DataScience Tools - Exploring  Missing Values or NaN .ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Science Tools\n",
    "### Packages For Exploring with Missing Data/Values\n",
    "+ Pandas\n",
    "+ BadFish\n",
    "+ Dora\n",
    "\n",
    "\n",
    "- pip install pandas\n",
    "- pip install badfish\n",
    "- pip install dora"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Pkgs\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Our dataset\n",
    "df = pd.read_csv(\"data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "      <th>Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Mark</td>\n",
       "      <td>23.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Matt Drops</td>\n",
       "      <td>34.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Kofi Assiedu</td>\n",
       "      <td>22.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mary Kay</td>\n",
       "      <td>22.0</td>\n",
       "      <td>F</td>\n",
       "      <td>25000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ansu Sighn</td>\n",
       "      <td>NaN</td>\n",
       "      <td>M</td>\n",
       "      <td>5400</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name   Age Gender Salary  Address\n",
       "0     John Mark  23.0      M  23040      NaN\n",
       "1    Matt Drops  34.0      M  23040      NaN\n",
       "2  Kofi Assiedu  22.0    NaN  40000      NaN\n",
       "3      Mary Kay  22.0      F  25000      NaN\n",
       "4    Ansu Sighn   NaN      M   5400      NaN"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "      <th>Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Name    Age  Gender  Salary  Address\n",
       "0   False  False   False   False     True\n",
       "1   False  False   False   False     True\n",
       "2   False  False    True   False     True\n",
       "3   False  False   False   False     True\n",
       "4   False   True   False   False     True\n",
       "5   False  False    True   False     True\n",
       "6   False   True   False   False     True\n",
       "7   False  False   False   False     True\n",
       "8   False  False   False    True     True\n",
       "9   False  False   False    True     True\n",
       "10  False  False   False   False     True\n",
       "11  False  False   False    True     True\n",
       "12  False  False   False   False     True\n",
       "13  False  False   False   False     True\n",
       "14  False  False   False   False     True\n",
       "15  False  False   False   False     True\n",
       "16  False  False    True   False     True\n",
       "17  False  False   False   False     True\n",
       "18  False  False   False   False     True\n",
       "19  False  False   False   False     True"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check For Missing NAN\n",
    "df.isnull()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Name        0\n",
       "Age         2\n",
       "Gender      3\n",
       "Salary      3\n",
       "Address    20\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Sum of Missing NANA\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Using Badfish\n",
    "+ Counts\n",
    "+ Pattern"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Pkg\n",
    "import badfish as bf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['MissFrame',\n",
       " '__builtins__',\n",
       " '__cached__',\n",
       " '__doc__',\n",
       " '__file__',\n",
       " '__loader__',\n",
       " '__name__',\n",
       " '__package__',\n",
       " '__path__',\n",
       " '__spec__',\n",
       " '__version__',\n",
       " 'badfish',\n",
       " 'plotting']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(bf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "miss_df = bf.MissFrame(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Address    20\n",
       "Salary      3\n",
       "Gender      3\n",
       "Age         2\n",
       "Name        0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Count the Number of Missing NAN In Entire dataset\n",
    "# Similar to df.isnull().sum()\n",
    "miss_df.counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Salary    3\n",
       "Age       2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Count Number of Missing NAN in Columns\n",
    "miss_df.counts(columns=['Salary','Age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "      <th>Address</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>0.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>0.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0.15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Name    Age  Gender  Salary  Address     0\n",
       "0  False  False   False   False     True  0.60\n",
       "1  False  False    True   False     True  0.15\n",
       "2  False  False   False    True     True  0.15"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Show Pattern\n",
    "# Similar to df.isnull()\n",
    "miss_df.pattern()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Visualize The Pattern of NAN\n",
    "+ Red/True : Missing\n",
    "+ Blue/False : Not Missing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualize The Pattern of NAN\n",
    "miss_df.plot(kind='pattern')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Using Where with Plot\n",
