = df[[\"close\"]].values.astype('float32')\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "signal_data = scaler.fit_transform(signal_data)\n",
    "\n",
    "train_size = int(len(signal_data) * 0.80)\n",
    "test_size = len(signal_data) - train_size\n",
    "\n",
    "train = signal_data[0:train_size]\n",
    "test = signal_data[train_size: len(signal_data)]\n",
    "\n",
    "x_train, y_train = create_dataset(train, look_back)\n",
    "x_test, y_test = create_dataset(test, look_back)\n",
    "\n",
    "\n",
    "# K.clear_session()\n",
    "\n",
    "model = tf.keras.Sequential([\n",
    "    layers.LSTM(10, input_shape=(None, x_train.shape[2])),\n",
    "    layers.Dense(1)\n",
    "])\n",
    "\n",
    "# callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5, verbose=2)\n",
    "# model.compile(optimizer=optimizers.adam(lr=0.01), metrics='mse')\n",
    "\n",
    "model.compile(optimizer='adam', loss='mae')\n",
    "\n",
    "history = model.fit(x_train, y_train, epochs=100, batch_size=64, verbose=0)\n",
    "\n",
    "p = model.predict(x_test)\n",
    "mse = mean_squared_error(y_test, p)\n",
    "print(mse)\n",
    "print()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(20, 1)"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test[-1].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "a = model.predict(x_test[-1].reshape(-1, 20, 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.00083278],\n",
       "       [0.0011277 ],\n",
       "       [0.00196161],\n",
       "       [0.00167912],\n",
       "       [0.00128702],\n",
       "       [0.00188025],\n",
       "       [0.00144194],\n",
       "       [0.00306252],\n",
       "       [0.00356784],\n",
       "       [0.00438084],\n",
       "       [0.00543283],\n",
       "       [0.01982058],\n",
       "       [0.00246116],\n",
       "       [0.00160318],\n",
       "       [0.00106216],\n",
       "       [0.00115244],\n",
       "       [0.00092543],\n",
       "       [0.00170635],\n",
       "       [0.00075933],\n",
       "       [0.00456051]], dtype=float32)"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test[-2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.0011277 ],\n",
       "       [0.00196161],\n",
       "       [0.00167912],\n",
       "       [0.00128702],\n",
       "       [0.00188025],\n",
       "       [0.00144194],\n",
       "       [0.00306252],\n",
       "       [0.00356784],\n",
       "       [0.00438084],\n",
       "       [0.00543283],\n",
       "       [0.01982058],\n",
       "       [0.00246116],\n",
       "       [0.00160318],\n",
       "       [0.00106216],\n",
       "       [0.00115244],\n",
       "       [0.00092543],\n",
       "       [0.00170635],\n",
       "       [0.00075933],\n",
       "       [0.00456051],\n",
       "       [0.00073334]], dtype=float32)"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test[-1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "맨 끝에다가 저장, 맨앞은 지워짐."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.00139093]], dtype=float32)"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [],
   "source": [
    "plist = x_test[-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "numpy.ndarray"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(plist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.0011277 ],\n",
       "       [0.00196161],\n",
       "       [0.00167912],\n",
       "       [0.00128702],\n",
       "       [0.00188025],\n",
       "       [0.00144194],\n",
       "       [0.00306252],\n",
       "       [0.00356784],\n",
       "       [0.00438084],\n",
       "       [0.00543283],\n",
       "       [0.01982058],\n",
       "       [0.00246116],\n",
       "       [0.00160318],\n",
       "       [0.00106216],\n",
       "       [0.00115244],\n",
       "       [0.00092543],\n",
       "       [0.00170635],\n",
       "       [0.00075933],\n",
       "       [0.00456051],\n",
       "       [0.00073334]], dtype=float32)"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [],
   "source": [
    "# plist = np.delete(plist, 0)\n",
    "# plist = np.append(plist, a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.0011277 ],\n",
       "       [0.00196161],\n",
       "       [0.00167912],\n",
       "       [0.00128702],\n",
       "       [0.00188025],\n",
       "       [0.00144194],\n",
       "       [0.00306252],\n",
       "       [0.00356784],\n",
       "       [0.00438084],\n",
       "       [0.00543283],\n",
       "       [0.01982058],\n",
       "       [0.00246116],\n",
       "       [0.00160318],\n",
       "       [0.00106216],\n",
       "       [0.00115244],\n",
       "       [0.00092543],\n",
       "       [0.00170635],\n",
       "       [0.00075933],\n",
       "       [0.00456051],\n",
       "       [0.00073334]], dtype=float32)"
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test[-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(20, 1)\n",
      "(20,)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([0.00196161, 0.00167912, 0.00128702, 0.00188025, 0.00144194,\n",
       "       0.00306252, 0.00356784, 0.00438084, 0.00543283, 0.01982058,\n",
       "       0.00246116, 0.00160318, 0.00106216, 0.00115244, 0.00092543,\n",
       "       0.00170635, 0.00075933, 0.00456051, 0.00073334, 0.00139093],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plist = x_test[-1]\n",
    "print(plist.shape)\n",
    "plist = plist[1:]\n",
    "plist = np.insert(plist,19, a)\n",
    "plist.reshape(20, 1)\n",
    "print(plist.shape)\n",
    "plist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(20, 1)"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test[-1].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(20,)"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plist.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.0012325]], dtype=float32)"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.predict(plist.reshape(-1,20,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [],
   "source": [
    "plist = x_test[-1]\n",
    "for i in range(20):\n",
    "    temp = model.predict(plist.reshape(-1,20,1))\n",
    "    plist = plist[1:]\n",
    "    plist = np.insert(plist,19, temp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1.39092910e-03,  1.23249786e-03,  1.07771973e-03,  9.26735636e-04,\n",
       "        7.79195107e-04,  6.35388133e-04,  4.95451852e-04,  3.60288483e-04,\n",
       "        2.30436068e-04,  1.06500396e-04, -1.09285247e-05, -1.16587653e-04,\n",
       "       -2.16844521e-04, -3.12037242e-04, -4.02977574e-04, -4.90083476e-04,\n",
       "       -5.73731260e-04, -6.53820462e-04, -7.30780768e-04, -8.03303090e-04],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1e28c3ccc08>]"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(plist)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1e267f90d88>]"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x_test[-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1e23c421488>]"
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(y_test[-20:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [],
   "source": [
    "plist = x_test[-1]\n",
    "for i in range(100):\n",
    "    temp = model.predict(plist.reshape(-1,20,1))\n",
    "    plist = plist[1:]\n",
    "    plist = np.insert(plist,19, temp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1e27e9918c8>]"
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(plist) #100번 돌리고 난 뒤에는 plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}