diff --git a/POET_Training.ipynb b/POET_Training.ipynb index 5abcc83..e278521 100644 --- a/POET_Training.ipynb +++ b/POET_Training.ipynb @@ -30,26 +30,17 @@ "execution_count": 1, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "2025-02-14 15:03:29.350232: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n", - "2025-02-14 15:03:29.368766: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", - "To enable the following instructions: SSE4.1 SSE4.2 AVX AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n" - ] - }, { "name": "stdout", "output_type": "stream", "text": [ - "Running Keras in version 3.6.0\n" + "Running Keras in version 3.8.0\n" ] } ], "source": [ "import keras\n", - "from keras.layers import Dense, Dropout, Input, BatchNormalization\n", + "from keras.layers import Dense, Dropout, Input,BatchNormalization\n", "import tensorflow as tf\n", "import h5py\n", "import numpy as np\n", @@ -453,7 +444,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -523,7 +514,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -557,7 +548,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "/home/signer/bin/miniconda3/envs/training/lib/python3.11/site-packages/sklearn/base.py:1473: ConvergenceWarning: Number of distinct clusters (1) found smaller than n_clusters (2). Possibly due to duplicate points in X.\n", + "/Users/hannessigner/miniforge3/envs/ai/lib/python3.12/site-packages/sklearn/base.py:1474: ConvergenceWarning: Number of distinct clusters (1) found smaller than n_clusters (2). Possibly due to duplicate points in X.\n", " return fit_method(estimator, *args, **kwargs)\n" ] }, @@ -566,10 +557,7 @@ "output_type": "stream", "text": [ "Amount class 0 before: 0.9521309523809524\n", - "Amount class 1 before: 0.04786904761904762\n", - "Using Oversampling\n", - "Amount class 0 after: 0.5\n", - "Amount class 1 after: 0.5\n" + "Amount class 1 before: 0.04786904761904762\n" ] } ], @@ -579,7 +567,7 @@ "# X, y = preprocess.funcTranform(X, y)\n", "\n", "X_train, X_test, y_train, y_test = preprocess.split(X, y, ratio = 0.2)\n", - "X_train, y_train = preprocess.balancer(X_train, y_train, strategy = \"over\")\n", + "X_train, y_train = preprocess.balancer(X_train, y_train, strategy = \"off\")\n", "preprocess.scale_fit(X_train, y_train, scaling = \"individual\")\n", "X_train, X_test, y_train, y_test = preprocess.scale_transform(X_train, X_test, y_train, y_test)\n", "X_train, X_val, y_train, y_val = preprocess.split(X_train, y_train, ratio = 0.1)" @@ -587,22 +575,22 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 52, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 12, + "execution_count": 52, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -635,14 +623,14 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 53, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "/home/signer/bin/miniconda3/envs/training/lib/python3.11/site-packages/sklearn/base.py:1473: ConvergenceWarning: Number of distinct clusters (1) found smaller than n_clusters (2). Possibly due to duplicate points in X.\n", + "/Users/hannessigner/miniforge3/envs/ai/lib/python3.12/site-packages/sklearn/base.py:1474: ConvergenceWarning: Number of distinct clusters (1) found smaller than n_clusters (2). Possibly due to duplicate points in X.\n", " return fit_method(estimator, *args, **kwargs)\n" ] }, @@ -653,10 +641,10 @@ "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[0;32mIn[13], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m X_train, X_val, X_test, y_train, y_val, y_test, scaler_X, scaler_y \u001b[38;5;241m=\u001b[39m preprocessing_training(df_design[species_columns], df_results[species_columns], func_dict_in, func_dict_out, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moff\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mglobal\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;241m0.1\u001b[39m)\n", - "File \u001b[0;32m~/Documents/model-training/preprocessing.py:161\u001b[0m, in \u001b[0;36mpreprocessing_training\u001b[0;34m(df_design, df_targets, func_dict_in, func_dict_out, sampling, scaling, test_size)\u001b[0m\n\u001b[1;32m 158\u001b[0m df_design \u001b[38;5;241m=\u001b[39m clustering(df_design)\n\u001b[1;32m 159\u001b[0m df_targets \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat([df_targets, df_design[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mClass\u001b[39m\u001b[38;5;124m'\u001b[39m]], axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m--> 161\u001b[0m df_design_log \u001b[38;5;241m=\u001b[39m FuncTransform(func_dict_in, func_dict_out)\u001b[38;5;241m.\u001b[39mfit_transform(df_design)\n\u001b[1;32m 162\u001b[0m df_results_log \u001b[38;5;241m=\u001b[39m FuncTransform(func_dict_in, func_dict_out)\u001b[38;5;241m.\u001b[39mfit_transform(df_targets)\n\u001b[1;32m 164\u001b[0m X_train, X_test, y_train, y_test \u001b[38;5;241m=\u001b[39m sk\u001b[38;5;241m.\u001b[39mtrain_test_split(df_design_log, df_results_log, test_size \u001b[38;5;241m=\u001b[39m test_size, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m42\u001b[39m)\n", - "File \u001b[0;32m~/Documents/model-training/preprocessing.py:63\u001b[0m, in \u001b[0;36mFuncTransform.fit_transform\u001b[0;34m(self, X, y)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfit_transform\u001b[39m(\u001b[38;5;28mself\u001b[39m, X, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfit(X)\n\u001b[0;32m---> 63\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtransform(X, y)\n", - "File \u001b[0;32m~/Documents/model-training/preprocessing.py:58\u001b[0m, in \u001b[0;36mFuncTransform.transform\u001b[0;34m(self, X, y)\u001b[0m\n\u001b[1;32m 56\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m X\u001b[38;5;241m.