fix minor bug on stock prediction notebook

Author: x4nth055

machine-learning/stock-prediction/stock_prediction.ipynb

@@ -47,7 +47,6 @@
     "import time\n",
     "from tensorflow.keras.layers import LSTM\n",
     "\n",
-    "\n",
     "# Window size or the sequence length\n",
     "N_STEPS = 70\n",
     "# Lookup step, 1 is the next day\n",
@@ -82,8 +81,8 @@
     "BATCH_SIZE = 64\n",
     "EPOCHS = 400\n",
     "\n",
-    "# Apple stock market\n",
-    "ticker = \"AAPL\"\n",
+    "# Tesla stock market\n",
+    "ticker = \"TSLA\"\n",
     "ticker_data_filename = os.path.join(\"data\", f\"{ticker}_{date_now}.csv\")\n",
     "# model name to save, making it as unique as possible based on parameters\n",
     "model_name = f\"{date_now}_{ticker}-{LOSS}-{OPTIMIZER}-{CELL.__name__}-seq-{N_STEPS}-step-{LOOKUP_STEP}-layers-{N_LAYERS}-units-{UNITS}\"\n",
@@ -1116,7 +1115,7 @@
     "# evaluate the model\n",
     "mse, mae = model.evaluate(data[\"X_test\"], data[\"y_test\"], verbose=0)\n",
     "# calculate the mean absolute error (inverse scaling)\n",
-    "mean_absolute_error = data[\"column_scaler\"][\"adjclose\"].inverse_transform(mae.reshape(1, -1))[0][0]\n",
+    "mean_absolute_error = data[\"column_scaler\"][\"adjclose\"].inverse_transform([[mae]])[0][0]\n",
     "print(\"Mean Absolute Error:\", mean_absolute_error)\n",
     "# predict the future price\n",
     "future_price = predict(model, data)\n",