diff --git a/src/POET_Training.ipynb b/src/POET_Training.ipynb
new file mode 100644
index 0000000..5091c02
--- /dev/null
+++ b/src/POET_Training.ipynb
@@ -0,0 +1,3206 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## General Information"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This notebook is used to train a simple neural network model to predict the chemistry in the barite benchmark (50x50 grid). The training data is stored in the repository using **git large file storage** and can be downloaded after the installation of git lfs using the `git lfs pull` command.\n",
+ "\n",
+ "It is then recommended to create a Python environment using miniconda. The necessary dependencies are contained in `environment.yml` and can be installed using `conda env create -f environment.yml`.\n",
+ "\n",
+ "The data set is divided into a design and result part and consists of the iterations of a reference simulation. The design part of the data set contains the chemical concentrations at time $t$ and the result part at time $t+1$, which are to be learned by the model."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Setup Libraries"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "2025-02-18 16:48:16.636424: 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",
+ "2025-02-18 16:48:16.655319: 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"
+ ]
+ }
+ ],
+ "source": [
+ "import keras\n",
+ "from keras.layers import Dense, Dropout, Input,BatchNormalization, LeakyReLU\n",
+ "import tensorflow as tf\n",
+ "import h5py\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import time\n",
+ "import sklearn.model_selection as sk\n",
+ "import matplotlib.pyplot as plt\n",
+ "from sklearn.cluster import KMeans\n",
+ "from sklearn.pipeline import Pipeline, make_pipeline\n",
+ "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
+ "from imblearn.over_sampling import SMOTE\n",
+ "from imblearn.under_sampling import RandomUnderSampler\n",
+ "from imblearn.over_sampling import RandomOverSampler\n",
+ "from collections import Counter\n",
+ "import os\n",
+ "from preprocessing import *\n",
+ "from sklearn import set_config\n",
+ "from importlib import reload\n",
+ "set_config(transform_output = \"pandas\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "%load_ext autoreload\n",
+ "%autoreload 2"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Define parameters"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "dtype = \"float32\"\n",
+ "activation = \"relu\"\n",
+ "\n",
+ "lr = 0.001\n",
+ "batch_size = 512\n",
+ "epochs = 50 # default 400 epochs\n",
+ "\n",
+ "lr_schedule = keras.optimizers.schedules.ExponentialDecay(\n",
+ " initial_learning_rate=lr,\n",
+ " decay_steps=2000,\n",
+ " decay_rate=0.9,\n",
+ " staircase=True\n",
+ ")\n",
+ "\n",
+ "optimizer_simple = keras.optimizers.Adam(learning_rate=lr_schedule)\n",
+ "optimizer_large = keras.optimizers.Adam(learning_rate=lr_schedule)\n",
+ "optimizer_paper = keras.optimizers.Adam(learning_rate=lr_schedule)\n",
+ "\n",
+ "\n",
+ "loss = keras.losses.Huber()\n",
+ "\n",
+ "sample_fraction = 0.8"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Setup the model"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/home/signer/bin/miniconda3/envs/training/lib/python3.11/site-packages/keras/src/layers/activations/leaky_relu.py:41: UserWarning: Argument `alpha` is deprecated. Use `negative_slope` instead.\n",
+ " warnings.warn(\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Model: \"sequential\"\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1mModel: \"sequential\"\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ dense (Dense) │ (None, 128) │ 1,152 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu (LeakyReLU) │ (None, 128) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_1 (Dense) │ (None, 128) │ 16,512 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_1 (LeakyReLU) │ (None, 128) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_2 (Dense) │ (None, 8) │ 1,032 │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m1,152\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m16,512\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_1 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m) │ \u001b[38;5;34m1,032\u001b[0m │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Total params: 18,696 (73.03 KB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m18,696\u001b[0m (73.03 KB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Trainable params: 18,696 (73.03 KB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m18,696\u001b[0m (73.03 KB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Non-trainable params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# small model\n",
+ "model_simple = keras.Sequential(\n",
+ " [\n",
+ " keras.Input(shape=(8,), dtype=\"float32\"),\n",
+ " keras.layers.Dense(units=128, dtype=\"float32\"),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " # Dropout(0.2),\n",
+ " keras.layers.Dense(units=128, dtype=\"float32\"),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(units=8, dtype=\"float32\")\n",
+ " ]\n",
+ ")\n",
+ "\n",
+ "model_simple.compile(optimizer=optimizer_simple, loss = loss)\n",
+ "model_simple.summary()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "Model: \"sequential_1\"\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ dense_3 (Dense) │ (None, 512) │ 4,608 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_2 (LeakyReLU) │ (None, 512) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_4 (Dense) │ (None, 1024) │ 525,312 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_3 (LeakyReLU) │ (None, 1024) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_5 (Dense) │ (None, 512) │ 524,800 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_4 (LeakyReLU) │ (None, 512) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_6 (Dense) │ (None, 8) │ 4,104 │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ dense_3 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m4,608\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_2 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_4 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m525,312\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_3 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_5 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m524,800\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_4 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_6 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m) │ \u001b[38;5;34m4,104\u001b[0m │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Total params: 1,058,824 (4.04 MB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m1,058,824\u001b[0m (4.04 MB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Trainable params: 1,058,824 (4.04 MB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,058,824\u001b[0m (4.04 MB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Non-trainable params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# large model\n",
+ "model_large = keras.Sequential(\n",
+ " [\n",
+ " keras.layers.Input(shape=(8,), dtype=dtype),\n",
+ " keras.layers.Dense(512, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(1024, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(512, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(8, dtype=dtype)\n",
+ " ]\n",
+ ")\n",
+ "\n",
+ "model_large.compile(optimizer=optimizer_large, loss = loss)\n",
+ "model_large.summary()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "Model: \"sequential_2\"\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1mModel: \"sequential_2\"\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ dense_7 (Dense) │ (None, 128) │ 1,152 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_5 (LeakyReLU) │ (None, 128) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_8 (Dense) │ (None, 256) │ 33,024 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_6 (LeakyReLU) │ (None, 256) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_9 (Dense) │ (None, 512) │ 131,584 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_7 (LeakyReLU) │ (None, 512) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_10 (Dense) │ (None, 256) │ 131,328 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_8 (LeakyReLU) │ (None, 256) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_11 (Dense) │ (None, 8) │ 2,056 │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ dense_7 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m1,152\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_5 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_8 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m33,024\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_6 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_9 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m131,584\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_7 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_10 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m131,328\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ leaky_re_lu_8 (\u001b[38;5;33mLeakyReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_11 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m) │ \u001b[38;5;34m2,056\u001b[0m │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Total params: 299,144 (1.14 MB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m299,144\u001b[0m (1.14 MB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Trainable params: 299,144 (1.14 MB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m299,144\u001b[0m (1.14 MB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Non-trainable params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# model from paper\n",
+ "# (see https://doi.org/10.1007/s11242-022-01779-3 model for the complex chemistry)\n",
+ "model_paper = keras.Sequential(\n",
+ " [keras.layers.Input(shape=(8,), dtype=dtype),\n",
+ " keras.layers.Dense(128, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(256, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(512, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(256, dtype=dtype),\n",
+ " LeakyReLU(alpha=0.01),\n",
+ " keras.layers.Dense(8, dtype=dtype)\n",
+ " ])\n",
