{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from matplotlib.pyplot import axis\n", "import pandas as pd\n", "import tensorflow as tf\n", "import numpy as np\n", "import seaborn as sb\n", "import keras as k\n", "from sklearn.model_selection import train_test_split \n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "data=pd.read_csv('winequality.csv')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "fixed acidity False\n", "volatile acidity False\n", "citric acid False\n", "residual sugar False\n", "chlorides False\n", "free sulfur dioxide False\n", "total sulfur dioxide False\n", "density False\n", "pH False\n", "sulphates False\n", "alcohol False\n", "quality False\n", "dtype: bool\n" ] } ], "source": [ "print(data.isnull().any())" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 1599 entries, 0 to 1598\n", "Data columns (total 12 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 fixed acidity 1599 non-null float64\n", " 1 volatile acidity 1599 non-null float64\n", " 2 citric acid 1599 non-null float64\n", " 3 residual sugar 1599 non-null float64\n", " 4 chlorides 1599 non-null float64\n", " 5 free sulfur dioxide 1599 non-null float64\n", " 6 total sulfur dioxide 1599 non-null float64\n", " 7 density 1599 non-null float64\n", " 8 pH 1599 non-null float64\n", " 9 sulphates 1599 non-null float64\n", " 10 alcohol 1599 non-null float64\n", " 11 quality 1599 non-null int64 \n", "dtypes: float64(11), int64(1)\n", "memory usage: 150.0 KB\n", "None\n" ] } ], "source": [ "print(data.info())" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 5\n", "1 5\n", "2 5\n", "3 6\n", "4 5\n", "5 5\n", "6 5\n", "7 7\n", "8 7\n", "9 5\n", "Name: quality, dtype: int64\n", " fixed acidity volatile acidity citric acid residual sugar chlorides \\\n", "0 7.4 0.70 0.00 1.9 0.076 \n", "1 7.8 0.88 0.00 2.6 0.098 \n", "2 7.8 0.76 0.04 2.3 0.092 \n", "3 11.2 0.28 0.56 1.9 0.075 \n", "4 7.4 0.70 0.00 1.9 0.076 \n", "5 7.4 0.66 0.00 1.8 0.075 \n", "6 7.9 0.60 0.06 1.6 0.069 \n", "7 7.3 0.65 0.00 1.2 0.065 \n", "8 7.8 0.58 0.02 2.0 0.073 \n", "9 7.5 0.50 0.36 6.1 0.071 \n", "\n", " free sulfur dioxide total sulfur dioxide density pH sulphates \\\n", "0 11.0 34.0 0.9978 3.51 0.56 \n", "1 25.0 67.0 0.9968 3.20 0.68 \n", "2 15.0 54.0 0.9970 3.26 0.65 \n", "3 17.0 60.0 0.9980 3.16 0.58 \n", "4 11.0 34.0 0.9978 3.51 0.56 \n", "5 13.0 40.0 0.9978 3.51 0.56 \n", "6 15.0 59.0 0.9964 3.30 0.46 \n", "7 15.0 21.0 0.9946 3.39 0.47 \n", "8 9.0 18.0 0.9968 3.36 0.57 \n", "9 17.0 102.0 0.9978 3.35 0.80 \n", "\n", " alcohol \n", "0 9.4 \n", "1 9.8 \n", "2 9.8 \n", "3 9.8 \n", "4 9.4 \n", "5 9.4 \n", "6 9.4 \n", "7 10.0 \n", "8 9.5 \n", "9 10.5 \n" ] } ], "source": [ "y=data.pop('quality')\n", "x=data\n", "\n", "x_train,x_test,y_train,y_test=train_test_split(x,y,train_size=0.7,random_state=50)\n", "\n", "print(y.head(10))\n", "print(x.head(10))" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "normalizer=tf.keras.layers.Normalization(axis=-1)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "normalizer.adapt(np.array(x_train))" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "alcohol=np.array(x_train['alcohol'])\n", "alcohol_normalizer=tf.keras.layers.Normalization(input_shape=[1,],axis=None)\n", "alcohol_normalizer=alcohol_normalizer.adapt(alcohol)" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [], "source": [ "alcohol_model = tf.keras.models.Sequential()\n", "alcohol_model.add(tf.keras.layers.Dense(input_dim=11, units=100, activation='relu'))\n", "\n" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [], "source": [ "alcohol_model.compile(\n", " optimizer=tf.optimizers.Adam(learning_rate=0.1),\n", " loss='mean_absolute_error'\n", ")" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/100\n", "28/28 [==============================] - 0s 5ms/step - loss: 3.2390 - val_loss: 2.5426\n", "Epoch 2/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.4418 - val_loss: 2.3977\n", "Epoch 