feat: house sales example

docs/examples/display_column_description.py

@@ -0,0 +1,44 @@
+import pandas as pd
+from IPython.core.display_functions import DisplayHandle
+from IPython.display import display
+from safeds.data.tabular import Table
+
+
+def display_column_descriptions(column_descriptions: Table) -> DisplayHandle:
+    """
+    Displays a Table containing the column descriptions.
+
+    Parameters
+    ----------
+    column_descriptions : Table
+        The column descriptions.
+
+    Returns
+    -------
+    DisplayHandle
+        The display handle.
+    """
+
+    # Remember the current value of the max_colwidth option
+    max_colwidth = pd.get_option("max_colwidth")
+
+    # Don't cut off the column descriptions
+    pd.set_option("max_colwidth", None)
+
+    # Create a DisplayHandle that displays the column descriptions nicely
+    styler = (
+        column_descriptions._data.style.relabel_index(["Name", "Description"], axis="columns")
+        .hide(axis="index")
+        .set_properties(
+            **{
+                "text-align": "left",
+                "white-space": "pre-wrap",
+            }
+        )
+    )
+    result = display(styler)
+
+    # Restore the max_colwidth option
+    pd.set_option("max_colwidth", max_colwidth)
+
+    return result

docs/examples/house_sales.ipynb

@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# House Sales\n",
+    "\n",
+    "The dataset contains house sale prices for King County, USA between May 2014 and May 2015. It is well suited to practice regression techniques."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Column descriptions"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "from safeds_examples.tabular import describe_house_sales_columns\n",
+    "from display_column_description import display_column_descriptions\n",
+    "\n",
+    "house_sales_description = describe_house_sales_columns()\n",
+    "display_column_descriptions(house_sales_description)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Sample"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "from safeds_examples.tabular import load_house_sales\n",
+    "\n",
+    "house_sales = load_house_sales()\n",
+    "house_sales.slice(end=10)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "is_executing": true
+    }
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Schema"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "house_sales.schema"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Statistics"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "house_sales.summary()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Correlation heatmap"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "from safeds.plotting import correlation_heatmap\n",
+    "\n",
+    "house_sales_correlation = house_sales.drop_columns([\n",
+    "    \"id\",\n",
+    "    \"year\",\n",
+    "    \"month\",\n",
+    "    \"day\",\n",
+    "    \"zipcode\",\n",
+    "    \"latitude\",\n",
+    "    \"longitude\"\n",
+    "])\n",
+    "correlation_heatmap(house_sales_correlation)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Attribution\n",
+    "\n",
+    "This dataset is a modified version of the [\"House Sales in King County, USA\" dataset](https://www.kaggle.com/datasets/harlfoxem/housesalesprediction) by Kaggle user [`harlfoxem`](https://www.kaggle.com/harlfoxem). The original dataset is licensed under `CC0: Public Domain`.\n",
+    "\n",
+    "Column descriptions are based on [this Kaggle discussion](https://www.kaggle.com/datasets/harlfoxem/housesalesprediction/discussion/207885).\n"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

mkdocs.yml

@@ -7,6 +7,7 @@ nav:
     - README.md
     - Changelog: CHANGELOG.md
   - Examples:
+    - House Sales: examples/house_sales.ipynb
     - Titanic: examples/titanic.ipynb
   - API Reference: reference/
   - Development:
@@ -64,6 +65,7 @@ plugins:
       include: ["*.ipynb"]
       execute: true
       allow_errors: false
+      no_input: true
 
 watch:
   - src

src/safeds_examples/tabular/__init__.py

@@ -1 +1,2 @@
+from ._house_sales import describe_house_sales_columns, load_house_sales
 from ._titanic import load_titanic

src/safeds_examples/tabular/_house_sales/__init__.py

@@ -0,0 +1 @@
+from ._house_sales import describe_house_sales_columns, load_house_sales

src/safeds_examples/tabular/_house_sales/_house_sales.py

@@ -0,0 +1,69 @@
+import os
+
+from safeds.data.tabular import Table
+
+_path = os.path.join(os.path.dirname(__file__), "data", "house_sales.csv")
+
+
+def load_house_sales() -> Table:
+    """
+    Loads the "House Sales" dataset.
+
+    Returns
+    -------
+    Table
+        The "House Sales" dataset.
+    """
+
+    return Table.from_csv(_path)
+
+
+def describe_house_sales_columns() -> Table:
+    """
+    Returns a `Table` with two columns `"Name"` and `"Description"`, containing the name of a column in the "House
+    Sales" dataset and its description respectively.
+
+    Returns
+    -------
+    Table
+        A `Table` with names and descriptions for all columns of the "House Sales" dataset.
+    """
+
+    return Table(
+        [
+            {"Name": "id", "Description": "A unique identifier"},
+            {"Name": "year", "Description": "Year of sale"},
+            {"Name": "month", "Description": "Month of sale"},
+            {"Name": "day", "Description": "Day of sale"},
+            {"Name": "zipcode", "Description": "Zipcode"},
+            {"Name": "latitude", "Description": "Latitude"},
+            {"Name": "longitude", "Description": "Longitude"},
+            {"Name": "sqft_lot", "Description": "Lot area in square feet"},
+            {"Name": "sqft_living", "Description": "Interior living space in square feet"},
+            {"Name": "sqft_above", "Description": "Interior living space above ground in square feet"},
+            {"Name": "sqft_basement", "Description": "Interior living space below ground in square feet"},
+            {"Name": "floors", "Description": "Number of floors"},
+            {"Name": "bedrooms", "Description": "Number of bedrooms"},
+            {
+                "Name": "bathrooms",
+                "Description": "Number of bathrooms.\n\n"
+                "Fractional values indicate that components (toilet/sink/shower/bathtub) are missing.",
+            },
+            {"Name": "waterfront", "Description": "Whether the building overlooks a waterfront (0 = no, 1 = yes)"},
+            {"Name": "view", "Description": "Rating of the view (1 to 5, higher is better)"},
+            {"Name": "condition", "Description": "Rating of the condition of the house (1 to 5, higher is better)"},
+            {"Name": "grade", "Description": "Rating of building construction and design (1 to 13, higher is better)"},
+            {"Name": "year_built", "Description": "Year the house was built"},
+            {
+                "Name": "year_renovated",
+                "Description": "Year the house was last renovated.\n\n"
+                "A value of 0 indicates that it was never renovated.",
+            },
+            {"Name": "sqft_lot_15nn", "Description": "Lot area of the 15 nearest neighbors in square feet"},
+            {
+                "Name": "sqft_living_15nn",
+                "Description": "Interior living space of the 15 nearest neighbors in square feet",
+            },
+            {"Name": "price", "Description": "Price the house sold for in USD"},
+        ]
+    )