+ "\n",
+ "model_paper.compile(optimizer=optimizer_paper, loss = loss)\n",
+ "model_paper.summary()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Define transformer functions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def Safelog(val):\n",
+ " # get range of vector\n",
+ " if val > 0:\n",
+ " return np.log10(val)\n",
+ " elif val < 0:\n",
+ " return -np.log10(-val)\n",
+ " else:\n",
+ " return 0\n",
+ "\n",
+ "def Safeexp(val):\n",
+ " if val > 0:\n",
+ " return -10 ** -val\n",
+ " elif val < 0:\n",
+ " return 10 ** val\n",
+ " else:\n",
+ " return 0"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ? Why does the charge is using another logarithm than the other species\n",
+ "\n",
+ "func_dict_in = {\n",
+ " \"H\" : np.log1p,\n",
+ " \"O\" : np.log1p,\n",
+ " \"Charge\" : Safelog,\n",
+ " \"H_0_\" : np.log1p,\n",
+ " \"O_0_\" : np.log1p,\n",
+ " \"Ba\" : np.log1p,\n",
+ " \"Cl\" : np.log1p,\n",
+ " \"S_2_\" : np.log1p,\n",
+ " \"S_6_\" : np.log1p,\n",
+ " \"Sr\" : np.log1p,\n",
+ " \"Barite\" : np.log1p,\n",
+ " \"Celestite\" : np.log1p,\n",
+ "}\n",
+ "\n",
+ "func_dict_out = {\n",
+ " \"H\" : np.expm1,\n",
+ " \"O\" : np.expm1,\n",
+ " \"Charge\" : Safeexp,\n",
+ " \"H_0_\" : np.expm1,\n",
+ " \"O_0_\" : np.expm1,\n",
+ " \"Ba\" : np.expm1,\n",
+ " \"Cl\" : np.expm1,\n",
+ " \"S_2_\" : np.expm1,\n",
+ " \"S_6_\" : np.expm1,\n",
+ " \"Sr\" : np.expm1,\n",
+ " \"Barite\" : np.expm1,\n",
+ " \"Celestite\" : np.expm1,\n",
+ "}\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Read data from `.h5` file and convert it to a `pandas.DataFrame`"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# os.chdir('/mnt/beegfs/home/signer/projects/model-training')\n",
+ "# data_file = h5py.File(\"barite_50_ai_20k.h5\")\n",
+ "data_file = h5py.File(\"../datasets/barite_50_4_corner.h5\")\n",
+ "\n",
+ "design = data_file[\"design\"]\n",
+ "results = data_file[\"result\"]\n",
+ "\n",
+ "df_design = pd.DataFrame(np.array(design[\"data\"]).transpose(), columns = np.array(design[\"names\"].asstr()))\n",
+ "df_results = pd.DataFrame(np.array(results[\"data\"]).transpose(), columns = np.array(results[\"names\"].asstr()))\n",
+ "\n",
+ "data_file.close()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Preprocess Data\n",
+ "\n",
+ "The data are preprocessed in the following way:\n",
+ "\n",
+ "1. Label data points in the `design` dataset with `reactive` and `non-reactive` labels using kmeans clustering\n",
+ "2. Transform `design` and `results` data set into log-scaled data.\n",
+ "3. Split data into training and test sets.\n",
+ "4. Learn scaler on training data for `design` and `results` together (option `global`) or individual (option `individual`).\n",
+ "5. Transform training and test data.\n",
+ "6. Split training data into training and validation dataset."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "species_columns = ['H', 'O', 'Ba', 'Cl', 'S', 'Sr', 'Barite', 'Celestite']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "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",
+ " return fit_method(estimator, *args, **kwargs)\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "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"
+ ]
+ },
+ {
+ "ename": "Exception",
+ "evalue": "No valid scaler type found",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mException\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[11], line 7\u001b[0m\n\u001b[1;32m 5\u001b[0m X_train, X_test, y_train, y_test \u001b[38;5;241m=\u001b[39m preprocess\u001b[38;5;241m.\u001b[39msplit(X, y, ratio \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0.2\u001b[39m)\n\u001b[1;32m 6\u001b[0m X_train, y_train \u001b[38;5;241m=\u001b[39m preprocess\u001b[38;5;241m.\u001b[39mbalancer(X_train, y_train, strategy \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mover\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 7\u001b[0m preprocess\u001b[38;5;241m.\u001b[39mscale_fit(X_train, y_train, scaling \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mglobal\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28mtype\u001b[39m\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMinMax\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 8\u001b[0m X_train, X_test, y_train, y_test \u001b[38;5;241m=\u001b[39m preprocess\u001b[38;5;241m.\u001b[39mscale_transform(X_train, X_test, y_train, y_test)\n\u001b[1;32m 9\u001b[0m X_train, X_val, y_train, y_val \u001b[38;5;241m=\u001b[39m preprocess\u001b[38;5;241m.\u001b[39msplit(X_train, y_train, ratio \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0.1\u001b[39m)\n",
+ "File \u001b[0;32m~/Documents/model-training/src/preprocessing.py:341\u001b[0m, in \u001b[0;36mpreprocessing.scale_fit\u001b[0;34m(self, X, y, scaling, type)\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscaler_y \u001b[38;5;241m=\u001b[39m StandardScaler()\n\u001b[1;32m 340\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 341\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo valid scaler type found\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 343\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m scaling \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mindividual\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m 344\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscaler_X\u001b[38;5;241m.\u001b[39mfit(X\u001b[38;5;241m.\u001b[39miloc[:, X\u001b[38;5;241m.\u001b[39mcolumns \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mClass\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n",
+ "\u001b[0;31mException\u001b[0m: No valid scaler type found"
+ ]
+ }
+ ],
+ "source": [
+ "preprocess = preprocessing(func_dict_in=func_dict_in, func_dict_out=func_dict_out)\n",
+ "X, y = preprocess.cluster(df_design[species_columns], df_results[species_columns])\n",
+ "# 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",
+ "preprocess.scale_fit(X_train, y_train, scaling = \"global\", type=\"MinMax\")\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)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaEAAAGdCAYAAAC7EMwUAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAI11JREFUeJzt3X94VPWB7/HPSSaZJDAJRCFDJNpYUvzBYq9gKdQK/iCVx7VYt91WfCxWu1cFXFJuF0WfvWL3LkF6pepGsdZete0qbltQt7d6yX2U0D5c7wYkK4WWlTbFXCANKMwMPzL5Md/7h81IyMyZTDKT78zk/Xqe+YNzzky+PZTz9mS+5xzHGGMEAIAFebYHAAAYvYgQAMAaIgQAsIYIAQCsIUIAAGuIEADAGiIEALCGCAEArPHYHsDZIpGIDh06JJ/PJ8dxbA8HAJAkY4xCoZAqKyuVl+d+rpNxETp06JCqqqpsDwMAMExtbW2aPHmy6zYZFyGfzydJ+v3OKvnGjuxvCwuc/Ljruk1vWn7mv1/h0WeCv3fd5q/1lwo7Mf6quOMSMPJcfkPjfPqimMvLu4L6H3uecv3Y3pvGqOeRc4c0JBvHLjehExF9ckZb9HjuJuMi1PcrON/YPJX6RjpC8X9ed5oO+GOcfJUm2KbAKVBvrAiJCAEjzi1C+d6YywvyvQn/nfcWOOoZ4jHPxrFrMAbzlQoTEwAA1hAhAIA1RAgAYE3GfSeUTnly//2k2xd4bu+NJPhu5snjn4y9whh96VSL63v7tuP7HyBDuHzHkv+n47GX95xI+LHOgW7X9W7HoKEeu6TEx69040zIFmM0d917qu7+wHWzNo1VWPFnvgDIfIH8Yn2QN8Z1m7x/Cyv/0WMjNKLMQYRs+HOAZrzwvutmHzrF+nt9ToaLdoGs1uPk679OWKhOn/svnzyPHh91ISJCIy2JAK2s+IoOOonn2QPIfH8onKCfPj+DEJ2FCI2kZANUMH6EBgZgJBy52EeIzkKERgoBAiBCdDYiNBIIEIAzEKKPEaER8Pn1+wkQgH6SCtE/HR+ZQVngGJNZd8EMBoMqKytTx74LUn7vOLeb/ElS2MSfp+9xmSbtOs8+GJHn4veV77KbP1SRvl18vQ7mDby7VOTUqfifDSCj5JWUuK5/7zvTByy7+OBBvfTkUyoNh+O+z3gd9bz3CckTe6Zsj+JfJ+R1ClzHlI4bnAZDEU2cekCBQEClpe53zeNMKN26jGuAJOnf8/0xAwQg9/32vPP0TvUnXLdxwkaKjMx4RhoRAgBYQ4QAANYQIQCANUQIAGANEQIAWJN1j3JIdFvyfJfH3J6KdLm+tySvMO46t2mMR3tPx13nbQnLq48exBBv5JHeiCKn438GgOyQ6N/xlI2xH+lQcjjxNGnz27DMZbEfH+42DXs4x71e4z4lLxWPgeBMKI0Kd3ap/O7jkuIHSJK2O5UjMh4Amen/jLso4TYFX2uXsyf+tUTZigilSeHOLp2z6JjyTrn/l8JTzmXa5lSN0KgAZKL/OXGmgt9yf96QE4io4Mu5FyIilAaDDdCGqi9os/OpERoVgEwWWuEblSEiQimWVID8s0doVACywWgMERFKIQIEYLhGW4iIUIoQIACpMppCRIRSgAABSLVkQqQsDlHGXidU4OSrIMY1P4luO97j8jgGt/nwg/nsWJwdnRrzlRPK63YP0NMFM/TK0Qlyju7vtzzDnqQBYDgS/Ht2frM/7rrrv7cyxhukez77hpa8vSX+ZwYi0l8dVPfPJ8lcMvAYl+i45/YIm7wE5ynxHo9T4Lhfz9n/Z2DInB2dKvhau0q63S8Ge7pghjZ7Lh6hUQHIJRvmXK+nPlvruo0TiKjgrw7L2et+LMpERGiI+gLkJPgV3CPzFhIgAMOyYc716lkxznWbbA0RERqCZAL0k8vnjtCoAOSy3m+Pz8kQEaEkESAAtuRiiIhQEggQANtyLUREaJAIEIBMkUyIMn36dsZO0e42veqOMd0x0aMc8hR7ymDfZw6Fs6NT3V/+QIVdCaZhj5mtt/b4dd6eff2W93Z2DunnAsgtEZdjwXk/3hd3nSRd4l/Wf4Ff+tvr/peW/+9BTN/+mV/m0tiPgfC4HDMTiXdM7U7wCIgzcSaUQN8Z0JiuBNOwx8zWKyXTR2hUACA9UfsFPX7dIKZvZ/CdFYiQi8H+Co4AAbDlidovDO5XcxkaIiIUx2AD9A83LiRAAKwa9HdEGRgiIhRDMgF6/vNXjdCoACC+bA0REToLAQKQrbIxREToDAQIQLbLthA5JsNu4xwMBlVWVqaOfReo1JfCRhqjwO6Q8o7Gnjro+WOvCh/uTHwz0hiTEHqPfpCyYQJALPnnnhN33cHbpg5Yds9297tvS1Kk1FHv358jc16cadp+j8xF7nfhjiUYimji1AMKBAIqLS113TZjrxNKKWOUv/pDTfxBcFgfwyw4ANliw5zrJck1RHlBo7y/O+r6OT3fHqfeFeNTOrZ+Y0jbJ2eKPwfIQ4AAjDIb5lyf8MF4iXj++3HlP3osRSOK8flp++RMkKIAPTJvod7a40/RoABg5IRW+CRJpd87OeTP8Dx6XJLU+19Sf0aUu2dCKQwQ94IDkM0G86jwRDyPpueMKDcjRIAAoJ9MDVHuRShFAVo3lwAByC2ZGKLcilAKA/TjGQQIQO7JtBBl3XVCP9pTqa9+fWfM9xYFulV4amiPa+jzdMEMbfZcPGC52y3YAcCmvKKiuOvMtCkxl9928C3ddqhpWD/XjMuTxgx8vE4wYjTucCQ3rxMa296p0sNDC8KHnhJt9s+WifNMovc6jFryJw1neACQFX583tXaN+Y8+T51POb6/IjRsl83qijUE/cznOMRKcbb3Z/61l/WRcjpHdqJ25GxY7Wy+nYdLDo3/md/sH+owwKArPNv4z6l/deMjbu+4psf6iu373QN0XBl3XdCJpnE/tmRsWP1tWVLXQMEAOjvyMU+/fT5Ger0pe98JesilGyD+gLUOmFCWsYDALks3SHKugglgwABwPClM0Q5GyECBACpk64QZewU7av/0/3y5HsHrJ/2/h6t7/iZ62d8qCJ9u/h6HczrPzUwcvq0+w/PrF0BAMPnuH+JkVdcHH9d+cB7xV3YdURrO34mn4n/2JugpDIpN6doH8336aCnLO76I5FiPeH97IAAAQCG7w+FE3TfxC9rybGtGu/EvlwmZIzUNbiLWbMuQkc8pfrmpNvjro98mL5bjgMApNbCCfq7iq+ot2JczPU9vWFp19pBfVbOficEAMh8RAgAYA0RAgBYQ4QAANYQIQCANcOaHVdfX68HHnhAy5cv12OPPSZJMsbo4Ycf1jPPPKNjx45p1qxZevLJJ3XppZcm9dmm5XcyTsGA5T1cywMAg5fgmBk5dWpI6yRJBw/F+ZHdCYfVZ8hnQs3NzXrmmWc0ffr0fsvXrVun9evXq6GhQc3NzfL7/Zo/f75CodBQfxQAIEcNKUInTpzQrbfeqh/84AcaP/7jK2qNMXrsscf04IMP6uabb9a0adP0wgsv6NSpU3rxxRdTNmgAQG4YUoSWLl2qG264Qdddd12/5a2trWpvb1dtbW10mdfr1dy5c7V9+/aYnxUOhxUMBvu9AACjQ9LfCW3cuFHvvPOOmpubB6xrb2+XJFVUVPRbXlFRoQMHDsT8vPr6ej388MPJDgMAkAOSOhNqa2vT8uXL9ZOf/ERFLs80d866YZ4xZsCyPqtWrVIgEIi+2trakhkSACCLJXUmtHPnTnV0dGjGjBnRZb29vdq2bZsaGhq0b98+SR+dEU2aNCm6TUdHx4Czoz5er1de78C7ZQMAcl9SZ0LXXnutdu/erZaWluhr5syZuvXWW9XS0qILL7xQfr9fjY2N0fd0dXWpqalJc+bMSW5kxsR+AQAyQ7zjdBLH6qTOhHw+n6ZNm9Zv2ZgxY3TOOedEl9fV1WnNmjWqqalRTU2N1qxZo5KSEi1atCiZHwUAGAVS/iiHlStX6vTp01qyZEn0YtUtW7bI5/Ol+kcBALJcxj5ZdZ4WyhPjjgkAgMzWY7q1Va8O6smq3DsOAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWJBWhDRs2aPr06SotLVVpaalmz56t119/PbreGKPVq1ersrJSxcXFmjdvnvbs2ZPyQQMAckNSEZo8ebLWrl2rHTt2aMeOHbrmmmu0cOHCaGjWrVun9evXq6GhQc3NzfL7/Zo/f75CoVBaBg8AyG6OMcYM5wPKy8v13e9+V3fccYcqKytVV1en++67T5IUDodVUVGhRx55RHfdddegPi8YDKqsrEzztFAep2A4QwMAWNBjurVVryoQCKi0tNR12yF/J9Tb26uNGzfq5MmTmj17tlpbW9Xe3q7a2troNl6vV3PnztX27dvjfk44HFYwGOz3AgCMDklHaPfu3Ro7dqy8Xq/uvvtubd68WZdccona29slSRUVFf22r6ioiK6Lpb6+XmVlZdFXVVVVskMCAGSppCM0depUtbS06O2339Y999yjxYsXa+/evdH1juP0294YM2DZmVatWqVAIBB9tbW1JTskAECW8iT7hsLCQk2ZMkWSNHPmTDU3N+vxxx+Pfg/U3t6uSZMmRbfv6OgYcHZ0Jq/XK6/Xm+wwAAA5YNjXCRljFA6HVV1dLb/fr8bGxui6rq4uNTU1ac6cOcP9MQCAHJTUmdADDzygBQsWqKqqSqFQSBs3btTWrVv1xhtvyHEc1dXVac2aNaqpqVFNTY3WrFmjkpISLVq0KF3jBwBksaQi9Kc//Um33XabDh8+rLKyMk2fPl1vvPGG5s+fL0lauXKlTp8+rSVLlujYsWOaNWuWtmzZIp/Pl5bBAwCy27CvE0o1rhMCgOw2ItcJAQAwXEQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWJNUhOrr63XFFVfI5/Np4sSJuummm7Rv375+2xhjtHr1alVWVqq4uFjz5s3Tnj17UjpoAEBuSCpCTU1NWrp0qd5++201Njaqp6dHtbW1OnnyZHSbdevWaf369WpoaFBzc7P8fr/mz5+vUCiU8sEDALKbY4wxQ33zkSNHNHHiRDU1Nemqq66SMUaVlZWqq6vTfffdJ0kKh8OqqKjQI488orvuuivhZwaDQZWVlWmeFsrjFAx1aAAAS3pMt7bqVQUCAZWWlrpuO6zvhAKBgCSpvLxcktTa2qr29nbV1tZGt/F6vZo7d662b98e8zPC4bCCwWC/FwBgdBhyhIwxWrFiha688kpNmzZNktTe3i5Jqqio6LdtRUVFdN3Z6uvrVVZWFn1VVVUNdUgAgCwz5AgtW7ZM7777rl566aUB6xzH6fdnY8yAZX1WrVqlQCAQfbW1tQ11SACALOMZypvuvfdevfbaa9q2bZsmT54cXe73+yV9dEY0adKk6PKOjo4BZ0d9vF6vvF7vUIYBAMhySZ0JGWO0bNkybdq0SW+++aaqq6v7ra+urpbf71djY2N0WVdXl5qamjRnzpzUjBgAkDOSOhNaunSpXnzxRb366qvy+XzR73nKyspUXFwsx3FUV1enNWvWqKamRjU1NVqzZo1KSkq0aNGitPwPAABkr6QitGHDBknSvHnz+i1/7rnndPvtt0uSVq5cqdOnT2vJkiU6duyYZs2apS1btsjn86VkwACA3DGs64TSgeuEACC7jdh1QgAADAcRAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYQ4QAANYQIQCANUQIAGANEQIAWEOEAADWECEAgDVECABgDRECAFhDhAAA1hAhAIA1RAgAYA0RAgBYk3SEtm3bphtvvFGVlZVyHEevvPJKv/XGGK1evVqVlZUqLi7WvHnztGfPnlSNFwCQQ5KO0MmTJ3XZZZepoaEh5vp169Zp/fr1amhoUHNzs/x+v+bPn69QKDTswQIAcosn2TcsWLBACxYsiLnOGKPHHntMDz74oG6++WZJ0gsvvKCKigq9+OKLuuuuu4Y3WgBATknpd0Ktra1qb29XbW1tdJnX69XcuXO1ffv2VP4oAEAOSPpMyE17e7skqaKiot/yiooKHThwIOZ7wuGwwuFw9M/BYDCVQwIAZLC0zI5zHKffn40xA5b1qa+vV1lZWfRVVVWVjiEBADJQSiPk9/slfXxG1Kejo2PA2VGfVatWKRAIRF9tbW2pHBIAIIOlNELV1dXy+/1qbGyMLuvq6lJTU5PmzJkT8z1er1elpaX9XgCA0SHp74ROnDih/fv3R//c2tqqlpYWlZeX6/zzz1ddXZ3WrFmjmpoa1dTUaM2aNSopKdGiRYuS+0GO89HrbMYkO2QAQDrE+ZpFcqRBHqqTjtCOHTt09dVXR/+8YsUKSdLixYv1/PPPa+XKlTp9+rSWLFmiY8eOadasWdqyZYt8Pl+yPwoAkOMcYzLr1CIYDKqsrEzznJvkcQoGbpBZwwWA0SvOmVCP6dZW84oCgUDCr1i4dxwAwBoiBACwhggBAKxJ6R0TRkKR6dF0HYm7/oiK1eqMG7kBAcBoY4xqdFzjFY65Omx6tHWQH5WxEXI+fZGcfO+A5ZP+3+/1j+2vuL73ec+n9VLh9AHLI6dPu/9QJj0AyDVxp1F/JK+4OP668vEDFxqjOwO/1pdD78Sdhh2U9Oggh5d1v44r7UkQEkm3d7folq53R2A0ADCKnBmgFMm6CCWIehQhAoAUSkOApCyMUN5gL8MVIQKAlEhTgKQsjFBvktsTIgAYhjQGSMrgiQnxDfL3cWe4vbtFkvTPqknxWAAgh6U5QFIWngkNdf7a7d0tWmR+m9KxAEDOGoEASVl4JnQqb+C07cH6hvmNvmj2x13/Hxqv7+oKhZzCIf8MAMgG5ea0VppmfeJU7KdZ5xmj8epM+zgy9gamHfsuUKlv4Inas++fr0s3HYr53qJAt/7iuUMa09UVc71R4l/m7dc43V80XyGnf+winen/ywCAocgrKoq7zkybMmBZeVdI3/3dc6oKfzjkn9lZ6pHnb8ZKYwcep4Nho3PWHhvUDUyz7kwoXFqgd26/IO76fyy5Sf+84WmVxojGYL5NmqLjWtvZGDNEAJDtUhGgk+UF+pcfzdSiy9tjru8NRaS1xwb1WVn3nVAieyZP1q333K2gy38ZJNIXIp+JfUsKAMhGqQzQsQvHpGRMORchiRABwNkyMUBSjkZIIkQA0CdTAyTlcISkVIco9mQHAMhkmRwgKccjJKUuROvURIgAZJVycyqjAyRl4RTtoXJ2h2UeOqK8DyIx1+cfjCjvlPuu+H3+Obpv3F/qRF7/oPUe/SBl4wSAWPLPPSfuuoO3TR2w7NwTQT33Lw36xPGjrp9rfI6MP85EaX++ev7bOTI1yV07GQxFNHHqgdycoj1U5i+8OvrT+H+JChvtn1+uua3x76rwyd4P9MjxX8QMEQBkisEG6NQXvcpvmCR5kr8dWqrk/K/jBs3r6Fs3fkNN1Re7btYXorERLl4FkHmSCdCxx8dZDZBEhPrp9ngIEYCslW0BkojQAIQIQDbKxgBJRCimZEPErDkANmVrgCQiFFcyIWL6NgBbyntPZm2AJCLkarAhmqIAIQIw4sp7T2rd8X/N2gBJWXidUN4QnqzaJzLUR+KFjbZfX6Sr9/3OdTOuIwIwVG7XAUnSe3/3qX5/nhAM6sUNDbrwA/fjS+/CMer5pwlxA5SOY2oy1wlxJjQYXkdLFn9Db029yHUzJisAGAmpClAmIEKD1OXxECIA1uVSgCQilBRCBMCmXAuQRISSRogA2JCLAZKI0JAkGyJmzQEYjvLekzkZIIkIDVkyIWL6NoCh6puGnYsBkjJ4ivax/7gw5hTtbtPr+v6IYj+qQZK8ToHrexN9dkxho/97TZGuanWfvr1f43R/0XyFHG+/5ZFOfl0HjBZ5Ls81O3TP5QOWDfZOCG4BKnDyXd8bNt1x1+UlOE+J99nBUETjP/UHpmiPCK+juhvvGMQFrTwqHMDgpSJA2YAIpcDg76xAiAAkNloCJBGhlCFEAFJhNAVIIkIpRYgADMdoC5BEhFIu+RAxaw7A6AyQRITSIpkQMX0bQLk5NSoDJEke2wOIp9v0qjvG7PFEd3wtcJmGfSrifrAvySt0HU88b3xrXewVf2vUeWehipri/9wpCuhr+p1+4FwWe4PMmkEPwI3jfnwy06bEXL649VV94miCAN1YMqRp2MM57vWa+Je8SPGPi90J3ncmzoTSyevo+LqyhJudq9MjMBgAmeqc7lDCbXq+l1tnQH2IUJqZ+P+RAQCDl4MBkogQAMAiIgQAsIYIAQCsIUIAAGuIUAYoUY/tIQCwxRiV9I7eu6dk7HVC8UTkft1MxOV6Hrf58JL7Lc09ij8P/9z84vgfWm7UXhqWPxiMu8lndVi35r+nlwqnD1gXOXUq/mcDyCh5xS7HAknvfW1s/wXG6P5f/EKXnmhzfV/kwgLlFThSnOsk3Y5diY57Q3qETQpxJpRuBY7+5s47FHR5jogk3d7dolu63h2hQQGw7s8B+s9bm9w3OydPPc9NTHghbLYiQiNgz+TJuvWeuwkRgI8kEaDuTZNkanL3gkMiNEIIEQBJBOgsRGgEESJglCNAAxChEUaIgFGKAMVEhCxIJkRfNb8boVEBSKdvdO8iQDFk3RTt4Uh0W/K8NDV52YI3Yi5/7XPTdcuXm5XvMu3869qrTaZG3S63ageQGfLKx8dcPra3U3996Deu7zVFzpAD5HbsSnTcs40zIYs6LinVO0Xnu25TqIhrpABkPq/pSXiwjVxfMqrOgPoQIct6+SsAIEkFuXkdUCIcAQEA1hAhAIA1RAgAYA0RAgBYk7YIPfXUU6qurlZRUZFmzJihX/3qV+n6UVktmF+sU06BOuVRp+NRpzwKK19dylOP8tShYubGAVku4jg6kj9WkXxHvQWOegoddXvz1F2Up66iPIXHemTGjc5zAscYk/Jj3Msvv6zbbrtNTz31lD73uc/p+9//vp599lnt3btX55/vPiU5GAyqrKxMHfsuUKlvZP9SClyuxUnX7c5v/OLXXdebd/a6rCRPwIhzuZu1c/klrm/919d+lOrRSLJz7HITDEU0ceoBBQIBlZaWum6blqP8+vXrdeedd+qb3/ymLr74Yj322GOqqqrShg0b0vHjAABZKuUR6urq0s6dO1VbW9tveW1trbZv357qHwcAyGIpv23P0aNH1dvbq4qKin7LKyoq1N7ePmD7cDiscPjjR9sGXZ5ACgDILWn70sU56/emxpgByySpvr5eZWVl0VdVVVW6hgQAyDApj9C5556r/Pz8AWc9HR0dA86OJGnVqlUKBALRV1ub+7PWAQC5I+W/jissLNSMGTPU2NioL33pS9HljY2NWrhw4YDtvV6vvF5v9M99k/VCJ0b+zq8FLrNeutN0J9qe3rDremO63VameDQAEnOZHZfg33MwlJ7jiI1jl5u+4/egJl+bNNi4caMpKCgwP/zhD83evXtNXV2dGTNmjPnjH/+Y8L1tbW1GEi9evHjxyvJXW1tbwmN+Wp4n9NWvflUffPCBvvOd7+jw4cOaNm2afvnLX+qCCy5I+N7Kykq1tbXJ5/PJcRwFg0FVVVWpra0t4Xzz0Yz9NDjsp8FhPw0O+yk2Y4xCoZAqKysTbpuWi1VTqe/i1cFc9DSasZ8Gh/00OOynwWE/Dd/ovE8EACAjECEAgDUZHyGv16uHHnqo3ww6DMR+Ghz20+CwnwaH/TR8Gf+dEAAgd2X8mRAAIHcRIQCANUQIAGANEQIAWJPxEeIx4f1t27ZNN954oyorK+U4jl555ZV+640xWr16tSorK1VcXKx58+Zpz549dgZrSX19va644gr5fD5NnDhRN910k/bt29dvG/aTtGHDBk2fPl2lpaUqLS3V7Nmz9frrr0fXs49iq6+vl+M4qquriy5jXw1dRkfo5ZdfVl1dnR588EHt2rVLn//857VgwQK9//77todmzcmTJ3XZZZepoaEh5vp169Zp/fr1amhoUHNzs/x+v+bPn69QKDTCI7WnqalJS5cu1dtvv63Gxkb19PSotrZWJ0+ejG7DfpImT56stWvXaseOHdqxY4euueYaLVy4MHrwZB8N1NzcrGeeeUbTp0/vt5x9NQzDuE9p2n3mM58xd999d79lF110kbn//vstjSizSDKbN2+O/jkSiRi/32/Wrl0bXdbZ2WnKysrM008/bWGEmaGjo8NIMk1NTcYY9pOb8ePHm2effZZ9FEMoFDI1NTWmsbHRzJ071yxfvtwYw/+fhitjz4R4THjyWltb1d7e3m+feb1ezZ07d1Tvs0AgIEkqLy+XxH6Kpbe3Vxs3btTJkyc1e/Zs9lEMS5cu1Q033KDrrruu33L21fCk5S7aqZDsY8Kh6H6Jtc8OHDhgY0jWGWO0YsUKXXnllZo2bZok9tOZdu/erdmzZ6uzs1Njx47V5s2bdckll0QPnuyjj2zcuFHvvPOOmpubB6zj/0/Dk7ER6jPYx4TjY+yzjy1btkzvvvuufv3rXw9Yx36Spk6dqpaWFh0/flw///nPtXjxYjU1NUXXs4+ktrY2LV++XFu2bFFRUVHc7dhXQ5Oxv45L9jHhkPx+vySxz/7s3nvv1Wuvvaa33npLkydPji5nP32ssLBQU6ZM0cyZM1VfX6/LLrtMjz/+OPvoDDt37lRHR4dmzJghj8cjj8ejpqYmPfHEE/J4PNH9wb4amoyN0JmPCT9TY2Oj5syZY2lUma26ulp+v7/fPuvq6lJTU9Oo2mfGGC1btkybNm3Sm2++qerq6n7r2U/xGWMUDofZR2e49tprtXv3brW0tERfM2fO1K233qqWlhZdeOGF7KvhsDcnIrHhPCY8V4VCIbNr1y6za9cuI8msX7/e7Nq1yxw4cMAYY8zatWtNWVmZ2bRpk9m9e7e55ZZbzKRJk0wwGLQ88pFzzz33mLKyMrN161Zz+PDh6OvUqVPRbdhPxqxatcps27bNtLa2mnfffdc88MADJi8vz2zZssUYwz5yc+bsOGPYV8OR0REyxpgnn3zSXHDBBaawsNBcfvnl0Wm2o9Vbb70V81nuixcvNsZ8NF30oYceMn6/33i9XnPVVVeZ3bt32x30CIu1fySZ5557LroN+8mYO+64I/pva8KECebaa6+NBsgY9pGbsyPEvho6HuUAALAmY78TAgDkPiIEALCGCAEArCFCAABriBAAwBoiBACwhggBAKwhQgAAa4gQAMAaIgQAsIYIAQCsIUIAAGv+PwlvAcOcq2RNAAAAAElFTkSuQmCC",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "timestep=250\n",
+ "plt.imshow(np.array(X[\"Barite\"][(timestep*2500):(timestep*2500+2500)]).reshape(50,50), origin='lower')\n",
+ "plt.contour(np.array(X[\"Class\"][(timestep*2500):(timestep*2500+2500)]).reshape(50,50), origin='lower', colors='red')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Custom Loss function"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "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\"), \"H\":X.columns.get_loc(\"H\"), \"H\":X.columns.get_loc(\"H\"), \"O\":X.columns.get_loc(\"O\")}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def custom_loss(preprocess, column_dict, h1, h2, h3, h4, scaler_type=\"minmax\"):\n",
+ " # extract the scaling parameters\n",
+ " \n",
+ " if scaler_type == \"minmax\":\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",
+ " elif scaler_type == \"standard\":\n",
+ " scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32)\n",
+ " mean_X = tf.convert_to_tensor(preprocess.scaler_X.mean_, dtype=tf.float32)\n",
+ " scale_y = tf.convert_to_tensor(preprocess.scaler_y.scale_, dtype=tf.float32)\n",
+ " mean_y = tf.convert_to_tensor(preprocess.scaler_y.mean_, dtype=tf.float32)\n",
+ "\n",
+ " def loss(results, predicted):\n",
+ " \n",
+ " # inverse min/max scaling\n",
+ " if scaler_type == \"minmax\":\n",
+ " predicted_inverse = predicted * scale_y + min_y\n",
+ " results_inverse = results * scale_X + min_X\n",
+ " \n",
+ " elif scaler_type == \"standard\":\n",
+ " predicted_inverse = predicted * scale_y + mean_y\n",
+ " results_inverse = results * scale_X + mean_X\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 + h3 * dSr #+ h4 * h2o_ratio\n",
+ " # total_loss = huber_loss\n",
+ " return total_loss\n",
+ "\n",
+ " return loss\n",
+ "\n",
+ "\n",
+ "def custom_metric(preprocess, column_dict, scaler_type=\"minmax\"):\n",
+ " \n",
+ " if scaler_type == \"minmax\":\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",
+ " elif scaler_type == \"standard\":\n",
+ " scale_X = tf.convert_to_tensor(preprocess.scaler_X.scale_, dtype=tf.float32)\n",
+ " mean_X = tf.convert_to_tensor(preprocess.scaler_X.mean_, dtype=tf.float32)\n",
+ " scale_y = tf.convert_to_tensor(preprocess.scaler_y.scale_, dtype=tf.float32)\n",
+ " mean_y = tf.convert_to_tensor(preprocess.scaler_y.mean_, dtype=tf.float32)\n",
+ " \n",
+ " \n",
+ " def mass_balance(results, predicted):\n",
+ " # inverse min/max scaling\n",
+ " if scaler_type == \"minmax\":\n",
+ " predicted_inverse = predicted * scale_y + min_y\n",
+ " results_inverse = results * scale_X + min_X\n",
+ " \n",
+ " elif scaler_type == \"standard\":\n",
+ " predicted_inverse = predicted * scale_y + mean_y\n",
+ " results_inverse = results * scale_X + mean_X\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",
+ " return tf.reduce_mean(dBa + dSr)\n",
+ " \n",
+ " return mass_balance\n",
+ "\n",
+ "\n",
+ "def huber_metric(delta=1.0):\n",
+ " def huber(results, predicted):\n",
+ " return tf.keras.losses.huber(results, predicted, delta=delta)\n",
+ " \n",
+ " return huber"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model_simple.compile(optimizer=optimizer_simple, loss=custom_loss(preprocess, column_dict, 1, 1, 1, 1, \"minmax\"))\n",
