Created using Colaboratory

stock_predictor.ipynb

@@ -4,7 +4,10 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPcuRkmq64yTPWXIBG7lLf0",
+      "collapsed_sections": [
+        "Z3N2WMYNV-qX"
+      ],
+      "authorship_tag": "ABX9TyOuk8MIfThoeWnRbBQlPf+h",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -40,9 +43,9 @@
           "base_uri": "https://localhost:8080/"
         },
         "id": "Xr3Qozgfktoc",
-        "outputId": "28119a16-7e41-437a-969b-3713f019548e"
+        "outputId": "e80033fb-a41f-438f-fc90-60bc0317d5d3"
       },
-      "execution_count": 1,
+      "execution_count": 2,
       "outputs": [
         {
           "output_type": "stream",
@@ -54,157 +57,409 @@
         }
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "id": "e8SQqogMQYLh"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "import pandas as pd\n",
+        "import pandas_datareader as web\n",
+        "import datetime as dt\n",
+        "import yfinance as yfin\n",
+        "import tensorflow as tf\n",
+        "import os\n",
+        "import re\n",
+        "\n",
+        "from sklearn.preprocessing import MinMaxScaler\n",
+        "from tensorflow.keras.models import Sequential\n",
+        "from tensorflow.keras.layers import Dense, Dropout, LSTM\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Get Data"
+      ],
+      "metadata": {
+        "id": "5vO8pty3VwkG"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Select a company for now\n",
+        "ticker = 'AAPL'\n",
+        "\n",
+        "start = dt.datetime(2013,1,1)\n",
+        "end = dt.datetime(2023,4,5)"
+      ],
+      "metadata": {
+        "id": "O6dtJpJwS5Eg"
+      },
+      "execution_count": 93,
+      "outputs": []
+    },
     {
       "cell_type": "code",
       "source": [
-        "# install dotenv\n",
-        "!pip install python-dotenv"
+        "yfin.pdr_override()\n",
+        "data = web.data.get_data_yahoo(ticker, start, end)\n"
       ],
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "id": "E0itUkoVeKYn",
-        "outputId": "bc2a7293-a9f0-4f4d-d42f-f7ecfab7e5c5"
+        "id": "LwPyk8Uh-Zz_",
+        "outputId": "63953807-ca2e-4e18-c571-a6bcc4f8db5d"
       },
-      "execution_count": 2,
+      "execution_count": 5,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
-            "Collecting python-dotenv\n",
-            "  Downloading python_dotenv-1.0.0-py3-none-any.whl (19 kB)\n",
-            "Installing collected packages: python-dotenv\n",
-            "Successfully installed python-dotenv-1.0.0\n"
+            "\r[*********************100%***********************]  1 of 1 completed\n"
           ]
         }
       ]
     },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Preprocess_data"
+      ],
+      "metadata": {
+        "id": "SSuS9OONV5-a"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def normalize_data(data, relative_to_previous=True, scaler=None):\n",
+        "  def substract_to_values(data, value):\n",
+        "    df_copy = pd.DataFrame.copy(data)\n",
+        "    df_copy[['Open', 'High', 'Low', 'Close', 'Adj Close']] = df_copy[['Open', 'High', 'Low', 'Close', 'Adj Close']] - value\n",
+        "    return df_copy\n",
+        "  if relative_to_previous:\n",
+        "    the_data = pd.DataFrame(substract_to_values(data.iloc[0], data.iloc[0]['Open'])).T\n",
+        "    # the_data = substract_to_values(data.iloc[0], data.iloc[0]['Open']).to_frame().T # This is the same as the previous line\n",
+        "    for i in range(1,len(data)):\n",
+        "      the_data = pd.concat((the_data, substract_to_values(data.iloc[i], data.iloc[i-1]['Close']).to_frame().T))\n",
+        "  else:\n",
+        "    the_data = pd.DataFrame.copy(data)\n",
+        "  \n",
+        "  if scaler is None:\n",
+        "    # Create the scaler\n",
+        "    values = the_data.values\n",
+        "    # print('values')\n",
+        "    # print(values)\n",
+        "    max_value = np.max(values[:,:-1])\n",
+        "    # print(max_value)\n",
+        "    min_value = np.min(values[:,:-1])\n",
+        "    # print(min_value)\n",
+        "    max_volume = np.max(values[:,-1])\n",
+        "    min_volume = np.min(values[:,-1])\n",
+        "    # print(max_volume, min_volume)\n",
+        "    def scaler(data):\n",
+        "      values = data.values\n",
+        "      # print(values)\n",
