Feat/cleanup examples

docs/example-notebooks/Extending-pandas.ipynb

@@ -385,11 +385,7 @@
     "Auto cleaning and the low code UI work together for more fine grained editting of data.  The low code UI presents a gui that works on columns and allows functions with arguments.  \n",
     "\n",
     "Auto cleaning works to suggest operations that are then loaded into the low code ui.  Then these operations can be editted or removed.\n",
-    "Auto cleaning options can be cycled through to generate different cleanings.\n",
-    "\n",
-    "## Why did this release remove auto cleaning and the low code UI?\n",
-    "\n",
-    "Although auto cleaning and the low code UI is my favorite feature of Buckaroo, and the first part I built, it hasn't seemed to have gained traction with users.  Buckaroo for that matter hasn't gained a lot of traction.  For the time being I have decided to put more effort into refining and promoting the parts of Buckaroo that people do understand.  "
+    "Auto cleaning options can be cycled through to generate different cleanings.\n"
    ]
   },
   {
@@ -417,7 +413,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.20"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

docs/example-notebooks/Extending.ipynb

@@ -434,7 +434,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.19"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

docs/example-notebooks/Full-tour.ipynb

@@ -248,7 +248,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.20"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

docs/example-notebooks/introduction.ipynb → docs/example-notebooks/Introduction.ipynb

@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "w = BuckarooWidget(df, showCommands=False)\n",
+    "w = BuckarooWidget(df)\n",
     "w"
    ]
   },
@@ -46,7 +46,8 @@
    },
    "outputs": [],
    "source": [
-    "from buckaroo.pluggable_analysis_framework import (ColAnalysis)\n",
+    "w = BuckarooWidget(df)\n",
+    "from buckaroo.pluggable_analysis_framework.pluggable_analysis_framework import ColAnalysis\n",
     "from scipy.stats import skew\n",
     "class Skew(ColAnalysis):\n",
     "    provides_summary = [\"skew\"]\n",
@@ -60,6 +61,7 @@
     "            return dict(skew=skew(sampled_ser.astype('float64')))\n",
     "        else:\n",
     "            return dict(skew=\"NA\")\n",
+    "    #fixme\n",
     "    summary_stats_display = [\n",
     "        'dtype',\n",
     "        'length',\n",
@@ -78,7 +80,8 @@
     "        'mean',\n",
     "        # we must add skew to the list of summary_stats_display, otherwise our new stat won't be displayed\n",
     "        'skew']\n",
-    "w.add_analysis(Skew)"
+    "w.add_analysis(Skew)\n",
+    "w"
    ]
   },
   {
@@ -236,8 +239,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from buckaroo.all_transforms import Command\n",
-    "from buckaroo.lispy import s\n",
+    "w = BuckarooWidget(df[:500])\n",
+    "w"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from buckaroo.customizations.all_transforms import Command\n",
+    "from buckaroo.jlisp.lisp_utils import s\n",
+    "w = BuckarooWidget(df[:500])\n",
     "#Here we start adding commands to the Buckaroo Widget.  Every call to add_command replaces a command with the same name\n",
     "@w.add_command\n",
     "class GroupBy2(Command):\n",
@@ -283,6 +297,15 @@
    "source": [
     "Note that `groupby2` has been added to the commands"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w.ac_obj."
+   ]
   }
  ],
  "metadata": {
@@ -301,7 +324,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.20"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

