{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "42ffe538-0da7-4ab8-9bb2-efce0add67a9",
   "metadata": {},
   "source": [
    "WESTROXBURY EXAMPLE"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ea268c67-637e-42e1-adee-cf6a86d5db0f",
   "metadata": {},
   "source": [
    "The data in Westroxbury.csv includes information on a single owner-occupied homes in West Roxbury, a neighborhood in southwest Boston MA, in 2014."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "cc9e94f2-60e2-4a36-a7f8-1ec000501586",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Learning objectives:\n",
    "# 1) Learn how to load datasets into a Pandas DataFrame and inspect the structure\n",
    "# 2) Apply column renaming techniques and clean variable names to improve data manipulation using dot notation.\n",
    "# 3) Understand how to convert columns to appropriate data types, such as continuous, discrete, and categorical variables.\n",
    "# 4) Practice selecting subsets of data using loc[], iloc[], and pd.concat() to combine columns from different positions in a DataFrame..\n",
    "# 5) Explore random sampling techniques in Pandas, including weighted sampling to oversample specific cases.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb30738e-82af-4198-bb15-1de9dba29005",
   "metadata": {},
   "source": [
    "Pandas is a powerful data manipulation and analysis library for Python, widely used for working with structured data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "219f1e81-8f78-407a-ada9-ca35e0586a8a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import the required package\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "dbf98e2b-f485-4356-a7fb-5835a3db172d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Data\n",
    "housing_df = pd.read_csv(r'/Users/patriciaxufre/Downloads/WestRoxbury.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "effbcb7c-f38a-4cda-9d2f-98d8567aef03",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5802, 14)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Find the dimension of the data frame\n",
    "housing_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e87fa007-9e30-4601-adb7-ff1acf2afae1",
   "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>TOTAL VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>LOT SQFT</th>\n",
       "      <th>YR BUILT</th>\n",
       "      <th>GROSS AREA</th>\n",
       "      <th>LIVING AREA</th>\n",
       "      <th>FLOORS</th>\n",
       "      <th>ROOMS</th>\n",
       "      <th>BEDROOMS</th>\n",
       "      <th>FULL BATH</th>\n",
       "      <th>HALF BATH</th>\n",
       "      <th>KITCHEN</th>\n",
       "      <th>FIREPLACE</th>\n",
       "      <th>REMODEL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>344.2</td>\n",
       "      <td>4330</td>\n",
       "      <td>9965</td>\n",
       "      <td>1880</td>\n",
       "      <td>2436</td>\n",
       "      <td>1352</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>412.6</td>\n",
       "      <td>5190</td>\n",
       "      <td>6590</td>\n",
       "      <td>1945</td>\n",
       "      <td>3108</td>\n",
       "      <td>1976</td>\n",
       "      <td>2.0</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Recent</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>330.1</td>\n",
       "      <td>4152</td>\n",
       "      <td>7500</td>\n",
       "      <td>1890</td>\n",
       "      <td>2294</td>\n",
       "      <td>1371</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>498.6</td>\n",
       "      <td>6272</td>\n",
       "      <td>13773</td>\n",
       "      <td>1957</td>\n",
       "      <td>5032</td>\n",
       "      <td>2608</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>331.5</td>\n",
       "      <td>4170</td>\n",
       "      <td>5000</td>\n",
       "      <td>1910</td>\n",
       "      <td>2370</td>\n",
       "      <td>1438</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   TOTAL VALUE    TAX  LOT SQFT   YR BUILT  GROSS AREA   LIVING AREA  FLOORS   \\\n",
       "0         344.2  4330       9965      1880         2436         1352      2.0   \n",
       "1         412.6  5190       6590      1945         3108         1976      2.0   \n",
       "2         330.1  4152       7500      1890         2294         1371      2.0   \n",
       "3         498.6  6272      13773      1957         5032         2608      1.0   \n",
       "4         331.5  4170       5000      1910         2370         1438      2.0   \n",
       "\n",
       "   ROOMS  BEDROOMS   FULL BATH  HALF BATH  KITCHEN  FIREPLACE REMODEL  \n",
       "0      6          3          1          1        1          0     NaN  \n",
       "1     10          4          2          1        1          0  Recent  \n",
       "2      8          4          1          1        1          0     NaN  \n",