3/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3838 - val_loss: 2.3266\n", "Epoch 4/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3546 - val_loss: 2.3361\n", "Epoch 5/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3218 - val_loss: 2.2931\n", "Epoch 6/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3508 - val_loss: 2.2979\n", "Epoch 7/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3198 - val_loss: 2.3019\n", "Epoch 8/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3683 - val_loss: 2.3992\n", "Epoch 9/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3907 - val_loss: 2.4212\n", "Epoch 10/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3593 - val_loss: 2.3958\n", "Epoch 11/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3772 - val_loss: 2.3542\n", "Epoch 12/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3353 - val_loss: 2.3437\n", "Epoch 13/100\n", "28/28 [==============================] - 0s 4ms/step - loss: 2.3947 - val_loss: 2.3969\n", "Epoch 14/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3660 - val_loss: 2.3823\n", "Epoch 15/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3374 - val_loss: 2.3699\n", "Epoch 16/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3862 - val_loss: 2.3677\n", "Epoch 17/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3393 - val_loss: 2.2889\n", "Epoch 18/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3500 - val_loss: 2.4911\n", "Epoch 19/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3905 - val_loss: 2.3490\n", "Epoch 20/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3631 - val_loss: 2.3380\n", "Epoch 21/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3155 - val_loss: 2.5694\n", "Epoch 22/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.4091 - val_loss: 2.2998\n", "Epoch 23/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3569 - val_loss: 2.3790\n", "Epoch 24/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3409 - val_loss: 2.3120\n", "Epoch 25/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3285 - val_loss: 2.3552\n", "Epoch 26/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3403 - val_loss: 2.3427\n", "Epoch 27/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3078 - val_loss: 2.3340\n", "Epoch 28/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3293 - val_loss: 2.4440\n", "Epoch 29/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3468 - val_loss: 2.2857\n", "Epoch 30/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3323 - val_loss: 2.3261\n", "Epoch 31/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3532 - val_loss: 2.3838\n", "Epoch 32/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3031 - val_loss: 2.3436\n", "Epoch 33/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3755 - val_loss: 2.3305\n", "Epoch 34/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.4398 - val_loss: 2.3591\n", "Epoch 35/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3882 - val_loss: 2.3554\n", "Epoch 36/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3765 - val_loss: 2.5028\n", "Epoch 37/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3764 - val_loss: 2.2674\n", "Epoch 38/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.4234 - val_loss: 2.4326\n", "Epoch 39/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3838 - val_loss: 2.3662\n", "Epoch 40/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3232 - val_loss: 2.3354\n", "Epoch 41/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3284 - val_loss: 2.3060\n", "Epoch 42/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.2972 - val_loss: 2.3030\n", "Epoch 43/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3795 - val_loss: 2.2788\n", "Epoch 44/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3426 - val_loss: 2.4253\n", "Epoch 45/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3658 - val_loss: 2.3137\n", "Epoch 