Adds notes to the notebook

Signed-off-by: Timm638 <[email protected]>

notebook/showcase_notebook.ipynb

@@ -68,7 +68,7 @@
    "source": [
     "### Source of Data\n",
     "\n",
-    "The source data describes the generation of energy in the country of Germany by generation type.\n",
+    "The source data is sourced from ENTSO-E (European Network of Transmission System Operators for Electricity) and contains the amount of energy generated 2024 in Germany split up by generation type.\n",
     "\n",
     "Link: https://transparency.entsoe.eu/generation/r2/actualGenerationPerProductionType/show?name=&defaultValue=false&viewType=GRAPH&areaType=CTY&atch=false&datepicker-day-offset-select-dv-date-from_input=D&dateTime.dateTime=18.11.2024+00:00|CET|DAYTIMERANGE&dateTime.endDateTime=18.11.2024+00:00|CET|DAYTIMERANGE&area.values=CTY|10Y1001A1001A83F!CTY|10Y1001A1001A83F&productionType.values=B01&productionType.values=B25&productionType.values=B02&productionType.values=B03&productionType.values=B04&productionType.values=B05&productionType.values=B06&productionType.values=B07&productionType.values=B08&productionType.values=B09&productionType.values=B10&productionType.values=B11&productionType.values=B12&productionType.values=B13&productionType.values=B14&productionType.values=B20&productionType.values=B15&productionType.values=B16&productionType.values=B17&productionType.values=B18&productionType.values=B19&dateTime.timezone=CET_CEST&dateTime.timezone_input=CET+(UTC+1)+/+CEST+(UTC+2)#"
    ],
@@ -131,7 +131,13 @@
   {
    "metadata": {},
    "cell_type": "markdown",
-   "source": "### Normalization",
+   "source": [
+    "### Normalization\n",
+    "*Scenario*:\n",
+    "We want to normalize sensor data, so it better used in other components or Machine Learning applications.\n",
+    "We show our three implemented methods of normalization: Z-score, min-max & mean.\n",
+    "The denormalization of data is also supported, e. g. for storing processed data in a human-readable format."
+   ],
    "id": "5eb48b97e8a0baf0"
   },
   {
@@ -284,7 +290,12 @@
   {
    "metadata": {},
    "cell_type": "markdown",
-   "source": "### Duplicate Detection",
+   "source": [
+    "### Duplicate Detection\n",
+    "*Scenario*:\n",
+    "Because of some error reading in the sensor data, some entries are duplicated.\n",
+    "Cleaning these will decrease the size of the dataframe without losing any information.\n"
+   ],
    "id": "f363d141e3f2e403"
   },
   {
@@ -334,7 +345,12 @@
   {
    "metadata": {},
    "cell_type": "markdown",
-   "source": "### Sigma Anomaly Detection",
+   "source": [
+    "### Sigma Anomaly Detection\n",
+    "*Scenario*:\n",
+    "In raw sensor data, there are sometimes measurement outliers or errors, which pollute the data.\n",
+    "Identifying these spikes and removing them improves the data quality."
+   ],
    "id": "50078d362d4525d1"
   },
   {
@@ -378,7 +394,13 @@
   {
    "metadata": {},
    "cell_type": "markdown",
-   "source": "### Interval Filtering",
+   "source": [
+    "### Interval Filtering\n",
+    "*Scenario*:\n",
+    "Interval Filtering ensures, that the points in a dataframe are roughly equally in time, so that between two adjacent points roughly the same time period passes.\n",
+    "When working with too large data sets, some models are computationally too expensive to train on the whole dataset.\n",
+    "Interval Filtering can be used to reduce the amount of points in the data set, which allows it to be used e.g. for ARIMA-modelling."
+   ],
    "id": "eb8df1922029670f"
   },
   {
@@ -429,7 +451,11 @@
   {
    "metadata": {},
    "cell_type": "markdown",
-   "source": "### ARIMA Prediction",
+   "source": [
+    "### ARIMA Prediction\n",
+    "*Scenario*:\n",
+    "We want to predict how much solar energy will be used next week. For that we will apply the reduced data from Interval Filtering on a ARIMA-Model."
+   ],
    "id": "a96f089021e00143"
   },
   {
@@ -492,6 +518,8 @@
    "cell_type": "markdown",
    "source": [
     "### Value Imputation\n",
+    "*Scenario*:\n",
+    "Sometimes a value is missing because of sensor error or similar issues. This makes it difficult to use these time series on algorithms expecting a time series without gaps. To fix that issue, Value Imputation is used to fill in these gaps with meaningful values.\n",
     "\n"
    ],
    "id": "f1a0d8869448844f"