       "3      9          5          1          1        1          1     NaN  \n",
       "4      7          3          2          0        1          0     NaN  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Show the first 5 rows\n",
    "housing_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6ad2b13c-57bd-4a1a-9b7a-8dfd244ad660",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['TOTAL VALUE ', 'TAX', 'LOT SQFT ', 'YR BUILT', 'GROSS AREA ',\n",
       "       'LIVING AREA', 'FLOORS ', 'ROOMS', 'BEDROOMS ', 'FULL BATH',\n",
       "       'HALF BATH', 'KITCHEN', 'FIREPLACE', 'REMODEL'], dtype=object)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Identify the names of the columns\n",
    "housing_df.columns.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "16641259-e3f6-427a-8739-6dddf5aae052",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Rename one column\n",
    "housing_df = housing_df.rename(columns = {'TOTAL VALUE ': 'T_VALUE'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "8b61c60f-1e9a-4bb9-9d72-77f6022d92cc",
   "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>T_VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>LOT SQFT</th>\n",
       "      <th>YR BUILT</th>\n",
       "      <th>GROSS AREA</th>\n",
       "      <th>LIVING AREA</th>\n",
       "      <th>FLOORS</th>\n",
       "      <th>ROOMS</th>\n",
       "      <th>BEDROOMS</th>\n",
       "      <th>FULL BATH</th>\n",
       "      <th>HALF BATH</th>\n",
       "      <th>KITCHEN</th>\n",
       "      <th>FIREPLACE</th>\n",
       "      <th>REMODEL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>344.2</td>\n",
       "      <td>4330</td>\n",
       "      <td>9965</td>\n",
       "      <td>1880</td>\n",
       "      <td>2436</td>\n",
       "      <td>1352</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>412.6</td>\n",
       "      <td>5190</td>\n",
       "      <td>6590</td>\n",
       "      <td>1945</td>\n",
       "      <td>3108</td>\n",
       "      <td>1976</td>\n",
       "      <td>2.0</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Recent</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>330.1</td>\n",
       "      <td>4152</td>\n",
       "      <td>7500</td>\n",
       "      <td>1890</td>\n",
       "      <td>2294</td>\n",
       "      <td>1371</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   T_VALUE   TAX  LOT SQFT   YR BUILT  GROSS AREA   LIVING AREA  FLOORS   \\\n",
       "0    344.2  4330       9965      1880         2436         1352      2.0   \n",
       "1    412.6  5190       6590      1945         3108         1976      2.0   \n",
       "2    330.1  4152       7500      1890         2294         1371      2.0   \n",
       "\n",
       "   ROOMS  BEDROOMS   FULL BATH  HALF BATH  KITCHEN  FIREPLACE REMODEL  \n",
       "0      6          3          1          1        1          0     NaN  \n",
       "1     10          4          2          1        1          0  Recent  \n",
       "2      8          4          1          1        1          0     NaN  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "70296ae9-e643-4875-a459-d7298e82b2c9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Rename several columns: replace 'spaces' with '_' to allow dot notation\n",
    "housing_df.columns = [s.strip().replace(' ','_') for s in housing_df.columns]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "920a75b3-024d-47eb-a66d-0e736026c302",
   "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>T_VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>LOT_SQFT</th>\n",
       "      <th>YR_BUILT</th>\n",
       "      <th>GROSS_AREA</th>\n",
       "      <th>LIVING_AREA</th>\n",
       "      <th>FLOORS</th>\n",
       "      <th>ROOMS</th>\n",
       "      <th>BEDROOMS</th>\n",
       "      <th>FULL_BATH</th>\n",
       "      <th>HALF_BATH</th>\n",
       "      <th>KITCHEN</th>\n",
       "      <th>FIREPLACE</th>\n",
       "      <th>REMODEL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>344.2</td>\n",
       "      <td>4330</td>\n",
       "      <td>9965</td>\n",
       "      <td>1880</td>\n",
       "      <td>2436</td>\n",
       "      <td>1352</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>412.6</td>\n",
       "      <td>5190</td>\n",
       "      <td>6590</td>\n",
       "      <td>1945</td>\n",
       "      <td>3108</td>\n",
       "      <td>1976</td>\n",
       "      <td>2.0</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Recent</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>330.1</td>\n",
       "      <td>4152</td>\n",
       "      <td>7500</td>\n",
       "      <td>1890</td>\n",
       "      <td>2294</td>\n",
       "      <td>1371</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   T_VALUE   TAX  LOT_SQFT  YR_BUILT  GROSS_AREA  LIVING_AREA  FLOORS  ROOMS  \\\n",