+        "      values[:,:-1] = (values[:,:-1] - min_value) / (max_value-min_value) * 2 - 1\n",
+        "      values[:,-1] = (values[:,-1] - min_volume) / (max_volume-min_volume) * 2 - 1\n",
+        "      # print(values)\n",
+        "      return data\n",
+        "    def anti_scaler(values):\n",
+        "      decoded_values = (values + 1) * (max_value-min_value) / 2 + min_value  \n",
+        "      return decoded_values\n",
+        "  \n",
+        "  normalized_data = scaler(the_data)\n",
+        "\n",
+        "  return normalized_data, scaler, anti_scaler\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "v9RoqzBvtrOb"
+      },
+      "execution_count": 111,
+      "outputs": []
+    },
     {
       "cell_type": "code",
       "source": [
-        "# install polygon client\n",
-        "!pip install polygon-api-client"
+        "norm_data, the_scaler, the_decoder = normalize_data(data, relative_to_previous=True)\n",
+        "#todo: save the_scaler somehow to use in new runtimes"
+      ],
+      "metadata": {
+        "id": "-kgo__Q3hw1_"
+      },
+      "execution_count": 112,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "len(norm_data)"
       ],
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "id": "2bylenpXc1oB",
-        "outputId": "74b2587b-2b58-42a1-f5bf-c3866c13b8a1"
+        "id": "A1L8giqcsutX",
+        "outputId": "0aaf515b-3835-432c-b882-c2111a221ed4"
       },
-      "execution_count": 3,
+      "execution_count": 41,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "2583"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 41
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "prediction_days = 100\n",
+        "\n",
+        "x_train_list = []\n",
+        "y_train_list = []\n",
+        "\n",
+        "for i in range(prediction_days, len(norm_data)):\n",
+        "  x_train_list.append(norm_data[i-prediction_days:i])\n",
+        "  y_train_list.append(norm_data.iloc[i].values[0:4])\n",
+        "\n",
+        "x_train = np.array(x_train_list)\n",
+        "y_train = np.array(y_train_list)"
+      ],
+      "metadata": {
+        "id": "jMXkRAYFomHM"
+      },
+      "execution_count": 9,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(x_train.shape)\n",
+        "print(y_train.shape)\n",
+        "print(x_train.shape[1:])"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "G7oMd1fRyOYt",
+        "outputId": "2094c403-096d-4f3a-9b15-bae0fbb7bf11"
+      },
+      "execution_count": 10,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
-            "Collecting polygon-api-client\n",
-            "  Downloading polygon_api_client-1.8.5-py3-none-any.whl (38 kB)\n",
-            "Collecting websockets<11.0,>=10.3\n",
-            "  Downloading websockets-10.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (106 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.5/106.5 KB\u001b[0m \u001b[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: urllib3<2.0.0,>=1.26.9 in /usr/local/lib/python3.9/dist-packages (from polygon-api-client) (1.26.15)\n",
-            "Requirement already satisfied: certifi<2023.0.0,>=2022.5.18 in /usr/local/lib/python3.9/dist-packages (from polygon-api-client) (2022.12.7)\n",
-            "Installing collected packages: websockets, polygon-api-client\n",
-            "Successfully installed polygon-api-client-1.8.5 websockets-10.4\n"
+            "(2483, 100, 6)\n",
+            "(2483, 4)\n",
+            "(100, 6)\n"
           ]
         }
       ]
     },
     {
-      "cell_type": "code",
-      "execution_count": 4,
+      "cell_type": "markdown",
+      "source": [
+        "# Model"
+      ],
       "metadata": {
-        "id": "e8SQqogMQYLh"
-      },
-      "outputs": [],
+        "id": "Z3N2WMYNV-qX"
+      }
+    },
+    {
+      "cell_type": "markdown",
       "source": [
-        "import numpy as np\n",
-        "import matplotlib.pyplot as plt\n",
-        "import pandas as pd\n",
-        "import pandas_datareader as web\n",
-        "import datetime as dt\n",
-        "import yfinance as yfin\n",
+        "## Create Model"
+      ],
+      "metadata": {
+        "id": "emDyvzVUp5KJ"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def create_model():\n",
+        "  model = Sequential()\n",
+        "  # model.add(LSTM(units=112, return_sequences=True, input_shape=(x_train.shape[1:])))\n",
