alexander/ames-housing
1
0
Fork 0
Code Issues Pull requests Releases Activity
ames-housing/1_data_cleaning.ipynb
Alexander Hess 7775a89f7b
Update rendered versions of the notebooks 
- Run notebooks with new Python & dependencies
- Remove manually discovered 'interesting' features
2020-06-29 01:10:19 +02:00

4353 lines
398 KiB
Text
Raw Blame History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Data Cleaning"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## \"Housekeeping\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Import all the third-party (scientific) libraries needed."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import missingno as msno\n",
"import numpy as np\n",
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The *utils.py* module defines helper dictionaries, lists, and functions that help with parsing the data types correctly, look up column descriptions, and refer to groups of data columns.\n",
"\n",
"**Note:** the suffix \\_*COLUMNS* indicates a dictionary with all meta information on the provided data file and \\_*VARIABLES* a list with only the column names (i.e., the keys of the respective \\_*COLUMNS* dictionary)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from utils import (\n",
" ALL_COLUMNS,\n",
" ALL_VARIABLES,\n",
" CONTINUOUS_COLUMNS,\n",
" CONTINUOUS_VARIABLES,\n",
" DISCRETE_COLUMNS,\n",
" DISCRETE_VARIABLES,\n",
" INDEX_COLUMNS,\n",
" LABEL_COLUMNS, # groups nominal and ordinal\n",
" LABEL_TYPES,\n",
" NOMINAL_COLUMNS,\n",
" NOMINAL_VARIABLES,\n",
" NUMERIC_VARIABLES, # groups continuous and discrete\n",
" ORDINAL_COLUMNS,\n",
" ORDINAL_VARIABLES,\n",
" TARGET_VARIABLES, # = Sale Price\n",
" correct_column_names,\n",
" print_column_list,\n",
" update_column_descriptions,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Show all data columns.\n",
"pd.set_option(\"display.max_columns\", 100)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load the Data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The original data are available for [download](https://www.amstat.org/publications/jse/v19n3/decock/AmesHousing.xls) and a detailed description of the data types for each column can be found [here](https://www.amstat.org/publications/jse/v19n3/decock/DataDocumentation.txt). These meta data go into the `dtype` argument of the `read_excel` function below to parse the data correctly. There are four different generic data types defined that are casted as follows:\n",
"\n",
"- continuous -> np.float64\n",
"- discrete -> actually np.int64 but np.float64 because of missing values\n",
"- nominal -> object (str)\n",
"- ordinal -> object (str), the order can be looked up in the above mentioned *ALL_COLUMNS* dictionary\n",
"\n",
"**Note 1:** the data come with a lot of \"NA\" text strings that do **not** indicate missing data but, for example, the absence of a basement or a parking lot (see the linked data description).\n",
"\n",
"**Note 2:** the mappings from column names to data types are encoded in the \"utils.py\" module that defines the aforementioned helper dictionaries / lists.\n",
"\n",
"**Note 3:** the Excel file with all the data is either loaded from the local dictionary (= \"cache\") or obtained fresh from the source."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# To avoid redundancy.\n",
"kwargs = {\n",
" \"dtype\": { # Ensure each column is parsed as the correct data type.\n",
" column: ( # This creates a mapping from column name to data type.\n",
" object if mapping_info[\"type\"] in LABEL_TYPES else np.float64\n",
" )\n",
" for (column, mapping_info) in ALL_COLUMNS.items()\n",
" },\n",
" \"na_values\": \"\", # By default, pandas treats NA strings as missing,\n",
" \"keep_default_na\": False, # which is not the correct meaning here.\n",
"}\n",
"\n",
"try:\n",
" df = pd.read_excel(\"data/data_raw.xls\", **kwargs)\n",
"except FileNotFoundError:\n",
" df = pd.read_excel(\n",
" \"https://www.amstat.org/publications/jse/v19n3/decock/AmesHousing.xls\", **kwargs\n",
" )\n",
" # Cache the obtained file.\n",
" df.to_excel(\"data/data_raw.xls\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# Some columns names differ between the Excel file and\n",
"# the data description file. Correct that with the values\n",
"# in the Excel file.\n",
"correct_column_names(df.columns)\n",
"# Use a compound index and keep both\n",
"# identifying columns in the DataFrame.\n",
"df = df.set_index(INDEX_COLUMNS)\n",
"# Put the provided columns into the same\n",
"# order as in the encoded description file.\n",
"# Note that the target variable \"SalePrice\"\n",
"# is not in the description file.\n",
"df = df[ALL_VARIABLES + TARGET_VARIABLES]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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></th>\n",
" <th>1st Flr SF</th>\n",
" <th>2nd Flr SF</th>\n",
" <th>3Ssn Porch</th>\n",
" <th>Alley</th>\n",
" <th>Bedroom AbvGr</th>\n",
" <th>Bldg Type</th>\n",
" <th>Bsmt Cond</th>\n",
" <th>Bsmt Exposure</th>\n",
" <th>Bsmt Full Bath</th>\n",
" <th>Bsmt Half Bath</th>\n",
" <th>Bsmt Qual</th>\n",
" <th>Bsmt Unf SF</th>\n",
" <th>BsmtFin SF 1</th>\n",
" <th>BsmtFin SF 2</th>\n",
" <th>BsmtFin Type 1</th>\n",
" <th>BsmtFin Type 2</th>\n",
" <th>Central Air</th>\n",
" <th>Condition 1</th>\n",
" <th>Condition 2</th>\n",
" <th>Electrical</th>\n",
" <th>Enclosed Porch</th>\n",
" <th>Exter Cond</th>\n",
" <th>Exter Qual</th>\n",
" <th>Exterior 1st</th>\n",
" <th>Exterior 2nd</th>\n",
" <th>Fence</th>\n",
" <th>Fireplace Qu</th>\n",
" <th>Fireplaces</th>\n",
" <th>Foundation</th>\n",
" <th>Full Bath</th>\n",
" <th>Functional</th>\n",
" <th>Garage Area</th>\n",
" <th>Garage Cars</th>\n",
" <th>Garage Cond</th>\n",
" <th>Garage Finish</th>\n",
" <th>Garage Qual</th>\n",
" <th>Garage Type</th>\n",
" <th>Garage Yr Blt</th>\n",
" <th>Gr Liv Area</th>\n",
" <th>Half Bath</th>\n",
" <th>Heating</th>\n",
" <th>Heating QC</th>\n",
" <th>House Style</th>\n",
" <th>Kitchen AbvGr</th>\n",
" <th>Kitchen Qual</th>\n",
" <th>Land Contour</th>\n",
" <th>Land Slope</th>\n",
" <th>Lot Area</th>\n",
" <th>Lot Config</th>\n",
" <th>Lot Frontage</th>\n",
" <th>Lot Shape</th>\n",
" <th>Low Qual Fin SF</th>\n",
" <th>MS SubClass</th>\n",
" <th>MS Zoning</th>\n",
" <th>Mas Vnr Area</th>\n",
" <th>Mas Vnr Type</th>\n",
" <th>Misc Feature</th>\n",
" <th>Misc Val</th>\n",
" <th>Mo Sold</th>\n",
" <th>Neighborhood</th>\n",
" <th>Open Porch SF</th>\n",
" <th>Overall Cond</th>\n",
" <th>Overall Qual</th>\n",
" <th>Paved Drive</th>\n",
" <th>Pool Area</th>\n",
" <th>Pool QC</th>\n",
" <th>Roof Matl</th>\n",
" <th>Roof Style</th>\n",
" <th>Sale Condition</th>\n",
" <th>Sale Type</th>\n",
" <th>Screen Porch</th>\n",
" <th>Street</th>\n",
" <th>TotRms AbvGrd</th>\n",
" <th>Total Bsmt SF</th>\n",
" <th>Utilities</th>\n",
" <th>Wood Deck SF</th>\n",
" <th>Year Built</th>\n",
" <th>Year Remod/Add</th>\n",
" <th>Yr Sold</th>\n",
" <th>SalePrice</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Order</th>\n",
" <th>PID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <th>526301100</th>\n",
" <td>1656.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>Gd</td>\n",
" <td>Gd</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>441.0</td>\n",
" <td>639.0</td>\n",
" <td>0.0</td>\n",
" <td>BLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>BrkFace</td>\n",
" <td>Plywood</td>\n",
" <td>NA</td>\n",
" <td>Gd</td>\n",
" <td>2.0</td>\n",
" <td>CBlock</td>\n",
" <td>1.0</td>\n",
" <td>Typ</td>\n",
" <td>528.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1960.0</td>\n",
" <td>1656.0</td>\n",
" <td>0.0</td>\n",
" <td>GasA</td>\n",
" <td>Fa</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>31770.0</td>\n",
" <td>Corner</td>\n",
" <td>141.0</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>112.0</td>\n",
" <td>Stone</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>NAmes</td>\n",
" <td>62.0</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>P</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>7</td>\n",
" <td>1080.0</td>\n",
" <td>AllPub</td>\n",
" <td>210.0</td>\n",
" <td>1960.0</td>\n",
" <td>1960.0</td>\n",
" <td>2010.0</td>\n",
" <td>215000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <th>526350040</th>\n",
" <td>896.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>2</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>270.0</td>\n",
" <td>468.0</td>\n",
" <td>144.0</td>\n",
" <td>Rec</td>\n",
" <td>LwQ</td>\n",
" <td>Y</td>\n",
" <td>Feedr</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>MnPrv</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>CBlock</td>\n",
" <td>1.0</td>\n",
" <td>Typ</td>\n",
" <td>730.0</td>\n",
" <td>1.0</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1961.0</td>\n",
" <td>896.0</td>\n",
" <td>0.0</td>\n",
" <td>GasA</td>\n",
" <td>TA</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>11622.0</td>\n",
" <td>Inside</td>\n",
" <td>80.0</td>\n",
" <td>Reg</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RH</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>NAmes</td>\n",
" <td>0.0</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>120.0</td>\n",
" <td>Pave</td>\n",
" <td>5</td>\n",
" <td>882.0</td>\n",
" <td>AllPub</td>\n",
" <td>140.0</td>\n",
" <td>1961.0</td>\n",
" <td>1961.0</td>\n",
" <td>2010.0</td>\n",
" <td>105000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <th>526351010</th>\n",
" <td>1329.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>406.0</td>\n",
" <td>923.0</td>\n",
" <td>0.0</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>Wd Sdng</td>\n",
" <td>Wd Sdng</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>CBlock</td>\n",
" <td>1.0</td>\n",
" <td>Typ</td>\n",
" <td>312.0</td>\n",
" <td>1.0</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1958.0</td>\n",
" <td>1329.0</td>\n",
" <td>1.0</td>\n",
" <td>GasA</td>\n",
" <td>TA</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>14267.0</td>\n",
" <td>Corner</td>\n",
" <td>81.0</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>108.0</td>\n",
" <td>BrkFace</td>\n",
" <td>Gar2</td>\n",
" <td>12500.0</td>\n",
" <td>6.0</td>\n",
" <td>NAmes</td>\n",
" <td>36.0</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>6</td>\n",
" <td>1329.0</td>\n",
" <td>AllPub</td>\n",
" <td>393.0</td>\n",
" <td>1958.0</td>\n",
" <td>1958.0</td>\n",
" <td>2010.0</td>\n",
" <td>172000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>526353030</th>\n",
" <td>2110.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>1045.0</td>\n",
" <td>1065.0</td>\n",
" <td>0.0</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>BrkFace</td>\n",
" <td>BrkFace</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>2.0</td>\n",
" <td>CBlock</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>522.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1968.0</td>\n",
" <td>2110.0</td>\n",
" <td>1.0</td>\n",
" <td>GasA</td>\n",
" <td>Ex</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Ex</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>11160.0</td>\n",
" <td>Corner</td>\n",
" <td>93.0</td>\n",
" <td>Reg</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>4.0</td>\n",
" <td>NAmes</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>8</td>\n",
" <td>2110.0</td>\n",
" <td>AllPub</td>\n",
" <td>0.0</td>\n",
" <td>1968.0</td>\n",
" <td>1968.0</td>\n",
" <td>2010.0</td>\n",
" <td>244000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>527105010</th>\n",
" <td>928.0</td>\n",
" <td>701.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>Gd</td>\n",
" <td>137.0</td>\n",
" <td>791.0</td>\n",
" <td>0.0</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>MnPrv</td>\n",
" <td>TA</td>\n",
" <td>1.0</td>\n",
" <td>PConc</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>482.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1997.0</td>\n",
" <td>1629.0</td>\n",
" <td>1.0</td>\n",
" <td>GasA</td>\n",
" <td>Gd</td>\n",
" <td>2Story</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>13830.0</td>\n",
" <td>Inside</td>\n",
" <td>74.0</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>Gilbert</td>\n",
" <td>34.0</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>6</td>\n",
" <td>928.0</td>\n",
" <td>AllPub</td>\n",
" <td>212.0</td>\n",
" <td>1997.0</td>\n",
" <td>1998.0</td>\n",
" <td>2010.0</td>\n",
" <td>189900</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <th>527105030</th>\n",
" <td>926.0</td>\n",
" <td>678.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>324.0</td>\n",
" <td>602.0</td>\n",
" <td>0.0</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>NA</td>\n",
" <td>Gd</td>\n",
" <td>1.0</td>\n",
" <td>PConc</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>470.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1998.0</td>\n",
" <td>1604.0</td>\n",
" <td>1.0</td>\n",
" <td>GasA</td>\n",
" <td>Ex</td>\n",
" <td>2Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>9978.0</td>\n",
" <td>Inside</td>\n",
" <td>78.0</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>20.0</td>\n",
" <td>BrkFace</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>Gilbert</td>\n",
" <td>36.0</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>7</td>\n",
" <td>926.0</td>\n",
" <td>AllPub</td>\n",
" <td>360.0</td>\n",
" <td>1998.0</td>\n",
" <td>1998.0</td>\n",
" <td>2010.0</td>\n",
" <td>195500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <th>527127150</th>\n",
" <td>1338.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>2</td>\n",
" <td>TwnhsE</td>\n",
" <td>TA</td>\n",
" <td>Mn</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>Gd</td>\n",
" <td>722.0</td>\n",
" <td>616.0</td>\n",
" <td>0.0</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>170.0</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>CemntBd</td>\n",
" <td>CmentBd</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>PConc</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>582.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>2001.0</td>\n",
" <td>1338.0</td>\n",
" <td>0.0</td>\n",
" <td>GasA</td>\n",
" <td>Ex</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>4920.0</td>\n",
" <td>Inside</td>\n",
" <td>41.0</td>\n",
" <td>Reg</td>\n",
" <td>0.0</td>\n",
" <td>120</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>4.0</td>\n",
" <td>StoneBr</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>6</td>\n",
" <td>1338.0</td>\n",
" <td>AllPub</td>\n",
" <td>0.0</td>\n",
" <td>2001.0</td>\n",
" <td>2001.0</td>\n",
" <td>2010.0</td>\n",
" <td>213500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <th>527145080</th>\n",
" <td>1280.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>2</td>\n",