       "0    344.2  4330      9965      1880        2436         1352     2.0      6   \n",
       "1    412.6  5190      6590      1945        3108         1976     2.0     10   \n",
       "2    330.1  4152      7500      1890        2294         1371     2.0      8   \n",
       "\n",
       "   BEDROOMS  FULL_BATH  HALF_BATH  KITCHEN  FIREPLACE REMODEL  \n",
       "0         3          1          1        1          0     NaN  \n",
       "1         4          2          1        1          0  Recent  \n",
       "2         4          1          1        1          0     NaN  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "39ffd6e1-c8ab-4e9e-8512-c1cbf346bd34",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    4330\n",
       "1    5190\n",
       "2    4152\n",
       "3    6272\n",
       "Name: TAX, dtype: int64"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Practice showing some part of the data frame:\n",
    "# the first 4 rows of variable 'TAX'\n",
    "housing_df.loc[0:3,'TAX']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "36ed0b5b-bb2d-48b4-bf75-b92a6a4dc85e",
   "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>TAX</th>\n",
       "      <th>LOT_SQFT</th>\n",
       "      <th>YR_BUILT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4330</td>\n",
       "      <td>9965</td>\n",
       "      <td>1880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5190</td>\n",
       "      <td>6590</td>\n",
       "      <td>1945</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4152</td>\n",
       "      <td>7500</td>\n",
       "      <td>1890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6272</td>\n",
       "      <td>13773</td>\n",
       "      <td>1957</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    TAX  LOT_SQFT  YR_BUILT\n",
       "0  4330      9965      1880\n",
       "1  5190      6590      1945\n",
       "2  4152      7500      1890\n",
       "3  6272     13773      1957"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# the first 4 rows of the variables 2, 3 and 4 - iloc does not include the right extreme\n",
    "housing_df.iloc[0:4,1:4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "bd0fc4e5-f5e9-4aeb-83fe-706f98ae94c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use pd.concat to combine non-consecutive columns into a new data frame\n",
    "# The axis argument specifies the dimension along which the concatenation happens: 0 - rows; 1 - columns "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "b485cf6f-707f-404c-b1c8-6c58df18bd8f",
   "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>T_VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>GROSS_AREA</th>\n",
       "      <th>LIVING_AREA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>331.5</td>\n",
       "      <td>4170</td>\n",
       "      <td>2370</td>\n",
       "      <td>1438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>337.4</td>\n",
       "      <td>4244</td>\n",
       "      <td>2124</td>\n",
       "      <td>1060</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   T_VALUE   TAX  GROSS_AREA  LIVING_AREA\n",
       "4    331.5  4170        2370         1438\n",
       "5    337.4  4244        2124         1060"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([housing_df.iloc[4:6,0:2], housing_df.iloc[4:6,4:6]], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "e21fd59a-bed4-40d4-b47c-963714a408d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# To specify a data frame that is a subset of the initial data frame, use:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "9aadeb1a-c7b0-4f86-b43e-7ef4a33aea1a",
   "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>T_VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>GROSS_AREA</th>\n",
       "      <th>LIVING_AREA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>344.2</td>\n",
       "      <td>4330</td>\n",
       "      <td>2436</td>\n",
       "      <td>1352</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>412.6</td>\n",
       "      <td>5190</td>\n",
       "      <td>3108</td>\n",
       "      <td>1976</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>330.1</td>\n",
       "      <td>4152</td>\n",
       "      <td>2294</td>\n",
       "      <td>1371</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>498.6</td>\n",
       "      <td>6272</td>\n",
       "      <td>5032</td>\n",
       "      <td>2608</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>331.5</td>\n",
       "      <td>4170</td>\n",
       "      <td>2370</td>\n",
       "      <td>1438</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   T_VALUE   TAX  GROSS_AREA  LIVING_AREA\n",
       "0    344.2  4330        2436         1352\n",
       "1    412.6  5190        3108         1976\n",
       "2    330.1  4152        2294         1371\n",
       "3    498.6  6272        5032         2608\n",