+        "  model.add(LSTM(units=112, return_sequences=True, input_shape=(None,x_train.shape[-1],)))\n",
+        "  model.add(Dropout(0.2))\n",
+        "  model.add(LSTM(units=112, return_sequences=True))\n",
+        "  model.add(Dropout(0.2))\n",
+        "  model.add(LSTM(units=50))\n",
+        "  model.add(Dropout(0.2))\n",
+        "  model.add(Dense(units=4))\n",
+        "  return model\n",
         "\n",
-        "from sklearn.preprocessing import MinMaxScaler\n",
-        "from tensorflow.keras.models import Sequential\n",
-        "from tensorflow.keras.layers import Dense, Dropout, LSTM\n",
-        "from dotenv import dotenv_values\n",
-        "from polygon import RESTClient\n"
+        "model = create_model()\n",
+        "print(model.summary())"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "GXhYAKzXVfku",
+        "outputId": "c54da788-6e82-4679-df1f-d3e89a20d228"
+      },
+      "execution_count": 66,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Model: \"sequential_1\"\n",
+            "_________________________________________________________________\n",
+            " Layer (type)                Output Shape              Param #   \n",
+            "=================================================================\n",
+            " lstm_3 (LSTM)               (None, None, 112)         53312     \n",
+            "                                                                 \n",
+            " dropout_3 (Dropout)         (None, None, 112)         0         \n",
+            "                                                                 \n",
+            " lstm_4 (LSTM)               (None, None, 112)         100800    \n",
+            "                                                                 \n",
+            " dropout_4 (Dropout)         (None, None, 112)         0         \n",
+            "                                                                 \n",
+            " lstm_5 (LSTM)               (None, 50)                32600     \n",
+            "                                                                 \n",
+            " dropout_5 (Dropout)         (None, 50)                0         \n",
+            "                                                                 \n",
+            " dense_1 (Dense)             (None, 4)                 204       \n",
+            "                                                                 \n",
+            "=================================================================\n",
+            "Total params: 186,916\n",
+            "Trainable params: 186,916\n",
+            "Non-trainable params: 0\n",
+            "_________________________________________________________________\n",
+            "None\n"
+          ]
+        }
       ]
     },
     {
       "cell_type": "code",
       "source": [
-        "# geting poligon api key\n",
-        "config = dotenv_values(\"env_stock_predictor\")\n",
-        "POLYGON_API_KEY = config['POLYGON_API_KEY']"
+        "model.compile(optimizer='adam', loss='mean_squared_error')"
       ],
       "metadata": {
-        "id": "MwIQIS6GeSJr"
+        "id": "ZhoWj_XeXQws"
       },
-      "execution_count": 18,
+      "execution_count": 12,
       "outputs": []
     },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Create checkpoint callback"
+      ],
+      "metadata": {
+        "id": "XU0vc4n8p92L"
+      }
+    },
     {
       "cell_type": "code",
       "source": [
-        "# Select a company for now\n",
-        "ticker = 'AAPL'\n",
-        "\n",
-        "data_sources = {'pandas': 'pandas-datareader',\n",
-        "                'polygon':'polygon'}\n",
-        "source = data_sources['polygon']\n",
-        "# source = data_sources['pandas']\n",
+        "# Directory where the checkpoints will be saved\n",
+        "checkpoint_dir = './training_checkpoints_'+dt.datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
+        "# Name of the checkpoint files\n",
+        "checkpoint_prefix = os.path.join(checkpoint_dir, \"ckpt_epoch{epoch}_loss{loss}\")\n",
         "\n",
-        "start = dt.datetime(2013,1,1)\n",
-        "end = dt.date.today()"
+        "checkpoint_callback=tf.keras.callbacks.ModelCheckpoint(\n",
+        "    filepath=checkpoint_prefix,\n",
+        "    save_weights_only=True)"
       ],
       "metadata": {