\u001b[39mkeys(): \n\u001b[1;32m 57\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mClass\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m key:\n\u001b[0;32m---> 58\u001b[0m X[key] \u001b[38;5;241m=\u001b[39m X[key]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunc_transform[key])\n\u001b[1;32m 59\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m X\n", + "Cell \u001b[0;32mIn[53], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m X_train, X_val, X_test, y_train, y_val, y_test, scaler_X, scaler_y \u001b[38;5;241m=\u001b[39m \u001b[43mpreprocessing_training\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf_design\u001b[49m\u001b[43m[\u001b[49m\u001b[43mspecies_columns\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdf_results\u001b[49m\u001b[43m[\u001b[49m\u001b[43mspecies_columns\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunc_dict_in\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunc_dict_out\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43moff\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mglobal\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0.1\u001b[39;49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m~/Documents/Work/model-training/preprocessing.py:161\u001b[0m, in \u001b[0;36mpreprocessing_training\u001b[0;34m(df_design, df_targets, func_dict_in, func_dict_out, sampling, scaling, test_size)\u001b[0m\n\u001b[1;32m 158\u001b[0m df_design \u001b[38;5;241m=\u001b[39m clustering(df_design)\n\u001b[1;32m 159\u001b[0m df_targets \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat([df_targets, df_design[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mClass\u001b[39m\u001b[38;5;124m'\u001b[39m]], axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m--> 161\u001b[0m df_design_log \u001b[38;5;241m=\u001b[39m \u001b[43mFuncTransform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfunc_dict_in\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunc_dict_out\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf_design\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 162\u001b[0m df_results_log \u001b[38;5;241m=\u001b[39m FuncTransform(func_dict_in, func_dict_out)\u001b[38;5;241m.\u001b[39mfit_transform(df_targets)\n\u001b[1;32m 164\u001b[0m X_train, X_test, y_train, y_test \u001b[38;5;241m=\u001b[39m sk\u001b[38;5;241m.\u001b[39mtrain_test_split(df_design_log, df_results_log, test_size \u001b[38;5;241m=\u001b[39m test_size, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m42\u001b[39m)\n", + "File \u001b[0;32m~/Documents/Work/model-training/preprocessing.py:63\u001b[0m, in \u001b[0;36mFuncTransform.fit_transform\u001b[0;34m(self, X, y)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mfit_transform\u001b[39m(\u001b[38;5;28mself\u001b[39m, X, y\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfit(X)\n\u001b[0;32m---> 63\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtransform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m~/Documents/Work/model-training/preprocessing.py:58\u001b[0m, in \u001b[0;36mFuncTransform.transform\u001b[0;34m(self, X, y)\u001b[0m\n\u001b[1;32m 56\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m X\u001b[38;5;241m.\u001b[39mkeys(): \n\u001b[1;32m 57\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mClass\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m key:\n\u001b[0;32m---> 58\u001b[0m X[key] \u001b[38;5;241m=\u001b[39m X[key]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunc_transform\u001b[49m\u001b[43m[\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m]\u001b[49m)\n\u001b[1;32m 59\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m X\n", "\u001b[0;31mKeyError\u001b[0m: 'S'" ] } @@ -667,7 +655,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": null, "metadata": {}, "outputs": [ { @@ -689,7 +677,7 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 54, "metadata": {}, "outputs": [ { @@ -700,7 +688,7 @@ " 1.00047941e+00]])" ] }, - "execution_count": 44, + "execution_count": 54, "metadata": {}, "output_type": "execute_result" } @@ -722,69 +710,61 @@ "metadata": {}, "outputs": [], "source": [ - "def custom_loss_H20(df_design_log, df_result_log, data_min_log, data_max_log, func_dict_out, postprocess):\n", - " df_result = postprocess(df_result_log, func_dict_out, data_min_log, data_max_log) \n", - " return keras.losses.Huber + np.sum(((df_result['H'] / df_result['O']) - 2)**2)\n", + "column_dict = {\"Ba\": X.columns.get_loc(\"Ba\"), \"Barite\":X.columns.get_loc(\"Barite\"), \"Sr\":X.columns.get_loc(\"Sr\"), \"Celestite\":X.columns.get_loc(\"Celestite\"), \"H\":X.columns.get_loc(\"H\"), \"H\":X.columns.get_loc(\"H\"), \"O\":X.columns.get_loc(\"O\")}" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "def custom_loss(preprocess, column_dict, h1, h2, h3, h4):\n", + " # extract the scaling parameters\n", + " scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32)\n", + " min_X = tf.convert_to_tensor(preprocess.scaler_X.min_, dtype=tf.float32)\n", + " scale_y = tf.convert_to_tensor(preprocess.scaler_y.scale_, dtype=tf.float32)\n", + " min_y = tf.convert_to_tensor(preprocess.scaler_y.min_, dtype=tf.float32)\n", + "\n", + " def loss(results, predicted):\n", + " # inverse min/max scaling\n", + " predicted_inverse = predicted * scale_X + min_X\n", + " results_inverse = results * scale_y + min_y\n", + "\n", + " # mass balance\n", + " dBa = tf.keras.backend.abs(\n", + " (predicted_inverse[:, column_dict[\"Ba\"]] + predicted_inverse[:, column_dict[\"Barite\"]]) -\n", + " (results_inverse[:, column_dict[\"Ba\"]] + results_inverse[:, column_dict[\"Barite\"]])\n", + " )\n", + " dSr = tf.keras.backend.abs(\n", + " (predicted_inverse[:, column_dict[\"Sr\"]] + predicted_inverse[:, column_dict[\"Celestite\"]]) -\n", + " (results_inverse[:, column_dict[\"Sr\"]] + results_inverse[:, column_dict[\"Celestite\"]])\n", + " )\n", + " \n", + " # H/O