    "miss_df.plot(kind='pattern',where=['Gender', 'Salary'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using Dora\n",
    "+ for data cleaning, \n",
    "+ feature selection & extraction, \n",
    "+ visualization, partitioning data for model validation, and \n",
    "+ versioning transformations of data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the Pkgs\n",
    "from Dora import Dora"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load and Initialize\n",
    "dora = Dora(data = df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['__class__',\n",
       " '__delattr__',\n",
       " '__dict__',\n",
       " '__dir__',\n",
       " '__doc__',\n",
       " '__eq__',\n",
       " '__format__',\n",
       " '__ge__',\n",
       " '__getattribute__',\n",
       " '__gt__',\n",
       " '__hash__',\n",
       " '__init__',\n",
       " '__init_subclass__',\n",
       " '__le__',\n",
       " '__lt__',\n",
       " '__module__',\n",
       " '__ne__',\n",
       " '__new__',\n",
       " '__reduce__',\n",
       " '__reduce_ex__',\n",
       " '__repr__',\n",
       " '__setattr__',\n",
       " '__sizeof__',\n",
       " '__str__',\n",
       " '__subclasshook__',\n",
       " '__weakref__',\n",
       " '_log',\n",
       " 'configure',\n",
       " 'data',\n",
       " 'explore',\n",
       " 'extract_feature',\n",
       " 'extract_ordinal_feature',\n",
       " 'impute_missing_values',\n",
       " 'initial_data',\n",
       " 'input_columns',\n",
       " 'logs',\n",
       " 'plot_feature',\n",
       " 'remove_feature',\n",
       " 'scale_input_values',\n",
       " 'set_training_and_validation',\n",
       " 'snapshot',\n",
       " 'snapshots',\n",
       " 'use_snapshot']"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(dora)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "      <th>Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Mark</td>\n",
       "      <td>23.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Matt Drops</td>\n",
       "      <td>34.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Kofi Assiedu</td>\n",
       "      <td>22.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mary Kay</td>\n",
       "      <td>22.0</td>\n",
       "      <td>F</td>\n",
       "      <td>25000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ansu Sighn</td>\n",
       "      <td>NaN</td>\n",
       "      <td>M</td>\n",
       "      <td>5400</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mohammed Ali</td>\n",
       "      <td>34.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>M</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Paul Ayo</td>\n",
       "      <td>NaN</td>\n",
       "      <td>M</td>\n",
       "      <td>23400</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>David Bomerrang</td>\n",
       "      <td>24.0</td>\n",
       "      <td>M</td>\n",
       "      <td>50000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>John Mark</td>\n",
       "      <td>56.0</td>\n",
       "      <td>M.35000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Afia Nyame</td>\n",
       "      <td>25.0</td>\n",
       "      <td>34000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Ivan Ivanovich</td>\n",
       "      <td>45.0</td>\n",
       "      <td>M</td>\n",
       "      <td>24000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Vladmir Vyna</td>\n",
       "      <td>20.0</td>\n",
       "      <td>40000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Dan Lee</td>\n",
       "      <td>45.0</td>\n",
       "      <td>M</td>\n",
       "      <td>34000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Elizabeth Grace</td>\n",
       "      <td>23.0</td>\n",
       "      <td>F</td>\n",
       "      <td>43000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Pierre Santos</td>\n",
       "      <td>37.0</td>\n",
       "      <td>M</td>\n",
       "      <td>34560</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Carlos Bin</td>\n",
       "      <td>40.0</td>\n",
       "      <td>M</td>\n",
       "      <td>34560</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Myles Finer</td>\n",
       "      <td>54.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>54300</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Sara Mokuba</td>\n",
       "      <td>35.0</td>\n",
       "      <td>F</td>\n",
       "      <td>34567</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Paul Grahams</td>\n",
       "      <td>46.0</td>\n",
       "      <td>M</td>\n",
       "      <td>56890</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Yvonne Yumoshki</td>\n",
       "      <td>43.0</td>\n",
       "      <td>F</td>\n",
       "      <td>34560</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               Name   Age   Gender Salary  Address\n",
       "0         John Mark  23.0        M  23040      NaN\n",
       "1        Matt Drops  34.0        M  23040      NaN\n",
       "2      Kofi Assiedu  22.0      NaN  40000      NaN\n",
       "3          Mary Kay  22.0        F  25000      NaN\n",
       "4        Ansu Sighn   NaN        M   5400      NaN\n",
       "5      Mohammed Ali  34.0      NaN      M      NaN\n",
       "6          Paul Ayo   NaN        M  23400      NaN\n",
       "7   David Bomerrang  24.0        M  50000      NaN\n",
       "8         John Mark  56.0  M.35000    NaN      NaN\n",