-        "id": "O6dtJpJwS5Eg"
+        "id": "M5MBAB1-qCZr"
       },
-      "execution_count": 19,
+      "execution_count": 35,
       "outputs": []
     },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Model Train"
+      ],
+      "metadata": {
+        "id": "65QbfffusPoJ"
+      }
+    },
     {
       "cell_type": "code",
       "source": [
-        "if source == data_sources['pandas']:\n",
-        "  yfin.pdr_override()\n",
-        "  data = web.data.get_data_yahoo(ticker, start, end)\n",
-        "elif source == data_sources['polygon']:\n",
-        "  # using the poligon API\n",
-        "  poligon_client = RESTClient(api_key=POLYGON_API_KEY)\n",
-        "  # bars = poligon_client.get_aggs(ticker=ticker, multiplier=1, timespan=\"day\", from_=\"2023-01-09\", to=\"2023-01-15\")\n",
-        "  # bars = poligon_client.get_aggs(ticker=ticker, multiplier=1, timespan=\"day\", from_=start, to=end)\n",
-        "  bars = poligon_client.get_aggs(ticker=ticker, multiplier=1, timespan=\"hour\", from_=dt.datetime.now() - dt.timedelta(days=5), to=dt.datetime.now())\n",
-        "  print(len(bars))\n",
-        "  for bar in bars[-2:]:\n",
-        "    print(type(bar))\n",
-        "    print(bar)\n",
-        "    print(bar.timestamp)\n",
-        "    print(dt.date.fromtimestamp(bar.timestamp/1000))\n",
-        "    print(dt.datetime.fromtimestamp(bar.timestamp/1000))"
-      ],
-      "metadata": {
-        "id": "LwPyk8Uh-Zz_"
+        "print(x_train.shape)\n",
+        "print(y_train.shape)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "HDT9XPXHvqyN",
+        "outputId": "60938333-8afe-4b80-9af3-37bca3d67f83"
       },
-      "execution_count": 36,
-      "outputs": []
+      "execution_count": 15,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "(2483, 100, 6)\n",
+            "(2483, 4)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y_train[-2]"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "F1wZkJMh3XNH",
+        "outputId": "37a023db-0727-434a-85be-141c3c377907"
+      },
+      "execution_count": 40,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([ 0.02002301,  0.0391905 , -0.09898045, -0.05744885])"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 40
+        }
+      ]
     },
     {
       "cell_type": "code",
-      "source": [],
+      "source": [
+        "model.fit(x_train, y_train, epochs=25, batch_size=32, callbacks=[checkpoint_callback])\n"
+      ],
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
-        "id": "IX_o3NTggblq",
-        "outputId": "27d4d43b-e063-4651-db16-f5ecf819860b"
+        "id": "9Ccc_Ej2TmYO",
+        "outputId": "235efc3b-616b-4e57-fb87-07efcb377e8e"
       },
       "execution_count": 37,
       "outputs": [
@@ -212,46 +467,99 @@
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "41\n",
-            "<class 'polygon.rest.models.aggs.Agg'>\n",
-            "Agg(open=165.57, high=165.68, low=165.53, close=165.64, volume=11712, vwap=165.6067, timestamp=1680645600000, transactions=258, otc=None)\n",
-            "1680645600000\n",
-            "2023-04-04\n",
-            "2023-04-04 22:00:00\n",
-            "<class 'polygon.rest.models.aggs.Agg'>\n",
-            "Agg(open=165.6, high=165.85, low=165.6, close=165.79, volume=28951, vwap=165.7385, timestamp=1680649200000, transactions=533, otc=None)\n",
-            "1680649200000\n",
-            "2023-04-04\n",
-            "2023-04-04 23:00:00\n"
+            "Epoch 1/25\n",
+            "78/78 [==============================] - 31s 395ms/step - loss: 0.0117\n",
+            "Epoch 2/25\n",
+            "78/78 [==============================] - 31s 394ms/step - loss: 0.0111\n",
+            "Epoch 3/25\n",
+            "78/78 [==============================] - 33s 429ms/step - loss: 0.0109\n",
+            "Epoch 4/25\n",
+            "78/78 [==============================] - 31s 396ms/step - loss: 0.0109\n",
+            "Epoch 5/25\n",
+            "78/78 [==============================] - 31s 398ms/step - loss: 0.0108\n",
+            "Epoch 6/25\n",
+            "78/78 [==============================] - 31s 400ms/step - loss: 0.0108\n",
+            "Epoch 7/25\n",
+            "78/78 [==============================] - 32s 405ms/step - loss: 0.0108\n",
+            "Epoch 8/25\n",
+            "78/78 [==============================] - 31s 394ms/step - loss: 0.0108\n",