ratio has to be 2\n", + " h2o_ratio = tf.keras.backend.abs(\n", + " (predicted_inverse[:, column_dict[\"H\"]] / predicted_inverse[:, column_dict[\"O\"]]) - 2\n", + " )\n", + "\n", + " # huber loss\n", + " huber_loss = tf.keras.losses.Huber()(results, predicted)\n", + " \n", + " # total loss\n", + " total_loss = h1 * huber_loss + h2 * dBa**2 + h3 * dSr**2 + h4 * h2o_ratio**2\n", + "\n", + " return total_loss\n", "\n", - "def loss_wrapper(data_min_log, data_max_log, func_dict_out, postprocess):\n", - " def loss(df_design_log, df_result_log):\n", - " return custom_loss_H20(df_design_log, df_result_log, data_min_log, data_max_log, func_dict_out, postprocess)\n", " return loss" ] }, { "cell_type": "code", - "execution_count": 133, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ - "column_dict = {\"Ba\": X.columns.get_loc(\"Ba\"), \"Barite\":X.columns.get_loc(\"Barite\"), \"Sr\":X.columns.get_loc(\"Sr\"), \"Celestite\":X.columns.get_loc(\"Celestite\")}" - ] - }, - { - "cell_type": "code", - "execution_count": 160, - "metadata": {}, - "outputs": [], - "source": [ - "def custom_loss(preprocess, column_dict):\n", - " def loss(results, predicted):\n", - " \n", - " # predicted = preprocess.funcInverse(predicted)\n", - " # results = preprocess.funcInverse(results)\n", - " # predicted = tf.keras.backend.constant(predicted)\n", - " # results = tf.keras.backend.constant(results)\n", - " \n", - " # predicted = tf.keras.backend.constant(preprocess.scaler_X.inverse_transform(predicted))\n", - " # results = tf.keras.backend.constant(preprocess.scaler_y.inverse_transform(results))\n", - " \n", - " # dBa = tf.keras.backend.abs((predicted[\"Ba\"] + predicted[\"Barite\"]) - (results[\"Ba\"] + results[\"Barite\"]))\n", - " # dSr = tf.keras.backend.abs((predicted[\"Sr\"] + predicted[\"Celestite\"]) - (results[\"Sr\"] + results[\"Celestite\"]))\n", - " # huber_loss = tf.keras.losses.Huber()(results, predicted)\n", - " # total_loss = huber_loss + 0.1 * dBa + 0.1 * dSr\n", - " \n", - " predicted_inverse = predicted * tf.keras.backend.constant(preprocess.scaler_X.scale_) + tf.keras.backend.constant(preprocess.scaler_X.min_)\n", - " results_inverse = results * tf.keras.backend.constant(preprocess.scaler_y.scale_) + tf.keras.backend.constant(preprocess.scaler_y.min_)\n", - " \n", - " dBa = tf.keras.backend.abs((predicted_inverse[:,column_dict[\"Ba\"]] + predicted_inverse[:, column_dict[\"Barite\"]]) - (results_inverse[:, column_dict[\"Ba\"]] + results_inverse[:, column_dict[\"Barite\"]]))\n", - " dSa = tf.keras.backend.abs((predicted_inverse[:,column_dict[\"Sr\"]] + predicted_inverse[:, column_dict[\"Celestite\"]]) - (results_inverse[:, column_dict[\"Sr\"]] + results_inverse[:, column_dict[\"Celestite\"]]))\n", - " \n", - " huber_loss = tf.keras.losses.Huber()(results, predicted)\n", - " total_loss = huber_loss # + 0.1 * dBa + 0.1 * dSa\n", - " \n", - " return total_loss\n", - "\n", - " return loss\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": 165, - "metadata": {}, - "outputs": [], - "source": [ - "model_simple.compile(optimizer=optimizer_simple, loss=loss)#custom_loss(preprocess, column_dict))" + "model_simple.compile(optimizer=optimizer_simple, loss=custom_loss(preprocess, column_dict, 1, 1, 1, 1))#custom_loss(preprocess, column_dict))\n", + "# model_large.compile(optimizer=optimizer_large, loss=custom_loss(preprocess, column_dict))#custom_loss(preprocess, column_dict))" ] }, { @@ -796,29 +776,7 @@ }, { "cell_type": "code", - "execution_count": 166, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "array([1.15182858e+07, 4.02793041e+02, 1.88096044e+06, 1.03308956e+01,\n", - " 5.06871734e+00, 1.61113403e+03, 1.74937705e+01, 9.88625768e-01,\n", - " 9.99215371e-01])" - ] - }, - "execution_count": 166, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "preprocess.scaler_X.scale_" - ] - }, - { - "cell_type": "code", - "execution_count": 167, + "execution_count": 15, "metadata": {}, "outputs": [], "source": [ @@ -829,9 +787,10 @@ " history = model.fit(X_train.loc[:, X_train.columns != \"Class\"], \n", " y_train.loc[:, y_train.columns != \"Class\"], \n", " batch_size=batch_size, \n", - " epochs=20, \n", + " epochs=50, \n", " validation_data=(X_val.loc[:, X_val.columns != \"Class\"], y_val.loc[:, y_val.columns != \"Class\"]),\n", " callbacks=[callback])\n", + " \n", "\n", " end = time.time()\n", "\n", @@ -840,54 +799,112 @@ }, { "cell_type": "code", - "execution_count": 168, + "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Epoch 1/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.8797e-04 - val_loss: 2.8113e-04\n", - "Epoch 2/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.8380e-04 - val_loss: 2.7753e-04\n", - "Epoch 3/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.8036e-04 - val_loss: 2.7414e-04\n", - "Epoch 4/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.7782e-04 - val_loss: 2.7140e-04\n", - "Epoch 5/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.7578e-04 - val_loss: 2.6949e-04\n", - "Epoch 6/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.7396e-04 - val_loss: 2.6790e-04\n", - "Epoch 7/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.7167e-04 - val_loss: 2.6644e-04\n", - "Epoch 8/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.6910e-04 - val_loss: 2.6501e-04\n", - "Epoch 9/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.6823e-04 - val_loss: 2.6271e-04\n", - "Epoch 10/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.6424e-04 - val_loss: 2.5818e-04\n", - "Epoch 11/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.6078e-04 - val_loss: 2.5062e-04\n", - "Epoch 12/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.5335e-04 - val_loss: 2.4440e-04\n", - "Epoch 13/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.4686e-04 - val_loss: 2.4047e-04\n", - "Epoch 14/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.4252e-04 - val_loss: 2.3637e-04\n", - "Epoch 15/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - loss: 2.3795e-04 - val_loss: 2.3264e-04\n", - "Epoch 16/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.3383e-04 - val_loss: 2.2967e-04\n", - "Epoch 17/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.3237e-04 - val_loss: 2.2776e-04\n", - "Epoch 18/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.2965e-04 - val_loss: 2.2670e-04\n", - "Epoch 19/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.2929e-04 - val_loss: 2.2598e-04\n", - "Epoch 20/20\n", - "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - loss: 2.2851e-04 - val_loss: 2.2543e-04\n", - "Training took 56.33732986450195 seconds\n" + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.6440 - val_loss: 0.5460\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.2363 - val_loss: 0.1153\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.1663 - val_loss: 0.1348\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.1211 - val_loss: 0.1081\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0994 - val_loss: 0.0932\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0824 - val_loss: 0.0344\n", + "Epoch 7/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0787 - val_loss: 0.0577\n", + "Epoch 8/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0704 - val_loss: 0.0882\n", + "Epoch 9/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0672 - val_loss: 0.0456\n", + "Epoch 10/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0543 - val_loss: 0.0487\n", + "Epoch 11/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.0548 - val_loss: 0.0402\n", + "Epoch 12/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0484 - val_loss: 0.0576\n", + "Epoch 13/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0487 - val_loss: 0.0234\n", + "Epoch 14/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0499 - val_loss: 0.0357\n", + "Epoch 15/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0406 - val_loss: 0.0262\n", + "Epoch 16/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0388 - val_loss: 0.0258\n", + "Epoch 17/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0312 - val_loss: 0.0369\n", + "Epoch 18/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0340 - val_loss: 0.0571\n", + "Epoch 19/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.0349 - val_loss: 0.0306\n", + "Epoch 20/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0276 - val_loss: 0.0579\n", + "Epoch 21/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0255 - val_loss: 0.0264\n", + "Epoch 22/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.0233 - val_loss: 0.0334\n", + "Epoch 23/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0232 - val_loss: 0.0155\n", + "Epoch 24/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0230 - val_loss: 0.0194\n", + "Epoch 25/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0232 - val_loss: 0.0099\n", + "Epoch 26/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0195 - val_loss: 0.0136\n", + "Epoch 27/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0199 - val_loss: 0.0166\n", + "Epoch 28/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0185 - val_loss: 0.0133\n", + "Epoch 29/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0174 - val_loss: 0.0094\n", + "Epoch 30/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0170 - val_loss: 0.0148\n", + "Epoch 31/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0141 - val_loss: 0.0132\n", + "Epoch 32/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0161 - val_loss: 0.0078\n", + "Epoch 33/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0158 - val_loss: 0.0279\n", + "Epoch 34/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0152 - val_loss: 0.0106\n", + "Epoch 35/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0132 - val_loss: 0.0190\n", + "Epoch 36/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0140 - val_loss: 0.0184\n", + "Epoch 37/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0116 - val_loss: 0.0092\n", + "Epoch 38/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0106 - val_loss: 0.0178\n", + "Epoch 39/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0113 - val_loss: 0.0113\n", + "Epoch 40/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0094 - val_loss: 0.0090\n", + "Epoch 41/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0093 - val_loss: 0.0097\n", + "Epoch 42/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0092 - val_loss: 0.0081\n", + "Epoch 43/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0085 - val_loss: 0.0093\n", + "Epoch 44/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0083 - val_loss: 0.0082\n", + "Epoch 45/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0091 - val_loss: 0.0135\n", + "Epoch 46/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0081 - val_loss: 0.0065\n", + "Epoch 47/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0076 - val_loss: 0.0100\n", + "Epoch 48/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0091 - val_loss: 0.0064\n", + "Epoch 49/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 0.0079 - val_loss: 0.0070\n", + "Training took 79.01837086677551 seconds\n" ] } ], @@ -904,7 +921,7 @@ }, { "cell_type": "code", - "execution_count": 98, + "execution_count": 16, "metadata": {}, "outputs": [], "source": [ @@ -930,24 +947,24 @@ }, { "cell_type": "code", - "execution_count": 99, + "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[1m26993/26993\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 358us/step\n" + "\u001b[1m3938/3938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 311us/step\n" ] } ], "source": [ - "mass_balance_results = mass_balance(model_simple, X_train, preprocess)" + "mass_balance_results = mass_balance(model_simple, X_test, preprocess)" ] }, { "cell_type": "code", - "execution_count": 100, + "execution_count": 21, "metadata": {}, "outputs": [ { @@ -956,18 +973,18 @@ "0.0" ] }, - "execution_count": 100, + "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "len(mass_balance_results[mass_balance_results < 1e-5]) / len(mass_balance_results)" + "len(mass_balance_results[mass_balance_results < 1e-2]) / len(mass_balance_results)" ] }, { "cell_type": "code", - "execution_count": 101, + "execution_count": 99, "metadata": {}, "outputs": [ { @@ -976,7 +993,7 @@ "Series([], dtype: float64)" ] }, - "execution_count": 101, + "execution_count": 99, "metadata": {}, "output_type": "execute_result" } @@ -985,6 +1002,505 @@ "mass_balance_results[mass_balance_results < 1e-5]" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Optimizing with Optuna" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "import optuna\n", + "\n", + "def create_model(model, preprocess, h1, h2, h3, h4):\n", + " \n", + " model.compile(optimizer=optimizer_simple, loss=custom_loss(preprocess, column_dict, h1, h2, h3, h4))\n", + " \n", + " return model\n", + "\n", + "\n", + "def objective(trial, preprocess, X_train, y_train, X_val, y_val, X_test, y_test):\n", + " h1 = trial.suggest_float(\"h1\", 0.1, 100)\n", + " h2 = trial.suggest_float(\"h2\", 0.1, 100)\n", + " h3 = trial.suggest_float(\"h3\", 0.1, 100)\n", + " h4 = trial.suggest_float(\"h4\", 0.1, 100)\n", + " \n", + " model = create_model(model_simple, preprocess, h1, h2, h3, h4)\n", + " \n", + " callback = keras.callbacks.EarlyStopping(monitor='loss', patience=3)\n", + " history = model.fit(X_train.loc[:, X_train.columns != \"Class\"], \n", + " y_train.loc[:, y_train.columns != \"Class\"], \n", + " batch_size=batch_size, \n", + " epochs=50, \n", + " validation_data=(X_val.loc[:, X_val.columns != \"Class\"], y_val.loc[:, y_val.columns != \"Class\"]),\n", + " callbacks=[callback])\n", + " \n", + " mass_balance_results = mass_balance(model, X_test, preprocess)\n", + " \n", + " loss = len(mass_balance_results[mass_balance_results < 1e-5]) / len(mass_balance_results)\n", + "\n", + " return loss" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[I 2025-02-17 00:06:24,572] A new study created in memory with name: no-name-585ded5e-6499-4f70-9577-49339316366a\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12377019392.0000 - val_loss: 43404600.0000\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 36439708.0000 - val_loss: 19609912.0000\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 15841922.0000 - val_loss: 7256873.5000\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 5500834.0000 - val_loss: 1881962.5000\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1413300.5000 - val_loss: 617048.8125\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 496590.9375 - val_loss: 194345.2812\n", + "Epoch 7/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 139668.2969 - val_loss: 31873.9043\n", + "Epoch 8/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 21170.1543 - val_loss: 4920.2520\n", + "Epoch 9/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 4156.0869 - val_loss: 3427.2729\n", + "Epoch 10/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 3414.1331 - val_loss: 3416.1082\n", + "Epoch 11/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 3416.9729 - val_loss: 3429.7239\n", + "Epoch 12/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 3412.4482 - val_loss: 3435.3306\n", + "Epoch 13/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 3425.5073 - val_loss: 3403.7925\n", + "Epoch 14/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 3425.9592 - val_loss: 3423.5193\n", + "\u001b[1m3938/3938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 296us/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[I 2025-02-17 00:06:49,285] Trial 0 finished with value: 0.0 and parameters: {'h1': 72.40785703177082, 'h2': 25.825548427085515, 'h3': 61.927211067692724, 'h4': 19.232336897801325}. Best is trial 0 with value: 0.0.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2791.0564 - val_loss: 2618.3965\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2622.5496 - val_loss: 2616.2480\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2620.7339 - val_loss: 2631.9077\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2650.9636 - val_loss: 2814.0315\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2722.9919 - val_loss: 2598.4248\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2778.1111 - val_loss: 2559.9062\n", + "\u001b[1m3938/3938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 291us/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[I 2025-02-17 00:07:00,296] Trial 1 finished with value: 0.0 and parameters: {'h1': 55.156241799815355, 'h2': 78.4033434954878, 'h3': 95.18824024469184, 'h4': 14.82240562501995}. Best is trial 0 with value: 0.0.