+ "\n",
+ "model_large.compile(optimizer=optimizer_large, loss=custom_loss(preprocess, column_dict, 1, 1, 1, 1, \"minmax\"), metrics=[huber_metric(1.0), custom_metric(preprocess, column_dict, scaler_type=\"minmax\")])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Train the model"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# measure time\n",
+ "def model_training(model):\n",
+ " start = time.time()\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=100, \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",
+ " print(\"Training took {} seconds\".format(end - start))\n",
+ " \n",
+ " return history"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Epoch 1/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 13ms/step - huber: 0.0280 - loss: 0.5766 - mass_balance: 0.5486 - val_huber: 0.0052 - val_loss: 0.3554 - val_mass_balance: 0.3502\n",
+ "Epoch 2/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 0.0038 - loss: 0.1885 - mass_balance: 0.1847 - val_huber: 0.0013 - val_loss: 0.1407 - val_mass_balance: 0.1394\n",
+ "Epoch 3/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 17ms/step - huber: 9.8317e-04 - loss: 0.1252 - mass_balance: 0.1242 - val_huber: 6.6276e-04 - val_loss: 0.1825 - val_mass_balance: 0.1818\n",
+ "Epoch 4/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m47s\u001b[0m 28ms/step - huber: 5.5962e-04 - loss: 0.1058 - mass_balance: 0.1052 - val_huber: 4.2667e-04 - val_loss: 0.1063 - val_mass_balance: 0.1058\n",
+ "Epoch 5/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m34s\u001b[0m 20ms/step - huber: 4.1409e-04 - loss: 0.0987 - mass_balance: 0.0983 - val_huber: 2.7614e-04 - val_loss: 0.0551 - val_mass_balance: 0.0548\n",
+ "Epoch 6/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 13ms/step - huber: 2.9547e-04 - loss: 0.0840 - mass_balance: 0.0837 - val_huber: 2.2160e-04 - val_loss: 0.0798 - val_mass_balance: 0.0796\n",
+ "Epoch 7/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 13ms/step - huber: 2.2008e-04 - loss: 0.0703 - mass_balance: 0.0701 - val_huber: 1.5488e-04 - val_loss: 0.0621 - val_mass_balance: 0.0620\n",
+ "Epoch 8/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 15ms/step - huber: 1.5455e-04 - loss: 0.0563 - mass_balance: 0.0562 - val_huber: 1.4596e-04 - val_loss: 0.0520 - val_mass_balance: 0.0519\n",
+ "Epoch 9/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m34s\u001b[0m 20ms/step - huber: 1.3447e-04 - loss: 0.0548 - mass_balance: 0.0547 - val_huber: 9.0868e-05 - val_loss: 0.0258 - val_mass_balance: 0.0257\n",
+ "Epoch 10/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 17ms/step - huber: 1.0780e-04 - loss: 0.0512 - mass_balance: 0.0511 - val_huber: 1.0800e-04 - val_loss: 0.0882 - val_mass_balance: 0.0880\n",
+ "Epoch 11/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 13ms/step - huber: 9.2014e-05 - loss: 0.0469 - mass_balance: 0.0468 - val_huber: 6.0724e-05 - val_loss: 0.0343 - val_mass_balance: 0.0343\n",
+ "Epoch 12/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 14ms/step - huber: 7.2128e-05 - loss: 0.0386 - mass_balance: 0.0386 - val_huber: 5.6025e-05 - val_loss: 0.0444 - val_mass_balance: 0.0444\n",
+ "Epoch 13/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 21ms/step - huber: 6.2327e-05 - loss: 0.0383 - mass_balance: 0.0382 - val_huber: 4.8252e-05 - val_loss: 0.0264 - val_mass_balance: 0.0263\n",
+ "Epoch 14/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 5.0254e-05 - loss: 0.0289 - mass_balance: 0.0289 - val_huber: 4.7942e-05 - val_loss: 0.0367 - val_mass_balance: 0.0366\n",
+ "Epoch 15/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 14ms/step - huber: 4.9434e-05 - loss: 0.0317 - mass_balance: 0.0316 - val_huber: 3.9466e-05 - val_loss: 0.0483 - val_mass_balance: 0.0483\n",
+ "Epoch 16/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 4.1831e-05 - loss: 0.0292 - mass_balance: 0.0292 - val_huber: 3.3752e-05 - val_loss: 0.0254 - val_mass_balance: 0.0254\n",
+ "Epoch 17/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 22ms/step - huber: 3.5998e-05 - loss: 0.0254 - mass_balance: 0.0254 - val_huber: 3.6478e-05 - val_loss: 0.0198 - val_mass_balance: 0.0197\n",
+ "Epoch 18/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m25s\u001b[0m 15ms/step - huber: 3.1113e-05 - loss: 0.0216 - mass_balance: 0.0216 - val_huber: 2.5108e-05 - val_loss: 0.0183 - val_mass_balance: 0.0183\n",
+ "Epoch 19/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 18ms/step - huber: 2.6720e-05 - loss: 0.0199 - mass_balance: 0.0198 - val_huber: 2.1269e-05 - val_loss: 0.0195 - val_mass_balance: 0.0195\n",
+ "Epoch 20/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 24ms/step - huber: 2.2666e-05 - loss: 0.0166 - mass_balance: 0.0166 - val_huber: 2.1749e-05 - val_loss: 0.0166 - val_mass_balance: 0.0166\n",
+ "Epoch 21/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 21ms/step - huber: 1.9886e-05 - loss: 0.0147 - mass_balance: 0.0147 - val_huber: 2.0177e-05 - val_loss: 0.0258 - val_mass_balance: 0.0258\n",
+ "Epoch 22/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 1.7967e-05 - loss: 0.0145 - mass_balance: 0.0145 - val_huber: 1.5768e-05 - val_loss: 0.0225 - val_mass_balance: 0.0225\n",
+ "Epoch 23/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 18ms/step - huber: 1.6283e-05 - loss: 0.0129 - mass_balance: 0.0129 - val_huber: 1.3621e-05 - val_loss: 0.0099 - val_mass_balance: 0.0099\n",
+ "Epoch 24/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 25ms/step - huber: 1.4158e-05 - loss: 0.0120 - mass_balance: 0.0120 - val_huber: 1.2725e-05 - val_loss: 0.0219 - val_mass_balance: 0.0219\n",
+ "Epoch 25/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 23ms/step - huber: 1.3349e-05 - loss: 0.0122 - mass_balance: 0.0122 - val_huber: 1.1089e-05 - val_loss: 0.0058 - val_mass_balance: 0.0058\n",
+ "Epoch 26/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 1.1305e-05 - loss: 0.0094 - mass_balance: 0.0094 - val_huber: 1.0137e-05 - val_loss: 0.0094 - val_mass_balance: 0.0094\n",
+ "Epoch 27/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 18ms/step - huber: 1.0401e-05 - loss: 0.0087 - mass_balance: 0.0087 - val_huber: 8.7671e-06 - val_loss: 0.0097 - val_mass_balance: 0.0097\n",
+ "Epoch 28/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 25ms/step - huber: 9.2662e-06 - loss: 0.0084 - mass_balance: 0.0084 - val_huber: 7.9543e-06 - val_loss: 0.0042 - val_mass_balance: 0.0042\n",
+ "Epoch 29/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m34s\u001b[0m 20ms/step - huber: 8.7411e-06 - loss: 0.0083 - mass_balance: 0.0083 - val_huber: 7.5361e-06 - val_loss: 0.0047 - val_mass_balance: 0.0047\n",
+ "Epoch 30/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 13ms/step - huber: 8.3025e-06 - loss: 0.0069 - mass_balance: 0.0069 - val_huber: 7.4451e-06 - val_loss: 0.0094 - val_mass_balance: 0.0094\n",
+ "Epoch 31/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 17ms/step - huber: 7.6382e-06 - loss: 0.0057 - mass_balance: 0.0057 - val_huber: 6.9163e-06 - val_loss: 0.0050 - val_mass_balance: 0.0050\n",
+ "Epoch 32/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 23ms/step - huber: 7.3375e-06 - loss: 0.0056 - mass_balance: 0.0056 - val_huber: 6.7540e-06 - val_loss: 0.0046 - val_mass_balance: 0.0046\n",
+ "Epoch 33/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m33s\u001b[0m 20ms/step - huber: 7.0753e-06 - loss: 0.0051 - mass_balance: 0.0051 - val_huber: 6.2671e-06 - val_loss: 0.0072 - val_mass_balance: 0.0072\n",
+ "Epoch 34/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 6.7945e-06 - loss: 0.0048 - mass_balance: 0.0048 - val_huber: 6.2241e-06 - val_loss: 0.0072 - val_mass_balance: 0.0072\n",
+ "Epoch 35/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 19ms/step - huber: 6.5585e-06 - loss: 0.0045 - mass_balance: 0.0045 - val_huber: 6.1400e-06 - val_loss: 0.0036 - val_mass_balance: 0.0036\n",
+ "Epoch 36/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 6.4420e-06 - loss: 0.0038 - mass_balance: 0.0038 - val_huber: 5.8129e-06 - val_loss: 0.0028 - val_mass_balance: 0.0027\n",
+ "Epoch 37/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 18ms/step - huber: 6.0778e-06 - loss: 0.0034 - mass_balance: 0.0034 - val_huber: 5.7370e-06 - val_loss: 0.0020 - val_mass_balance: 0.0020\n",
+ "Epoch 38/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 13ms/step - huber: 6.0100e-06 - loss: 0.0030 - mass_balance: 0.0030 - val_huber: 5.4983e-06 - val_loss: 0.0026 - val_mass_balance: 0.0026\n",
+ "Epoch 39/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 5.8758e-06 - loss: 0.0032 - mass_balance: 0.0032 - val_huber: 5.4214e-06 - val_loss: 0.0016 - val_mass_balance: 0.0016\n",
+ "Epoch 40/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 22ms/step - huber: 5.6621e-06 - loss: 0.0026 - mass_balance: 0.0026 - val_huber: 5.2990e-06 - val_loss: 0.0034 - val_mass_balance: 0.0034\n",
+ "Epoch 41/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m34s\u001b[0m 20ms/step - huber: 5.5953e-06 - loss: 0.0026 - mass_balance: 0.0026 - val_huber: 5.1084e-06 - val_loss: 0.0017 - val_mass_balance: 0.0016\n",
+ "Epoch 42/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 5.4874e-06 - loss: 0.0027 - mass_balance: 0.0027 - val_huber: 5.0405e-06 - val_loss: 0.0015 - val_mass_balance: 0.0015\n",
+ "Epoch 43/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 18ms/step - huber: 5.3323e-06 - loss: 0.0022 - mass_balance: 0.0022 - val_huber: 4.9327e-06 - val_loss: 0.0017 - val_mass_balance: 0.0017\n",
+ "Epoch 44/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 5.1880e-06 - loss: 0.0022 - mass_balance: 0.0022 - val_huber: 4.8816e-06 - val_loss: 0.0023 - val_mass_balance: 0.0023\n",
+ "Epoch 45/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m34s\u001b[0m 20ms/step - huber: 5.2677e-06 - loss: 0.0019 - mass_balance: 0.0019 - val_huber: 4.8684e-06 - val_loss: 0.0030 - val_mass_balance: 0.0030\n",
+ "Epoch 46/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 13ms/step - huber: 5.0820e-06 - loss: 0.0016 - mass_balance: 0.0016 - val_huber: 4.7764e-06 - val_loss: 0.0017 - val_mass_balance: 0.0017\n",
+ "Epoch 47/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 5.1720e-06 - loss: 0.0017 - mass_balance: 0.0017 - val_huber: 4.6949e-06 - val_loss: 0.0014 - val_mass_balance: 0.0014\n",
