Merge branch 'main' into 150-improve-error-handling-of-taggedtable

docs/tutorials/getting_started.ipynb → docs/tutorials/classification.ipynb

@@ -3,7 +3,7 @@
   {
    "cell_type": "markdown",
    "source": [
-    "# Getting started\n",
+    "# Classification\n",
     "\n",
     "This tutorial uses safeds on **titanic passenger data** to predict who will survive and who will not, using sex as a feature for the prediction.\n"
    ],
@@ -27,7 +27,9 @@
    "source": [
     "from safeds.data.tabular.containers import Table\n",
     "\n",
-    "titanic = Table.from_csv_file(\"data/titanic.csv\")"
+    "titanic = Table.from_csv_file(\"data/titanic.csv\")\n",
+    "#For visualisation purposes we only print out the first 15 rows.\n",
+    "titanic.slice_rows(0,15)"
    ],
    "metadata": {
     "collapsed": false
@@ -51,9 +53,9 @@
     "split_tuple = titanic.split_rows(0.60)\n",
     "\n",
     "train_table = split_tuple[0]\n",
-    "test_table = split_tuple[1]\n",
+    "testing_table = split_tuple[1]\n",
     "\n",
-    "test_table = test_table.remove_columns([\"survived\"])"
+    "test_table = testing_table.remove_columns([\"survived\"]).shuffle_rows()"
    ],
    "metadata": {
     "collapsed": false
@@ -170,9 +172,11 @@
     "encoder = OneHotEncoder().fit(test_table, [\"sex\"])\n",
     "transformed_test_table = encoder.transform(test_table)\n",
     "\n",
-    "fitted_model.predict(\n",
+    "predicition = fitted_model.predict(\n",
     "    transformed_test_table\n",
-    ")\n"
+    ")\n",
+    "#For visualisation purposes we only print out the first 15 rows.\n",
+    "predicition.slice_rows(0,15)"
    ],
    "metadata": {
     "collapsed": false
@@ -181,7 +185,7 @@
   {
    "cell_type": "markdown",
    "source": [
-    "7. You can test the accuracy of that model as follows:"
+    "8. You can test the accuracy of that model with the initial testing_table as follows:"
    ],
    "metadata": {
     "collapsed": false
@@ -192,6 +196,12 @@
    "execution_count": null,
    "outputs": [],
    "source": [
+    "encoder = OneHotEncoder().fit(test_table, [\"sex\"])\n",
+    "testing_table = encoder.transform(testing_table)\n",
+    "\n",
+    "tagged_test_table= testing_table.tag_columns(\"survived\", feature_names=[\n",
+    "    *new_columns\n",
+    "])\n",
     "fitted_model.accuracy(tagged_train_table)\n"
    ],
    "metadata": {