" <td>TwnhsE</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>Gd</td>\n",
" <td>1017.0</td>\n",
" <td>263.0</td>\n",
" <td>0.0</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>HdBoard</td>\n",
" <td>HdBoard</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>PConc</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>506.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>RFn</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1992.0</td>\n",
" <td>1280.0</td>\n",
" <td>0.0</td>\n",
" <td>GasA</td>\n",
" <td>Ex</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>HLS</td>\n",
" <td>Gtl</td>\n",
" <td>5005.0</td>\n",
" <td>Inside</td>\n",
" <td>43.0</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>120</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>StoneBr</td>\n",
" <td>82.0</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>144.0</td>\n",
" <td>Pave</td>\n",
" <td>5</td>\n",
" <td>1280.0</td>\n",
" <td>AllPub</td>\n",
" <td>0.0</td>\n",
" <td>1992.0</td>\n",
" <td>1992.0</td>\n",
" <td>2010.0</td>\n",
" <td>191500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <th>527146030</th>\n",
" <td>1616.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>2</td>\n",
" <td>TwnhsE</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>Gd</td>\n",
" <td>415.0</td>\n",
" <td>1180.0</td>\n",
" <td>0.0</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>CemntBd</td>\n",
" <td>CmentBd</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>1.0</td>\n",
" <td>PConc</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>608.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>RFn</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1995.0</td>\n",
" <td>1616.0</td>\n",
" <td>0.0</td>\n",
" <td>GasA</td>\n",
" <td>Ex</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>5389.0</td>\n",
" <td>Inside</td>\n",
" <td>39.0</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>120</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>StoneBr</td>\n",
" <td>152.0</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>5</td>\n",
" <td>1595.0</td>\n",
" <td>AllPub</td>\n",
" <td>237.0</td>\n",
" <td>1995.0</td>\n",
" <td>1996.0</td>\n",
" <td>2010.0</td>\n",
" <td>236500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <th>527162130</th>\n",
" <td>1028.0</td>\n",
" <td>776.0</td>\n",
" <td>0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>994.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>Unf</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>1.0</td>\n",
" <td>PConc</td>\n",
" <td>2.0</td>\n",
" <td>Typ</td>\n",
" <td>442.0</td>\n",
" <td>2.0</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1999.0</td>\n",
" <td>1804.0</td>\n",
" <td>1.0</td>\n",
" <td>GasA</td>\n",
" <td>Gd</td>\n",
" <td>2Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>7500.0</td>\n",
" <td>Inside</td>\n",
" <td>60.0</td>\n",
" <td>Reg</td>\n",
" <td>0.0</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>Gilbert</td>\n",
" <td>60.0</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>7</td>\n",
" <td>994.0</td>\n",
" <td>AllPub</td>\n",
" <td>140.0</td>\n",
" <td>1999.0</td>\n",
" <td>1999.0</td>\n",
" <td>2010.0</td>\n",
" <td>189000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 1st Flr SF 2nd Flr SF 3Ssn Porch Alley Bedroom AbvGr \\\n",
"Order PID \n",
"1 526301100 1656.0 0.0 0 NA 3 \n",
"2 526350040 896.0 0.0 0 NA 2 \n",
"3 526351010 1329.0 0.0 0 NA 3 \n",
"4 526353030 2110.0 0.0 0 NA 3 \n",
"5 527105010 928.0 701.0 0 NA 3 \n",
"6 527105030 926.0 678.0 0 NA 3 \n",
"7 527127150 1338.0 0.0 0 NA 2 \n",
"8 527145080 1280.0 0.0 0 NA 2 \n",
"9 527146030 1616.0 0.0 0 NA 2 \n",
"10 527162130 1028.0 776.0 0 NA 3 \n",
"\n",
" Bldg Type Bsmt Cond Bsmt Exposure Bsmt Full Bath \\\n",
"Order PID \n",
"1 526301100 1Fam Gd Gd 1.0 \n",
"2 526350040 1Fam TA No 0.0 \n",
"3 526351010 1Fam TA No 0.0 \n",
"4 526353030 1Fam TA No 1.0 \n",
"5 527105010 1Fam TA No 0.0 \n",
"6 527105030 1Fam TA No 0.0 \n",
"7 527127150 TwnhsE TA Mn 1.0 \n",
"8 527145080 TwnhsE TA No 0.0 \n",
"9 527146030 TwnhsE TA No 1.0 \n",
"10 527162130 1Fam TA No 0.0 \n",
"\n",
" Bsmt Half Bath Bsmt Qual Bsmt Unf SF BsmtFin SF 1 \\\n",
"Order PID \n",
"1 526301100 0.0 TA 441.0 639.0 \n",
"2 526350040 0.0 TA 270.0 468.0 \n",
"3 526351010 0.0 TA 406.0 923.0 \n",
"4 526353030 0.0 TA 1045.0 1065.0 \n",
"5 527105010 0.0 Gd 137.0 791.0 \n",
"6 527105030 0.0 TA 324.0 602.0 \n",
"7 527127150 0.0 Gd 722.0 616.0 \n",
"8 527145080 0.0 Gd 1017.0 263.0 \n",
"9 527146030 0.0 Gd 415.0 1180.0 \n",
"10 527162130 0.0 TA 994.0 0.0 \n",
"\n",
" BsmtFin SF 2 BsmtFin Type 1 BsmtFin Type 2 Central Air \\\n",
"Order PID \n",
"1 526301100 0.0 BLQ Unf Y \n",
"2 526350040 144.0 Rec LwQ Y \n",
"3 526351010 0.0 ALQ Unf Y \n",
"4 526353030 0.0 ALQ Unf Y \n",
"5 527105010 0.0 GLQ Unf Y \n",
"6 527105030 0.0 GLQ Unf Y \n",
"7 527127150 0.0 GLQ Unf Y \n",
"8 527145080 0.0 ALQ Unf Y \n",
"9 527146030 0.0 GLQ Unf Y \n",
"10 527162130 0.0 Unf Unf Y \n",
"\n",
" Condition 1 Condition 2 Electrical Enclosed Porch Exter Cond \\\n",
"Order PID \n",
"1 526301100 Norm Norm SBrkr 0.0 TA \n",
"2 526350040 Feedr Norm SBrkr 0.0 TA \n",
"3 526351010 Norm Norm SBrkr 0.0 TA \n",
"4 526353030 Norm Norm SBrkr 0.0 TA \n",
"5 527105010 Norm Norm SBrkr 0.0 TA \n",
"6 527105030 Norm Norm SBrkr 0.0 TA \n",
"7 527127150 Norm Norm SBrkr 170.0 TA \n",
"8 527145080 Norm Norm SBrkr 0.0 TA \n",
"9 527146030 Norm Norm SBrkr 0.0 TA \n",
"10 527162130 Norm Norm SBrkr 0.0 TA \n",
"\n",
" Exter Qual Exterior 1st Exterior 2nd Fence Fireplace Qu \\\n",
"Order PID \n",
"1 526301100 TA BrkFace Plywood NA Gd \n",
"2 526350040 TA VinylSd VinylSd MnPrv NA \n",
"3 526351010 TA Wd Sdng Wd Sdng NA NA \n",
"4 526353030 Gd BrkFace BrkFace NA TA \n",
"5 527105010 TA VinylSd VinylSd MnPrv TA \n",
"6 527105030 TA VinylSd VinylSd NA Gd \n",
"7 527127150 Gd CemntBd CmentBd NA NA \n",
"8 527145080 Gd HdBoard HdBoard NA NA \n",
"9 527146030 Gd CemntBd CmentBd NA TA \n",
"10 527162130 TA VinylSd VinylSd NA TA \n",
"\n",
" Fireplaces Foundation Full Bath Functional Garage Area \\\n",
"Order PID \n",
"1 526301100 2.0 CBlock 1.0 Typ 528.0 \n",
"2 526350040 0.0 CBlock 1.0 Typ 730.0 \n",
"3 526351010 0.0 CBlock 1.0 Typ 312.0 \n",
"4 526353030 2.0 CBlock 2.0 Typ 522.0 \n",
"5 527105010 1.0 PConc 2.0 Typ 482.0 \n",
"6 527105030 1.0 PConc 2.0 Typ 470.0 \n",
"7 527127150 0.0 PConc 2.0 Typ 582.0 \n",
"8 527145080 0.0 PConc 2.0 Typ 506.0 \n",
"9 527146030 1.0 PConc 2.0 Typ 608.0 \n",
"10 527162130 1.0 PConc 2.0 Typ 442.0 \n",
"\n",
" Garage Cars Garage Cond Garage Finish Garage Qual \\\n",
"Order PID \n",
"1 526301100 2.0 TA Fin TA \n",
"2 526350040 1.0 TA Unf TA \n",
"3 526351010 1.0 TA Unf TA \n",
"4 526353030 2.0 TA Fin TA \n",
"5 527105010 2.0 TA Fin TA \n",
"6 527105030 2.0 TA Fin TA \n",
"7 527127150 2.0 TA Fin TA \n",
"8 527145080 2.0 TA RFn TA \n",
"9 527146030 2.0 TA RFn TA \n",
"10 527162130 2.0 TA Fin TA \n",
"\n",
" Garage Type Garage Yr Blt Gr Liv Area Half Bath Heating \\\n",
"Order PID \n",
"1 526301100 Attchd 1960.0 1656.0 0.0 GasA \n",
"2 526350040 Attchd 1961.0 896.0 0.0 GasA \n",
"3 526351010 Attchd 1958.0 1329.0 1.0 GasA \n",
"4 526353030 Attchd 1968.0 2110.0 1.0 GasA \n",
"5 527105010 Attchd 1997.0 1629.0 1.0 GasA \n",
"6 527105030 Attchd 1998.0 1604.0 1.0 GasA \n",
"7 527127150 Attchd 2001.0 1338.0 0.0 GasA \n",
"8 527145080 Attchd 1992.0 1280.0 0.0 GasA \n",
"9 527146030 Attchd 1995.0 1616.0 0.0 GasA \n",
"10 527162130 Attchd 1999.0 1804.0 1.0 GasA \n",
"\n",
" Heating QC House Style Kitchen AbvGr Kitchen Qual \\\n",
"Order PID \n",
"1 526301100 Fa 1Story 1 TA \n",
"2 526350040 TA 1Story 1 TA \n",
"3 526351010 TA 1Story 1 Gd \n",
"4 526353030 Ex 1Story 1 Ex \n",
"5 527105010 Gd 2Story 1 TA \n",
"6 527105030 Ex 2Story 1 Gd \n",
"7 527127150 Ex 1Story 1 Gd \n",
"8 527145080 Ex 1Story 1 Gd \n",
"9 527146030 Ex 1Story 1 Gd \n",
"10 527162130 Gd 2Story 1 Gd \n",
"\n",
" Land Contour Land Slope Lot Area Lot Config Lot Frontage \\\n",
"Order PID \n",
"1 526301100 Lvl Gtl 31770.0 Corner 141.0 \n",
"2 526350040 Lvl Gtl 11622.0 Inside 80.0 \n",
"3 526351010 Lvl Gtl 14267.0 Corner 81.0 \n",
"4 526353030 Lvl Gtl 11160.0 Corner 93.0 \n",
"5 527105010 Lvl Gtl 13830.0 Inside 74.0 \n",
"6 527105030 Lvl Gtl 9978.0 Inside 78.0 \n",
"7 527127150 Lvl Gtl 4920.0 Inside 41.0 \n",
"8 527145080 HLS Gtl 5005.0 Inside 43.0 \n",
"9 527146030 Lvl Gtl 5389.0 Inside 39.0 \n",
"10 527162130 Lvl Gtl 7500.0 Inside 60.0 \n",
"\n",
" Lot Shape Low Qual Fin SF MS SubClass MS Zoning \\\n",
"Order PID \n",
"1 526301100 IR1 0.0 020 RL \n",
"2 526350040 Reg 0.0 020 RH \n",
"3 526351010 IR1 0.0 020 RL \n",
"4 526353030 Reg 0.0 020 RL \n",
"5 527105010 IR1 0.0 060 RL \n",
"6 527105030 IR1 0.0 060 RL \n",
"7 527127150 Reg 0.0 120 RL \n",
"8 527145080 IR1 0.0 120 RL \n",
"9 527146030 IR1 0.0 120 RL \n",
"10 527162130 Reg 0.0 060 RL \n",
"\n",
" Mas Vnr Area Mas Vnr Type Misc Feature Misc Val Mo Sold \\\n",
"Order PID \n",
"1 526301100 112.0 Stone NA 0.0 5.0 \n",
"2 526350040 0.0 None NA 0.0 6.0 \n",
"3 526351010 108.0 BrkFace Gar2 12500.0 6.0 \n",
"4 526353030 0.0 None NA 0.0 4.0 \n",
"5 527105010 0.0 None NA 0.0 3.0 \n",
"6 527105030 20.0 BrkFace NA 0.0 6.0 \n",
"7 527127150 0.0 None NA 0.0 4.0 \n",
"8 527145080 0.0 None NA 0.0 1.0 \n",
"9 527146030 0.0 None NA 0.0 3.0 \n",
"10 527162130 0.0 None NA 0.0 6.0 \n",
"\n",
" Neighborhood Open Porch SF Overall Cond Overall Qual \\\n",
"Order PID \n",
"1 526301100 NAmes 62.0 5 6 \n",
"2 526350040 NAmes 0.0 6 5 \n",
"3 526351010 NAmes 36.0 6 6 \n",
"4 526353030 NAmes 0.0 5 7 \n",
"5 527105010 Gilbert 34.0 5 5 \n",
"6 527105030 Gilbert 36.0 6 6 \n",
"7 527127150 StoneBr 0.0 5 8 \n",
"8 527145080 StoneBr 82.0 5 8 \n",
"9 527146030 StoneBr 152.0 5 8 \n",
"10 527162130 Gilbert 60.0 5 7 \n",
"\n",
" Paved Drive Pool Area Pool QC Roof Matl Roof Style \\\n",
"Order PID \n",
"1 526301100 P 0.0 NA CompShg Hip \n",
"2 526350040 Y 0.0 NA CompShg Gable \n",
"3 526351010 Y 0.0 NA CompShg Hip \n",
"4 526353030 Y 0.0 NA CompShg Hip \n",
"5 527105010 Y 0.0 NA CompShg Gable \n",
"6 527105030 Y 0.0 NA CompShg Gable \n",
"7 527127150 Y 0.0 NA CompShg Gable \n",
"8 527145080 Y 0.0 NA CompShg Gable \n",
"9 527146030 Y 0.0 NA CompShg Gable \n",
"10 527162130 Y 0.0 NA CompShg Gable \n",
"\n",
" Sale Condition Sale Type Screen Porch Street TotRms AbvGrd \\\n",
"Order PID \n",
"1 526301100 Normal WD 0.0 Pave 7 \n",
"2 526350040 Normal WD 120.0 Pave 5 \n",
"3 526351010 Normal WD 0.0 Pave 6 \n",
"4 526353030 Normal WD 0.0 Pave 8 \n",
"5 527105010 Normal WD 0.0 Pave 6 \n",
"6 527105030 Normal WD 0.0 Pave 7 \n",
"7 527127150 Normal WD 0.0 Pave 6 \n",
"8 527145080 Normal WD 144.0 Pave 5 \n",
"9 527146030 Normal WD 0.0 Pave 5 \n",
"10 527162130 Normal WD 0.0 Pave 7 \n",
"\n",
" Total Bsmt SF Utilities Wood Deck SF Year Built \\\n",
"Order PID \n",
"1 526301100 1080.0 AllPub 210.0 1960.0 \n",
"2 526350040 882.0 AllPub 140.0 1961.0 \n",
"3 526351010 1329.0 AllPub 393.0 1958.0 \n",
"4 526353030 2110.0 AllPub 0.0 1968.0 \n",
"5 527105010 928.0 AllPub 212.0 1997.0 \n",
"6 527105030 926.0 AllPub 360.0 1998.0 \n",
"7 527127150 1338.0 AllPub 0.0 2001.0 \n",
"8 527145080 1280.0 AllPub 0.0 1992.0 \n",
"9 527146030 1595.0 AllPub 237.0 1995.0 \n",
"10 527162130 994.0 AllPub 140.0 1999.0 \n",
"\n",
" Year Remod/Add Yr Sold SalePrice \n",
"Order PID \n",
"1 526301100 1960.0 2010.0 215000 \n",
"2 526350040 1961.0 2010.0 105000 \n",
"3 526351010 1958.0 2010.0 172000 \n",
"4 526353030 1968.0 2010.0 244000 \n",
"5 527105010 1998.0 2010.0 189900 \n",
"6 527105030 1998.0 2010.0 195500 \n",
"7 527127150 2001.0 2010.0 213500 \n",
"8 527145080 1992.0 2010.0 191500 \n",
"9 527146030 1996.0 2010.0 236500 \n",
"10 527162130 1999.0 2010.0 189000 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Spelling Mistakes & Data Types"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Some textual values appear differently in the provided data file as compared to the specification. These inconsistencies are manually repaired."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# Repair spelling and whitespace mistakes.\n",
"df[\"Bldg Type\"] = df[\"Bldg Type\"].replace(to_replace=\"2fmCon\", value=\"2FmCon\")\n",
"df[\"Bldg Type\"] = df[\"Bldg Type\"].replace(to_replace=\"Duplex\", value=\"Duplx\")\n",
"df[\"Bldg Type\"] = df[\"Bldg Type\"].replace(to_replace=\"Twnhs\", value=\"TwnhsI\")\n",
"df[\"Exterior 2nd\"] = df[\"Exterior 2nd\"].replace(to_replace=\"Brk Cmn\", value=\"BrkComm\")\n",
"df[\"Exterior 2nd\"] = df[\"Exterior 2nd\"].replace(to_replace=\"CmentBd\", value=\"CemntBd\")\n",
"df[\"Exterior 2nd\"] = df[\"Exterior 2nd\"].replace(to_replace=\"Wd Shng\", value=\"WdShing\")\n",
"df[\"MS Zoning\"] = df[\"MS Zoning\"].replace(to_replace=\"A (agr)\", value=\"A\")\n",
"df[\"MS Zoning\"] = df[\"MS Zoning\"].replace(to_replace=\"C (all)\", value=\"C\")\n",
"df[\"MS Zoning\"] = df[\"MS Zoning\"].replace(to_replace=\"I (all)\", value=\"I\")\n",
"df[\"Neighborhood\"] = df[\"Neighborhood\"].replace(to_replace=\"NAmes\", value=\"Names\")\n",
"df[\"Sale Type\"] = df[\"Sale Type\"].replace(to_replace=\"WD \", value=\"WD\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"# Ensure that the remaining textual values in the data file are a subset\n",
"# of the values allowed in the specification.\n",
"for column, mapping_info in LABEL_COLUMNS.items():\n",
" # Note that .unique() returns a numpy array with integer dtype in cases\n",
" # where the provided data can be casted as such (e.g., \"Overall Qual\" column).\n",
" values_in_data = set(str(x) for x in df[column].unique() if x is not np.NaN)\n",
" values_in_description = set(mapping_info[\"lookups\"].keys())\n",
" assert values_in_data <= values_in_description"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Interestingly, all numeric columns (i.e. also \"continuous\" variables) come with only integer values."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"# Show that all \"continuous\" variables come as integers.\n",
"for column in NUMERIC_VARIABLES + TARGET_VARIABLES:\n",
" not_null = df[column].notnull()\n",
" mask = (\n",
" df.loc[not_null, column].astype(np.int64)\n",
" != df.loc[not_null, column].astype(np.float64)\n",
" )\n",
" assert not mask.any()\n",
"# Cast discrete fields as integers where possible,\n",
"# i.e., all columns without missing values.\n",
"for column in DISCRETE_VARIABLES:\n",
" try:\n",
" df[column] = df[column].astype(np.int64)\n",
" except ValueError:\n",
" mask = df[column].notnull()\n",
" df.loc[mask, column].astype(np.int64)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Raw Data Overview"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The overall shape of the data is a 2930 rows x 80 columns matrix."