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 7852.1719 - val_loss: 2412.7383\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2426.0986 - val_loss: 2597.7363\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2473.9902 - val_loss: 2277.7488\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2471.1829 - val_loss: 2443.7427\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2402.8818 - val_loss: 2218.1780\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2367.2834 - val_loss: 2218.3396\n", + "Epoch 7/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2340.9314 - val_loss: 2119.3755\n", + "Epoch 8/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 2219.4814 - val_loss: 2298.2070\n", + "Epoch 9/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2155.6299 - val_loss: 2612.8733\n", + "Epoch 10/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2100.1267 - val_loss: 2046.4711\n", + "Epoch 11/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 2001.3557 - val_loss: 2211.9299\n", + "Epoch 12/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1971.5155 - val_loss: 1997.1703\n", + "Epoch 13/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1947.2655 - val_loss: 1892.0009\n", + "Epoch 14/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1915.1980 - val_loss: 1860.9949\n", + "Epoch 15/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1882.3663 - val_loss: 1861.6248\n", + "Epoch 16/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1869.7008 - val_loss: 1896.9276\n", + "Epoch 17/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1883.5923 - val_loss: 1915.4973\n", + "Epoch 18/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1871.5115 - val_loss: 1837.4102\n", + "Epoch 19/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1877.5151 - val_loss: 1879.3440\n", + "Epoch 20/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1862.3589 - val_loss: 1957.3567\n", + "Epoch 21/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1845.3960 - val_loss: 1814.5060\n", + "Epoch 22/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1835.3391 - val_loss: 1809.6317\n", + "Epoch 23/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1838.9376 - val_loss: 1833.8245\n", + "Epoch 24/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1831.4557 - val_loss: 1886.3599\n", + "Epoch 25/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1833.6478 - val_loss: 1800.0344\n", + "Epoch 26/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1833.5480 - val_loss: 1797.0282\n", + "Epoch 27/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1819.1056 - val_loss: 1794.1648\n", + "Epoch 28/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1812.3524 - val_loss: 1881.1871\n", + "Epoch 29/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1805.2583 - val_loss: 1802.8263\n", + "Epoch 30/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1808.2974 - val_loss: 1777.7633\n", + "Epoch 31/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1792.2367 - val_loss: 1791.2937\n", + "Epoch 32/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1789.2295 - val_loss: 1778.8715\n", + "Epoch 33/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1772.3083 - val_loss: 1778.3553\n", + "Epoch 34/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1781.2627 - val_loss: 1760.8132\n", + "Epoch 35/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1783.0363 - val_loss: 1763.7234\n", + "Epoch 36/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1765.7679 - val_loss: 1752.7267\n", + "Epoch 37/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1761.1954 - val_loss: 1762.8220\n", + "Epoch 38/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1762.9722 - val_loss: 1747.1544\n", + "Epoch 39/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1753.7981 - val_loss: 1763.1051\n", + "Epoch 40/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1752.4087 - val_loss: 1739.5280\n", + "Epoch 41/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1748.3682 - val_loss: 1728.5411\n", + "Epoch 42/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1739.5088 - val_loss: 1729.1458\n", + "Epoch 43/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1736.5480 - val_loss: 1724.7151\n", + "Epoch 44/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1740.2578 - val_loss: 1734.8917\n", + "Epoch 45/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1730.3800 - val_loss: 1736.1029\n", + "Epoch 46/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1714.5963 - val_loss: 1715.0453\n", + "Epoch 47/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1717.4546 - val_loss: 1771.3018\n", + "Epoch 48/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1712.6161 - val_loss: 1711.4847\n", + "Epoch 49/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 1702.8785 - val_loss: 1712.8119\n", + "Epoch 50/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1711.1716 - val_loss: 1700.8627\n", + "\u001b[1m3938/3938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 296us/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[I 2025-02-17 00:08:19,362] Trial 2 finished with value: 0.0 and parameters: {'h1': 32.18807766864932, 'h2': 32.38115474529778, 'h3': 82.71542742505292, 'h4': 21.39993663591346}. Best is trial 0 with value: 0.0.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1814.5203 - val_loss: 1661.1248\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1621.0743 - val_loss: 1503.6709\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1466.0696 - val_loss: 1357.3704\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1319.6273 - val_loss: 1204.6761\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1164.8816 - val_loss: 1049.8190\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 1012.0715 - val_loss: 900.6155\n", + "Epoch 7/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 866.8824 - val_loss: 782.1039\n", + "Epoch 8/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 765.9833 - val_loss: 752.7275\n", + "Epoch 9/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 752.8401 - val_loss: 751.8625\n", + "Epoch 10/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 752.4477 - val_loss: 755.2651\n", + "Epoch 11/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 752.4553 - val_loss: 750.9076\n", + "Epoch 12/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 752.6575 - val_loss: 751.2373\n", + "Epoch 13/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 751.5120 - val_loss: 750.2513\n", + "Epoch 14/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 