+            "Epoch 9/25\n",
+            "78/78 [==============================] - 30s 385ms/step - loss: 0.0108\n",
+            "Epoch 10/25\n",
+            "78/78 [==============================] - 30s 385ms/step - loss: 0.0108\n",
+            "Epoch 11/25\n",
+            "78/78 [==============================] - 29s 373ms/step - loss: 0.0108\n",
+            "Epoch 12/25\n",
+            "78/78 [==============================] - 29s 375ms/step - loss: 0.0107\n",
+            "Epoch 13/25\n",
+            "78/78 [==============================] - 30s 383ms/step - loss: 0.0107\n",
+            "Epoch 14/25\n",
+            "78/78 [==============================] - 30s 388ms/step - loss: 0.0107\n",
+            "Epoch 15/25\n",
+            "78/78 [==============================] - 31s 396ms/step - loss: 0.0108\n",
+            "Epoch 16/25\n",
+            "78/78 [==============================] - 30s 379ms/step - loss: 0.0107\n",
+            "Epoch 17/25\n",
+            "78/78 [==============================] - 30s 386ms/step - loss: 0.0107\n",
+            "Epoch 18/25\n",
+            "78/78 [==============================] - 30s 383ms/step - loss: 0.0108\n",
+            "Epoch 19/25\n",
+            "78/78 [==============================] - 30s 382ms/step - loss: 0.0107\n",
+            "Epoch 20/25\n",
+            "78/78 [==============================] - 31s 397ms/step - loss: 0.0107\n",
+            "Epoch 21/25\n",
+            "78/78 [==============================] - 30s 384ms/step - loss: 0.0107\n",
+            "Epoch 22/25\n",
+            "78/78 [==============================] - 30s 381ms/step - loss: 0.0106\n",
+            "Epoch 23/25\n",
+            "78/78 [==============================] - 30s 380ms/step - loss: 0.0106\n",
+            "Epoch 24/25\n",
+            "78/78 [==============================] - 30s 385ms/step - loss: 0.0107\n",
+            "Epoch 25/25\n",
+            "78/78 [==============================] - 30s 383ms/step - loss: 0.0106\n"
           ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<keras.callbacks.History at 0x7f5203d70cd0>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 37
         }
       ]
     },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Testing a model"
+      ],
+      "metadata": {
+        "id": "dbSKl47vZvpe"
+      }
+    },
     {
       "cell_type": "code",
       "source": [
-        "print(type(spy))\n",
-        "print(spy.head())"
+        "#print trainings directories to pick one\n",
+        "!ls -d training_checkpoints_*/"
       ],
       "metadata": {
         "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 187
+          "base_uri": "https://localhost:8080/"
         },
-        "id": "EMoXLT5vd8Ex",
-        "outputId": "74416af4-da65-4d12-ed3a-27806b8f0965"
+        "id": "59CDDB0i4yTx",
+        "outputId": "497ae253-e3ac-47d0-d066-8e508f55782c"
       },
-      "execution_count": 10,
+      "execution_count": 49,
       "outputs": [
         {
-          "output_type": "error",
-          "ename": "NameError",
-          "evalue": "ignored",
-          "traceback": [
-            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-            "\u001b[0;32m<ipython-input-10-dab045b648a5>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mspy\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mspy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-            "\u001b[0;31mNameError\u001b[0m: name 'spy' is not defined"
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "training_checkpoints_20230406041748/\n"
           ]
         }
       ]
@@ -259,33 +567,390 @@
     {
       "cell_type": "code",
       "source": [
-        "df = web.DataReader('GE', 'yahoo', start='2019-09-10', end='2019-10-09')\n",
-        "print(start)\n",
-        "print(end)"
+        "test_model = create_model()"
       ],
       "metadata": {
-        "id": "THGxnQbSUgvw"
+        "id": "tpmru7nG9kbW"
       },
-      "execution_count": null,
+      "execution_count": 72,
       "outputs": []
     },
     {
       "cell_type": "code",
       "source": [
-        "scaler = MinMaxScaler(feature_range=(0,1))\n",
-        "scaled_data = scaler.fit_transform(data['Close'].values.reshape(-1,1))\n",
-        "prediction_days = 60\n",
+        "checkpoint_dir = 'training_checkpoints_20230406041748'\n",