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(2930, 80)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Continuous Variables"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The continuous columns are truly continuous in the sense that each column has at least 14 unique value realizations."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"for column in CONTINUOUS_VARIABLES:\n",
" mask = df[column].notnull()\n",
" num_realizations = len(list(x for x in df.loc[mask, column].unique()))\n",
" assert num_realizations > 13"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"A brief description of the variables:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1st Flr SF First Floor square feet\n",
"2nd Flr SF Second floor square feet\n",
"3Ssn Porch Three season porch area in square feet\n",
"Bsmt Unf SF Unfinished square feet of basement area\n",
"BsmtFin SF 1 Type 1 finished square feet\n",
"BsmtFin SF 2 Type 2 finished square feet\n",
"Enclosed Porch Enclosed porch area in square feet\n",
"Garage Area Size of garage in square feet\n",
"Gr Liv Area Above grade (ground) living area square feet\n",
"Lot Area Lot size in square feet\n",
"Lot Frontage Linear feet of street connected to property\n",
"Low Qual Fin SF Low quality finished square feet (all floors)\n",
"Mas Vnr Area Masonry veneer area in square feet\n",
"Misc Val $Value of miscellaneous feature\n",
"Open Porch SF Open porch area in square feet\n",
"Pool Area Pool area in square feet\n",
"Screen Porch Screen porch area in square feet\n",
"Total Bsmt SF Total square feet of basement area\n",
"Wood Deck SF Wood deck area in square feet\n"
]
}
],
"source": [
"print_column_list(CONTINUOUS_COLUMNS)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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></th>\n",
" <th>1st Flr SF</th>\n",
" <th>2nd Flr SF</th>\n",
" <th>3Ssn Porch</th>\n",
" <th>Bsmt Unf SF</th>\n",
" <th>BsmtFin SF 1</th>\n",
" <th>BsmtFin SF 2</th>\n",
" <th>Enclosed Porch</th>\n",
" <th>Garage Area</th>\n",
" <th>Gr Liv Area</th>\n",
" <th>Lot Area</th>\n",
" <th>Lot Frontage</th>\n",
" <th>Low Qual Fin SF</th>\n",
" <th>Mas Vnr Area</th>\n",
" <th>Misc Val</th>\n",
" <th>Open Porch SF</th>\n",
" <th>Pool Area</th>\n",
" <th>Screen Porch</th>\n",
" <th>Total Bsmt SF</th>\n",
" <th>Wood Deck SF</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Order</th>\n",
" <th>PID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <th>526301100</th>\n",
" <td>1656.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>441.0</td>\n",
" <td>639.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>528.0</td>\n",
" <td>1656.0</td>\n",
" <td>31770.0</td>\n",
" <td>141.0</td>\n",
" <td>0.0</td>\n",
" <td>112.0</td>\n",
" <td>0.0</td>\n",
" <td>62.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1080.0</td>\n",
" <td>210.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <th>526350040</th>\n",
" <td>896.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>270.0</td>\n",
" <td>468.0</td>\n",
" <td>144.0</td>\n",
" <td>0.0</td>\n",
" <td>730.0</td>\n",
" <td>896.0</td>\n",
" <td>11622.0</td>\n",
" <td>80.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>120.0</td>\n",
" <td>882.0</td>\n",
" <td>140.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <th>526351010</th>\n",
" <td>1329.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>406.0</td>\n",
" <td>923.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>312.0</td>\n",
" <td>1329.0</td>\n",
" <td>14267.0</td>\n",
" <td>81.0</td>\n",
" <td>0.0</td>\n",
" <td>108.0</td>\n",
" <td>12500.0</td>\n",
" <td>36.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1329.0</td>\n",
" <td>393.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>526353030</th>\n",
" <td>2110.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>1045.0</td>\n",
" <td>1065.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>522.0</td>\n",
" <td>2110.0</td>\n",
" <td>11160.0</td>\n",
" <td>93.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>2110.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>527105010</th>\n",
" <td>928.0</td>\n",
" <td>701.0</td>\n",
" <td>0</td>\n",
" <td>137.0</td>\n",
" <td>791.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>482.0</td>\n",
" <td>1629.0</td>\n",
" <td>13830.0</td>\n",
" <td>74.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>34.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>928.0</td>\n",
" <td>212.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 1st Flr SF 2nd Flr SF 3Ssn Porch Bsmt Unf SF \\\n",
"Order PID \n",
"1 526301100 1656.0 0.0 0 441.0 \n",
"2 526350040 896.0 0.0 0 270.0 \n",
"3 526351010 1329.0 0.0 0 406.0 \n",
"4 526353030 2110.0 0.0 0 1045.0 \n",
"5 527105010 928.0 701.0 0 137.0 \n",
"\n",
" BsmtFin SF 1 BsmtFin SF 2 Enclosed Porch Garage Area \\\n",
"Order PID \n",
"1 526301100 639.0 0.0 0.0 528.0 \n",
"2 526350040 468.0 144.0 0.0 730.0 \n",
"3 526351010 923.0 0.0 0.0 312.0 \n",
"4 526353030 1065.0 0.0 0.0 522.0 \n",
"5 527105010 791.0 0.0 0.0 482.0 \n",
"\n",
" Gr Liv Area Lot Area Lot Frontage Low Qual Fin SF \\\n",
"Order PID \n",
"1 526301100 1656.0 31770.0 141.0 0.0 \n",
"2 526350040 896.0 11622.0 80.0 0.0 \n",
"3 526351010 1329.0 14267.0 81.0 0.0 \n",
"4 526353030 2110.0 11160.0 93.0 0.0 \n",
"5 527105010 1629.0 13830.0 74.0 0.0 \n",
"\n",
" Mas Vnr Area Misc Val Open Porch SF Pool Area \\\n",
"Order PID \n",
"1 526301100 112.0 0.0 62.0 0.0 \n",
"2 526350040 0.0 0.0 0.0 0.0 \n",
"3 526351010 108.0 12500.0 36.0 0.0 \n",
"4 526353030 0.0 0.0 0.0 0.0 \n",
"5 527105010 0.0 0.0 34.0 0.0 \n",
"\n",
" Screen Porch Total Bsmt SF Wood Deck SF \n",
"Order PID \n",
"1 526301100 0.0 1080.0 210.0 \n",
"2 526350040 120.0 882.0 140.0 \n",
"3 526351010 0.0 1329.0 393.0 \n",
"4 526353030 0.0 2110.0 0.0 \n",
"5 527105010 0.0 928.0 212.0 "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[CONTINUOUS_VARIABLES].head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Except for the column *Lot Frontage* the columns with missing data only have a couple of missing values (i.e., < 1% of all the rows)."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"MultiIndex: 2930 entries, (1, 526301100) to (2930, 924151050)\n",
"Data columns (total 19 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 1st Flr SF 2930 non-null float64\n",
" 1 2nd Flr SF 2930 non-null float64\n",
" 2 3Ssn Porch 2930 non-null int64 \n",
" 3 Bsmt Unf SF 2929 non-null float64\n",
" 4 BsmtFin SF 1 2929 non-null float64\n",
" 5 BsmtFin SF 2 2929 non-null float64\n",
" 6 Enclosed Porch 2930 non-null float64\n",
" 7 Garage Area 2929 non-null float64\n",
" 8 Gr Liv Area 2930 non-null float64\n",
" 9 Lot Area 2930 non-null float64\n",
" 10 Lot Frontage 2440 non-null float64\n",
" 11 Low Qual Fin SF 2930 non-null float64\n",
" 12 Mas Vnr Area 2907 non-null float64\n",
" 13 Misc Val 2930 non-null float64\n",
" 14 Open Porch SF 2930 non-null float64\n",
" 15 Pool Area 2930 non-null float64\n",
" 16 Screen Porch 2930 non-null float64\n",
" 17 Total Bsmt SF 2929 non-null float64\n",
" 18 Wood Deck SF 2930 non-null float64\n",
"dtypes: float64(18), int64(1)\n",
"memory usage: 572.3 KB\n"
]
}
],
"source": [
"df[CONTINUOUS_VARIABLES].info()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"# The columns with a lot of missing\n",
"# values will be treated seperately below.\n",
"missing_a_lot = [\"Lot Frontage\"]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Discrete Variables"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The discrete columns have between 2 and 15 unique realizations each if year numbers are excluded from the analysis."
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"for column in DISCRETE_VARIABLES:\n",
" mask = df[column].notnull()\n",
" num_realizations = len(list(x for x in df.loc[mask, column].unique()))\n",
" if column not in (\"Year Built\", \"Year Remod/Add\", \"Garage Yr Blt\"):\n",
" assert num_realizations < 15\n",
" assert num_realizations > 2"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"A brief description of the variables:"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Bedroom AbvGr Bedrooms above grade (does NOT include basement bedrooms)\n",
"Bsmt Full Bath Basement full bathrooms\n",
"Bsmt Half Bath Basement half bathrooms\n",
"Fireplaces Number of fireplaces\n",
"Full Bath Full bathrooms above grade\n",
"Garage Cars Size of garage in car capacity\n",
"Garage Yr Blt Year garage was built\n",
"Half Bath Half baths above grade\n",
"Kitchen AbvGr Kitchens above grade\n",
"Mo Sold Month Sold (MM)\n",
"TotRms AbvGrd Total rooms above grade (does not include bathrooms)\n",
"Year Built Original construction date\n",
"Year Remod/Add Remodel date (same as construction date if no remodeling or additions)\n",
"Yr Sold Year Sold (YYYY)\n"
]
}
],
"source": [
"print_column_list(DISCRETE_COLUMNS)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Note:** columns with missing values are implicitly casted to a *float64* type an the *int64* type has no concept of a NaN (=\"Not a number\") value."
]
},
{
"cell_type": "code",
"execution_count": 18,
"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></th>\n",
" <th>Bedroom AbvGr</th>\n",
" <th>Bsmt Full Bath</th>\n",
" <th>Bsmt Half Bath</th>\n",
" <th>Fireplaces</th>\n",
" <th>Full Bath</th>\n",
" <th>Garage Cars</th>\n",
" <th>Garage Yr Blt</th>\n",
" <th>Half Bath</th>\n",
" <th>Kitchen AbvGr</th>\n",
" <th>Mo Sold</th>\n",
" <th>TotRms AbvGrd</th>\n",
" <th>Year Built</th>\n",
" <th>Year Remod/Add</th>\n",
" <th>Yr Sold</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Order</th>\n",
" <th>PID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <th>526301100</th>\n",
" <td>3</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2.0</td>\n",
" <td>1960.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>1960</td>\n",
" <td>1960</td>\n",
" <td>2010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <th>526350040</th>\n",
" <td>2</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>1961.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>1961</td>\n",
" <td>1961</td>\n",
" <td>2010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <th>526351010</th>\n",
" <td>3</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>1958.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>1958</td>\n",
" <td>1958</td>\n",
" <td>2010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>526353030</th>\n",
" <td>3</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2.0</td>\n",
" <td>1968.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>8</td>\n",
" <td>1968</td>\n",
" <td>1968</td>\n",
" <td>2010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>527105010</th>\n",
" <td>3</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2.0</td>\n",
" <td>1997.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>6</td>\n",
" <td>1997</td>\n",
" <td>1998</td>\n",
" <td>2010</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Bedroom AbvGr Bsmt Full Bath Bsmt Half Bath Fireplaces \\\n",
"Order PID \n",
"1 526301100 3 1.0 0.0 2 \n",
"2 526350040 2 0.0 0.0 0 \n",
"3 526351010 3 0.0 0.0 0 \n",
"4 526353030 3 1.0 0.0 2 \n",
"5 527105010 3 0.0 0.0 1 \n",
"\n",
" Full Bath Garage Cars Garage Yr Blt Half Bath \\\n",
"Order PID \n",
"1 526301100 1 2.0 1960.0 0 \n",
"2 526350040 1 1.0 1961.0 0 \n",
"3 526351010 1 1.0 1958.0 1 \n",
"4 526353030 2 2.0 1968.0 1 \n",
"5 527105010 2 2.0 1997.0 1 \n",
"\n",
" Kitchen AbvGr Mo Sold TotRms AbvGrd Year Built \\\n",
"Order PID \n",
"1 526301100 1 5 7 1960 \n",
"2 526350040 1 6 5 1961 \n",
"3 526351010 1 6 6 1958 \n",
"4 526353030 1 4 8 1968 \n",
"5 527105010 1 3 6 1997 \n",
"\n",
" Year Remod/Add Yr Sold \n",
"Order PID \n",
"1 526301100 1960 2010 \n",
"2 526350040 1961 2010 \n",
"3 526351010 1958 2010 \n",
"4 526353030 1968 2010 \n",
"5 527105010 1998 2010 "
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[DISCRETE_VARIABLES].head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Except for the *Garage Yr Blt* column no variable has a significant number of missing values (i.e., > 1% of all rows)."
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"MultiIndex: 2930 entries, (1, 526301100) to (2930, 924151050)\n",
"Data columns (total 14 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Bedroom AbvGr 2930 non-null int64 \n",
" 1 Bsmt Full Bath 2928 non-null float64\n",
" 2 Bsmt Half Bath 2928 non-null float64\n",
" 3 Fireplaces 2930 non-null int64 \n",
" 4 Full Bath 2930 non-null int64 \n",
" 5 Garage Cars 2929 non-null float64\n",
" 6 Garage Yr Blt 2771 non-null float64\n",
" 7 Half Bath 2930 non-null int64 \n",
" 8 Kitchen AbvGr 2930 non-null int64 \n",
" 9 Mo Sold 2930 non-null int64 \n",
" 10 TotRms AbvGrd 2930 non-null int64 \n",
" 11 Year Built 2930 non-null int64 \n",
" 12 Year Remod/Add 2930 non-null int64 \n",
" 13 Yr Sold 2930 non-null int64 \n",
"dtypes: float64(4), int64(10)\n",
"memory usage: 457.8 KB\n"
]
}
],
"source": [
"df[DISCRETE_VARIABLES].info()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"missing_a_lot.append(\"Garage Yr Blt\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Nominal Variables"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Except for the total of 28 neighborhoods, the nominal columns come with anywhere between 1 and 18 different labels each."