750.1327 - val_loss: 749.1887\n", + "Epoch 15/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 750.2402 - val_loss: 748.8613\n", + "Epoch 16/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 751.2623 - val_loss: 748.6445\n", + "Epoch 17/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 750.6178 - val_loss: 748.5185\n", + "Epoch 18/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 749.1051 - val_loss: 748.1081\n", + "Epoch 19/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 749.3755 - val_loss: 747.6932\n", + "Epoch 20/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 748.1135 - val_loss: 747.2830\n", + "Epoch 21/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 747.3423 - val_loss: 747.2092\n", + "Epoch 22/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 747.1829 - val_loss: 747.7263\n", + "Epoch 23/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 747.6171 - val_loss: 746.8931\n", + "Epoch 24/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 746.1934 - val_loss: 746.4072\n", + "Epoch 25/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 747.4377 - val_loss: 746.0536\n", + "Epoch 26/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 747.3806 - val_loss: 745.7092\n", + "Epoch 27/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 746.1663 - val_loss: 745.9564\n", + "Epoch 28/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 746.9430 - val_loss: 745.2064\n", + "Epoch 29/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 744.6080 - val_loss: 745.0362\n", + "Epoch 30/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 745.1031 - val_loss: 745.5790\n", + "Epoch 31/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 744.9517 - val_loss: 746.2484\n", + "Epoch 32/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 745.3198 - val_loss: 744.7700\n", + "Epoch 33/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 746.6561 - val_loss: 744.3752\n", + "Epoch 34/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 744.4594 - val_loss: 744.5372\n", + "Epoch 35/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 745.4088 - val_loss: 744.5147\n", + "Epoch 36/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 745.0701 - val_loss: 743.8632\n", + "Epoch 37/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.1857 - val_loss: 744.3721\n", + "Epoch 38/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.1999 - val_loss: 743.6331\n", + "Epoch 39/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 744.2258 - val_loss: 743.9576\n", + "Epoch 40/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 744.8534 - val_loss: 743.3392\n", + "Epoch 41/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 744.1964 - val_loss: 743.3118\n", + "Epoch 42/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.2463 - val_loss: 744.1565\n", + "Epoch 43/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.7304 - val_loss: 742.9604\n", + "Epoch 44/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 742.8326 - val_loss: 743.0219\n", + "Epoch 45/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.7935 - val_loss: 742.7424\n", + "Epoch 46/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 742.9843 - val_loss: 742.6505\n", + "Epoch 47/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 741.9490 - val_loss: 742.4158\n", + "Epoch 48/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 741.9554 - val_loss: 742.6078\n", + "Epoch 49/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.1502 - val_loss: 742.2740\n", + "Epoch 50/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 743.5102 - val_loss: 742.0992\n", + "\u001b[1m3938/3938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 290us/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[I 2025-02-17 00:09:41,637] Trial 3 finished with value: 0.0 and parameters: {'h1': 51.147323536824445, 'h2': 56.78563118722674, 'h3': 31.302312703064025, 'h4': 0.2323539329544047}. Best is trial 0 with value: 0.0.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 27736.6758 - val_loss: 25335.9141\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 24856.6797 - val_loss: 23624.0430\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 23591.7324 - val_loss: 22455.3379\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 22087.6445 - val_loss: 21249.2285\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 21055.1582 - val_loss: 20346.3613\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 20397.3496 - val_loss: 19634.5000\n", + "Epoch 7/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 19168.5645 - val_loss: 18746.1426\n", + "Epoch 8/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 18433.6738 - val_loss: 18086.1094\n", + "Epoch 9/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 17888.7070 - val_loss: 17506.1172\n", + "Epoch 10/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 17398.0664 - val_loss: 16952.9180\n", + "Epoch 11/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 16835.0117 - val_loss: 16448.4297\n", + "Epoch 12/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 16369.1172 - val_loss: 15983.9541\n", + "Epoch 13/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 15914.9648 - val_loss: 15574.0117\n", + "Epoch 14/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 15417.1514 - val_loss: 15182.9922\n", + "Epoch 15/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 14972.8398 - val_loss: 14841.6963\n", + "Epoch 16/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 14821.4219 - val_loss: 14586.0078\n", + "Epoch 17/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 14475.7656 - val_loss: 14208.0049\n", + "Epoch 18/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 14218.5225 - val_loss: 13965.6191\n", + "Epoch 19/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 