       "4    331.5  4170        2370         1438"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df = pd.concat([housing_df.iloc[:,0:2],housing_df.iloc[:,4:6]], axis = 1)\n",
    "new_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "26ca6c71-1b2f-462c-bfdd-2545ae5fe8b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Sampling from a data frame\n",
    "# Obtaining a random sample of 5 observations from the data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "c110910f-15b7-48a0-a2db-c0b86735aabf",
   "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>T_VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>LOT_SQFT</th>\n",
       "      <th>YR_BUILT</th>\n",
       "      <th>GROSS_AREA</th>\n",
       "      <th>LIVING_AREA</th>\n",
       "      <th>FLOORS</th>\n",
       "      <th>ROOMS</th>\n",
       "      <th>BEDROOMS</th>\n",
       "      <th>FULL_BATH</th>\n",
       "      <th>HALF_BATH</th>\n",
       "      <th>KITCHEN</th>\n",
       "      <th>FIREPLACE</th>\n",
       "      <th>REMODEL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2940</th>\n",
       "      <td>470.9</td>\n",
       "      <td>5923</td>\n",
       "      <td>12606</td>\n",
       "      <td>1880</td>\n",
       "      <td>4031</td>\n",
       "      <td>2070</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>897</th>\n",
       "      <td>306.3</td>\n",
       "      <td>3853</td>\n",
       "      <td>6710</td>\n",
       "      <td>1960</td>\n",
       "      <td>2232</td>\n",
       "      <td>1044</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5609</th>\n",
       "      <td>418.4</td>\n",
       "      <td>5263</td>\n",
       "      <td>5000</td>\n",
       "      <td>1935</td>\n",
       "      <td>3107</td>\n",
       "      <td>1836</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Recent</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4975</th>\n",
       "      <td>384.0</td>\n",
       "      <td>4830</td>\n",
       "      <td>5777</td>\n",
       "      <td>1958</td>\n",
       "      <td>2610</td>\n",
       "      <td>1284</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3997</th>\n",
       "      <td>295.1</td>\n",
       "      <td>3712</td>\n",
       "      <td>3590</td>\n",
       "      <td>1950</td>\n",
       "      <td>1898</td>\n",
       "      <td>1274</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      T_VALUE   TAX  LOT_SQFT  YR_BUILT  GROSS_AREA  LIVING_AREA  FLOORS  \\\n",
       "2940    470.9  5923     12606      1880        4031         2070     2.0   \n",
       "897     306.3  3853      6710      1960        2232         1044     1.0   \n",
       "5609    418.4  5263      5000      1935        3107         1836     2.0   \n",
       "4975    384.0  4830      5777      1958        2610         1284     1.0   \n",
       "3997    295.1  3712      3590      1950        1898         1274     2.0   \n",
       "\n",
       "      ROOMS  BEDROOMS  FULL_BATH  HALF_BATH  KITCHEN  FIREPLACE REMODEL  \n",
       "2940      9         4          1          1        1          1     NaN  \n",
       "897       6         2          1          0        1          1     NaN  \n",
       "5609      8         3          2          1        1          1  Recent  \n",
       "4975      5         2          1          1        1          2     NaN  \n",
       "3997      7         3          1          0        1          1     NaN  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_1 = housing_df.sample(5)\n",
    "sample_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "008e4294-a992-4f06-b7df-0f08e404c236",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Oversample houses with over 10 rooms "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "c5fcdb08-82c1-4548-9ef5-ee171939f715",
   "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>T_VALUE</th>\n",
       "      <th>TAX</th>\n",
       "      <th>LOT_SQFT</th>\n",
       "      <th>YR_BUILT</th>\n",
       "      <th>GROSS_AREA</th>\n",
       "      <th>LIVING_AREA</th>\n",
       "      <th>FLOORS</th>\n",
       "      <th>ROOMS</th>\n",
       "      <th>BEDROOMS</th>\n",
       "      <th>FULL_BATH</th>\n",
       "      <th>HALF_BATH</th>\n",
       "      <th>KITCHEN</th>\n",
       "      <th>FIREPLACE</th>\n",
       "      <th>REMODEL</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1837</th>\n",
       "      <td>409.5</td>\n",
       "      <td>5151</td>\n",
       "      <td>4864</td>\n",
       "      <td>1950</td>\n",
       "      <td>3998</td>\n",
       "      <td>2176</td>\n",
       "      <td>1.5</td>\n",
       "      <td>11</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4326</th>\n",
       "      <td>358.8</td>\n",
       "      <td>4513</td>\n",
       "      <td>2828</td>\n",
       "      <td>1964</td>\n",
       "      <td>2272</td>\n",
