Showing how to add counts for unique and nan to buckaroo

Buckaroo-Unique-Nan-Count.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install buckaroo\n",
    "try:\n",
    "    from google.colab import output\n",
    "    output.enable_custom_widget_manager()\n",
    "except Exception as e:\n",
    "    print(e)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import buckaroo\n",
    "from buckaroo.pluggable_analysis_framework.pluggable_analysis_framework import (ColAnalysis)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Demonstrating Buckaroo on Citibike data.\n",
    "This might take a little time to download\n",
    "\n",
    "*once the view loads click 0's and 1's on the top left to toggle different parts of the UI*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"/Users/paddy/code/example-notebooks/citibike-trips.csv\") #for airplane work\n",
    "w = buckaroo.BuckarooWidget(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "class Variance(ColAnalysis):\n",
    "    provides_summary = [\"unique_count\", \"nan_count\"]\n",
    "    @staticmethod\n",
    "    def summary(sampled_ser, summary_ser, ser):\n",
    "        l = len(ser)\n",
    "        val_counts = ser.value_counts()\n",
    "        return dict(unique_count=len(val_counts[val_counts==1]), \n",
    "                    nan_count=(l - len(ser.dropna())))\n",
    "    summary_stats_display = [\n",
    "        'dtype', 'length', 'nan_count', 'distinct_count', 'empty_count',\n",
    "        'empty_per', 'unique_per', 'nan_per', \n",
    "        'is_numeric', 'is_integer', 'is_datetime',\n",
    "        'mode', 'min', 'max', 'mean', \n",
    "        # we must add unique_count and nan_count to the list of summary_stats_display, otherwise our new stat won't be displayed\n",
    "        'unique_count', 'nan_count']\n",
    "w.add_analysis(Variance)\n",
    "w"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "analysis is added interactively,  toggle the summary stats view on the widget above and notice that `unique_count` and `nan_count` has been added"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.5"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}