Updated Notebook comments

Notebooks/39_svgp_hyperparameter_estimation.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Bayesian Optimisation of starting Gaussian Process hyperparameters"
+    "# Sparse and Variational Gaussian Process Model Training and Performance Evaluation"
    ]
   },
   {
@@ -78,9 +78,6 @@
    "cell_type": "markdown",
    "metadata": {
     "id": "90fdac33-eed4-4ab4-b2b1-de0f1f27727b",
-    "jupyter": {
-     "source_hidden": true
-    },
     "tags": []
    },
    "source": [
@@ -199,7 +196,7 @@
     "id": "0aba0df5-b0e3-4738-bb61-1dad869d1ea3"
    },
    "source": [
-    "## Load previously exported data"
+    "## Load previously exported CARNOT 'experimental' data"
    ]
   },
   {
@@ -212,6 +209,13 @@
     "dfs_test = []"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Separate into training and testing data sets:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 13,
@@ -235,6 +239,13 @@
     "    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": 15,
@@ -248,6 +259,13 @@
     "y_cols = ['SimulatedTemp']"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Impose the autoregressive lags for each input group:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 16,
@@ -497,6 +515,13 @@
     "    return df_gpr"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Merge all the training dataframes:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 25,
@@ -647,15 +672,6 @@
     "df_gpr_train.head()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#df_gpr_train = df_gpr_train.sample(n = 500)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 27,
@@ -1245,6 +1261,13 @@
     "y_lags = 5"
    ]
   },
+  {
+   "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": 54,
@@ -1470,6 +1493,13 @@
     "## Multistep prediction"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Select the dataset which will be used for multistep prediction:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 47,
@@ -1481,6 +1511,13 @@
     "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": 48,