       "      <td>1847</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>500.0</td>\n",
       "      <td>6290</td>\n",
       "      <td>8000</td>\n",
       "      <td>1966</td>\n",
       "      <td>4400</td>\n",
       "      <td>3494</td>\n",
       "      <td>1.0</td>\n",
       "      <td>12</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3854</th>\n",
       "      <td>419.6</td>\n",
       "      <td>5278</td>\n",
       "      <td>5730</td>\n",
       "      <td>1931</td>\n",
       "      <td>2471</td>\n",
       "      <td>1870</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Recent</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5002</th>\n",
       "      <td>414.4</td>\n",
       "      <td>5213</td>\n",
       "      <td>6165</td>\n",
       "      <td>1930</td>\n",
       "      <td>3033</td>\n",
       "      <td>1831</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      T_VALUE   TAX  LOT_SQFT  YR_BUILT  GROSS_AREA  LIVING_AREA  FLOORS  \\\n",
       "1837    409.5  5151      4864      1950        3998         2176     1.5   \n",
       "4326    358.8  4513      2828      1964        2272         1847     2.0   \n",
       "686     500.0  6290      8000      1966        4400         3494     1.0   \n",
       "3854    419.6  5278      5730      1931        2471         1870     1.0   \n",
       "5002    414.4  5213      6165      1930        3033         1831     2.0   \n",
       "\n",
       "      ROOMS  BEDROOMS  FULL_BATH  HALF_BATH  KITCHEN  FIREPLACE REMODEL  \n",
       "1837     11         4          2          1        2          1     NaN  \n",
       "4326      6         3          2          1        1          1     NaN  \n",
       "686      12         6          4          0        2          2     NaN  \n",
       "3854      6         2          2          0        1          1  Recent  \n",
       "5002      7         3          1          1        1          1     NaN  "
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "w = [0.99 if r > 10 else 0.01 for r in housing_df.ROOMS]\n",
    "sample_2 = housing_df.sample(5, weights = w)\n",
    "sample_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "540f4ca7-109a-4693-a2eb-11678842d27b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "T_VALUE        float64\n",
       "TAX              int64\n",
       "LOT_SQFT         int64\n",
       "YR_BUILT         int64\n",
       "GROSS_AREA       int64\n",
       "LIVING_AREA      int64\n",
       "FLOORS         float64\n",
       "ROOMS            int64\n",
       "BEDROOMS         int64\n",
       "FULL_BATH        int64\n",
       "HALF_BATH        int64\n",
       "KITCHEN          int64\n",
       "FIREPLACE        int64\n",
       "REMODEL         object\n",
       "dtype: object"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "f31a8946-8f55-43ce-880e-1ff0f2461d40",
   "metadata": {},
   "outputs": [],
   "source": [
    "# TAX needs to be converted to a numerical continuous variable\n",
    "# LOT_SQFT needs to be converted to a numerical continuous variable\n",
    "# GROSS_AREA needs to be converted to a numerical continuous variable\n",
    "# LIVING_AREA needs to be converted to a numerical continuous variable\n",
    "# FLOORS needs to be converted to a numerical discrete variable\n",
    "# REMODEL needs to be converted to a categorical variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "b3ec834b-ec3b-48a9-9e06-b9047de89942",
   "metadata": {},
   "outputs": [],
   "source": [
    "housing_df.TAX = housing_df.TAX.astype('float64')\n",
    "housing_df.LOT_SQFT = housing_df.LOT_SQFT.astype('float64')\n",
    "housing_df.GROSS_AREA = housing_df.GROSS_AREA.astype('float64')\n",
    "housing_df.LIVING_AREA = housing_df.LIVING_AREA.astype('float64')\n",
    "housing_df.FLOORS = housing_df.FLOORS.astype('int64')\n",
    "housing_df.REMODEL = housing_df.REMODEL.astype('category')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "ffdb0e00-f9df-498b-8307-1ea1024da704",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "T_VALUE         float64\n",
       "TAX             float64\n",
       "LOT_SQFT        float64\n",
       "YR_BUILT          int64\n",
       "GROSS_AREA      float64\n",
       "LIVING_AREA     float64\n",
       "FLOORS            int64\n",
       "ROOMS             int64\n",
       "BEDROOMS          int64\n",
       "FULL_BATH         int64\n",
       "HALF_BATH         int64\n",
       "KITCHEN           int64\n",
       "FIREPLACE         int64\n",
       "REMODEL        category\n",
       "dtype: object"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "b42a5548-70d4-4749-8b4d-5e9722489fab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Old', 'Recent'], dtype='object')"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:base] *",
   "language": "python",
   "name": "conda-base-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}