46/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3441 - val_loss: 2.3908\n", "Epoch 47/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3660 - val_loss: 2.3661\n", "Epoch 48/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3679 - val_loss: 2.4015\n", "Epoch 49/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3980 - val_loss: 2.2734\n", "Epoch 50/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3172 - val_loss: 2.2789\n", "Epoch 51/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3712 - val_loss: 2.4158\n", "Epoch 52/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3482 - val_loss: 2.4234\n", "Epoch 53/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3460 - val_loss: 2.3237\n", "Epoch 54/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3464 - val_loss: 2.3347\n", "Epoch 55/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3212 - val_loss: 2.3744\n", "Epoch 56/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.4494 - val_loss: 2.4416\n", "Epoch 57/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3685 - val_loss: 2.3786\n", "Epoch 58/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3238 - val_loss: 2.3690\n", "Epoch 59/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3290 - val_loss: 2.3558\n", "Epoch 60/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.2945 - val_loss: 2.3152\n", "Epoch 61/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3685 - val_loss: 2.3844\n", "Epoch 62/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3706 - val_loss: 2.3879\n", "Epoch 63/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3617 - val_loss: 2.3169\n", "Epoch 64/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3492 - val_loss: 2.3538\n", "Epoch 65/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3171 - val_loss: 2.3248\n", "Epoch 66/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3519 - val_loss: 2.3258\n", "Epoch 67/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3455 - val_loss: 2.4234\n", "Epoch 68/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3749 - val_loss: 2.3730\n", "Epoch 69/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3214 - val_loss: 2.3482\n", "Epoch 70/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3555 - val_loss: 2.3381\n", "Epoch 71/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3340 - val_loss: 2.3827\n", "Epoch 72/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3381 - val_loss: 2.3250\n", "Epoch 73/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.2971 - val_loss: 2.3090\n", "Epoch 74/100\n", "28/28 [==============================] - 0s 4ms/step - loss: 2.3481 - val_loss: 2.3699\n", "Epoch 75/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3503 - val_loss: 2.2994\n", "Epoch 76/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3147 - val_loss: 2.4079\n", "Epoch 77/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.4143 - val_loss: 2.4446\n", "Epoch 78/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3824 - val_loss: 2.3323\n", "Epoch 79/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3369 - val_loss: 2.3382\n", "Epoch 80/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3366 - val_loss: 2.3542\n", "Epoch 81/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3614 - val_loss: 2.3811\n", "Epoch 82/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3423 - val_loss: 2.3483\n", "Epoch 83/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.4029 - val_loss: 2.3844\n", "Epoch 84/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3726 - val_loss: 2.3316\n", "Epoch 85/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.2985 - val_loss: 2.2900\n", "Epoch 86/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3137 - val_loss: 2.2679\n", "Epoch 87/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3316 - val_loss: 2.3294\n", "Epoch 88/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3564 - val_loss: 2.2853\n", "Epoch 89/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3279 - val_loss: 2.2747\n", "Epoch 90/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3132 - val_loss: 2.3006\n", "Epoch 91/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3021 - val_loss: 2.3415\n", "Epoch 92/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3285 - val_loss: 2.2832\n", "Epoch 93/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3216 - val_loss: 2.2953\n", "Epoch 94/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.2975 - val_loss: 2.3521\n", "Epoch 95/100\n", "28/28 [==============================] - 0s 3ms/step - loss: 2.3378 - val_loss: 2.3166\n", "Epoch 96/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3435 - val_loss: 2.3407\n", "Epoch 97/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3489 - val_loss: 2.4008\n", "Epoch 98/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3463 - val_loss: 2.4423\n", "Epoch 99/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3215 - val_loss: 2.2958\n", "Epoch 100/100\n", "28/28 [==============================] - 0s 2ms/step - loss: 2.3137 - val_loss: 2.4183\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "alcohol_model.fit( x_train,y_train,epochs=100,validation_split=0.2)" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "ename": "AttributeError", "evalue": "Exception encountered when calling layer \"sequential_12\" (type Sequential).\n\n'tuple' object has no attribute 'rank'\n\nCall arguments received:\n • inputs= fixed acidity volatile acidity citric acid residual sugar chlorides \\\n453 10.4 0.33 0.63 2.80 0.084 \n1415 6.2 0.58 0.00 1.60 0.065 \n1242 9.0 0.40 0.41 2.00 0.058 \n885 8.9 0.75 0.14 2.50 0.086 \n488 11.6 0.32 0.55 2.80 0.081 \n... ... ... ... ... ... \n34 5.2 0.32 0.25 1.80 0.103 \n1493 7.7 0.54 0.26 1.90 0.089 \n501 10.4 0.44 0.73 6.55 0.074 \n1464 6.8 0.59 0.10 1.70 0.063 \n911 9.1 0.28 0.46 9.00 0.114 \n\n free sulfur dioxide total sulfur dioxide density pH sulphates \\\n453 5.0 22.0 0.99980 3.26 0.74 \n1415 8.0 18.0 0.99660 3.56 0.84 \n1242 15.0 40.0 0.99414 3.22 0.60 \n885 9.0 30.0 0.99824 3.34 0.64 \n488 35.0 67.0 1.00020 3.32 0.92 \n... ... ... ... ... ... \n34 13.0 50.0 0.99570 3.38 0.55 \n1493 23.0 147.0 0.99636 3.26 0.59 \n501 38.0 76.0 0.99900 3.17 0.85 \n1464 34.0 53.0 0.99580 3.41 0.67 \n911 3.0 9.0 0.99901 3.18 0.60 \n\n alcohol \n453 11.2 \n1415 9.4 \n1242 12.2 \n885 10.5 \n488 10.8 \n... ... \n34 9.2 \n1493 9.7 \n501 12.0 \n1464 9.7 \n911 10.9 \n\n[480 rows x 11 columns]\n • training=None\n • mask=None", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", "\u001b[1;32md:\\Rad\\SI\\TENSORFLOW\\zadaci\\2.ipynb Cell 12'\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[0m y_pred\u001b[39m=\u001b[39malcohol_model(x_test)\n", "File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\keras\\utils\\traceback_utils.py:67\u001b[0m, in \u001b[0;36mfilter_traceback..error_handler\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m 65\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mException\u001b[39;00m \u001b[39mas\u001b[39;00m e: \u001b[39m# pylint: disable=broad-except\u001b[39;00m\n\u001b[0;32m 66\u001b[0m filtered_tb \u001b[39m=\u001b[39m _process_traceback_frames(e\u001b[39m.\u001b[39m__traceback__)\n\u001b[1;32m---> 67\u001b[0m \u001b[39mraise\u001b[39;00m e\u001b[39m.\u001b[39mwith_traceback(filtered_tb) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39m\n\u001b[0;32m 68\u001b[0m \u001b[39mfinally\u001b[39;00m:\n\u001b[0;32m 69\u001b[0m \u001b[39mdel\u001b[39;00m filtered_tb\n", "File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\keras\\engine\\input_spec.py:226\u001b[0m, in \u001b[0;36massert_input_compatibility\u001b[1;34m(input_spec, inputs, layer_name)\u001b[0m\n\u001b[0;32m 221\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mInput \u001b[39m\u001b[39m{\u001b[39;00minput_index\u001b[39m}\u001b[39;00m\u001b[39m of layer \u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00mlayer_name\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m\u001b[39m \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 222\u001b[0m \u001b[39m'\u001b[39m\u001b[39mis incompatible with the layer: \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 223\u001b[0m \u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mexpected max_ndim=\u001b[39m\u001b[39m{\u001b[39;00mspec\u001b[39m.