       "9        Afia Nyame  25.0    34000    NaN      NaN\n",
       "10   Ivan Ivanovich  45.0        M  24000      NaN\n",
       "11     Vladmir Vyna  20.0    40000    NaN      NaN\n",
       "12          Dan Lee  45.0        M  34000      NaN\n",
       "13  Elizabeth Grace  23.0        F  43000      NaN\n",
       "14    Pierre Santos  37.0        M  34560      NaN\n",
       "15       Carlos Bin  40.0        M  34560      NaN\n",
       "16      Myles Finer  54.0      NaN  54300      NaN\n",
       "17      Sara Mokuba  35.0        F  34567      NaN\n",
       "18     Paul Grahams  46.0        M  56890      NaN\n",
       "19  Yvonne Yumoshki  43.0        F  34560      NaN"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# To View Or Explore Data\n",
    "dora.data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     23.0\n",
       "1     34.0\n",
       "2     22.0\n",
       "3     22.0\n",
       "4      NaN\n",
       "5     34.0\n",
       "6      NaN\n",
       "7     24.0\n",
       "8     56.0\n",
       "9     25.0\n",
       "10    45.0\n",
       "11    20.0\n",
       "12    45.0\n",
       "13    23.0\n",
       "14    37.0\n",
       "15    40.0\n",
       "16    54.0\n",
       "17    35.0\n",
       "18    46.0\n",
       "19    43.0\n",
       "Name: Age, dtype: float64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dora.data['Age']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop A Column/Feature\n",
    "dora.remove_feature('Address')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Mark</td>\n",
       "      <td>23.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Matt Drops</td>\n",
       "      <td>34.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Kofi Assiedu</td>\n",
       "      <td>22.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mary Kay</td>\n",
       "      <td>22.0</td>\n",
       "      <td>F</td>\n",
       "      <td>25000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ansu Sighn</td>\n",
       "      <td>NaN</td>\n",
       "      <td>M</td>\n",
       "      <td>5400</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name   Age Gender Salary\n",
       "0     John Mark  23.0      M  23040\n",
       "1    Matt Drops  34.0      M  23040\n",
       "2  Kofi Assiedu  22.0    NaN  40000\n",
       "3      Mary Kay  22.0      F  25000\n",
       "4    Ansu Sighn   NaN      M   5400"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dora.data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Name    Age  Gender  Salary\n",
       "0   False  False   False   False\n",
       "1   False  False   False   False\n",
       "2   False  False    True   False\n",
       "3   False  False   False   False\n",
       "4   False   True   False   False\n",
       "5   False  False    True   False\n",
       "6   False   True   False   False\n",
       "7   False  False   False   False\n",
       "8   False  False   False    True\n",
       "9   False  False   False    True\n",
       "10  False  False   False   False\n",
       "11  False  False   False    True\n",
       "12  False  False   False   False\n",
       "13  False  False   False   False\n",
       "14  False  False   False   False\n",
       "15  False  False   False   False\n",
       "16  False  False    True   False\n",
       "17  False  False   False   False\n",
       "18  False  False   False   False\n",
       "19  False  False   False   False"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check For Missing NAN\n",
    "dora.data.isnull()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Type is DataFrame Hence You Can Use it as such\n",
    "type(dora.data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "# To Use Functions You Need to Set Output\n",
    "dora2 = Dora(output=0,data = df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Salary</th>\n",
       "      <th>Address</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>John Mark</td>\n",
       "      <td>23.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Matt Drops</td>\n",
       "      <td>34.0</td>\n",
       "      <td>M</td>\n",
       "      <td>23040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Kofi Assiedu</td>\n",
       "      <td>22.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>40000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mary Kay</td>\n",
       "      <td>22.0</td>\n",
       "      <td>F</td>\n",
       "      <td>25000</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Ansu Sighn</td>\n",
       "      <td>NaN</td>\n",
       "      <td>M</td>\n",
       "      <td>5400</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name   Age Gender Salary  Address\n",
       "0     John Mark  23.0      M  23040      NaN\n",
       "1    Matt Drops  34.0      M  23040      NaN\n",
       "2  Kofi Assiedu  22.0    NaN  40000      NaN\n",
       "3      Mary Kay  22.0      F  25000      NaN\n",
       "4    Ansu Sighn   NaN      M   5400      NaN"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dora2.data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "# More to Add"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### Jesus Saves@JCharisTech\n",
    "#### By Jesse E.Agbe (JCharis)\n",
    "#### J-Secur1ty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}