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"for column in NOMINAL_VARIABLES:\n",
" mask = df[column].notnull()\n",
" num_realizations = len(list(x for x in df.loc[mask, column].unique()))\n",
" if column not in (\"Neighborhood\"):\n",
" assert num_realizations < 18\n",
" assert num_realizations > 1"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"A brief description of the variables:"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Alley Type of alley access to property\n",
"Bldg Type Type of dwelling\n",
"Central Air Central air conditioning\n",
"Condition 1 Proximity to various conditions\n",
"Condition 2 Proximity to various conditions (if more than one is present)\n",
"Exterior 1st Exterior covering on house\n",
"Exterior 2nd Exterior covering on house (if more than one material)\n",
"Foundation Type of foundation\n",
"Garage Type Garage location\n",
"Heating Type of heating\n",
"House Style Style of dwelling\n",
"Land Contour Flatness of the property\n",
"Lot Config Lot configuration\n",
"MS SubClass Identifies the type of dwelling involved in the sale.\n",
"MS Zoning Identifies the general zoning classification of the sale.\n",
"Mas Vnr Type Masonry veneer type\n",
"Misc Feature Miscellaneous feature not covered in other categories\n",
"Neighborhood Physical locations within Ames city limits (map available)\n",
"Roof Matl Roof material\n",
"Roof Style Type of roof\n",
"Sale Condition Condition of sale\n",
"Sale Type Type of sale\n",
"Street Type of road access to property\n"
]
}
],
"source": [
"print_column_list(NOMINAL_COLUMNS)"
]
},
{
"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></th>\n",
" <th>Alley</th>\n",
" <th>Bldg Type</th>\n",
" <th>Central Air</th>\n",
" <th>Condition 1</th>\n",
" <th>Condition 2</th>\n",
" <th>Exterior 1st</th>\n",
" <th>Exterior 2nd</th>\n",
" <th>Foundation</th>\n",
" <th>Garage Type</th>\n",
" <th>Heating</th>\n",
" <th>House Style</th>\n",
" <th>Land Contour</th>\n",
" <th>Lot Config</th>\n",
" <th>MS SubClass</th>\n",
" <th>MS Zoning</th>\n",
" <th>Mas Vnr Type</th>\n",
" <th>Misc Feature</th>\n",
" <th>Neighborhood</th>\n",
" <th>Roof Matl</th>\n",
" <th>Roof Style</th>\n",
" <th>Sale Condition</th>\n",
" <th>Sale Type</th>\n",
" <th>Street</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Order</th>\n",
" <th>PID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <th>526301100</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>BrkFace</td>\n",
" <td>Plywood</td>\n",
" <td>CBlock</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>Lvl</td>\n",
" <td>Corner</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>Stone</td>\n",
" <td>NA</td>\n",
" <td>Names</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <th>526350040</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Feedr</td>\n",
" <td>Norm</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>CBlock</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>Lvl</td>\n",
" <td>Inside</td>\n",
" <td>020</td>\n",
" <td>RH</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>Names</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <th>526351010</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>Wd Sdng</td>\n",
" <td>Wd Sdng</td>\n",
" <td>CBlock</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>Lvl</td>\n",
" <td>Corner</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>BrkFace</td>\n",
" <td>Gar2</td>\n",
" <td>Names</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>526353030</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>BrkFace</td>\n",
" <td>BrkFace</td>\n",
" <td>CBlock</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>Lvl</td>\n",
" <td>Corner</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>Names</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>527105010</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>PConc</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>2Story</td>\n",
" <td>Lvl</td>\n",
" <td>Inside</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>Gilbert</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <th>527105030</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>PConc</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>2Story</td>\n",
" <td>Lvl</td>\n",
" <td>Inside</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>BrkFace</td>\n",
" <td>NA</td>\n",
" <td>Gilbert</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <th>527127150</th>\n",
" <td>NA</td>\n",
" <td>TwnhsE</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>CemntBd</td>\n",
" <td>CemntBd</td>\n",
" <td>PConc</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>Lvl</td>\n",
" <td>Inside</td>\n",
" <td>120</td>\n",
" <td>RL</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>StoneBr</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <th>527145080</th>\n",
" <td>NA</td>\n",
" <td>TwnhsE</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>HdBoard</td>\n",
" <td>HdBoard</td>\n",
" <td>PConc</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>HLS</td>\n",
" <td>Inside</td>\n",
" <td>120</td>\n",
" <td>RL</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>StoneBr</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <th>527146030</th>\n",
" <td>NA</td>\n",
" <td>TwnhsE</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>CemntBd</td>\n",
" <td>CemntBd</td>\n",
" <td>PConc</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>1Story</td>\n",
" <td>Lvl</td>\n",
" <td>Inside</td>\n",
" <td>120</td>\n",
" <td>RL</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>StoneBr</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <th>527162130</th>\n",
" <td>NA</td>\n",
" <td>1Fam</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>PConc</td>\n",
" <td>Attchd</td>\n",
" <td>GasA</td>\n",
" <td>2Story</td>\n",
" <td>Lvl</td>\n",
" <td>Inside</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>Gilbert</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>Pave</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Alley Bldg Type Central Air Condition 1 Condition 2 \\\n",
"Order PID \n",
"1 526301100 NA 1Fam Y Norm Norm \n",
"2 526350040 NA 1Fam Y Feedr Norm \n",
"3 526351010 NA 1Fam Y Norm Norm \n",
"4 526353030 NA 1Fam Y Norm Norm \n",
"5 527105010 NA 1Fam Y Norm Norm \n",
"6 527105030 NA 1Fam Y Norm Norm \n",
"7 527127150 NA TwnhsE Y Norm Norm \n",
"8 527145080 NA TwnhsE Y Norm Norm \n",
"9 527146030 NA TwnhsE Y Norm Norm \n",
"10 527162130 NA 1Fam Y Norm Norm \n",
"\n",
" Exterior 1st Exterior 2nd Foundation Garage Type Heating \\\n",
"Order PID \n",
"1 526301100 BrkFace Plywood CBlock Attchd GasA \n",
"2 526350040 VinylSd VinylSd CBlock Attchd GasA \n",
"3 526351010 Wd Sdng Wd Sdng CBlock Attchd GasA \n",
"4 526353030 BrkFace BrkFace CBlock Attchd GasA \n",
"5 527105010 VinylSd VinylSd PConc Attchd GasA \n",
"6 527105030 VinylSd VinylSd PConc Attchd GasA \n",
"7 527127150 CemntBd CemntBd PConc Attchd GasA \n",
"8 527145080 HdBoard HdBoard PConc Attchd GasA \n",
"9 527146030 CemntBd CemntBd PConc Attchd GasA \n",
"10 527162130 VinylSd VinylSd PConc Attchd GasA \n",
"\n",
" House Style Land Contour Lot Config MS SubClass MS Zoning \\\n",
"Order PID \n",
"1 526301100 1Story Lvl Corner 020 RL \n",
"2 526350040 1Story Lvl Inside 020 RH \n",
"3 526351010 1Story Lvl Corner 020 RL \n",
"4 526353030 1Story Lvl Corner 020 RL \n",
"5 527105010 2Story Lvl Inside 060 RL \n",
"6 527105030 2Story Lvl Inside 060 RL \n",
"7 527127150 1Story Lvl Inside 120 RL \n",
"8 527145080 1Story HLS Inside 120 RL \n",
"9 527146030 1Story Lvl Inside 120 RL \n",
"10 527162130 2Story Lvl Inside 060 RL \n",
"\n",
" Mas Vnr Type Misc Feature Neighborhood Roof Matl Roof Style \\\n",
"Order PID \n",
"1 526301100 Stone NA Names CompShg Hip \n",
"2 526350040 None NA Names CompShg Gable \n",
"3 526351010 BrkFace Gar2 Names CompShg Hip \n",
"4 526353030 None NA Names CompShg Hip \n",
"5 527105010 None NA Gilbert CompShg Gable \n",
"6 527105030 BrkFace NA Gilbert CompShg Gable \n",
"7 527127150 None NA StoneBr CompShg Gable \n",
"8 527145080 None NA StoneBr CompShg Gable \n",
"9 527146030 None NA StoneBr CompShg Gable \n",
"10 527162130 None NA Gilbert CompShg Gable \n",
"\n",
" Sale Condition Sale Type Street \n",
"Order PID \n",
"1 526301100 Normal WD Pave \n",
"2 526350040 Normal WD Pave \n",
"3 526351010 Normal WD Pave \n",
"4 526353030 Normal WD Pave \n",
"5 527105010 Normal WD Pave \n",
"6 527105030 Normal WD Pave \n",
"7 527127150 Normal WD Pave \n",
"8 527145080 Normal WD Pave \n",
"9 527146030 Normal WD Pave \n",
"10 527162130 Normal WD Pave "
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[NOMINAL_VARIABLES].head(10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For the nominal variables there is only a neglectable number of missing values."
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"MultiIndex: 2930 entries, (1, 526301100) to (2930, 924151050)\n",
"Data columns (total 23 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Alley 2930 non-null object\n",
" 1 Bldg Type 2930 non-null object\n",
" 2 Central Air 2930 non-null object\n",
" 3 Condition 1 2930 non-null object\n",
" 4 Condition 2 2930 non-null object\n",
" 5 Exterior 1st 2930 non-null object\n",
" 6 Exterior 2nd 2930 non-null object\n",
" 7 Foundation 2930 non-null object\n",
" 8 Garage Type 2930 non-null object\n",
" 9 Heating 2930 non-null object\n",
" 10 House Style 2930 non-null object\n",
" 11 Land Contour 2930 non-null object\n",
" 12 Lot Config 2930 non-null object\n",
" 13 MS SubClass 2930 non-null object\n",
" 14 MS Zoning 2930 non-null object\n",
" 15 Mas Vnr Type 2907 non-null object\n",
" 16 Misc Feature 2930 non-null object\n",
" 17 Neighborhood 2930 non-null object\n",
" 18 Roof Matl 2930 non-null object\n",
" 19 Roof Style 2930 non-null object\n",
" 20 Sale Condition 2930 non-null object\n",
" 21 Sale Type 2930 non-null object\n",
" 22 Street 2930 non-null object\n",
"dtypes: object(23)\n",
"memory usage: 663.8+ KB\n"
]
}
],
"source": [
"df[NOMINAL_VARIABLES].info()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Ordinal Variables"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The ordinal columns come with anywhere between 2 and 11 distinct labels each."
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"for column in ORDINAL_VARIABLES:\n",
" mask = df[column].notnull()\n",
" num_realizations = len(list(x for x in df.loc[mask, column].unique()))\n",
" assert 2 < num_realizations < 11"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"A brief description of the variables:"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Bsmt Cond Evaluates the general condition of the basement\n",
"Bsmt Exposure Refers to walkout or garden level walls\n",
"Bsmt Qual Evaluates the height of the basement\n",
"BsmtFin Type 1 Rating of basement finished area\n",
"BsmtFin Type 2 Rating of basement finished area (if multiple types)\n",
"Electrical Electrical system\n",
"Exter Cond Evaluates the present condition of the material on the exterior\n",
"Exter Qual Evaluates the quality of the material on the exterior\n",
"Fence Fence quality\n",
"Fireplace Qu Fireplace quality\n",
"Functional Home functionality (Assume typical unless deductions are warranted)\n",
"Garage Cond Garage condition\n",
"Garage Finish Interior finish of the garage\n",
"Garage Qual Garage quality\n",
"Heating QC Heating quality and condition\n",
"Kitchen Qual Kitchen quality\n",
"Land Slope Slope of property\n",
"Lot Shape General shape of property\n",
"Overall Cond Rates the overall condition of the house\n",
"Overall Qual Rates the overall material and finish of the house\n",
"Paved Drive Paved driveway\n",
"Pool QC Pool quality\n",
"Utilities Type of utilities available\n"
]
}
],
"source": [
"print_column_list(ORDINAL_COLUMNS)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"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></th>\n",
" <th>Bsmt Cond</th>\n",
" <th>Bsmt Exposure</th>\n",
" <th>Bsmt Qual</th>\n",
" <th>BsmtFin Type 1</th>\n",
" <th>BsmtFin Type 2</th>\n",
" <th>Electrical</th>\n",
" <th>Exter Cond</th>\n",
" <th>Exter Qual</th>\n",
" <th>Fence</th>\n",
" <th>Fireplace Qu</th>\n",
" <th>Functional</th>\n",
" <th>Garage Cond</th>\n",
" <th>Garage Finish</th>\n",
" <th>Garage Qual</th>\n",
" <th>Heating QC</th>\n",
" <th>Kitchen Qual</th>\n",
" <th>Land Slope</th>\n",
" <th>Lot Shape</th>\n",
" <th>Overall Cond</th>\n",
" <th>Overall Qual</th>\n",
" <th>Paved Drive</th>\n",
" <th>Pool QC</th>\n",
" <th>Utilities</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Order</th>\n",
" <th>PID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <th>526301100</th>\n",
" <td>Gd</td>\n",
" <td>Gd</td>\n",
" <td>TA</td>\n",
" <td>BLQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>NA</td>\n",
" <td>Gd</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Fa</td>\n",
" <td>TA</td>\n",
" <td>Gtl</td>\n",
" <td>IR1</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>P</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <th>526350040</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>TA</td>\n",
" <td>Rec</td>\n",
" <td>LwQ</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>MnPrv</td>\n",
" <td>NA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>Gtl</td>\n",
" <td>Reg</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <th>526351010</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>TA</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>Gtl</td>\n",
" <td>IR1</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>526353030</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>TA</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Ex</td>\n",
" <td>Ex</td>\n",
" <td>Gtl</td>\n",
" <td>Reg</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>527105010</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>Gd</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>MnPrv</td>\n",
" <td>TA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>TA</td>\n",
" <td>Gtl</td>\n",
" <td>IR1</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <th>527105030</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>TA</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>NA</td>\n",
" <td>Gd</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Ex</td>\n",
" <td>Gd</td>\n",
" <td>Gtl</td>\n",
" <td>IR1</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <th>527127150</th>\n",
" <td>TA</td>\n",
" <td>Mn</td>\n",
" <td>Gd</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Ex</td>\n",
" <td>Gd</td>\n",
" <td>Gtl</td>\n",
" <td>Reg</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <th>527145080</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>Gd</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>RFn</td>\n",
" <td>TA</td>\n",
" <td>Ex</td>\n",
" <td>Gd</td>\n",
" <td>Gtl</td>\n",
" <td>IR1</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <th>527146030</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>Gd</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>RFn</td>\n",
" <td>TA</td>\n",
" <td>Ex</td>\n",
" <td>Gd</td>\n",
" <td>Gtl</td>\n",
" <td>IR1</td>\n",
" <td>5</td>\n",
" <td>8</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <th>527162130</th>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>Unf</td>\n",
" <td>SBrkr</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>Typ</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>Gd</td>\n",
" <td>Gtl</td>\n",
" <td>Reg</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>Y</td>\n",
" <td>NA</td>\n",
" <td>AllPub</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Bsmt Cond Bsmt Exposure Bsmt Qual BsmtFin Type 1 \\\n",
"Order PID \n",
"1 526301100 Gd Gd TA BLQ \n",
"2 526350040 TA No TA Rec \n",
"3 526351010 TA No TA ALQ \n",
"4 526353030 TA No TA ALQ \n",
"5 527105010 TA No Gd GLQ \n",
"6 527105030 TA No TA GLQ \n",
"7 527127150 TA Mn Gd GLQ \n",
"8 527145080 TA No Gd ALQ \n",
"9 527146030 TA No Gd GLQ \n",
"10 527162130 TA No TA Unf \n",
"\n",
" BsmtFin Type 2 Electrical Exter Cond Exter Qual Fence \\\n",
"Order PID \n",
"1 526301100 Unf SBrkr TA TA NA \n",
"2 526350040 LwQ SBrkr TA TA MnPrv \n",
"3 526351010 Unf SBrkr TA TA NA \n",
"4 526353030 Unf SBrkr TA Gd NA \n",
"5 527105010 Unf SBrkr TA TA MnPrv \n",
"6 527105030 Unf SBrkr TA TA NA \n",
"7 527127150 Unf SBrkr TA Gd NA \n",
"8 527145080 Unf SBrkr TA Gd NA \n",
"9 527146030 Unf SBrkr TA Gd NA \n",
"10 527162130 Unf SBrkr TA TA NA \n",
"\n",
" Fireplace Qu Functional Garage Cond Garage Finish Garage Qual \\\n",
"Order PID \n",
"1 526301100 Gd Typ TA Fin TA \n",
"2 526350040 NA Typ TA Unf TA \n",
"3 526351010 NA Typ TA Unf TA \n",
"4 526353030 TA Typ TA Fin TA \n",
"5 527105010 TA Typ TA Fin TA \n",
"6 527105030 Gd Typ TA Fin TA \n",
"7 527127150 NA Typ TA Fin TA \n",
"8 527145080 NA Typ TA RFn TA \n",
"9 527146030 TA Typ TA RFn TA \n",
"10 527162130 TA Typ TA Fin TA \n",
"\n",
" Heating QC Kitchen Qual Land Slope Lot Shape Overall Cond \\\n",
"Order PID \n",
"1 526301100 Fa TA Gtl IR1 5 \n",
"2 526350040 TA TA Gtl Reg 6 \n",
"3 526351010 TA Gd Gtl IR1 6 \n",
"4 526353030 Ex Ex Gtl Reg 5 \n",
"5 527105010 Gd TA Gtl IR1 5 \n",
"6 527105030 Ex Gd Gtl IR1 6 \n",
"7 527127150 Ex Gd Gtl Reg 5 \n",
"8 527145080 Ex Gd Gtl IR1 5 \n",
"9 527146030 Ex Gd Gtl IR1 5 \n",
"10 527162130 Gd Gd Gtl Reg 5 \n",
"\n",
" Overall Qual Paved Drive Pool QC Utilities \n",
"Order PID \n",
"1 526301100 6 P NA AllPub \n",
"2 526350040 5 Y NA AllPub \n",
"3 526351010 6 Y NA AllPub \n",
"4 526353030 7 Y NA AllPub \n",
"5 527105010 5 Y NA AllPub \n",
"6 527105030 6 Y NA AllPub \n",
"7 527127150 8 Y NA AllPub \n",
"8 527145080 8 Y NA AllPub \n",
"9 527146030 8 Y NA AllPub \n",
"10 527162130 7 Y NA AllPub "
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[ORDINAL_VARIABLES].head(10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For the ordinal variables there is only a neglectable number of missing values."