+ "Epoch 48/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 4.9894e-06 - loss: 0.0015 - mass_balance: 0.0015 - val_huber: 4.6528e-06 - val_loss: 0.0013 - val_mass_balance: 0.0013\n",
+ "Epoch 49/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 18ms/step - huber: 5.0818e-06 - loss: 0.0014 - mass_balance: 0.0014 - val_huber: 4.6386e-06 - val_loss: 0.0013 - val_mass_balance: 0.0013\n",
+ "Epoch 50/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 13ms/step - huber: 4.9151e-06 - loss: 0.0014 - mass_balance: 0.0014 - val_huber: 4.5971e-06 - val_loss: 0.0017 - val_mass_balance: 0.0017\n",
+ "Epoch 51/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 5.1078e-06 - loss: 0.0013 - mass_balance: 0.0013 - val_huber: 4.5822e-06 - val_loss: 0.0012 - val_mass_balance: 0.0012\n",
+ "Epoch 52/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 22ms/step - huber: 4.8951e-06 - loss: 0.0012 - mass_balance: 0.0012 - val_huber: 4.5595e-06 - val_loss: 0.0012 - val_mass_balance: 0.0012\n",
+ "Epoch 53/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 4.7999e-06 - loss: 0.0012 - mass_balance: 0.0011 - val_huber: 4.5535e-06 - val_loss: 0.0011 - val_mass_balance: 0.0011\n",
+ "Epoch 54/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 5.0074e-06 - loss: 0.0010 - mass_balance: 0.0010 - val_huber: 4.5312e-06 - val_loss: 0.0011 - val_mass_balance: 0.0011\n",
+ "Epoch 55/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 21ms/step - huber: 4.7403e-06 - loss: 0.0011 - mass_balance: 0.0010 - val_huber: 4.5230e-06 - val_loss: 0.0011 - val_mass_balance: 0.0011\n",
+ "Epoch 56/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 22ms/step - huber: 4.8505e-06 - loss: 0.0010 - mass_balance: 0.0010 - val_huber: 4.4992e-06 - val_loss: 9.9706e-04 - val_mass_balance: 9.9211e-04\n",
+ "Epoch 57/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 16ms/step - huber: 4.7829e-06 - loss: 0.0010 - mass_balance: 0.0010 - val_huber: 4.4840e-06 - val_loss: 0.0011 - val_mass_balance: 0.0011\n",
+ "Epoch 58/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 13ms/step - huber: 4.6865e-06 - loss: 9.4714e-04 - mass_balance: 9.4245e-04 - val_huber: 4.4743e-06 - val_loss: 0.0010 - val_mass_balance: 0.0010\n",
+ "Epoch 59/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 21ms/step - huber: 4.7369e-06 - loss: 9.1854e-04 - mass_balance: 9.1381e-04 - val_huber: 4.4658e-06 - val_loss: 9.0883e-04 - val_mass_balance: 9.0412e-04\n",
+ "Epoch 60/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 21ms/step - huber: 4.7842e-06 - loss: 8.9714e-04 - mass_balance: 8.9235e-04 - val_huber: 4.4619e-06 - val_loss: 0.0011 - val_mass_balance: 0.0010\n",
+ "Epoch 61/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 4.7509e-06 - loss: 9.0488e-04 - mass_balance: 9.0013e-04 - val_huber: 4.4496e-06 - val_loss: 8.7976e-04 - val_mass_balance: 8.7495e-04\n",
+ "Epoch 62/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 14ms/step - huber: 4.7354e-06 - loss: 8.7100e-04 - mass_balance: 8.6626e-04 - val_huber: 4.4387e-06 - val_loss: 8.0406e-04 - val_mass_balance: 7.9931e-04\n",
+ "Epoch 63/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 4.7464e-06 - loss: 8.3838e-04 - mass_balance: 8.3364e-04 - val_huber: 4.4327e-06 - val_loss: 7.9101e-04 - val_mass_balance: 7.8626e-04\n",
+ "Epoch 64/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 23ms/step - huber: 4.6876e-06 - loss: 8.1951e-04 - mass_balance: 8.1482e-04 - val_huber: 4.4294e-06 - val_loss: 8.9929e-04 - val_mass_balance: 8.9460e-04\n",
+ "Epoch 65/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 18ms/step - huber: 4.6590e-06 - loss: 8.0697e-04 - mass_balance: 8.0231e-04 - val_huber: 4.4291e-06 - val_loss: 8.6386e-04 - val_mass_balance: 8.5926e-04\n",
+ "Epoch 66/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 14ms/step - huber: 4.7361e-06 - loss: 8.0089e-04 - mass_balance: 7.9615e-04 - val_huber: 4.4201e-06 - val_loss: 9.0955e-04 - val_mass_balance: 9.0501e-04\n",
+ "Epoch 67/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 23ms/step - huber: 4.6704e-06 - loss: 7.8888e-04 - mass_balance: 7.8421e-04 - val_huber: 4.4193e-06 - val_loss: 8.9738e-04 - val_mass_balance: 8.9274e-04\n",
+ "Epoch 68/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 23ms/step - huber: 4.6470e-06 - loss: 7.7605e-04 - mass_balance: 7.7141e-04 - val_huber: 4.4142e-06 - val_loss: 8.5801e-04 - val_mass_balance: 8.5335e-04\n",
+ "Epoch 69/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 16ms/step - huber: 4.7550e-06 - loss: 7.7262e-04 - mass_balance: 7.6787e-04 - val_huber: 4.4084e-06 - val_loss: 7.9255e-04 - val_mass_balance: 7.8781e-04\n",
+ "Epoch 70/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 17ms/step - huber: 4.7623e-06 - loss: 7.5767e-04 - mass_balance: 7.5291e-04 - val_huber: 4.4077e-06 - val_loss: 7.4866e-04 - val_mass_balance: 7.4407e-04\n",
+ "Epoch 71/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 23ms/step - huber: 4.7104e-06 - loss: 7.4709e-04 - mass_balance: 7.4238e-04 - val_huber: 4.4048e-06 - val_loss: 7.6893e-04 - val_mass_balance: 7.6434e-04\n",
+ "Epoch 72/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 22ms/step - huber: 4.7597e-06 - loss: 7.4175e-04 - mass_balance: 7.3699e-04 - val_huber: 4.4023e-06 - val_loss: 7.5106e-04 - val_mass_balance: 7.4639e-04\n",
+ "Epoch 73/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 13ms/step - huber: 4.6848e-06 - loss: 7.3518e-04 - mass_balance: 7.3050e-04 - val_huber: 4.3981e-06 - val_loss: 8.2756e-04 - val_mass_balance: 8.2306e-04\n",
+ "Epoch 74/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 4.6485e-06 - loss: 7.3155e-04 - mass_balance: 7.2690e-04 - val_huber: 4.3989e-06 - val_loss: 8.4362e-04 - val_mass_balance: 8.3890e-04\n",
+ "Epoch 75/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 4.7278e-06 - loss: 7.2393e-04 - mass_balance: 7.1920e-04 - val_huber: 4.3956e-06 - val_loss: 7.3810e-04 - val_mass_balance: 7.3353e-04\n",
+ "Epoch 76/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 21ms/step - huber: 4.7837e-06 - loss: 7.2246e-04 - mass_balance: 7.1768e-04 - val_huber: 4.3947e-06 - val_loss: 7.2104e-04 - val_mass_balance: 7.1644e-04\n",
+ "Epoch 77/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 17ms/step - huber: 4.7795e-06 - loss: 7.1239e-04 - mass_balance: 7.0761e-04 - val_huber: 4.3899e-06 - val_loss: 7.5226e-04 - val_mass_balance: 7.4761e-04\n",
+ "Epoch 78/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 21ms/step - huber: 4.5890e-06 - loss: 7.1344e-04 - mass_balance: 7.0885e-04 - val_huber: 4.3891e-06 - val_loss: 7.4826e-04 - val_mass_balance: 7.4358e-04\n",
+ "Epoch 79/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 18ms/step - huber: 4.8303e-06 - loss: 7.1237e-04 - mass_balance: 7.0754e-04 - val_huber: 4.3876e-06 - val_loss: 7.2122e-04 - val_mass_balance: 7.1660e-04\n",
+ "Epoch 80/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 4.7512e-06 - loss: 7.0720e-04 - mass_balance: 7.0245e-04 - val_huber: 4.3860e-06 - val_loss: 7.8552e-04 - val_mass_balance: 7.8102e-04\n",
+ "Epoch 81/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m33s\u001b[0m 19ms/step - huber: 4.9366e-06 - loss: 7.0371e-04 - mass_balance: 6.9877e-04 - val_huber: 4.3859e-06 - val_loss: 7.4151e-04 - val_mass_balance: 7.3684e-04\n",
+ "Epoch 82/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 24ms/step - huber: 4.5501e-06 - loss: 6.9870e-04 - mass_balance: 6.9415e-04 - val_huber: 4.3839e-06 - val_loss: 7.2937e-04 - val_mass_balance: 7.2469e-04\n",
+ "Epoch 83/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m33s\u001b[0m 19ms/step - huber: 4.7512e-06 - loss: 6.9658e-04 - mass_balance: 6.9183e-04 - val_huber: 4.3828e-06 - val_loss: 6.9935e-04 - val_mass_balance: 6.9476e-04\n",
+ "Epoch 84/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 4.9666e-06 - loss: 6.9299e-04 - mass_balance: 6.8802e-04 - val_huber: 4.3836e-06 - val_loss: 6.9820e-04 - val_mass_balance: 6.9360e-04\n",
+ "Epoch 85/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 22ms/step - huber: 4.7241e-06 - loss: 6.8971e-04 - mass_balance: 6.8498e-04 - val_huber: 4.3817e-06 - val_loss: 7.0906e-04 - val_mass_balance: 7.0448e-04\n",
+ "Epoch 86/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 24ms/step - huber: 4.6853e-06 - loss: 6.8834e-04 - mass_balance: 6.8366e-04 - val_huber: 4.3801e-06 - val_loss: 6.9305e-04 - val_mass_balance: 6.8842e-04\n",
+ "Epoch 87/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 23ms/step - huber: 4.7930e-06 - loss: 6.8417e-04 - mass_balance: 6.7938e-04 - val_huber: 4.3793e-06 - val_loss: 6.8721e-04 - val_mass_balance: 6.8261e-04\n",
+ "Epoch 88/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 16ms/step - huber: 4.6025e-06 - loss: 6.8556e-04 - mass_balance: 6.8096e-04 - val_huber: 4.3797e-06 - val_loss: 6.9921e-04 - val_mass_balance: 6.9457e-04\n",
+ "Epoch 89/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 24ms/step - huber: 4.6096e-06 - loss: 6.8345e-04 - mass_balance: 6.7884e-04 - val_huber: 4.3777e-06 - val_loss: 7.1012e-04 - val_mass_balance: 7.0556e-04\n",
+ "Epoch 90/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 23ms/step - huber: 4.7352e-06 - loss: 6.8032e-04 - mass_balance: 6.7559e-04 - val_huber: 4.3785e-06 - val_loss: 6.8198e-04 - val_mass_balance: 6.7735e-04\n",
+ "Epoch 91/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 17ms/step - huber: 4.9625e-06 - loss: 6.7876e-04 - mass_balance: 6.7380e-04 - val_huber: 4.3782e-06 - val_loss: 6.8370e-04 - val_mass_balance: 6.7908e-04\n",
+ "Epoch 92/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 23ms/step - huber: 4.6216e-06 - loss: 6.7679e-04 - mass_balance: 6.7217e-04 - val_huber: 4.3776e-06 - val_loss: 6.9870e-04 - val_mass_balance: 6.9412e-04\n",
+ "Epoch 93/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 19ms/step - huber: 4.5977e-06 - loss: 6.8038e-04 - mass_balance: 6.7579e-04 - val_huber: 4.3780e-06 - val_loss: 6.7655e-04 - val_mass_balance: 6.7195e-04\n",
+ "Epoch 94/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 17ms/step - huber: 4.7114e-06 - loss: 6.7618e-04 - mass_balance: 6.7147e-04 - val_huber: 4.3773e-06 - val_loss: 6.8676e-04 - val_mass_balance: 6.8217e-04\n",