docs/example-notebooks/Lowcode-UI.ipynb

@@ -0,0 +1,149 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from buckaroo.buckaroo_widget import BuckarooInfiniteWidget, BuckarooWidget"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('./yellow_tripdata_2021-02.csv')\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w = BuckarooInfiniteWidget(df)\n",
+    "w"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Adding a Command to the Low Code UI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from buckaroo.customizations.all_transforms import Command\n",
+    "from buckaroo.jlisp.lisp_utils import s\n",
+    "w = BuckarooWidget(df[:500])\n",
+    "#Here we start adding commands to the Buckaroo Widget.  Every call to add_command replaces a command with the same name\n",
+    "#@w.add_command\n",
+    "class GroupBy2(Command):\n",
+    "    command_default = [s(\"groupby2\"), s('df'), 'col', {}]\n",
+    "    command_pattern = [[3, 'colMap', 'colEnum', ['null', 'sum', 'mean', 'median', 'count']]]\n",
+    "    @staticmethod \n",
+    "    def transform(df, col, col_spec):\n",
+    "        grps = df.groupby(col)\n",
+    "        df_contents = {}\n",
+    "        for k, v in col_spec.items():\n",
+    "            if v == \"sum\":\n",
+    "                df_contents[k] = grps[k].apply(lambda x: x.sum())\n",
+    "            elif v == \"mean\":\n",
+    "                df_contents[k] = grps[k].apply(lambda x: x.mean())\n",
+    "            elif v == \"median\":\n",
+    "                df_contents[k] = grps[k].apply(lambda x: x.median())\n",
+    "            elif v == \"count\":\n",
+    "                df_contents[k] = grps[k].apply(lambda x: x.count())\n",
+    "        return pd.DataFrame(df_contents)\n",
+    "\n",
+    "    @staticmethod \n",
+    "    def transform_to_py(df, col, col_spec):\n",
+    "        commands = [\n",
+    "            \"    grps = df.groupby('%s')\" % col,\n",
+    "            \"    df_contents = {}\"\n",
+    "        ]\n",
+    "        for k, v in col_spec.items():\n",
+    "            if v == \"sum\":\n",
+    "                commands.append(\"    paddydf_contents['%s'] = grps['%s'].apply(lambda x: x.sum())\" % (k, k))\n",
+    "            elif v == \"mean\":\n",
+    "                commands.append(\"    df_contents['%s'] = grps['%s'].apply(lambda x: x.mean())\" % (k, k))\n",
+    "            elif v == \"median\":\n",
+    "                commands.append(\"    df_contents['%s'] = grps['%s'].apply(lambda x: x.median())\" % (k, k))\n",
+    "            elif v == \"count\":\n",
+    "                commands.append(\"    df_contents['%s'] = grps['%s'].apply(lambda x: x.count())\" % (k, k))\n",
+    "        commands.append(\"    df = pd.DataFrame(df_contents)\")\n",
+    "        return \"\\n\".join(commands)\n",
+    "        \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from buckaroo.dataflow.autocleaning import AutocleaningConfig\n",
+    "from buckaroo.customizations.pd_autoclean_conf import BASE_COMMANDS, NoCleaningConf\n",
+    "\n",
+    "LOCAL_COMMANDS = BASE_COMMANDS.copy()\n",
+    "LOCAL_COMMANDS.append(GroupBy2)\n",
+    "\n",
+    "class ExtraGroupbyConf(NoCleaningConf):\n",
+    "    command_klasses = LOCAL_COMMANDS\n",
+    "\n",
+    "class BuckarooExtraCommands(BuckarooInfiniteWidget):\n",
+    "    #autoclean_conf = tuple([CleaningConf, NoCleaningConf]) #override the base CustomizableDataFlow conf\n",
+    "    autoclean_conf = tuple([ExtraGroupbyConf])\n",
+    "BuckarooExtraCommands(df)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Note that `groupby2` has been added to the commands"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w.ac_obj."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/example-notebooks/Styling-Gallery-Pandas.ipynb

@@ -541,6 +541,14 @@
    "metadata": {},
    "outputs": [],
    "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -559,7 +567,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.20"
+   "version": "3.12.8"
   }
  },
  "nbformat": 4,

scripts/clean_notebooks.sh

@@ -12,8 +12,10 @@ nbstripout docs/example-notebooks/DFViewer.ipynb \
  docs/example-notebooks/Itables-testcases.ipynb \
  docs/example-notebooks/Pluggable-Analysis-Framework.ipynb \
  docs/example-notebooks/Solara-Buckaroo.ipynb \
- docs/example-notebooks/introduction.ipynb \
+ docs/example-notebooks/Introduction.ipynb \
  docs/example-notebooks/Styling-Gallery-Polars.ipynb \
  docs/example-notebooks/Styling-Gallery-Pandas.ipynb \
- docs/example-notebooks/styling-howto.ipynb \
+ docs/example-notebooks/Styling-Howto.ipynb \
+ docs/example-notebooks/Lowcode-UI.ipynb \
  docs/example-notebooks/testcases-fast.ipynb
+