feat: replace other values than NaN with imputer (#707)

Closes #643 ### Summary of Changes * Add an optional argument to `Imputer` to configure the `value_to_replace`. This can be an int, float, or string. --------- Co-authored-by: megalinter-bot <[email protected]>
Safe-DS · May 3, 2024 · 4a059e0 · 4a059e0
1 parent 36e4a7a
commit 4a059e0
Show file tree

Hide file tree

Showing 5 changed files with 359 additions and 288 deletions.
diff --git a/docs/tutorials/data_processing.ipynb b/docs/tutorials/data_processing.ipynb
@@ -32,15 +32,15 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "from safeds.data.tabular.containers import Table\n",
     "\n",
     "titanic = Table.from_csv_file(\"data/titanic.csv\")"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -54,15 +54,15 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice = titanic.slice_rows(end=10)\n",
     "\n",
     "titanic_slice # just to show the output"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -76,13 +76,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.get_row(0)"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -96,13 +96,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.get_column(\"name\")"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -116,7 +116,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "Table.from_rows([\n",
     "    titanic_slice.get_row(0),\n",
@@ -125,7 +124,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -139,7 +139,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "Table.from_columns([\n",
     "    titanic_slice.get_column(\"name\"),\n",
@@ -148,7 +147,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -162,7 +162,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.remove_columns([\n",
     "    \"id\",\n",
@@ -175,7 +174,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -189,13 +189,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.keep_only_columns([\"name\", \"survived\"])"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -211,13 +211,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.sort_columns()"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -231,7 +231,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.sort_columns(\n",
     "    lambda column1, column2:\n",
@@ -240,7 +239,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -254,7 +254,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic.filter_rows(\n",
     "    lambda row:\n",
@@ -263,7 +262,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -278,7 +278,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "from safeds.data.tabular.transformation import Imputer\n",
     "\n",
@@ -287,7 +286,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -301,7 +301,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "from safeds.data.tabular.transformation import LabelEncoder\n",
     "\n",
@@ -310,7 +309,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -324,7 +324,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "from safeds.data.tabular.transformation import OneHotEncoder\n",
     "\n",
@@ -333,7 +332,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -347,7 +347,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "from safeds.data.tabular.transformation import RangeScaler\n",
     "\n",
@@ -356,7 +355,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -370,7 +370,6 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "from safeds.data.tabular.transformation import StandardScaler\n",
     "\n",
@@ -379,7 +378,8 @@
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -394,13 +394,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.transform_column(\"sex\", lambda row: 1 if row.get_value(\"sex\") == \"female\" else 0)\n"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -414,13 +414,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "outputs": [],
    "source": [
     "titanic_slice.transform_column(\"parents_children\", lambda row: \"No\" if row.get_value(\"parents_children\") == 0 else \"Yes\")\n"
    ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "outputs": []
   }
  ],
  "metadata": {