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"MultiIndex: 2930 entries, (1, 526301100) to (2930, 924151050)\n",
"Data columns (total 23 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Bsmt Cond 2929 non-null object\n",
" 1 Bsmt Exposure 2926 non-null object\n",
" 2 Bsmt Qual 2929 non-null object\n",
" 3 BsmtFin Type 1 2929 non-null object\n",
" 4 BsmtFin Type 2 2928 non-null object\n",
" 5 Electrical 2929 non-null object\n",
" 6 Exter Cond 2930 non-null object\n",
" 7 Exter Qual 2930 non-null object\n",
" 8 Fence 2930 non-null object\n",
" 9 Fireplace Qu 2930 non-null object\n",
" 10 Functional 2930 non-null object\n",
" 11 Garage Cond 2929 non-null object\n",
" 12 Garage Finish 2928 non-null object\n",
" 13 Garage Qual 2929 non-null object\n",
" 14 Heating QC 2930 non-null object\n",
" 15 Kitchen Qual 2930 non-null object\n",
" 16 Land Slope 2930 non-null object\n",
" 17 Lot Shape 2930 non-null object\n",
" 18 Overall Cond 2930 non-null object\n",
" 19 Overall Qual 2930 non-null object\n",
" 20 Paved Drive 2930 non-null object\n",
" 21 Pool QC 2930 non-null object\n",
" 22 Utilities 2930 non-null object\n",
"dtypes: object(23)\n",
"memory usage: 663.8+ KB\n"
]
}
],
"source": [
"df[ORDINAL_VARIABLES].info()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Missing Data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Visualizations"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1800x720 with 2 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"msno.matrix(df[CONTINUOUS_VARIABLES]);"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1800x720 with 2 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"msno.matrix(df[DISCRETE_VARIABLES]);"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1800x720 with 2 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"msno.matrix(df[NOMINAL_VARIABLES]);"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABc0AAAKgCAYAAABJHlWGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOydd5hdVdXGfysdkhASeu+9t9B7R0AQUXpAmjRBRaT3IkWQIr0qvaifFAUE6SIdRJoUpXekQyCzvj/edXL3nNyZTDDJOfdmv8+zn5m7z7nzrDX7nF3e1czdycjIyMjIyMjIyMjIyMjIyMjIyMjIyMiAXlULkJGRkZGRkZGRkZGRkZGRkZGRkZGRkVEXZNI8IyMjIyMjIyMjIyMjIyMjIyMjIyMjI5BJ84yMjIyMjIyMjIyMjIyMjIyMjIyMjIxAJs0zMjIyMjIyMjIyMjIyMjIyMjIyMjIyApk0z8jIyMjIyMjIyMjIyMjIyMjIyMjIyAhk0jwjIyMjIyMjIyMjIyMjIyMjIyMjIyMjkEnzjIyMjIyMjIyMjIyMjIyMjIyMjIyMjEAmzTMyMjIyMjIyMjIyMjIyMjIyMjIyMjICmTTPyMjIyMjIyMjIyMjIyMjIyMjIyMjICPSpWoCMjIyMVoeZTQvg7m9XLcv4hpnNDiwILAbcCzzr7m9VKVNGRkZGRkZGRkZGRkZGRkbGhET2NM/IqCHMLL+bLQIzWxZ4GNjFzKauWp7xCTNbHrgROBM4ErgNOMbMZq5UsIyMjIyMjIyMjIyMjIyMjIwJiEzMZWTUDGbWx907zKy/mS1hZhuZ2QxmNrhq2TI6w8zmBi4GZgJ+BuxoZlNVKtR4gpktAdwA/Bn4LjAAOAPYGlgz7rHKBMzIyMjIyMjIyMjIyMjIyMiYQDB3r1qGjIyMgJn1dvdRQZDfDMyCCNn/AlcBv3b3J6uUMUMws8mBk4B1gYOAVYGdgIOB8939vQrF+59gZkOB84AvgL1TXczsQeAjd1+zKvkyMjIyMjIyMjIyMjIyMjIyJiSyp3lGRo0QhPlkwF3AZ8CuwJzACcAI4FQzG1ahiBkBd/8MGAT8w92vdPfdgIuAo4GdWtzjfDpkrLm/IMzNrG9cexSYJvmckZGRkZGRkZGRkZGRkZGR0VbIhUAzMuqHjYF+yHv5EXf/ysyeQukxfufu75uZeQ4TqQzF/9/dt0v7gN0BR8Q5ZjaGx3mLjN3bwIXufh6M1u3ruPYvYH1gMPB+NeJlZGRkZGRkZGRkZGRkZGRkTDhkT/OMjIphZmXj1SLAMODRIMy3Af4AHOTuvzazKYBvm9nAiS1rhuDunhZrNbNeQaJ/DewBXIiI853NbEjcs5yZDa87YR6k/vvABclnT+T+HHnY902+M62ZzTnxpc3IyMjIyMjIyMjIyMjIyMgY/8ie5hkZFSLI1q8jlccO7n4S8Any6nUz2wr4DXCgu/8iiNofAEsA9wOfViX7pA537+ji96/NbI/4eBSAmT0KnAt8CCxaZ2/zQq5Cp+JzPKsd6PkcCXRE/2zApcALwPYViJyRkZGRkZGRkZGRkZGRkZExXpFJ84yMihDEaYeZ9QduA/qZ2QXAX4BjkXf5OsDBQZgbMA+wKfAk8FZFomeMBeFxvquGjMOBUcAzwHJxvZaE+ViQepr3BgaY2SzAFSgyYo2qBMvIyMjIyMjIyMjIyMjIyMgYn8jpWTIyKkCRziM8x9cC3gQ2Bz5294cQ0boGcB9wvpkNAFYGLgYmA/aO71sV8mf0GJci4+QjwLKRbqcljZUJ0e8oPcs8KApiCLBIK+uWkZGRMSminfYQqS7pWpTXpYyMjIyMjIyMjG+KvJHMyKgA4WE+ALgJ+Bj4yt3/mdxycfw8HLgFefK+B3wErBUpQHq7+6iJJ3VGTxGH96WAs4GngdVjzPqEF3or42PkOX8V8A6wWEGYt4FuGRkZGW0NM1sa2M7df1QY31s0+qmMfsCXZtbP3Uea2SDgUGBOM3sYuNndH6lWxIyMjIyMjIyMjFZC9jTPyKgOFm0jYG4zm7q44O4vu/uRwLLIm/dM4EBgjYSgzIT5REAzT7yxeecFAbE4IpWXrCth/k10Q4abyYDngUUzYZ6RkZHRGgiv642APc3sDBhd2LqlPc7NbFHg92a2cBDmUwAPAN8F5gSOAc4ys82qlDMjIyNjYsPMBprZDlE/KyMjIyNjHJFJ84yMiQQz6x0/DcDdPwc2Bi4D5gO2jYNecX8vd3/Q3U9291+4+5/cfVR4mGeCciIgyGA3sz5mNo2ZTWdmA3rilefu5yMP81qSyv+Dbs8BBwAr1dUYkJGRkZExJmKuPg/VTdndzM6L/lYnztcEVgJONrP5gVWBl1Bk3pLACsC0wCFm9r3qxBw3tPiYTLIws+vM7ISq5cjICBwBXADsaGZDqxYmIyMjo9WQSfOMjImEILwnA/5gZkVByI+B3YA/AkcC3zezwXGto6u/M5FEnqRRGCdiPK4BbgceBO4ws+UiH31X3+0FDSKibqTyN9UtdHnH3Y/PBpyMjIyM1oKZ9XX3V4GzUOqSHc3sZGht4tzdT0Hp7OYDTgO2RgXT/x3X7we2QPU4DmgF4jy8588ws4FVy5LRc5hZkU7xp2Z2cNXyZGS4+77AdcDRwK7t4HFuZn2rliEjI2PSQSbNMzImLlYDhgMXmtlSAO7+CbANIi5PBrYoiPOM6hCk8EDg78hD7ULgXOBD4C5g8yJ6oMl3O5Lfa5cr9pvqVtYlG3AyMjIyWgNh5Pwq9hc7orobHwP7mNmvoDWJ82KtcveTUSq7OYG1gRejfkzf0P3viEwfBPzczEZUJvRYEGOwK7A9cJKZTV6tRBk9hbu/jww4vwSONLNDqpUoY1JGOGvh7psD16JUn7u0MnFuZtcgo9SAqmXJyMiYNJBJ84yMiQh3/xPwY+Ar4IoScb41cBtwAvL+yoekipCQBgcDnwAj3P0Udz8aFW/tAwwsSOPuvM7rhnbWLSMjY8IicmLntBEtiMRY+jBKZfIgsAtwH/AjMzsr7msZ4jzI8FEJcX48cA7QF3mUL+TuXyX3FsT5fMDqVck9NoSBej9U02Yj4Fd5T9g6cPfXgV8h4vyITJxnVIGY8z6P37+PzpiDgB8BO0dUREshjL6jUMqZnTJxnpGRMTHQp2oBMjLaFeVcz2bW392/dPcrg4jcHxHnW7r7w+7+iZltDdwMfAs4tSLRJ3kkHtULA68C/4HRm85TgP3d/UIzmxIwd/+gGknHHe2sW0ZGxoRFpHUaBBxqZle6+yNVy5QxTvgJIk32Av4VntgPxOd9zOwLd/9xklqsdpFSBYo9VnhSbmBmz7v74+5+opl9DewLnGZme7r702bWO2rFPGBmw4Fnq9WgawTZ9amZ/RToDWwQ/fu4+2fVSpfRE7j760UEByLOcfejKhUqY5JC4vxyDYosug44A1gRRUNgZudGdERLwN0/NrM9gA/QmcXM7Dx3/6Ji0TIyMtoYmTTPyJhAiMPcQOAId9/X3b9MiPPLw5HrMOByM9vc3Z+IQ9LawJetcGhtZ4Sn3YzACxHS/n3gCuBAdz8hPC4PAvqZ2b6FN1sroJ11y8jImOBYExGSs5rZMe7+j6oFyugxZgU+dvdnYXTB8ZfM7HRgeWBvMxsVe5ba7j1KdTluAb5Aae+edveR7n5K5LzdA/i1me3u7s8kxPlTyd+pXZqxpGbIZ2a2T3Rn4rymiGdqjDpE7v6amZ0WHzNxnjHRYWa7AGsA3wdui7PlZGjPf0Tcc567v1ehmOMEd38v6gUYSmta6JCJ84yMjAmCHHafkTFh8T3gJ2Z2NUBBnMfvl6Nc0vMAV5rZ8tH/eXh/9arzobWd0CwFSfzvbwCWN7NTCFIZpc8BWAxYGni7zqRyO+uWkZEx8eHu/wf8AK1vh5jZIhWLlNFzvATMYmazx2criHOUD/wDtGfZvyL5eoRSXY6Pkdfk1e4+MrnnBOBslOP8NDNbxN1HlWqO1IowT9frQrYgyPcB/oSI85yqpUZICXMzW8HMNjKzTc1sRgB3fwU4nZyqJaMazAF8BjwUhHnvOGdugubPfVFK0GkqlXIcEST/wcAFiDjfuZVTtTQ7q7VKmrSMjEkBmTTPyBiPsDGLJ94I/Bz4tpn9DkYT58XCfinwAirGuE/6xWZeKxnjHxHi3WFmfcxsRjObPhnHm5AH297Ape7+C6CXmS2MQhwN+EU1ko8d7axbRkbGhEd5TQvvXdz9YlRM8rsoVcuiE1+6jK7QZC9S4AHgLeBYM5uhIJHjwD438FdgO+CkiSTqOKEgEeLnoagux67APbG3WiCIy/UA3P04ZAxYFdi5IrF7hGS97mtms5nZosn79hlaq29CxPmprUKcF44i7YgSYX4YcCXaP10LXGZmWwC4+8vAaYg4P8TMjqlI5IxJBAnh+jlK8TQ9jDY49o1rFwPD0F5/m2bEbR3QlVzu/i5wCHA+Is53aUXiPAwZxTwyo5nNG5Hp2XEuI6MmqOXkmJHRiogDzygzm8zMdjaz6dz9bbSYHwpsmBDnRQjZcGTpHwFsVYngkzBKId5/BO5F4/EXM1vcVTTsh8CLwKpmdiHyyr4EFRpb25MiZHVCO+uWkZExcRBzwORmtpeZDY10Tn3i2kWION8MOMjMFqtU2Ayg016kv5mtb2Yrm9ncAO7+F5TXdi3gZDObI+b4BVFhzEfc/dJYO2qRwjFI8L9CoyZH/JwHeCO85AeZ2W7A7cD/ATeZ2VFx7wnA9qgIey1RWq+vRilnbgYeMbPFzWxA4nF+E7AecEp429cSZragmR2OdFi3ankmBBKi6yA0Nge5+2zIe3dV4OdmtlXc+woizs9GRWrnrkbqjHZEmVhOCNdbEGE+wgJJBKkBv0UFh2+uo7NWyTC1tJl9y8xWN7PZANz9HZTq9HxklGop4tySFGFmdjYq1voo8KyZ7Wtmc1UqYEZGBpBzmmdkjBeUDjy3Iqv+UDM7yd0/MLPz4tYjzewGlEduKNpkP+3uNyZ/p1bhwu2K2DiOMuX2uxd5XV+MiqR9C7jNzH7s7r8xs22AddBB9UXgGuCkgljwpOBrHdDOurUbgrCy/H/OqBoxb3jyuTisHgH8FJjezE5w9w+LucHdLzKzWZG312dmdqa7P1iRCpM8YgyLvchtwCzAdMDDZnaGu1/i7vuamaMogWeA14GBwBtEiq7i71SjRQNBBC0GPFLq7wc8DXzPzC5G3pLrojQtjwNbAFubity94u5XxPdqt8dK1utByLD