mlessentials/Lab10/Exercise10.02/Exercise10_02.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "HEiOAwQPW0qb"
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "j7whidfaYjns"
   },
   "outputs": [],
   "source": [
    "file_url = '../dataset/ames_iowa_housing.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "nFMz2jNVt-xy"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(file_url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "qwSvQHzZhN2q"
   },
   "outputs": [],
   "source": [
    "obj_df = df.select_dtypes(include='object')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 187
    },
    "colab_type": "code",
    "id": "vdBz2p9w6w4K",
    "outputId": "d4769d6d-6956-4aa7-d026-472a54c9229c"
   },
   "outputs": [],
   "source": [
    "obj_cols = obj_df.columns\n",
    "obj_cols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "3yRUe0E7aJgk"
   },
   "outputs": [],
   "source": [
    "def describe_object(df, col_name):\n",
    "  print(f\"\\nCOLUMN: {col_name}\")\n",
    "  print(f\"{df[col_name].nunique()} different values\")\n",
    "  print(f\"List of values:\")\n",
    "  print(df[col_name].value_counts(dropna=False, normalize=True))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 187
    },
    "colab_type": "code",
    "id": "QRLrQjc5bl5b",
    "outputId": "0d9004f2-49b9-4934-b403-5539a8625a9e"
   },
   "outputs": [],
   "source": [
    "describe_object(df, 'MSZoning')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "colab_type": "code",
    "id": "hv3qvtqZf-TL",
    "outputId": "83c59b15-68b1-41c8-d590-08cbbf4529f2"
   },
   "outputs": [],
   "source": [
    "for col_name in obj_cols:\n",
    "  describe_object(df, col_name)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise10_02.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}