+ "Epoch 95/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 23ms/step - huber: 4.8114e-06 - loss: 6.7424e-04 - mass_balance: 6.6943e-04 - val_huber: 4.3775e-06 - val_loss: 6.7735e-04 - val_mass_balance: 6.7271e-04\n",
+ "Epoch 96/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 18ms/step - huber: 4.6262e-06 - loss: 6.7161e-04 - mass_balance: 6.6699e-04 - val_huber: 4.3762e-06 - val_loss: 6.8181e-04 - val_mass_balance: 6.7717e-04\n",
+ "Epoch 97/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 14ms/step - huber: 4.6763e-06 - loss: 6.7315e-04 - mass_balance: 6.6847e-04 - val_huber: 4.3764e-06 - val_loss: 6.7627e-04 - val_mass_balance: 6.7167e-04\n",
+ "Epoch 98/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 20ms/step - huber: 4.4961e-06 - loss: 6.7211e-04 - mass_balance: 6.6761e-04 - val_huber: 4.3764e-06 - val_loss: 6.7528e-04 - val_mass_balance: 6.7067e-04\n",
+ "Epoch 99/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 21ms/step - huber: 4.6732e-06 - loss: 6.6925e-04 - mass_balance: 6.6458e-04 - val_huber: 4.3758e-06 - val_loss: 6.7478e-04 - val_mass_balance: 6.7018e-04\n",
+ "Epoch 100/100\n",
+ "\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m25s\u001b[0m 15ms/step - huber: 4.8459e-06 - loss: 6.6713e-04 - mass_balance: 6.6228e-04 - val_huber: 4.3756e-06 - val_loss: 6.7381e-04 - val_mass_balance: 6.6918e-04\n",
+ "Training took 3161.1680614948273 seconds\n"
+ ]
+ }
+ ],
+ "source": [
+ "history = model_training(model_large)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'huber': [0.016467243432998657,\n",
+ " 0.0026575098745524883,\n",
+ " 0.0008205742342397571,\n",
+ " 0.0005093477666378021,\n",
+ " 0.0003787624591495842,\n",
+ " 0.0002784435637295246,\n",
+ " 0.00020736613078042865,\n",
+ " 0.00014805630780756474,\n",
+ " 0.0001245995081262663,\n",
+ " 0.0001012101347441785,\n",
+ " 8.732335845706984e-05,\n",
+ " 7.07938161212951e-05,\n",
+ " 6.000046414555982e-05,\n",
+ " 4.9258629587711766e-05,\n",
+ " 4.5853365008952096e-05,\n",
+ " 3.878949792124331e-05,\n",
+ " 3.496679710224271e-05,\n",
+ " 3.024175384780392e-05,\n",
+ " 2.5801549782045186e-05,\n",
+ " 2.228489756816998e-05,\n",
+ " 1.9326878827996552e-05,\n",
+ " 1.720393993309699e-05,\n",
+ " 1.545708619232755e-05,\n",
+ " 1.3873431271349546e-05,\n",
+ " 1.2577706002048217e-05,\n",
+ " 1.1043644917663187e-05,\n",
+ " 1.0004349860537332e-05,\n",
+ " 9.15171312954044e-06,\n",
+ " 8.605407856521197e-06,\n",
+ " 8.079078725131694e-06,\n",
+ " 7.523737622250337e-06,\n",
+ " 7.217747679533204e-06,\n",
+ " 6.9549328145512845e-06,\n",
+ " 6.68665734337992e-06,\n",
+ " 6.558057521033334e-06,\n",
+ " 6.348819169943454e-06,\n",
+ " 6.18170042798738e-06,\n",
+ " 5.973774477752158e-06,\n",
+ " 5.812943072669441e-06,\n",
+ " 5.673456598742632e-06,\n",
+ " 5.545334715861827e-06,\n",
+ " 5.442475867312169e-06,\n",
+ " 5.3044891501485836e-06,\n",
+ " 5.23393055118504e-06,\n",
+ " 5.18664319315576e-06,\n",
+ " 5.130440968059702e-06,\n",
+ " 5.0675025704549626e-06,\n",
+ " 5.022430286771851e-06,\n",
+ " 4.986327894584974e-06,\n",
+ " 4.958836598234484e-06,\n",
+ " 4.92672143082018e-06,\n",
+ " 4.920212177239591e-06,\n",
+ " 4.895785878034076e-06,\n",
+ " 4.880493179371115e-06,\n",
+ " 4.865618393523619e-06,\n",
+ " 4.846592673857231e-06,\n",
+ " 4.830980287806597e-06,\n",
+ " 4.8156484808714595e-06,\n",
+ " 4.8047577365650795e-06,\n",
+ " 4.800085662282072e-06,\n",
+ " 4.7918410928105e-06,\n",
+ " 4.782257747137919e-06,\n",
+ " 4.775091383635299e-06,\n",
+ " 4.770627583638998e-06,\n",
+ " 4.764243385579903e-06,\n",
+ " 4.759195689985063e-06,\n",
+ " 4.757103852170985e-06,\n",
+ " 4.750551852339413e-06,\n",
+ " 4.747769253299339e-06,\n",
+ " 4.743907993542962e-06,\n",
+ " 4.7424591684830375e-06,\n",
+ " 4.740706572192721e-06,\n",
+ " 4.737036761071067e-06,\n",
+ " 4.734663889394142e-06,\n",
+ " 4.732184152089758e-06,\n",
+ " 4.729894044430694e-06,\n",
+ " 4.728701242129318e-06,\n",
+ " 4.726135557575617e-06,\n",
+ " 4.7255007302737795e-06,\n",
+ " 4.723358870251104e-06,\n",
+ " 4.722523044620175e-06,\n",
+ " 4.721841378341196e-06,\n",
+ " 4.720112428913126e-06,\n",
+ " 4.719278877018951e-06,\n",
+ " 4.718392574432073e-06,\n",
+ " 4.7173257371468935e-06,\n",
+ " 4.716040621133288e-06,\n",
+ " 4.71549265057547e-06,\n",
+ " 4.71482553621172e-06,\n",
+ " 4.71395878776093e-06,\n",
+ " 4.714067017630441e-06,\n",
+ " 4.71353814646136e-06,\n",
+ " 4.712836471298942e-06,\n",
+ " 4.7125276978476904e-06,\n",
+ " 4.712316240329528e-06,\n",
+ " 4.712058398581576e-06,\n",
+ " 4.711535893875407e-06,\n",
+ " 4.711482688435353e-06,\n",
+ " 4.711087512987433e-06,\n",
+ " 4.711544988822425e-06],\n",
+ " 'loss': [0.30648601055145264,\n",
+ " 0.17231327295303345,\n",
+ " 0.12539470195770264,\n",
+ " 0.10020893812179565,\n",
+ " 0.09178448468446732,\n",
+ " 0.08137709647417068,\n",
+ " 0.07206308841705322,\n",
+ " 0.057256944477558136,\n",
+ " 0.05294961482286453,\n",
+ " 0.04877038672566414,\n",
+ " 0.04524555802345276,\n",
+ " 0.040079012513160706,\n",
+ " 0.03670475631952286,\n",
+ " 0.03016498312354088,\n",
+ " 0.029404371976852417,\n",
+ " 0.02616339921951294,\n",
+ " 0.02604585886001587,\n",
+ " 0.02159888669848442,\n",
+ " 0.01955566182732582,\n",
+ " 0.017443886026740074,\n",
+ " 0.015240314416587353,\n",
+ " 0.013656704686582088,\n",
+ " 0.012432842515408993,\n",
+ " 0.011758713982999325,\n",
+ " 0.011179047636687756,\n",
+ " 0.009406129829585552,\n",
+ " 0.008792762644588947,\n",
+ " 0.00785292312502861,\n",
+ " 0.00764220766723156,\n",
+ " 0.0069798934273421764,\n",
+ " 0.005929442122578621,\n",
+ " 0.00583580182865262,\n",
+ " 0.005070519633591175,\n",
+ " 0.004584070760756731,\n",
+ " 0.004380729515105486,\n",
+ " 0.0039043554570525885,\n",
+ " 0.0036823840346187353,\n",
+ " 0.003121868474408984,\n",
+ " 0.0029378121253103018,\n",
+ " 0.0027718590572476387,\n",
+ " 0.002403492806479335,\n",
+ " 0.002596942475065589,\n",
+ " 0.002093954710289836,\n",
+ " 0.002055332064628601,\n",
+ " 0.0019100041827186942,\n",
+ " 0.001678098109550774,\n",
+ " 0.0015641257632523775,\n",
+ " 0.0015202162321656942,\n",
+ " 0.001371403457596898,\n",
+ " 0.001403785077854991,\n",
+ " 0.0012853954685851932,\n",
+ " 0.0012285530101507902,\n",
+ " 0.0011501156259328127,\n",
+ " 0.0010609555756673217,\n",
+ " 0.001058138906955719,\n",
+ " 0.0009922973113134503,\n",
+ " 0.0010090821888297796,\n",
+ " 0.0009523544576950371,\n",
+ " 0.0009076613350771368,\n",
+ " 0.0008950438932515681,\n",
+ " 0.0008835873450152576,\n",
+ " 0.0008577112457714975,\n",
+ " 0.0008402072708122432,\n",
+ " 0.0008168538333848119,\n",
+ " 0.000813478312920779,\n",
+ " 0.0007976202177815139,\n",
+ " 0.0007844835636205971,\n",
+ " 0.0007707226905040443,\n",
+ " 0.000765060365665704,\n",
+ " 0.0007560566300526261,\n",
+ " 0.0007469917181879282,\n",
+ " 0.0007387903751805425,\n",
+ " 0.0007344671757891774,\n",
+ " 0.0007288424530997872,\n",
+ " 0.0007215943187475204,\n",
+ " 0.0007187195005826652,\n",
+ " 0.0007133104954846203,\n",
+ " 0.0007089162245392799,\n",
+ " 0.0007070220308378339,\n",
+ " 0.0007033782312646508,\n",
+ " 0.0007000636542215943,\n",
+ " 0.0006962578627280891,\n",
+ " 0.0006947630899958313,\n",
+ " 0.0006916335551068187,\n",
+ " 0.0006891160737723112,\n",
+ " 0.0006869803764857352,\n",
+ " 0.0006848273333162069,\n",
+ " 0.0006834670784883201,\n",
+ " 0.0006819777772761881,\n",
+ " 0.0006801678682677448,\n",
+ " 0.0006790790939703584,\n",
+ " 0.0006776662194170058,\n",
+ " 0.0006763586425222456,\n",
+ " 0.0006750965840183198,\n",
+ " 0.0006742294644936919,\n",
+ " 0.0006733413320034742,\n",
+ " 0.000672198599204421,\n",
+ " 0.0006714383489452302,\n",
+ " 0.0006705404375679791,\n",
+ " 0.000669809291139245],\n",
+ " 'mass_balance': [0.28992345929145813,\n",
+ " 0.1696203649044037,\n",
+ " 0.1245775818824768,\n",
+ " 0.09968571364879608,\n",
+ " 0.09139259904623032,\n",
+ " 0.08108312636613846,\n",
+ " 0.07183856517076492,\n",
+ " 0.05711941421031952,\n",
+ " 0.052825648337602615,\n",
+ " 0.048665404319763184,\n",
+ " 0.04515230283141136,\n",
+ " 0.04000015929341316,\n",
+ " 0.03663957118988037,\n",
+ " 0.030117226764559746,\n",
+ " 0.029365424066781998,\n",
+ " 0.026129310950636864,\n",
+ " 0.02601895108819008,\n",
+ " 0.021564332768321037,\n",
+ " 0.01952822133898735,\n",
+ " 0.017421750351786613,\n",
+ " 0.015222830697894096,\n",
+ " 0.013639131560921669,\n",
+ " 0.012420604936778545,\n",
+ " 0.011748346500098705,\n",
+ " 0.011165905743837357,\n",
+ " 0.009393330663442612,\n",
+ " 0.00878295861184597,\n",
+ " 0.007845276035368443,\n",
+ " 0.007633090019226074,\n",
+ " 0.006970338989049196,\n",
+ " 0.0059210676699876785,\n",
+ " 0.005827996879816055,\n",
+ " 0.005064042750746012,\n",
+ " 0.00457689817994833,\n",
+ " 0.004373996052891016,\n",
+ " 0.0038968229200690985,\n",
+ " 0.0036758396308869123,\n",
+ " 0.003116681706160307,\n",
+ " 0.002932669362053275,\n",
+ " 0.00276594003662467,\n",
+ " 0.002398006385192275,\n",
+ " 0.0025909102987498045,\n",
+ " 0.0020891136955469847,\n",
+ " 0.002050071721896529,\n",
+ " 0.0019051755079999566,\n",
+ " 0.0016737208934500813,\n",
+ " 0.0015591479605063796,\n",
+ " 0.0015149891842156649,\n",
+ " 0.0013664665166288614,\n",
+ " 0.001398497261106968,\n",
+ " 0.0012803340796381235,\n",
+ " 0.0012235511094331741,\n",
+ " 0.0011449819430708885,\n",
+ " 0.0010562300449237227,\n",
+ " 0.0010532340966165066,\n",
+ " 0.0009873538510873914,\n",
+ " 0.0010040433844551444,\n",
+ " 0.0009474873077124357,\n",
+ " 0.0009026402258314192,\n",
+ " 0.0008902117260731757,\n",
+ " 0.0008786250837147236,\n",
+ " 0.0008528471225872636,\n",
+ " 0.0008353753364644945,\n",
+ " 0.0008118956466205418,\n",
+ " 0.0008086940506473184,\n",
+ " 0.000793011044152081,\n",
+ " 0.0007796218851581216,\n",
+ " 0.0007659022230654955,\n",
+ " 0.0007601975230500102,\n",
+ " 0.0007513085147365928,\n",
+ " 0.0007420866750180721,\n",
+ " 0.0007340752054005861,\n",
+ " 0.0007296513067558408,\n",
+ " 0.0007241083076223731,\n",
+ " 0.0007167430012486875,\n",
+ " 0.0007139622466638684,\n",
+ " 0.000708507839590311,\n",
+ " 0.0007042676443234086,\n",
+ " 0.0007021916680969298,\n",
+ " 0.0006986657972447574,\n",
+ " 0.0006952557014301419,\n",
+ " 0.0006915002595633268,\n",
+ " 0.0006899730069562793,\n",
+ " 0.0006869392236694694,\n",
+ " 0.0006842977018095553,\n",
+ " 0.0006822088616900146,\n",