\u001b[39mmax_ndim\u001b[39m}\u001b[39;00m\u001b[39m, \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 224\u001b[0m \u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mfound ndim=\u001b[39m\u001b[39m{\u001b[39;00mndim\u001b[39m}\u001b[39;00m\u001b[39m'\u001b[39m)\n\u001b[0;32m 225\u001b[0m \u001b[39mif\u001b[39;00m spec\u001b[39m.\u001b[39mmin_ndim \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m--> 226\u001b[0m ndim \u001b[39m=\u001b[39m x\u001b[39m.\u001b[39;49mshape\u001b[39m.\u001b[39;49mrank\n\u001b[0;32m 227\u001b[0m \u001b[39mif\u001b[39;00m ndim \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m ndim \u001b[39m<\u001b[39m spec\u001b[39m.\u001b[39mmin_ndim:\n\u001b[0;32m 228\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mInput \u001b[39m\u001b[39m{\u001b[39;00minput_index\u001b[39m}\u001b[39;00m\u001b[39m of layer \u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00mlayer_name\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m\u001b[39m \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 229\u001b[0m \u001b[39m'\u001b[39m\u001b[39mis incompatible with the layer: \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 230\u001b[0m \u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mexpected min_ndim=\u001b[39m\u001b[39m{\u001b[39;00mspec\u001b[39m.\u001b[39mmin_ndim\u001b[39m}\u001b[39;00m\u001b[39m, \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 231\u001b[0m \u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mfound ndim=\u001b[39m\u001b[39m{\u001b[39;00mndim\u001b[39m}\u001b[39;00m\u001b[39m. \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 232\u001b[0m \u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mFull shape received: \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39mtuple\u001b[39m(shape)\u001b[39m}\u001b[39;00m\u001b[39m'\u001b[39m)\n", "\u001b[1;31mAttributeError\u001b[0m: Exception encountered when calling layer \"sequential_12\" (type Sequential).\n\n'tuple' object has no attribute 'rank'\n\nCall arguments received:\n • inputs= fixed acidity volatile acidity citric acid residual sugar chlorides \\\n453 10.4 0.33 0.63 2.80 0.084 \n1415 6.2 0.58 0.00 1.60 0.065 \n1242 9.0 0.40 0.41 2.00 0.058 \n885 8.9 0.75 0.14 2.50 0.086 \n488 11.6 0.32 0.55 2.80 0.081 \n... ... ... ... ... ... \n34 5.2 0.32 0.25 1.80 0.103 \n1493 7.7 0.54 0.26 1.90 0.089 \n501 10.4 0.44 0.73 6.55 0.074 \n1464 6.8 0.59 0.10 1.70 0.063 \n911 9.1 0.28 0.46 9.00 0.114 \n\n free sulfur dioxide total sulfur dioxide density pH sulphates \\\n453 5.0 22.0 0.99980 3.26 0.74 \n1415 8.0 18.0 0.99660 3.56 0.84 \n1242 15.0 40.0 0.99414 3.22 0.60 \n885 9.0 30.0 0.99824 3.34 0.64 \n488 35.0 67.0 1.00020 3.32 0.92 \n... ... ... ... ... ... \n34 13.0 50.0 0.99570 3.38 0.55 \n1493 23.0 147.0 0.99636 3.26 0.59 \n501 38.0 76.0 0.99900 3.17 0.85 \n1464 34.0 53.0 0.99580 3.41 0.67 \n911 3.0 9.0 0.99901 3.18 0.60 \n\n alcohol \n453 11.2 \n1415 9.4 \n1242 12.2 \n885 10.5 \n488 10.8 \n... ... \n34 9.2 \n1493 9.7 \n501 12.0 \n1464 9.7 \n911 10.9 \n\n[480 rows x 11 columns]\n • training=None\n • mask=None" ] } ], "source": [ "alcohol_model.evaluate(x_test, y_test)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "tok=pd.DataFrame(progres.progres)\n", "tok['epoch']=progres.epoch\n", "print(tok)" ] } ], "metadata": { "interpreter": { "hash": "a93f175750059abc13a87c3bf357a09033a91b4f6c1a54ccd901c5d335f83c0c" }, "kernelspec": { "display_name": "Python 3.10.2 64-bit", "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": "3.10.2" }, "orig_nbformat": 4 }, "nbformat": 4, "nbformat_minor": 2 }