9NioU/1/gL8iYvbeZ3ZHkOO8AdkJr9vEVid4lzGxFJPeTwIPAR+X5pV1gZquhd2l3d7/CzDZDkRpnA98BjgrVr3D3V8zsJOBMd3++Oqkz2gkl4nU2YIBH3Qp3vz+MV4cjr/PzgDfMbHpUn+R1d9+3EsHHghJhfigy0vcDJgMeMrNT3P1Gd3/bFOkB8prvF+td7XOcJ+N2OSrQeiJaA1ZEc/sKppocb1YnZUZGhrXh/iWjRqjjAWVCITx+7keL3X7AU+7+eXJ9KMoBezAwEzoQPQesHN57bXmgqCOKjVgQljOjnHh7ufvTcX1m4CxUGG0Nd3+ii79Tu+e7nXVrN4RR43pkqLjQc/74jAphZoYiEPsDXxXPY/RfCayG6nD8IojzvrF2rYG8ewcCx7n7QZUoMImjmLODaP4Tcow5CaV/2xXl9j7S3c+M+1dHtStmBV4GTgnCvVZzv5n1c/eRpnQkp7v7jtG/HIrSG46I8vPd/b64diQyBq+e7sPqClO6hIuQR+gW7v6umV0LLAe8D0yNdL3b3b+I/eYewC/rNFYgb1Dk8X8x8Ct3f7FaiSYszGwJ4Gcocm9JFNl3vLsfY2ZrooiBB4EL3P380nfzvj/jf0L6DJnZBch4OB1y4DoUeBgZFX+GzqZPoNoVA4AFgJXc/ckKRO8xTHUAfgzs6+4XmtmxSJ9ngEPc/Q9x3zTI8DsCmMPd/1OVzOMCUzqx05Ej3S2xrxoKvIfSzhzk7l9WKWNGxqSOTJpnTDCY8hjeDZzm7pdWLc+Ehpn9Ah3SNi0WajObDx1IP3T3B6JvKNrUvI8qmY/KHr0TH/F8PoyKiH0EbJiSlmY2C9p0vgKsG0S0ubvX/aDTzrq1E4I0/w8wEjgAuDIT5xlVwJSTfEdgZRSR8hkive5294eDOL8GWAUZ4k509/fju99HhOzfgbvyWlYdYk4ZhIzzV7v7vdG/AnAQsCwiGc7q4vu1IsxTmNn3kPHmLndfLfqGIO/Jfu7+SZDPs6Nn92lg51ZYz2JN3g/4i7v/n5ldiTwNN0LGjxvRnnEvlL/9i+S7tRkzMxuGxugNYB93/yD6R3uMtjK60sPMpg1v1z+guXNPd38/ns9HEYn5b5T27vWJKnRG26LkiX0ysAmKcOiDIlFGAj8Cbo39/fooVdUw9I7+wt2fqkL2niKM8iehCNjLzWxTlGLsUmAl4Cvgp+5+Q9w/LTBt3Q0BKcxsDxStN9zdXzazBYB7kPFxO3f/3MyWRM54tfeez8hoR+Sc5hkTEjMBnwLnRLhiu2N24Hl3/4+ZDTazPZHR4CrgfjPbF8DdP3D3K939liDMe2eSYeLAOufnng6FNi8ETAlMbkIvGJ1/8mZEBg2LvjSfaq3Qzrq1I+K9/xyYA0WdnARsZUo70LIwsyUt58FvKZhSKdwGzA/8DUU/vIs8nM43s+/EvLA5cBc6dB9nKla1HDqUz+but3uNcmFPaoj37neo0OeGKO0KAOGBfSQybBxpZjs1+xt1IV+7wE3Iu3oJM7sHwN0/BL4OwnwK4NuIMB8I/LAwBFclcFdoMke+i4igG81sSxQBsI27P+buDwH3AfOhCIJORXdrNmYzoHnkTwVhDu1T2D4hKH9oZj9M+t8Oh5jFUbqL9+PS9ChFzdbAbnUlzIs5O90nJtcyV1BTJM/jQsBUwM/c/QR3PxalXOxAkaXrRMTOnxAJuzawU90J80AH8DxwXURH/QY42N23Q6nj5gGODuM97v52QZi3wtwfMg4CRgVhPi9Kq3krsEMQ5tugFHlDJ7rAGRkZQCbNMyYgIiRzN0TOFXn+2hmvAeua2RnA71FBklOBDVCBkgPMbOryl+py4InwsLaGN4raLePuL6Mcf9cBy6ADjQMpafwJ2rDVngRsZ93aGe7+KUqV8zUKzdwqvCVbDqa8mQ+heTDvL1oAcdi+DrgcGOHue7j7T919LbR+TwWcZmbfduG7wA3IA/Yp5H3eD9iz+JvZCFwZOggjPUrJMjOMTv2Bq/jzkXH9XDPbuCI5x4pmhjd3/wR5Fx4ILGpmd0V/hyldyVGIWHgXWNobdTlqZwhO1us1zWzyMKDeGe/OUsjhJE2d9gnKdXsyiiKrK5YBhiAPyW4J1+K5rCOx1R1MKe72AfYzs+2SS6PQmK1tZvOZckZ/D5gbuMPd76qjrtaoyTQI+DXwJzO71cyONBV/7sjreX1hqulwKbAI2n8VY/ocqmH0JXAGsHoQ50Waj9pFNTZ7ztz9DpSW5UuUkuWPyJseFNXyIjANcKiZTZe+Y3Wd+wHM7AwzWzJkvA2YwcxOQ4T5X4Adwxg8LYpinwxFsWRkZFSAvAhmTBAkh7RnUH6xu4DfmNmGlQo2HtCNF+UhyMtrBRSGuZq7H+Pu9wMvAc+iULnawcwOAG4ys92qlmV8oZvDycWoWjzu/ggyblwOHBv/hynNbIApXcFGwD9QnvraoJ11mxRgCqktNs7nozlyFLAwcBiwRYsS51egzf9FwHr5oF1fJHPI94F/odDnN+NaHwB3PwfYFxnWDox5A3ffGdgGef0eCiyXPcwnPsrrQBy+f4tyo74JXGZmM7jyo6bE+QmIfL1xIovcIwTRPcrMJjOzrcxsLzOb38ymcPePkafhAcDiCXH+KXA1cDRKkdcKhazPRN6E65nZgPCK741I5ykQidLHzOZGEUmPu/vPiwjFCuXuDm8Dg9Fa1tTDPFkXtjGzjetIbHUHd38Vpb54HTjIzLaP/o9QbYfJUUqWO5CB5xB3/2/cUytdzToVoX0YGfBfjcvbAI+a2TTtEinQprgHFUtenIhCiTHt5e4vIeL8M3QWWLn4Ut2eRejkOb+XmW2SXHolyONFUIqSIpJjPvQeHgPs4u5v1VGvMsxsEWA74Duxb/oHcBpKkfcmsK27f2pmc6JioOugvOYfViVzRsakjpzTPGO8wzrnWDsVmBelalkY+AItBtdVKOI3RnEIs0YRpvmBD4FH3P23cc8UwEhXsaY+wGzokPcvFGpVu5fOzJYH9keE/2EehcJaGWY2pNkGw8x2RBusEe5+c/QtiA43WwGPoeIrfVDI3ApBOtQmJ2c76zYpwcwuAVZH3jOvo2JvJ6Cx2Y8WzHFuZnMB56BD3Ajgz/nZqieCdL0beM3dv1+6lq7jPwJ+hfJDX9DF36pNXmUYbbjvF2Rq2yHZi/RGKbb6A5+7+3ux79gMHbZB8/zrFoVbm/2diSv92GFmg1FKkulRtMNHiGQ+I3QZjEiHY4HH3H3V0vdrv6aZ2XQoUmNulKv8pgjFXwh5jD6PvCjnQA4Xy9bpHWsGMxuOyOILUAqFpiRPzD33AC+5+zYTT8JxQ/k5St8hU1qrk9D7d7y7Xxj9G6JogcmBG9z97iCna7f3h9FGjIvQc7i1u/87+s8BdkZntsuir7Z6TApI///p3G1m3wGuBf4K7OfuD0d/r4gUmAu4DKV8er4i8XuEIIpvQPP+9q6UMpjZAOAWZFBcDqWe3AHYFFgrjFYtA1PdiqWBxcOjfFEU3bcr8GegL3JYmBf4lrs/XpmwGRkZ4O655TZBGtqEvQJsiTZj26MF/Utgs6rl+wb69Iqfg1GBqReBx1Fxpi+A60r3DwW+iw4GjwJ9ot+q1qUL/ZZCYW/vAbtXLc//qMvqKPRw3ibX5kDh2yeU+heKZ/Yz5IE3DdA7rvWpWqdJQbdJqSGvoFeA3Yu5JfqnAp4BXkakc7+qZf0Gus2FwkvfQempelUtU25Nx6kv8ABwWXzuU7qePpdPIoK9b9Vy91CvR1B6tMFVyzMB9Cvm7sEoFdw/UdHnBxHpBTpsfw9Fub0EzNBsjOvUCr3i99MQcbAcqtHx29ibnAHMlOi/G0pLc2bV8vdUt9IYToOMA2/EfnFg9A+PveOdoXufZn+nji3k/RD4Tvq8leaTFVCaoG2qlreHOv0AmCt+T3VaERk4/o3I5WbfNWq67w/5+sc6cAyNc85mKPrtJ/F5EDBZ1bJOyq3JHDK49HmbmAuvB5ZK+osxre3c30TXDVCE+mvABtFnKMLjNXTmfip+1ppPKL/7xR4KncveAY5Lrk2N6pFciiIDfgzMWbUOueWWm2fSPLcJ0xBp8kZM+Jb0L46KOX0ObFS1nN9Arz4h/13AfNE3XWw2vwKuTu49GJHr/9cqBx5k9W5p4hyFH34KnF/qt2TzeAgilxct3bMocElsPPcsxqwuB5521m1SazQib3ZI+op5YnlEOjyAvE5qT1Q20W9uMnFe+4Y8t55MPvcqXS/mlT8gI3HtSWjk4flLZKA/uhVk/gY6DkTGtb8BB6EaFg/E/L5f3NMHpd95PuaaqaqWu4djNwJ5Kn+3tH88hzGJ8yGUyNm6NmAAsFjyuXi3CuL89dB5UPRPVtK/Njqiwvcbociow2IM5o5rsyEDzlvIcDMs+Z4hz8n7kBNNbffExf8eOZS8H/Pf7NHXN7lvLUQwP4eKz1Yu+zjqOQ0qRr5/fN4i5pED4vOAmEd3oIX2i60kaw90SQ2Kh8e6/RJwISr4WRCx29EgzpeoWu4e6FXeb/RPfl8f5fd+Ddgw+voC66IoquOBVeo81qVxG5D8brF2/R6t21OnepT/L7nlllv1rXIBcmvPhsjxDuC78blfcm3juPYBsEXVso6jXtMjD/Of0NlrZigKE/6s0AnlWlubFrDy09lzpmWJc0Q2jkQFswwdwI8FVi/dt1YcgnaNz+kBaEEUxtiBKtFXrle76zYptpgf3gZOoUSKI0Pc8zFOzwBTVC1vFzo0JVjjdyMT57VtyeFs23jOjkmujUFkxTheU/5+XRvyjDwckVltQ5wn+4mjkafdnMm1BRCx3AFsWYwlIlKubTauFeuyKEG0xmcDzkVFL98A5on+yZJ7zkFG4dOAWUt/r5Z7rBiDXihn9OPA8k3Gc1bkZPEMicd5+r+pWo9ElhVCzucQofVmPHOPEaQx2kfej/bEvwU2B1ZCBp6/o+jLguir23M5JSWvapQ+55kYw9mjLz3X3ImMHv8CZq5ah250K3u9GjLA3YUcfPaOsdw/eTZXiusjqpZ/LLo1fY7q9O6MBx2vRRGKV6AaRu/Gc/ez5H3aJta9u0iMdHVu6bNVeq/WQ4bh14F1S98pns9aRXKgvcdP6EySX4wcD7Yr3btKvG87Jn2j9amTXrnlNqm3ygXIrT0bsga/Alya9KULYeGF8hYtdJhFh9KOYuFDB6Fi4Z4OeWuc2OR7tSKLyvIwZlj+cFqMOA+ZPwXuSfr2onGg+x3wo+TaBejQN0banBjn61HI+9CqNy7trFu7t64OcnHteBR1s2mpfwEUnjknMEfVOnQhe0qQ74BIrDtQrYciCqdMnK/f3f8jt0rGcVbk8fkesHfSn3pILYKMxe8iL99rgIWrlr0HurU8cY4IrakpEXHAdShdzugoo+hfEKWLuA+YMvrS+b8W7x8iJl8GflzqXwp5UXaQ7KXo7IF4Zlz/SdV6jKPO30bRD7ehPPOdxgQZwTsQ0bxa1fJ2ocMysXc4DVg6+qZBKQVeRAaPg6J/OuBsZAD5Ghn9H4zxK/YmtTF0oDoiV8Xe6QlULHfD5PpuyJj9cLouA7MgwnkHVBS5cl260G/0fpCE0Iu+H8az10Gki6ARFXAvcHNd5o6x6DYQFa8+B+2vVq1atv9Rr3Ru3y3epTXonN7p/ujfggbZ+gMUrThL1To00amTNzWwRDx3Dyb3pPP99+P6K8DGVcvfA/3Oj/kg1eFnKMXdf1HarW2B6ePatcjbfPaqZc8tt9y6brkQaMb/hK6Kf0XBjgOAPYGT3P246DeUx+tMFNb5oLu/NRFF7jGaFbwxs2GIGHofWcb/UyqY9k/gTpE2HXgAACAASURBVHfffaIL3EOU5N0e5cieDx1Uz3b31+PacJRiZkV0CDq7GonHDjNbBbgVHcreRM/cOXFtRuSlvQeKgHgbuBId4kYAR7j7peXxNrP5gE/c/bWJqkwJ7axbuyOdH81sBCoY9hbwO1eh4GlQeO0awFGITDGU53xFYBl3/28lwneDUjGqo1GxsDsAR/PJoyjU+7GY8+dCZOtqKProhirkzuiMYhzNbClkpJkRHfgOdvfP456lgdPj2iMo5/5r7r5lRWKPE6Jg5E9R2qrjUMG+j6uVqmcws8WRx9oqiMw7yxtF+n4PLOju88XntCjcMUShcnd/swrZu4OZzYtI84/c/ZnYL04HvOIqWrcgeuYWRuN1cnyvv7t/Gb//DDi52f6zSkTBvZXQPPgZInquBV51FflcHxW5uxO9Z/cl3z06fh2IIsFqVaA1itxfjdawvYu1KSlKuygi05dABo0L4vrcSKeBwLPu/l7016Z4sJn9GaWceRQRkLMC66AUOYe5+7Fx3x7IG/trROaNRKlpRgArufu7E134HqD4X5vZIFTUeR4U7fu4ux8W9+yPDDfXI0P3dCgVRh9guKtofG3GrEBS7HIwIh+/QiRrX0T6Hw2c7u7vVyjmOKE0nxf6nY2MVsvFWPRz95FxLn0C+Ie7r5/8jSm8hsUxC7lK47YN2gP/y92Xj/sGuPsX8ftd6Jk1ZMR/t3w+rwuiEHc/d//MzL4N3O7uH5vZzMBi6Fw9GypuvT+wLLAVKrR+S1VyZ2RkjAVVs/a5tW6jsyfajijschcifyEiYq9HRN+ZaEO6GjqUPwZMU7UO3ehWeC30IkJrk2tHoA3ziTTCNHujA95/SLz16tbo7HF2LAp5uwptVkYh4mR4cs9w5MU8ksiDXbeG8nyPRBvjVZBXzIvAHqX7hsYzeSmN3K8dwIVd/Y+qbu2sW8hTqwiMCajn1eiA+n6My3XAQnFt1pgfv0Ze52+jQ3vtw2pRtMNbNNJwrRz6vYVI9EWjv/BYuwNYu2q5c+s0hoXzxBLAnxDh8CbyVH4UpQC5h4ZXWP/yd+vQ6D6iYwgt5nGOjGbvoXRa+yHCMU2j9kPk8XtY0leM0RExdsMmlrzjoNeqdE4f0wsRdE/GHFE8j4sgI+J/gJ8m3y97yNbJU3lF4IXQ5THksfw5Is4PB4bGfevHs3g7sGb0zR/z4zbJ36uVZy9KT/gqSR2O5FoxbouhfeXfaOSdH2OeqNnccTlKjbMUnff6q6Ocwx2l92wHlGanA63VnxBrYB1bMjYDgWejXYciUj6Nn9PFPbvFe/d2vJenUcOogCY69kXGqNuQMbHouxXtrZas0zPXjR6Tx1xxJ0mkdly7FKUIGpr09Yufe6IolgVpeKHXSl9U4+yq0OE+lJpwqbg2GeIPPoy5Iz2rzhXjuBdyJKlcl+6ew+T3InrjKEopFlFUwDWxPtwT991Ytfy55ZZb161yAXJr/YYIoTdQ6PZ/YzNZbJYXQl4NH8Si8BHKgbh41XJ3o0+x4RgEnBUbxyuJ4lpx7TxELtwZG+ifI7LykTpvLBP594gx2zw+fyvG56vYnCyd3Ls8cCM1JLuQoaIjNl8Do284DXJ51+Te9DA0OzL03IeIhzWr1mVS0i3knBwRQqvXbXM/HnRLDYqbIS+gFdGBZvOYB2+nc1G4VYEtkcdJ7UJqm+g4a8wLRVHZ78Tzui8i+ToYkzifvPi9avlz6zSWBakyI/KuvAh5x/4a2J5GrtS+5e/UoZXet02AfVB4+pJJ/5S0CHGOiMd3gVOBaZv9z1HKltsIQjb6eiHi+VGU87Y2YxTyrYxIgtOInNExL3wb7Qv/SmfifNHQ8d+U0rjUrSHC9b8xZoVBdChax/+OCK2zaaTMWQcZUV9GKUuepub7R2C5mNebpiBJxm2ruG+DqmXugU7LIsPgd5K+1Di1ENr/dwDbJv2zxty4I400NbV630Km4jzTCxlrbiHqICBnn21iDklTY0xOyeBGzQw4TfScGRmsdkrWqy2Q08nPy+NaxwYMjrn7XuRIsQlRFDiu7x7P4eZNvvszZKyqZbFnZJB/GhlrfhnP4UeoQPXOcc9kqPD9B+g8PSdKVbgfSolUW0e7kD/dhywZ79fvYm07Mh3L5L4N0T7rSWrMi+SWW26ZNM/tG7TSwrBNTParowP3Lijn32tEDk6UkmBmRC5vQGsQQgNjgX8uFvuHYrNyI40q14fFQt5Bw3OjloWNSrpNF4eAIu/kRohI+Ckq0vo5KliSepwPiZ+1OhTEJnMXxizatCzNyeVywcXFkPHg51XrMinpFvLNH8/d/YhQrtWzNZ503AQ4CZFEKeG4JvKouY3EQFXnRpOoABSmvggit94ADk2uXYcORQ8Q3kS5VTJu48XLs65rGp0Nhr9FJOQ/kbf8Q3QuMFYQ518gY+QYh9iqG9APGS3+QOQ8LY8ZDY/ymZFR/2NUgPC+2LM8RpN6FhXrtSIisE6mYTxLx2495N16B2MS57ci0rmWheMR2XMdciAZlvQX49QX1Yj5AoXjD4j+JZFTyTWISCrGrK7v2pJovzsiPo9BQiKiaF7kgPHjOj2DXeg0It6fGbu5Z1ngJVRYcfpu7qulnvF8/jbmissQgV68X/1QfuXPgEOa6VFXvUoyrhjP5uLxeZv4fEB8HoRq/SxUtaxdyD8QOZzdVpYxGav+wE3I2LYBDcPj9OhMdydxVqtTQwbcp1Bx4JQ/2ACdqUcS0bMxTtuh9awDcQmf0MRQUNeGHA5uRdxHX5Tf/E0UATYo7kkNc5NTKvycW2651a9VLkBurduA76Hwo2NoeDP0Rh6HL5AQ563QSov5t5En6LzxecrYhL0H3JDcNyQOCNMkG5taeTMwZtHPQcjbdS7k+Vos5v1jc/272KzcQoTC1XHTTJODJZ2Jha7I5V6l+66PzWb/CSVr1q1LPZeIeeJB2ow4R15OHcj7Z590jOJnQZzfDCxbtbzjoNfQJn37IA+p2WkQP79FRMML1Lg4Wju3ZCx6I6/XqZrNLaXvtOQ7iAiRl4A14vNpiLh7HtgxuW8ISq32HjX0XEPkyfOEUbub+4o91zDkkHAtCt8/lJqlU0Be2B3Ie7IgjAv5FwPWjd/XpZHaKSXOl4rxrCuZPCyevTFS8yVj0S/myOdICNqyTnUZs250fTD0KAi7ZsbUKVBKjF0npmzfUJ+9EGne7VyAaiJ8SU1J17HIviEqxP0OcGoxbnQ+tz0OXFu1rOOgk5V+DkNnmSOB78Z8c2By/5qocPKGE1vWnuiC6m3cCyxQ1rF071LI+PEVSh10MTqr/RdYpGpdmsi7MnKs2yTpSx1IFkZnzq9prN39gRmQI9euxP6x2f+jDo3O3MFwlH5mpWSOLBPnReRwref63HLLrXPrRUbGN4CZrYss22cCHa4CM71cBWJ+j0LFPgfujuIXtUfoMLmZXYMI8mfc/bm49l/kRbQPsIGZ/ST6P3T359z9HXf3+B/UqniTN4p+zhKfPwH+7O4vIO+u14Hz3P1LV/G3l5GH3opoM427exWydwdvUowoldPd/46KqL0B/NzMdon+4v9hUYBmauThZhND7p6gnXVL4e6PokiHmZDH3QpROLLl4e5XojQQ0wPbmNk80d8RBRhvQ57oawMHmFn/6qTtGczsh8DjhS5m1jsuzQ3M6u7/dhWEG4y8h/YCVnH3+6uReNJFFGwrxuIKlPrifuBmM1uwq/esjnP92GBmm6A0Cj9w99vN7ECUm/co9BweFYV4cfcP0Xs5n7u/U5XM3WAGFA32L+j0jpXRYWZDUJqZi9z9u+6+jbsfGePeuw57ETPrBawQH79AXnXFfmtJtNcoitfdirwMFwDOAeaJPdXD7v6j+E5X/48qMT0as1eh85jFWPRx95EoMmduROoV6Ch+iXWh8jHrCjGW1yJnizPNbPJYz3qX7lkDRRlNb2bLmdl6Uey1jvgIGaqK4oOdzsVR1A8UMVUUlkz7aw9X4e29kTf5bma2buwVPa6PQvv+Keq+DymetWKdStarrxF5vAfKm32Aux9rZr2i8PARKOXVTRNf6u4ROqyGDBfPlPoBzQ3R9zCwNXA8Kia5ODKGrODu/5h4UvcYC6L9/cNFh6uIaaHPkyj66DW0Tk8dZ9E33P2X7n5O3fePxXnNzI4ENkVr2gOuws993P0rNOf/HRkB9jWzwXWe6zMyMsZEJs0zvikeQQTyu8BKZjY0Ns+9YqH/PcptOwQd0nvXmQxLZNsAWYjXRxtMzKwfQBx6rkf5iRdv9ncK0rJuMLP9gRvNbFUAd/84Lk2LDnu9475h0Xcy8ryp9WZlbEjI5deBnyXGjmIzOhyFfx/jUaW9VdAOugVJ8AjyhGpZ4rx80C7g7ociD6IlgR+Z2WzR76H7X9Fh6efu/uXEkvd/QF/k4XSlmc2TGHduBPqZ2eVmtjFKXbU58Ja7v1aRrJM0gmAciMieWVAKiGsQafk34FtdPbctiDeQN9udQY7/HNje3Y9EBvzpkWFqbxht7H63Mmm7x0jklTwvNDegxtzhKOfrAbFud0Kz71WB2BNdAhyIiLuDAcxsCZTu4sK4VtxbEOfzIg/EmUp/rxZ6lfA50AelHBtDxoQceQ55NU+XXPNmv9cRMT6no/l+c+BcMxuUkEZ90DO5H4paPBhFun2/rnsQlAbpRbSXKozanYwe8eu0iJx8Lj7X8Tns0sjm7pcDB6D85b80s/VC1z5mNh9Ks/avOu9DgoAcZWYDzewIMzvHzE4ws6Xd/SMUZfMiyok9LIz7OwO/ISJsi3NqdVp0RpD6c6KIm1tibziGQaaYG+J/8Ja7H4wic5ZGxuKnJqrgPcd0aE17BzqR/578fg96DxdCUSpNUcf5sdDBzFZDhvofAaPcfWSMVWHALojze4GDgD1b7ZyTkTHJw2vg7p5bvRtNwi+jf3pUDfsLlIOzX3o/8m7dEJi7ah260a0IT0zzi+2MwqM/AuaPvn7J9duQt0LT/0sdG/Jm7UDehisl/VsDnwLnht7HorD1FZN7ahkSN476D0d5569J9UFGnWmrkmtS0627dwYRy6/TYqla6ByauQSq7zAcmCLp/2W8f6cDsyX9tdWx9CyluYd3jOftcWCe6JsGpel6C+WffJWksFpu1Ywfyqd/PzBX0r8vYxa1a6W1rKvnsqi7cTsqrDU4Pk+JiKJXYm6ZsmodeqDjH+Md6rIwGCJpz0Oh+rVMW1KSdyAiC0ahvMofocKYA5rc2wulyLu+RXQz4AbkLblEN/f1R4Ret6l36tpo7JcHo8jLL5Fn7GHI0HEi8qZ8BJgDmIcapx6LceuFiK4O4Kou7huI0j99iRyCLkPGuFqt3zRSAU2OCmIej5yb1kzuGYGI5a+As2Ic74j1vFZ1ELrQcRCqN/UiisZ5hc7FPmdHqeH+E+P1eIxXrVJWlXQajPZOp3T3rMbP4cCFVcs8Drr9IJ61Tbq4XtQBWzfewQ3jc633JPEcDij17RbP5kdEmh0afEgxd/aL53HeqnXILbfcxq1VLkBu9W6MWQ16HWDVZAGfEuUdG0kT4rwVWmww/0pSrA7lCH0lNmXzJ/0LAv8GflW13N3oUy7iUyzWq8Q43YVSJhTXj0ZE+ScoRLMtya4Yu+J/UdtDQbvqVppL5kW5DuemMwnWUsQ5nUm7i1Be2444JPwR+HZy/aS49itgzqplH4tezXJp9k9+34kGcV7UfZgixnMVwlCKSIlaj2E7N5Qv//LkYPp9RFr+LD5PWT741bkxZv7ndO4w5JX8Pg0CxWJOuQH4FonBqs4NEQ1folQYxftlpTl0EeS1dkjV8o6DXgORt+tIRLbOnFzrsvhgedzr2JAx8UtUELQwJlppjVgb5bW9GBlXtyGKorZKS/YZkwO7I6PNJ7Hm3Qec0Wy8qPGZAHnDnh7r843I67co2Dcnymc+MuaR21Gh3YWrlrvZ/xcRsP9Ae/nXY75/DTghuXeruP4eiuZYNVkj6kgqp05NR6HohYWQ4XA+tKfqAPaLe6aItW0ZVMejlvWmEp0mQ8btR1Gau+7uPSDmzpYoHImi3D6I56zLwtsobck7JDnd69aAAcjodAWKOH8cRdUsn9yzEzJ4P0Nj7R7DOS+33HJrvVa5ALnVt5U2+5fQIIS+jE3j8Lg2BIU2fgmcT+KV3QoN5V/soERkoUPQKyic9jSUY/Ne5EVTS48MOh80pyjGMVm0V6VBnK+e3Ls0SjkzT/nv1KXRdcTDOMlKDQ/g7axbWa6YI/4R79wjyNspnWsK4vxvKHVJ7Z7FJvpdHHPFNii1047I2+QfwPeS+44LvY9vhQ00SptwZfI5jbjZFR26HybxZM6tsrEqk4794uB2XnwuCtPuH5/7AqfGM1lbQivRJ50jDkYenxcAmyb9A1AU2EvIkLhIrNt/pwXIydL6fUqM1/8BS6f3oLRb94VetdyLdKPjEOSlOwoZEscoLNxKrZsxW6Z037yIGPsYkUifAtdULX8Tfbo0TCV95eLysyByOS3wV/v1LdUP1RI4HNWA+W/sTW5B+YlfAzYr/j+pnlW30vPXD3mN3xFzRJ+YA68NnY5P7t0G+CdK37Va3ccMefYeGOvV3km/hZ6norPNkl18v5ZrXPL8rY/O0GeU1rrUYDATSmPy6zqPVfl/jiLSR8X8OMa7E2N7IUr3enWs2WMUVa5Yl0HICeHBWHt/A9wT8/1TwJbJvbugNE7/pHGmruXZLGTbA9Wou65qWXLLrc6tcgFyq39DHpQvA9sDy6FQxscRsbVK3DMtCgPsAH5dtczjqN8c6BCzcXxON/47oFQtn8X/YW3CM6/OmxZkxLiC8KyjM3G+BvIK+gtJ2GadGw1ioB/yAlqIzkRsSxAGk5puTXS9FIXVfg+YGbg75oxrGDPNyZfIq2uyquXuQpfifRoeOo0oHXaWRQfwO+mckuUIYMGq5e+BflOg2gYdwDlJf0qcXxjXnyeHm1Y5VsWz2BeYMVmjfhnPZmGsOYDGIX0ZFGG1X9Xyj6OuV8Te4w5Ejn8O/CS5vhU6xHbEfW8Di1Ut97iOZfx+IvLifR8RCYeG/o8gwrxv+Tut0OicquWXwLCqZRrPY/YpIinPDj3PiTF7EO2VhwGLJN+p1RqPvMgPIYyhXck3rv11bcmcODnKS38q8oy9GaWzWqZuepFECCXyL4jOatuV9iKzowiIV4FVk/5tUcTYA8A6Ves0Fn13jzm9A/hR9I02GKLiwa8BR9VtrHqo31Q0jG6nATOUrs+A0nG9QQ33WnSfenFW4MzQ7cLYe1hy7SBUyPUu5Jj2L2oUyYH2ws+hehtr0NlQtT1KBfQ2sFXSv3Po8Rj19p4v6rRdFe/YVFXLlFtudW2VC5BbPVuyoC1a3oQhq/5isdF6lgjbB6aOSbfOC8QYRDcKjXuezl4YZY/KJ5DXaGE1rmVIezJGFyCPprOJcD9EnBeH7CMQKXlHuomuY0uexcHIwv8GDaJ1rfJ9rdTaWbcmuu4eG8iV4/OeyHjze0QwXEnng95ixftWh4YIyXmAb5X6i3oBa8Tn1EC1UVyrdcojdKheHVgPmItGmq2ZYq7oIDyWi/9F/Dw0xvSpYlxzm+hjVxAHg+IAdAkNkmdNdKAbPX6xfi+IIjlup+aEa2lOWAJ5664anxdGUR6jPeijf2nk7bUbMHvVOnwDnVMS9vsoOudlFM1yPSIZWjrkmwZx/jVwAjB11TKNxzHbAjlZvIZyFf8FRReNEYVJTTxg6ezR+tMYl7OBWaKvJfcgNPZYVu77pn+r6oZIxysoeVWjlHcdhDMM8oovzgSLxLXdS9/ZCqXFuAMZDWqhYxOdZ0aRAB+ggplFf7H+9UepM0+vWtax6NHlfI32XoXH/N9if7Usiqz6AyJmu6xzUXUbi25zoNQ6nyOP8rtQCsN70blns+Te/hNa1nHQaRDiB24iSZ1Tmu83Qs4Jz5Lsg1GatfdiLPvW7d1C6aaeRqkwax+Jl1tuVbcxKjRnTJows77oID0j8JC7vxOXpkablVc9Kq27qkH/E3nUXIEI9fPc/V0zO9vdO6rQoSuY2UzAe+7+Rcg+EIWAvYIWujfR4WbKQj93H1l8393PMTNHIcXXmNmW7v50BaqMATObBYX9foX0eBn4wt13NLOP0dj0NrOj3P3l0ANUvPUZlH/4qwpE7xHMrFc8d73RpuVzFKI5EDgSmNnMBrr7/7mrGru7e3d/sy5oZ93KMLN+yLvuOne/28x2R/PH5sjb9VLkff61mY1w91Hu/nh1EneGmRXho/MAc5nZ+u5+b3EZHUbnM7O/xpj2imsPAR+iA