+ " 0.0006800602423027158,\n",
+ " 0.0006787151214666665,\n",
+ " 0.0006773100467398763,\n",
+ " 0.0006753901834599674,\n",
+ " 0.0006744506536051631,\n",
+ " 0.0006728798034600914,\n",
+ " 0.000671558256726712,\n",
+ " 0.0006704204715788364,\n",
+ " 0.0006694469484500587,\n",
+ " 0.000668513064738363,\n",
+ " 0.0006674117757938802,\n",
+ " 0.0006666934350505471,\n",
+ " 0.0006657900521531701,\n",
+ " 0.0006664929678663611],\n",
+ " 'val_huber': [0.005201284773647785,\n",
+ " 0.0012923928443342447,\n",
+ " 0.0006627636030316353,\n",
+ " 0.00042667306843213737,\n",
+ " 0.00027613641577772796,\n",
+ " 0.0002216041466454044,\n",
+ " 0.00015488243661820889,\n",
+ " 0.00014596043911296874,\n",
+ " 9.086774662137032e-05,\n",
+ " 0.00010800284508150071,\n",
+ " 6.072385804145597e-05,\n",
+ " 5.602455712505616e-05,\n",
+ " 4.8251691623590887e-05,\n",
+ " 4.7942019591573626e-05,\n",
+ " 3.946639844798483e-05,\n",
+ " 3.375155574758537e-05,\n",
+ " 3.647833364084363e-05,\n",
+ " 2.510796366550494e-05,\n",
+ " 2.126926301571075e-05,\n",
+ " 2.1749185179942288e-05,\n",
+ " 2.0177141777821817e-05,\n",
+ " 1.5768278899486177e-05,\n",
+ " 1.3621114703710191e-05,\n",
+ " 1.2724695807264652e-05,\n",
+ " 1.1089017789345235e-05,\n",
+ " 1.0136632226931397e-05,\n",
+ " 8.767069630266633e-06,\n",
+ " 7.954341526783537e-06,\n",
+ " 7.5360685514169745e-06,\n",
+ " 7.445102255587699e-06,\n",
+ " 6.916348866070621e-06,\n",
+ " 6.754000423825346e-06,\n",
+ " 6.267141998250736e-06,\n",
+ " 6.224123353604227e-06,\n",
+ " 6.1399505284498446e-06,\n",
+ " 5.812878498545615e-06,\n",
+ " 5.73702027395484e-06,\n",
+ " 5.498338396137115e-06,\n",
+ " 5.421410605777055e-06,\n",
+ " 5.299044914863771e-06,\n",
+ " 5.108431196276797e-06,\n",
+ " 5.040476480644429e-06,\n",
+ " 4.9326554290018976e-06,\n",
+ " 4.881565018877154e-06,\n",
+ " 4.868429186899448e-06,\n",
+ " 4.776351488544606e-06,\n",
+ " 4.694877134170383e-06,\n",
+ " 4.6527843551302794e-06,\n",
+ " 4.6385612222366035e-06,\n",
+ " 4.597116003424162e-06,\n",
+ " 4.5821902858733665e-06,\n",
+ " 4.559493390843272e-06,\n",
+ " 4.553502549242694e-06,\n",
+ " 4.531224476522766e-06,\n",
+ " 4.522975359577686e-06,\n",
+ " 4.499182068684604e-06,\n",
+ " 4.484040800889488e-06,\n",
+ " 4.474295565159991e-06,\n",
+ " 4.4657635953626595e-06,\n",
+ " 4.46186004410265e-06,\n",
+ " 4.449606876733014e-06,\n",
+ " 4.4387397792888805e-06,\n",
+ " 4.432703462953214e-06,\n",
+ " 4.42938244304969e-06,\n",
+ " 4.429067757882876e-06,\n",
+ " 4.420137429406168e-06,\n",
+ " 4.419258402776904e-06,\n",
+ " 4.414219802129082e-06,\n",
+ " 4.4083758439228404e-06,\n",
+ " 4.4077228267269675e-06,\n",
+ " 4.404752871778328e-06,\n",
+ " 4.402321337693138e-06,\n",
+ " 4.398110377223929e-06,\n",
+ " 4.3989152800349984e-06,\n",
+ " 4.395626092446037e-06,\n",
+ " 4.394668849272421e-06,\n",
+ " 4.389917194203008e-06,\n",
+ " 4.389116384118097e-06,\n",
+ " 4.387592525745276e-06,\n",
+ " 4.385979536891682e-06,\n",
+ " 4.385893134895014e-06,\n",
+ " 4.383934083307395e-06,\n",
+ " 4.382837232697057e-06,\n",
+ " 4.383563464216422e-06,\n",
+ " 4.381744929560227e-06,\n",
+ " 4.380144673632458e-06,\n",
+ " 4.379347501526354e-06,\n",
+ " 4.379693109513028e-06,\n",
+ " 4.377741788630374e-06,\n",
+ " 4.37848348155967e-06,\n",
+ " 4.378244284453103e-06,\n",
+ " 4.37762719229795e-06,\n",
+ " 4.3779509724117815e-06,\n",
+ " 4.377348432171857e-06,\n",
+ " 4.377521236165194e-06,\n",
+ " 4.376238848635694e-06,\n",
+ " 4.376393917482346e-06,\n",
+ " 4.376391643745592e-06,\n",
+ " 4.375826847535791e-06,\n",
+ " 4.375569005787838e-06],\n",
+ " 'val_loss': [0.3554118573665619,\n",
+ " 0.14072169363498688,\n",
+ " 0.18250100314617157,\n",
+ " 0.10625234246253967,\n",
+ " 0.0550912544131279,\n",
+ " 0.07982474565505981,\n",
+ " 0.06212713196873665,\n",
+ " 0.052029162645339966,\n",
+ " 0.025773700326681137,\n",
+ " 0.08815066516399384,\n",
+ " 0.034315552562475204,\n",
+ " 0.04443306848406792,\n",
+ " 0.026383033022284508,\n",
+ " 0.036652978509664536,\n",
+ " 0.048315778374671936,\n",
+ " 0.02544834092259407,\n",
+ " 0.019760675728321075,\n",
+ " 0.018324358388781548,\n",
+ " 0.019503841176629066,\n",
+ " 0.016593070700764656,\n",
+ " 0.025827599689364433,\n",
+ " 0.02246992290019989,\n",
+ " 0.009874003008008003,\n",
+ " 0.02192152850329876,\n",
+ " 0.005770025309175253,\n",
+ " 0.009400702081620693,\n",
+ " 0.009708519093692303,\n",
+ " 0.004203513730317354,\n",
+ " 0.00473543256521225,\n",
+ " 0.009447645395994186,\n",
+ " 0.005036721937358379,\n",
+ " 0.004580398090183735,\n",
+ " 0.00723404623568058,\n",
+ " 0.007191700395196676,\n",
+ " 0.0035864152014255524,\n",
+ " 0.0027530172374099493,\n",
+ " 0.001993797719478607,\n",
+ " 0.002578657353296876,\n",
+ " 0.0016335397958755493,\n",
+ " 0.0034430362284183502,\n",
+ " 0.0016514776507392526,\n",
+ " 0.00154941959772259,\n",
+ " 0.001672835205681622,\n",
+ " 0.0022707339376211166,\n",
+ " 0.003024233039468527,\n",
+ " 0.0017011138843372464,\n",
+ " 0.00135646085254848,\n",
+ " 0.0013078938936814666,\n",
+ " 0.0013143954565748572,\n",
+ " 0.00168643519282341,\n",
+ " 0.0012276587076485157,\n",
+ " 0.0012025146279484034,\n",
+ " 0.0011409894796088338,\n",
+ " 0.0011019987286999822,\n",
+ " 0.0010852228151634336,\n",
+ " 0.0009970556711778045,\n",
+ " 0.001057568471878767,\n",
+ " 0.0010358155705034733,\n",
+ " 0.0009088307269848883,\n",
+ " 0.0010502993827685714,\n",
+ " 0.0008797580958344042,\n",
+ " 0.0008040553657338023,\n",
+ " 0.0007910137064754963,\n",
+ " 0.000899291830137372,\n",
+ " 0.0008638582658022642,\n",
+ " 0.0009095508721657097,\n",
+ " 0.0008973782532848418,\n",
+ " 0.0008580106659792364,\n",
+ " 0.0007925477693788707,\n",
+ " 0.0007486609974876046,\n",
+ " 0.0007689266931265593,\n",
+ " 0.0007510561845265329,\n",
+ " 0.000827563984785229,\n",
+ " 0.0008436156203970313,\n",
+ " 0.0007380963070318103,\n",
+ " 0.0007210447802208364,\n",
+ " 0.000752260850276798,\n",
+ " 0.0007482616929337382,\n",
+ " 0.000721216609235853,\n",
+ " 0.0007855220464989543,\n",
+ " 0.0007415070431306958,\n",
+ " 0.0007293731905519962,\n",
+ " 0.0006993496208451688,\n",
+ " 0.0006982010090723634,\n",
+ " 0.0007090615690685809,\n",
+ " 0.0006930531817488372,\n",
+ " 0.0006872066296637058,\n",
+ " 0.0006992127164267004,\n",
+ " 0.0007101157680153847,\n",
+ " 0.0006819805130362511,\n",
+ " 0.0006836954271420836,\n",
+ " 0.0006987039814703166,\n",
+ " 0.0006765545695088804,\n",
+ " 0.0006867556949146092,\n",
+ " 0.0006773460190743208,\n",
+ " 0.0006818092078901827,\n",
+ " 0.0006762673147022724,\n",
+ " 0.0006752805784344673,\n",
+ " 0.0006747819716110826,\n",
+ " 0.0006738057709299028],\n",
+ " 'val_mass_balance': [0.35021522641181946,\n",
+ " 0.1394379734992981,\n",
+ " 0.18183398246765137,\n",
+ " 0.10583663731813431,\n",
+ " 0.05481866002082825,\n",
+ " 0.07961198687553406,\n",
+ " 0.06197033077478409,\n",
+ " 0.051894836127758026,\n",
+ " 0.025688081979751587,\n",
+ " 0.08804472535848618,\n",
+ " 0.03425372764468193,\n",
+ " 0.04437873885035515,\n",
+ " 0.026329094544053078,\n",
+ " 0.03660159558057785,\n",
+ " 0.048272017389535904,\n",
+ " 0.025413667783141136,\n",
+ " 0.019724544137716293,\n",
+ " 0.018299173563718796,\n",
+ " 0.0194828100502491,\n",
+ " 0.016570812091231346,\n",
+ " 0.025805149227380753,\n",
+ " 0.022451717406511307,\n",
+ " 0.009862499311566353,\n",
+ " 0.021908782422542572,\n",
+ " 0.005759319290518761,\n",
+ " 0.009390369057655334,\n",
+ " 0.00970003753900528,\n",
+ " 0.004195359069854021,\n",
+ " 0.004727505147457123,\n",
+ " 0.009439199231564999,\n",
+ " 0.00502851651981473,\n",
+ " 0.0045739514753222466,\n",
+ " 0.007227415218949318,\n",
+ " 0.00718472758308053,\n",
+ " 0.003580695716664195,\n",
+ " 0.0027465075254440308,\n",
+ " 0.0019877778831869364,\n",
+ " 0.00257281051017344,\n",
+ " 0.0016277511604130268,\n",
+ " 0.0034374732058495283,\n",
+ " 0.0016461930936202407,\n",
+ " 0.0015438479604199529,\n",
+ " 0.0016676313243806362,\n",
+ " 0.002265515737235546,\n",
+ " 0.003019126830622554,\n",
+ " 0.0016960910288617015,\n",
+ " 0.0013514243764802814,\n",
+ " 0.0013028718531131744,\n",
+ " 0.001309368759393692,\n",
+ " 0.0016814287519082427,\n",
+ " 0.001222927705384791,\n",
+ " 0.0011976248351857066,\n",
+ " 0.001136238221079111,\n",
+ " 0.0010970447910949588,\n",
+ " 0.0010802543256431818,\n",
+ " 0.000992113258689642,\n",
+ " 0.001052781823091209,\n",
+ " 0.0010309231001883745,\n",
+ " 0.0009041248122230172,\n",
+ " 0.0010457386961206794,\n",
+ " 0.0008749476983211935,\n",
+ " 0.0007993136532604694,\n",
+ " 0.0007862630300223827,\n",
+ " 0.0008946022135205567,\n",
+ " 0.0008592592785134912,\n",
+ " 0.000905013526789844,\n",
+ " 0.0008927428280003369,\n",
+ " 0.0008533502114005387,\n",
+ " 0.0007878062315285206,\n",
+ " 0.0007440654444508255,\n",
+ " 0.0007643401622772217,\n",
+ " 0.0007463873480446637,\n",
+ " 0.0008230630191974342,\n",
+ " 0.0008388996939174831,\n",
+ " 0.0007335346890613437,\n",
+ " 0.0007164428243413568,\n",
+ " 0.000747605343349278,\n",
+ " 0.0007435783045366406,\n",
+ " 0.000716604117769748,\n",
+ " 0.000781018054112792,\n",
+ " 0.0007368420483544469,\n",
+ " 0.0007246945751830935,\n",
+ " 0.0006947608781047165,\n",
+ " 0.0006936006830073893,\n",
+ " 0.0007044760859571397,\n",
+ " 0.0006884249160066247,\n",
+ " 0.0006826136959716678,\n",
+ " 0.0006945744971744716,\n",
+ " 0.0007055643363855779,\n",
+ " 0.0006773463101126254,\n",
+ " 0.000679083401337266,\n",
+ " 0.000694122223649174,\n",
+ " 0.0006719458033330739,\n",
+ " 0.0006821651477366686,\n",
+ " 0.0006727080326527357,\n",
+ " 0.0006771697080694139,\n",
+ " 0.0006716735661029816,\n",
+ " 0.0006706715212203562,\n",
+ " 0.000670175941195339,\n",
+ " 0.0006691797752864659]}"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "history.history"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Test Mass Balance"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def mass_balance(model, X, preprocess):\n",
+ " \n",
+ " # predict the chemistry\n",
+ " columns = X.iloc[:, X.columns != \"Class\"].columns\n",
+ " prediction = pd.DataFrame(model.predict(X[columns]), columns=columns)\n",
+ " # backtransform min/max or standard scaler\n",
+ " X = pd.DataFrame(preprocess.scaler_X.inverse_transform(X.iloc[:, X.columns != \"Class\"]), columns=columns)\n",
