Updated Notebook comments

Notebooks/38_gp_hyperparameter_estimation.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Bayesian Optimisation of starting Gaussian Process hyperparameters"
+    "# Gaussian Process Model Training and Performance Evaluation"
    ]
   },
   {
@@ -213,7 +213,7 @@
     "id": "0aba0df5-b0e3-4738-bb61-1dad869d1ea3"
    },
    "source": [
-    "## Load previously exported data"
+    "## Load previously exported CARNOT 'experimental' data"
    ]
   },
   {
@@ -226,6 +226,13 @@
     "dfs_test = []"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Separate into training and testing data sets:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 16,
@@ -249,6 +256,13 @@
     "    dfs_test.append(pd.read_csv(f\"../Data/Good_CARNOT/{exp}_table.csv\").rename(columns = {'Power': 'SimulatedHeat'}))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Separate columns into exogenous inputs, controlled inputs and outputs:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 18,
@@ -262,6 +276,13 @@
     "y_cols = ['SimulatedTemp']"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Impose the autoregressive lags for each input group:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 19,
@@ -511,6 +532,13 @@
     "    return df_gpr"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Merge all the training dataframes:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 28,
@@ -667,13 +695,19 @@
     "df_gpr_train.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Select all points in the training dataset:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
-    "train_dataset_size = 15 * 96\n",
     "train_dataset_size = -1"
    ]
   },
@@ -1401,6 +1435,13 @@
     "y_range = np.arange(1,6)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Iterate over all combination of lags and compute for each the RMSE, SMSE, LPD and MSLL errors:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1545,6 +1586,13 @@
     "## Multistep prediction"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Select the dataset which will be used for multistep prediction:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 54,
@@ -1556,6 +1604,13 @@
     "df_output = dfs_gpr_test[test_dataset_idx][dict_cols['y'][1]]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Select the starting index in the test dataset and the number of consecutive points to simulate:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 55,
@@ -1617,26 +1672,6 @@
     "plt.title(f\"Multi step prediction over {N_pred} steps for Test dataset {test_dataset_idx}\")\n",
     "plt.savefig(f\"../Thesis/Plots/GP_{w_lags}{u_lags}{y_lags}_{train_dataset_size}pts_test_prediction_{N_pred}_steps.pdf\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 141,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "TensorShape([2612, 7])"
-      ]
-     },
-     "execution_count": 141,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "m.data[0].shape"
-   ]
   }
  ],
  "metadata": {