14080.0352 - val_loss: 13686.0967\n", + "Epoch 20/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 13640.7412 - val_loss: 13432.9609\n", + "Epoch 21/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 13297.7139 - val_loss: 13222.0645\n", + "Epoch 22/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 13205.2559 - val_loss: 13020.1660\n", + "Epoch 23/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 13046.4668 - val_loss: 12839.4688\n", + "Epoch 24/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12915.7373 - val_loss: 12695.6348\n", + "Epoch 25/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12565.1816 - val_loss: 12489.5596\n", + "Epoch 26/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12385.2871 - val_loss: 12334.8535\n", + "Epoch 27/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12441.1230 - val_loss: 12193.6494\n", + "Epoch 28/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12110.5723 - val_loss: 12051.1250\n", + "Epoch 29/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 12140.8193 - val_loss: 11922.8623\n", + "Epoch 30/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11870.8330 - val_loss: 11813.3994\n", + "Epoch 31/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11781.4502 - val_loss: 11694.6562\n", + "Epoch 32/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11774.9316 - val_loss: 11599.8086\n", + "Epoch 33/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11517.6182 - val_loss: 11493.0459\n", + "Epoch 34/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11443.8252 - val_loss: 11402.4766\n", + "Epoch 35/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11502.7910 - val_loss: 11311.7754\n", + "Epoch 36/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11410.6387 - val_loss: 11226.0420\n", + "Epoch 37/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11144.2510 - val_loss: 11152.2734\n", + "Epoch 38/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10994.5703 - val_loss: 11074.9717\n", + "Epoch 39/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11061.8809 - val_loss: 11009.4912\n", + "Epoch 40/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10965.7441 - val_loss: 10939.0264\n", + "Epoch 41/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 11017.5010 - val_loss: 10882.1914\n", + "Epoch 42/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10908.1650 - val_loss: 10822.1357\n", + "Epoch 43/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10795.5361 - val_loss: 10765.4912\n", + "Epoch 44/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10588.0283 - val_loss: 10712.4141\n", + "Epoch 45/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10675.9863 - val_loss: 10659.5850\n", + "Epoch 46/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10741.0137 - val_loss: 10615.9727\n", + "Epoch 47/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10552.5371 - val_loss: 10568.0938\n", + "Epoch 48/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10671.9209 - val_loss: 10526.0469\n", + "Epoch 49/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10479.7158 - val_loss: 10484.8340\n", + "Epoch 50/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 10387.6152 - val_loss: 10451.1416\n", + "\u001b[1m3938/3938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 313us/step\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[I 2025-02-17 00:11:09,995] Trial 4 finished with value: 0.0 and parameters: {'h1': 61.30953008699103, 'h2': 93.9200835460014, 'h3': 57.8376987539652, 'h4': 82.3346527788174}. Best is trial 0 with value: 0.0.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8271.6963 - val_loss: 8311.1768\n", + "Epoch 2/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8371.5420 - val_loss: 8275.3896\n", + "Epoch 3/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8377.3896 - val_loss: 8246.3291\n", + "Epoch 4/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8375.9121 - val_loss: 8216.7363\n", + "Epoch 5/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8269.5869 - val_loss: 8189.8159\n", + "Epoch 6/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8172.8184 - val_loss: 8167.1416\n", + "Epoch 7/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8084.1265 - val_loss: 8137.8125\n", + "Epoch 8/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8089.8613 - val_loss: 8119.4287\n", + "Epoch 9/50\n", + "\u001b[1m886/886\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2ms/step - loss: 8135.9199 - val_loss: 8094.7837\n", + "Epoch 10/50\n", + "\u001b[1m610/886\u001b[0m \u001b[32m━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 8253.8984" + ] + } + ], + "source": [ + "study = optuna.create_study(direction=\"maximize\")\n", + "study.optimize(lambda trial: objective(trial, preprocess, X_train, y_train, X_val, y_val, X_test, y_test), n_trials=100)" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -998,19 +1514,19 @@ }, { "cell_type": "code", - "execution_count": 102, + "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "\u001b[1m8/8\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 712us/step\n" + "\u001b[1m8/8\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step \n" ] }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -1020,7 +1536,7 @@ }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -1034,7 +1550,7 @@ "\n", "species = \"Ba\"\n", "iterations = 250\n", - "cell_offset = 900\n", + "cell_offset = 11\n", "y_design = []\n", "y_results = []\n", "y_differences = []\n", @@ -1478,7 +1994,7 @@ ], "metadata": { "kernelspec": { - "display_name": "training", + "display_name": "ai", "language": "python", "name": "python3" }, @@ -1492,7 +2008,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.11" + "version": "3.12.8" } }, "nbformat": 4,