         "\n",
-        "x_train = []\n",
-        "y_train = []\n",
+        "def load_weights(epoch=None):\n",
+        "  if epoch is None:\n",
+        "    weights_file = tf.train.latest_checkpoint(checkpoint_dir)\n",
+        "  else:\n",
+        "    with os.scandir(checkpoint_dir) as entries:\n",
+        "      for entry in entries:\n",
+        "        if re.search(f'^ckpt_epoch{epoch}_.*\\.index', entry.name):\n",
+        "          weights_file = checkpoint_dir + '/'+ entry.name[:-6]\n",
         "\n",
-        "for x in range()"
+        "  print(weights_file)\n",
+        "  test_model.load_weights(weights_file)\n",
+        "  return test_model\n",
+        "\n",
+        "test_model = load_weights()"
       ],
       "metadata": {
-        "id": "ccV59ukvXaNF"
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wQ0JTXsp4VKF",
+        "outputId": "d4b794c9-7a89-4867-d17c-de1f20b9b607"
       },
-      "execution_count": null,
+      "execution_count": 87,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "training_checkpoints_20230406041748/ckpt_epoch25_loss0.01064301934093237\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "test_start = dt.date.today() - dt.timedelta(days=200)\n",
+        "test_end = dt.date.today()\n",
+        "\n",
+        "yfin.pdr_override()\n",
+        "test_data = web.data.get_data_yahoo(ticker, test_start, test_end)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Mf4q97pfaSCA",
+        "outputId": "4317ef63-be5e-49ca-fdca-1d5760efbba1"
+      },
+      "execution_count": 99,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\r[*********************100%***********************]  1 of 1 completed\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "test_data_norm, _ = normalize_data(test_data, scaler=the_scaler)"
+      ],
+      "metadata": {
+        "id": "xEG2yEdKC8uy"
+      },
+      "execution_count": 100,
       "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(type(test_data_norm))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "mhbqRZ6cDhd6",
+        "outputId": "8b40a738-e143-4920-de03-8e8572f4389a"
+      },
+      "execution_count": 102,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "input_data = np.expand_dims(test_data_norm.values, axis=0)\n",
+        "print(input_data.shape)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "F2bnofchD0xv",
+        "outputId": "0b2261fb-056d-4ec2-a98b-82517d7806f1"
+      },
+      "execution_count": 104,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "(1, 138, 6)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "results = test_model.predict(input_data, batch_size=1)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "AVYFQZnqEqhx",
+        "outputId": "958d1669-c8bc-4eff-bb66-f25eb4dde011"
+      },
+      "execution_count": 105,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "1/1 [==============================] - 1s 1s/step\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(results)\n",
+        "print(the_decoder(results))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "FbdX4ulhExsX",
+        "outputId": "14a763ca-0983-41ec-e88b-da796fa4b51a"
+      },
+      "execution_count": 113,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "[[-0.01962117  0.09634934 -0.10176479 -0.00849891]]\n",
+            "[[-0.06636524  1.3856668  -1.0948591   0.0728941 ]]\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "test_data.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 237
+        },
+        "id": "m0k7toG3E2_9",
+        "outputId": "38ab6e43-1321-4028-9482-8e6687802a7d"
+      },
+      "execution_count": 107,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "                  Open        High         Low       Close   Adj Close  \\\n",
+              "Date                                                                     \n",
+              "2022-09-19  149.309998  154.559998  149.100006  154.479996  153.989029   \n",
+              "2022-09-20  153.399994  158.080002  153.080002  156.899994  156.401352   \n",
+              "2022-09-21  157.339996  158.740005  153.600006  153.720001  153.231461   \n",
+              "2022-09-22  152.380005  154.470001  150.910004  152.740005  152.254578   \n",
+              "2022-09-23  151.190002  151.470001  148.559998  150.429993  149.951904   \n",
+              "\n",
+              "               Volume  \n",