+ " prediction = pd.DataFrame(preprocess.scaler_y.inverse_transform(prediction), columns=columns)\n",
+ " \n",
+ " # calculate mass balance\n",
+ " dBa = np.abs((prediction[\"Ba\"] + prediction[\"Barite\"]) - (X[\"Ba\"] + X[\"Barite\"]))\n",
+ " print(dBa.min())\n",
+ " dSr = np.abs((prediction[\"Sr\"] + prediction[\"Celestite\"]) - (X[\"Sr\"] + X[\"Celestite\"]))\n",
+ " print(dSr.min())\n",
+ " return dBa, dSr, prediction"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model_large.save(\"../results/models/model_large_minmax.keras\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m26993/26993\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 958us/step\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " H | \n",
+ " O | \n",
+ " Ba | \n",
+ " Cl | \n",
+ " S | \n",
+ " Sr | \n",
+ " Barite | \n",
+ " Celestite | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 111.012436 | \n",
+ " 55.506577 | \n",
+ " 2.545392e-05 | \n",
+ " 0.056169 | \n",
+ " 9.056123e-05 | \n",
+ " 0.028152 | \n",
+ " 0.000378 | \n",
+ " 1.000338 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 111.012436 | \n",
+ " 55.506767 | \n",
+ " -2.754421e-06 | \n",
+ " 0.013520 | \n",
+ " 1.372749e-04 | \n",
+ " 0.006905 | \n",
+ " 0.001824 | \n",
+ " 1.001608 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 111.012436 | \n",
+ " 55.506561 | \n",
+ " 4.052742e-05 | \n",
+ " 0.066249 | \n",
+ " 8.696535e-05 | \n",
+ " 0.033175 | \n",
+ " -0.000851 | \n",
+ " 1.002237 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 111.012436 | \n",
+ " 55.506218 | \n",
+ " 4.709655e-02 | \n",
+ " 0.153739 | \n",
+ " 1.902060e-07 | \n",
+ " 0.029717 | \n",
+ " 1.007493 | \n",
+ " 0.000263 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 111.012436 | \n",
+ " 55.507805 | \n",
+ " 4.156423e-06 | \n",
+ " 0.001301 | \n",
+ " 3.962677e-04 | \n",
+ " 0.001057 | \n",
+ " 0.000573 | \n",
+ " 1.001946 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 863768 | \n",
+ " 111.012436 | \n",
+ " 55.506592 | \n",
+ " -3.092120e-08 | \n",
+ " 0.048117 | \n",
+ " 9.312747e-05 | \n",
+ " 0.024139 | \n",
+ " 0.002836 | \n",
+ " 0.999394 | \n",
+ "
\n",
+ " \n",
+ " | 863769 | \n",
+ " 111.012436 | \n",
+ " 55.506775 | \n",
+ " -2.154928e-06 | \n",
+ " 0.013042 | \n",
+ " 1.396511e-04 | \n",
+ " 0.006667 | \n",
+ " 0.001727 | \n",
+ " 1.002290 | \n",
+ "
\n",
+ " \n",
+ " | 863770 | \n",
+ " 111.012436 | \n",
+ " 55.506489 | \n",
+ " 3.149816e-05 | \n",
+ " 0.108516 | \n",
+ " 6.810994e-05 | \n",
+ " 0.054227 | \n",
+ " 0.108361 | \n",
+ " 0.891181 | \n",
+ "
\n",
+ " \n",
+ " | 863771 | \n",
+ " 111.012436 | \n",
+ " 55.506218 | \n",
+ " 3.613450e-02 | \n",
+ " 0.141631 | \n",
+ " -7.596697e-08 | \n",
+ " 0.034772 | \n",
+ " 0.996522 | \n",
+ " 0.000232 | \n",
+ "
\n",
+ " \n",
+ " | 863772 | \n",
+ " 111.012436 | \n",
+ " 55.506214 | \n",
+ " 4.155123e-02 | \n",
+ " 0.150297 | \n",
+ " -7.713574e-07 | \n",
+ " 0.033498 | \n",
+ " 1.020295 | \n",
+ " -0.003992 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
863773 rows × 8 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " H | \n",
+ " O | \n",
+ " Ba | \n",
+ " Cl | \n",
+ " S | \n",
+ " Sr | \n",
+ " Barite | \n",
+ " Celestite | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 111.012434 | \n",
+ " 55.506578 | \n",
+ " 1.977602e-05 | \n",
+ " 0.056160 | \n",
+ " 9.022655e-05 | \n",
+ " 0.028151 | \n",
+ " 0.001000 | \n",
+ " 1.000490 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 111.012434 | \n",
+ " 55.506767 | \n",
+ " 4.662127e-06 | \n",
+ " 0.013550 | \n",
+ " 1.374302e-04 | \n",
+ " 0.006908 | \n",
+ " 0.001000 | \n",
+ " 1.000091 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 111.012434 | \n",
+ " 55.506565 | \n",
+ " 2.349696e-05 | \n",
+ " 0.066235 | \n",
+ " 8.705933e-05 | \n",
+ " 0.033181 | \n",
+ " 0.001001 | \n",
+ " 1.000613 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " 4.713082e-02 | \n",
+ " 0.153692 | \n",
+ " 1.289482e-07 | \n",
+ " 0.029715 | \n",
+ " 1.003514 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 111.012434 | \n",
+ " 55.507809 | \n",
+ " 7.424997e-07 | \n",
+ " 0.001338 | \n",
+ " 3.981606e-04 | \n",
+ " 0.001067 | \n",
+ " 0.001000 | \n",
+ " 1.000093 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 863768 | \n",
+ " 111.012434 | \n",
+ " 55.506591 | \n",
+ " 1.684073e-05 | \n",
+ " 0.048120 | \n",
+ " 9.347094e-05 | \n",
+ " 0.024137 | \n",
+ " 0.001001 | \n",
+ " 1.000615 | \n",
+ "
\n",
+ " \n",
+ " | 863769 | \n",
+ " 111.012434 | \n",
+ " 55.506776 | \n",
+ " 4.502549e-06 | \n",
+ " 0.013076 | \n",
+ " 1.397029e-04 | \n",
+ " 0.006673 | \n",
+ " 0.001000 | \n",
+ " 1.000591 | \n",
+ "
\n",
+ " \n",
+ " | 863770 | \n",
+ " 111.012434 | \n",
+ " 55.506474 | \n",
+ " 2.738630e-04 | \n",
+ " 0.108422 | \n",
+ " 6.420915e-05 | \n",
+ " 0.054001 | \n",
+ " 0.104655 | \n",
+ " 0.892149 | \n",
+ "
\n",
+ " \n",
+ " | 863771 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " 3.604271e-02 | \n",
+ " 0.141633 | \n",
+ " 1.533977e-07 | \n",
+ " 0.034774 | \n",
+ " 1.006758 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ " | 863772 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " 4.167711e-02 | \n",
+ " 0.150324 | \n",
+ " 1.392182e-07 | \n",
+ " 0.033485 | \n",
+ " 1.006763 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
863773 rows × 8 columns
\n",
+ "
"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "species = \"Barite\"\n",
+ "iterations = 250\n",
+ "cell_offset = 9\n",
+ "y_design = []\n",
+ "y_results = []\n",
+ "y_differences = []\n",
+ "\n",
+ "df_design_transformed_scaled = preprocess.scaler_X.transform(df_design[species_columns])\n",
+ "df_results_transformed_scaled = preprocess.scaler_y.transform(df_results[species_columns])\n",
+ "\n",
+ "for i in range(0,iterations):\n",
+ " idx = i*50*50 + cell_offset-1\n",
+ " y_design.append(df_design_transformed_scaled.iloc[idx, :])\n",
+ " y_results.append(df_results_transformed_scaled.iloc[idx,:])\n",
+ " \n",
+ "y_design = pd.DataFrame(y_design)\n",
+ "y_results = pd.DataFrame(y_results)\n",
+ "\n",
+ "prediction = model_large.predict(y_design.iloc[:, y_design.columns != \"Class\"])\n",
+ "prediction = pd.DataFrame(prediction, columns = y_results.columns)\n",
+ "\n",
+ "# y_results_back, prediction = preprocess.funcInverse(y_results, prediction)\n",
+ "\n",
+ "y_results_back = pd.DataFrame(preprocess.scaler_y.inverse_transform(y_results), columns = species_columns)\n",
+ "prediction_back = pd.DataFrame(preprocess.scaler_X.inverse_transform(prediction), columns = species_columns)\n",
+ "\n",
+ "\n",
+ "plt.plot(np.arange(0,iterations), y_results_back[species], label = \"Results\")\n",
+ "plt.plot(np.arange(0,iterations), prediction_back[species], label = \"Prediction\")\n",
+ "plt.legend()\n",
+ "plt.xlabel('Iteration')\n",
+ "plt.ylabel(species)\n",
+ "plt.title(species+' Concentration over Iterations in cell ' + str(cell_offset))\n",
+ "plt.legend()\n",
+ "plt.show()\n",
+ "\n",
+ "\n",
+ "mass_balance = np.abs((prediction_back[\"Ba\"] + prediction_back[\"Barite\"]) - (y_results_back[\"Ba\"] + y_results_back[\"Barite\"])) \\\n",
+ " + np.abs((prediction_back[\"Sr\"] + prediction_back[\"Celestite\"]) - (y_results_back[\"Sr\"] + y_results_back[\"Celestite\"]))\n",
+ "plt.plot(np.arange(0,iterations), mass_balance, label = \"Results\")\n",
+ "plt.xlabel('Iteration')\n",
+ "plt.ylabel(species)\n",
+ "plt.title(species+' Absolute Differences between predictions and true values Iterations in cell ' + str(cell_offset))\n",
+ "plt.axhline(y=1e-5, color='r', linestyle='--', label='Threshold 1e-5')\n",
+ "plt.legend()\n",
+ "\n",
+ "\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " H | \n",
+ " O | \n",
+ " Charge | \n",
+ " Ba | \n",
+ " Cl | \n",
+ " S_6_ | \n",
+ " Sr | \n",
+ " Barite | \n",
+ " Celestite | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 111.012434 | \n",
+ " 55.510420 | \n",
+ " -5.285676e-07 | \n",
+ " 4.536952e-07 | \n",
+ " 0.000022 | \n",
+ " 1.050707e-03 | \n",
+ " 0.000625 | \n",
+ " 0.001010 | \n",
+ " 1.717461 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 111.012434 | \n",
+ " 55.507697 | \n",
+ " -5.292985e-07 | \n",
+ " 1.091671e-06 | \n",
+ " 0.002399 | \n",
+ " 3.700427e-04 | \n",
+ " 0.001488 | \n",
+ " 0.001738 | \n",
+ " 1.716139 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 111.012434 | \n",
+ " 55.506335 | \n",
+ " -5.311407e-07 | \n",
+ " 6.816584e-05 | \n",
+ " 0.008922 | \n",
+ " 2.946349e-05 | \n",
+ " 0.004445 | \n",
+ " 0.004898 | \n",
+ " 1.708478 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 111.012434 | \n",
+ " 55.506229 | \n",
+ " -5.326179e-07 | \n",
+ " 1.435037e-03 | \n",
+ " 0.017414 | \n",
+ " 3.035681e-06 | \n",
+ " 0.007281 | \n",
+ " 0.008778 | \n",
+ " 1.698481 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 111.012434 | \n",
+ " 55.506224 | \n",
+ " -5.354202e-07 | \n",
+ " 3.264876e-03 | \n",
+ " 0.026235 | \n",
+ " 1.872898e-06 | \n",
+ " 0.009764 | \n",
+ " 0.012641 | \n",
+ " 1.688408 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 995 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " -5.369526e-07 | \n",
+ " 6.381593e-02 | \n",
+ " 0.223770 | \n",
+ " 1.220403e-07 | \n",
+ " 0.032096 | \n",
+ " 1.714723 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ " | 996 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " -5.370535e-07 | \n",
+ " 6.386712e-02 | \n",
+ " 0.223789 | \n",
+ " 1.220029e-07 | \n",
+ " 0.032055 | \n",
+ " 1.714723 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ " | 997 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " -5.371457e-07 | \n",
+ " 6.391481e-02 | \n",
+ " 0.223807 | \n",
+ " 1.219644e-07 | \n",
+ " 0.032017 | \n",
+ " 1.714723 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ " | 998 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " -5.372196e-07 | \n",
+ " 6.395922e-02 | \n",
+ " 0.223826 | \n",
+ " 1.219672e-07 | \n",
+ " 0.031982 | \n",
+ " 1.714723 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ " | 999 | \n",
+ " 111.012434 | \n",
+ " 55.506217 | \n",
+ " -5.372770e-07 | \n",
+ " 6.400057e-02 | \n",
+ " 0.223844 | \n",
+ " 1.220142e-07 | \n",
+ " 0.031950 | \n",
+ " 1.714723 | \n",
+ " 0.000000 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
1000 rows × 9 columns
\n",
+ "