+              "Date                   \n",
+              "2022-09-19   81474200  \n",
+              "2022-09-20  107689800  \n",
+              "2022-09-21  101696800  \n",
+              "2022-09-22   86652500  \n",
+              "2022-09-23   96029900  "
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-51b6b5ba-2841-4317-9ce2-b32b40e2e9fc\">\n",
+              "    <div class=\"colab-df-container\">\n",
+              "      <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>2022-09-19</th>\n",
+              "      <td>149.309998</td>\n",
+              "      <td>154.559998</td>\n",
+              "      <td>149.100006</td>\n",
+              "      <td>154.479996</td>\n",
+              "      <td>153.989029</td>\n",
+              "      <td>81474200</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2022-09-20</th>\n",
+              "      <td>153.399994</td>\n",
+              "      <td>158.080002</td>\n",
+              "      <td>153.080002</td>\n",
+              "      <td>156.899994</td>\n",
+              "      <td>156.401352</td>\n",
+              "      <td>107689800</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2022-09-21</th>\n",
+              "      <td>157.339996</td>\n",
+              "      <td>158.740005</td>\n",
+              "      <td>153.600006</td>\n",
+              "      <td>153.720001</td>\n",
+              "      <td>153.231461</td>\n",
+              "      <td>101696800</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2022-09-22</th>\n",
+              "      <td>152.380005</td>\n",
+              "      <td>154.470001</td>\n",
+              "      <td>150.910004</td>\n",
+              "      <td>152.740005</td>\n",
+              "      <td>152.254578</td>\n",
+              "      <td>86652500</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2022-09-23</th>\n",
+              "      <td>151.190002</td>\n",
+              "      <td>151.470001</td>\n",
+              "      <td>148.559998</td>\n",
+              "      <td>150.429993</td>\n",
+              "      <td>149.951904</td>\n",
+              "      <td>96029900</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-51b6b5ba-2841-4317-9ce2-b32b40e2e9fc')\"\n",
+              "              title=\"Convert this dataframe to an interactive table.\"\n",
+              "              style=\"display:none;\">\n",
+              "        \n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "       width=\"24px\">\n",
+              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
+              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
+              "  </svg>\n",
+              "      </button>\n",
+              "      \n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      flex-wrap:wrap;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "      <script>\n",
+              "        const buttonEl =\n",
+              "          document.querySelector('#df-51b6b5ba-2841-4317-9ce2-b32b40e2e9fc button.colab-df-convert');\n",
+              "        buttonEl.style.display =\n",
+              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "        async function convertToInteractive(key) {\n",
+              "          const element = document.querySelector('#df-51b6b5ba-2841-4317-9ce2-b32b40e2e9fc');\n",
+              "          const dataTable =\n",
+              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                     [key], {});\n",
+              "          if (!dataTable) return;\n",
+              "\n",
+              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "            + ' to learn more about interactive tables.';\n",
+              "          element.innerHTML = '';\n",
+              "          dataTable['output_type'] = 'display_data';\n",
+              "          await google.colab.output.renderOutput(dataTable, element);\n",
+              "          const docLink = document.createElement('div');\n",
+              "          docLink.innerHTML = docLinkHtml;\n",
+              "          element.appendChild(docLink);\n",
+              "        }\n",
+              "      </script>\n",
+              "    </div>\n",
+              "  </div>\n",
+              "  "
+            ]
+          },
+          "metadata": {},
+          "execution_count": 107
+        }
+      ]
     }
   ]
 }