+vv6jiGZnYuIiOXQoa0T4DHzWwPd3/WzH6NDAEHhfw7uftXMabTokPeLe7+Wh31a2fE//vreD4fROvY7cCTAO5+m5ntjwi71c3sFLSmL4Ce21XcfZSZ9Xb3UdVo0T2K/YSZnYiMa/9CXta4+5NmdizyWD42/h/HuftD6N1rScSY9HL3Dne/CrjKzKZEB/X3ivti3L6uTtJvDnf/1MyKXMTHoL3LGdVK9c1RGrMrgSvNbCpElrydPMed3rU67JeL58jMBiNDxhBE3O0A9Ir94yutNr8X4xEfh5nZJ8Co0LXpnFfWMf1cI93nRca0XmZ2jLs/Ef3voqiULc3sUXd/P/aXIE/Zt9GaTfKsXm5mXwMPu/tnE1mPpkjHLZHzVTM7DxkCDjSzS9x9RDL/zR/X3qhI7C4RZ86j3f3H8ez1aTZvu/sLsZ7dhZwV9kURHy9H38ru/uzElH1sMLOrkVf8ymPR7SUzOxKlCtodkehToLPPre7+QPKujSx/vwrEHvc+9M5s5u4vR7/FfG8uXG9mQ1DKlnVQBC3ufqGZfQX8zd1rdc42sx8BswE7FWeZVpvfx4bS/J+R8b9jfDLwubVmQ5bUa5DF8UFkNS28mBZCHidpDrnCsj8YESwHVq1DN7qthg5laf7uzZDnz33ICvx83DMS5TC8HlnE16Wz9XsHtCmthdUYeZ89QaPwYAcKKf1ucs+paBN9Ho1ULYOjf11qmvoi5Cw8ZPqjiIdLgEWT62sgL8oHSSqzUxPPrUlVt5Az9cIo5ovp0CZtFkR8/YRGlMryyOjzFXBZ1fKXdBmMPEhuR0aoqShFmqAULM9RCptFnrAvASOq1qML3W5BXuK7IS+1pVEY7RvI+2yjuG96dIj7CuXr3QeFEH8KLFe1HpNyQ0TBRSjya+6kP/UcXRMR54+jtf6Q5L2svacyKjD7LI1CfZ3WX2TMOj+uH1G1vGMbr26utcT8Pj71QvvP7er8HI6vMaNmnoYl2QaiM8DtKLXAd9B+sgPtH1vK47w0P/wERag8HLoMjf7aPnM90G9rGnv+xZL+S5ADxi5EqgVk9F4SpWcZkdxbu/kmWZf6xr5jyXQ8kWPXkchQehsilvelUUizdmOKUvd1AL8v69nNdwYjh7Wl4t2sXXRzzN1HxvP2h7HpNra5o45zC3AZOvf/GpiuLGfp9+vRuW1QHXUp6XVdtLb0MKfzGXRYeaxyy+2btMoFyK3iB6AzIbQVUTwyrhkwFJEkbwHrl64tjAjnEVXr0YVuK6Nc5GfQBTmMvF9nRARQByKM7kJe2KMIgjy5f1tqUPQO5Vb7J/BD5HWyIvKE/yjGap/k3lOi726U0/YsZOxIDQm1WExik5ymxumLPBH+jQ50k0V/YdRZLTYpDxA56eva2lm3kp7pZmUnVHBqmqRvVeQxulLStxs69BxCQvxV3VBhwb+iw9nsNIwdxc9irFYGXkAevhvHWC9Eox7ErFXIPxbdjos5ZDE6p8DohdK0/B0R50Wqj+ljPF+i4fG7aRWy59ZpHAch4+mJTa71KX3uW/pc69QsiZyGoqL+jNKOFekH0gPr3Cgv58fIsFWLNa3ZeCAS5DAUqXcasH3VstVBr/LzWofWrmPWRM/9Yq1arNR/Og3ivEj1V7t3qyRzOi8cQCNV4Z+Qcf5pIh1QHZ+5LnSaHlii1LctDeJ8qaT/FkRkXhhr+Q9iPX+wznN+sp8ahFJ3PBf63QN8m4aTRUGcfxDXD0dRmgPSv1OXhqK7fooifP8v6e+KXE73Y7V815L/9TBktPiyJ7ql+sW6XjvDTZMxOBc5n50FTF8el2SNOD7m0NrmBUdOFlOhqJNOtQHG9n9olUbnM+gvYz6sTarP3Fq3VS5AbhUOvrxcb0eE0GxJf+/SfRsgMuhF5BE0GFgceXa9nn63Lg2RWCMRYVyQkb1K96SeeCMQCTQsFvL+KF1N7fKGAscismvxZLEuvDDWQN4075Ic6mLDdl/0P0bivVyXhrwFPwNWKPWfhIjlD4H5i2c02XitFs/mv6lpXuV21q2kT7rRvAIZ1Q4jKWqEPGc6gB/G5+nRgfwESqRe1Q3YFHkvrTGW+/qi3OYPhW4fogPfq9QwByWq43AP2uSn82B6mFkjdPgnMDi5pz8wJ8nhgZoe7Nq9xf9+bmQs/Un09SvdMxjlRe2frBO1HS+6IDxiXlwJkT9vAsuWdYnncoYJLeM3HatkPJ5Be6q/xnr8GfIQrZ034aSqV7vr1kTXU1DKwkLn/sm1PyBS7FzC47wVGjJ6Xw3skPRti/ZTL9IixDnyEr8l5r316LzPSonzJZP+i2jUyHkBGQxqWzg4ee4GxZ7jNmATdA77Ep1rtqNzvZUjkQPQ2emYV61LyDEQpR8cHJ+HIcemHpPLdW0oneK+wKB2062kZ0q+FsT5mXSx90VG+/uqlruHuj0L/Kab68X7OCc1rxPQTO74/dpYtw8lk+a5jYdWuQC5VTj48C0Umr9WF9fTyWcTVCimAx3QX0VesHUkhJZHXhYnEqFHNMigxUk85kvf+Zom5FidNpjIC/Q2lF4lPdSkY7VqbJYfAOZL+qdF3rIzFd+hJuQJSt0xH7Bl8T9PN7/Az+O5uwOYM/r6JOO6Lgo1q81YTQq6daPz2TE/rEYSLNWsIQAAIABJREFUvRLXJo/rHYh8eCI2owtXLXcTPU6OzWWXIYyld89QvsYDgR2poYd5yDkPMipuHJ/Tw0GxWe6DvPQ6CNKBmhk1chv9zD2I8mYWff2Saz9ABMp0VcvaA13S53BTdDDfh87FtZaPte1NIjVQXdaxHujXB5Fbfy2tzdfGe7ZqOq5Vyzup69XuuoXMxT7jZyiyaLnkWuHZuzUixN5ARGXtQ/pjDb4h9lVp+pI+KB/4fxBxXqQwqSXBh6JI30FpIrbt4p6uiPN5gOVQNGoxzrXUM2TrC/wWuJmITgQuR7U6/oPOndslz+XMKJVmB3B+1fKXdLk45NqVNiOXkTPFByjSua10a6Jrt8R5cm1xFM39s/hcy7UA7Qn7IiPavyillGxy/7Yx/8xYtezjqOdJyFi4PI2oiP7UILVubq3bKhcgtwoHXx7L/x7LPalHw4yIaD8c2JIaEkKouEgHyjE8bfQV3uJL0EjBUvY6nxOlHNhsYsr7DfSbDeUVHjGW+4pNdK31CVlXR+Gyw+NzP+RNuDfJ4Qyl7nglFvuCXO7dZCxrQy63s27d6DwfMsbtQxcka7xve6H8xOcAC1Qtd0m+gji+CrhnLPf2Qgfx2hkQu5F5ahSy3rQeRaL/sNgwn1y1zJN66+rdj3liF2QEuah0bX50kLu67geF0l7jKkSKv408CTuAo4GBcX3FmEdfIUnzVPeG0t09HXNjYdj4bozdvvG5Fp6SWa/21K2beWQR5GxyMaVoDWQIPhUZ394BZq5aj7HoOADV4PgIkXvF/qs4C/RGhcefjzlm6qpl7kKPhRBRfBrh7BL9hcd4OVp2DOK89PdqnWoBOZhcDHw/Pl8Wc/xsqBbOG8A/Qtf+yXcOD93PqFqHkj53oXPlbrQBuVxao+9GEZVtoVtZv1J/M+I8TdUyFLgA1YypHS/ShU4ro3RB55fmkVTXoSgK+CpawFCayD0ons8jkr55Ym65DTlU1urMmVtrtMoFyK3CwddG7MnYQHaVWy3N2dsKnmpToHzf7yEPuyHRvxQqWndWV5N/fOeoqnUYi34zxkbloPhczllriMSbNvQ5kxqTJcnCfVayCR6G8uh/gnIop+TyobGJvgmYI/pqeRBoZ91CtsEkRYOT/tXQAWaV4plMf8bvBfnVt44bahpeWSeiQ/VYCXHktTYi+Vzn925q5EH/F8K42MV9/UKvy+Jzp3RQuU208Sr+75MjT7ujEJFVRA3NiEitkYhMPgClW3gCRXO0zLiF3C8D6wNDUGqCE1Ek2IlxTy9gBeTx9iwtQFrG2rxIzI1rR19RzO+A+DwZqsGyTtXyTup6taNuyTwwABn0N4k5pTAG/CDes0vi/eqLikMX9UZmDd23r1qXHug6AyoA+hnyXi6I5tF1SWIsXyOp71OHRmPP9AtE8sxSuj4AeU0uHs9fodP2MT7XAEtXrcc30RvVyuqHogH+jYpYF2P3m9DvY2C90lgfCCxYtQ4hT0pC3ksbkcvtqFu8T1PG7106JyS/px7nc6O910fAolXr0kTudZDB9xi0L5wTnd0MpWfsQGfU6UrfmzLeqQ/pIhtBHVvoNT06tx0R69de6Mz9MCrW2gEcWrWsubVeq1yA3CocfHmaf0ojDK5LL1YU5tg0NLBuDVkZb4pFbDOUB/XTWOjGIMzRwaAv8mSr7cKeyHsf8FDyuSvr+KvULGSxJN9KiOQ5mVKhVlSo5DJEOpfJ5UPQZvpBahoy1s66JbKejfJslg03a8SGeXuaE+aboU12KxBdq8cG6+ix3LcO8jJZamLINZ502zV026fUn3oTLYyIyQPjc8vks22XRsNwPRjl138ERXI8hgjjueP6jIj0uh8d6B5FXkIFUVarta2LuWGK0Ou40nM4BB2AOoh6HOhwNJwwMNatJeNW1u9pRLLuGPocmFxfk8jlW7X8k5pek4BuaX72R2gUUXwSkcdF7Z8dENH8HvLsfRORDUVNgXdJUtJU3ejGsQCRJ/sjQ8DZyVw4upA34VVPDQ2KyFvyqpLMsyKHp3/G+N2NIo0K3Yoo02Orln8sunVLTqICfo+T1OhAUYlHIKNO2VmjVlGYjBu5/Luq5R1H3fomv3en2yfArVXLO7ZxQhG+T9FI1dRT4vxtlDboE7qI7qhYtyKn9+vIIesLtDc8BaU2Ggz8Cp1V70Xp8BaM+eQ8ZJzaPP5W7ebHkKsr/qPYL74JvAQcTMM4fCPitGo1Z+RW/1a5ALlVOPiwTCx2VyZ9Y0wiwFqIOFmlapnHQbdBsRB+Ee2CLnSbLRb3YUlfrciFRK5i0/xjdAg4I7lWJi4XQt56ByAr+uyUCsRVrMvyMS6nJAvZ6ENB/JwiNsfNyOUTgd93tWBm3SaKntPQqBkwnCRkGG1A7yPJ+4dIrulQfvYzqDlpToNkOBsYBezSxX1DUdjfndQ0zLsLuWdCm+pR6MAzeen6ZCh/bUfMN+8gInZo1bJPag15g96PCnfPHn33xNi8S+RapkE4zFaaU2q1pqEiabcBcyV9FuvU14Qhh86EydwoR+WFdVrLejBup9I5J/u5KMXaV8Dhxbih8OF7gT+2wNzflnq1q27JvNALuBL4M7ABigr7O438xMV6vjBKIXdirA3F969Ea3stiu3S2bC2PfKYvAYVFS8KME6JiPOv0Freu/zdurbQ5UXkeT01sDEigTriuTsXGTbeBjZIvrdu3eb8kl7FvngAcqL4Hp3rBfRCTkyvAMtE34JoDVwnua9WpBclYpGeEec/jfG8vGr5u9Gr23elG90ODt1qG/UQz9ph8Z6N3sN39WzRmTj/LUq/U8d6TDciY+86MQf2RbzAFTEmNyED3ABgC8TxfB7z5DvoDLpO/K3a1D/rZizmR9FRCyR9G4X+Syd906M6F8e3whqQW71a5QLkVuHgy8r4W+RVclzSn1qRC0LoLsIjvVVa6HdlLBCjF/Pk+qzIg+bZVpo80eb5z7FJOanJ9cmQx3JHtFeQZ9GQqmUP+SZHHsod6NCWenUtSefCg9PRIJd3pDMRVJCatRm7dtatG513D722oFFwZSPkqXY7MroNQcaEi4G3aKF8cigE+kZELh9K58PdYsgg9yE13Dj3QLdlEOHzdYzN5jFvrh+byi8RmfIDYE9goaplbvdGyZiEDiw/ijm/SNt0DYok2ht5Or1B4nFdmnfqeNjZFIXaD2py7RHgruRzSpz/HfhD1fKPRbeUKPlezI3XEXmVo//meOfOQt67P0aEUJpKp1Zzf7vq1e66JfIPQET5lSTh9og0SkmvgmxO55C1gEsRub7YxJS7h7odF/L/MXR5FRW5WyOuT4WI889inastoVzSa6uY298PfTpQFOIPk3tmQp6uY9QdqZOeaK+0YfJ5SLw7hRFgdERb8sz9GxlprkcREQ/WSaeSfimB1x+dw8rOTM3I5alR+oha7onpbJhaJMZl1WKeGItuUxE1murYSnPcT+MZvJtx8zivXdpatGd/Fli2i+vHo/PMJTSMBFMAC6Bz64w00tXUlTBPn8tLQt+OmPv/VMhf+s4cyIP+NcZSADW33Jq1ygXIraKBb5ByMyKPtU8QgT44uWdJGoTQIlXL/A31HIwIrw8RMVks5rMBf0NFZTrlOqxzo+GxPDOyln6FSNq1Qqf1kJfNSBRqtQUiXGqzIUOHtGUROfIcUcgNbao/QSGYA5P7p0UHnU8RSTQguVarxbyddUvkSjeMM8dzdy3yuNgy+vsjAvYlRDR8Gr+/RA0P3T3QeUnk4dqBDnJ/BP6KSLxn6qpTV3ManQ8LC6BCWkXBxc+Q9/IDwMZV69ADHcd4T+r67vRAlwVj3li81L8tsGv8flo8g4vE5yIM9dU6zfM90LVYd48hPIGQR+X+aL0+vXT/LMBDlFK31KnROZXOJSjn6ac0PLuWS+49H0VujIp37SLqm0qnLfVqV92QB3w6x/dCpP/rsV4V++B0v3EvIsV3JTFmoYiyUxBhWTvDMDJyvIGKsxae8kVatTTabxrkUdpRRz26ejZRbu9L0H7/x8BsyXVDjk2vAKdVLW83egxGkUVfEXsKZPi9BZF0S6H6Kv8BTki+tynaW96DzqLFu1Y3D/N0T3wESv3wcMg8TeneglzehYaBqq7rWUpMHo48lz+Mn/d1odu76MxZdlKr3Z6sNG6L0TiL3UpEn3f1rNXtGSzJdi5yWCobbVJ9z0Nns29VLe//qOvFMW9sF3PJD1Fq3n8Qxo+47xi0Br5MTc9rudW/VS5AbhN5wEsb6fg5E6qO/CkKy7kTHQieiMWxJSaYrhZllKqlIM53QCTRPSgn4BhV6OvQygtyadyKQ950wEmIiCy8yt+JsdtwYsn6TccKEZFPIQ+S7VH+tLNJSOXk/mlpEJW123xNKrqV5L4NhfBNhcjz3yHidcvknsGxidkP+A5RuLBOjc5ehsNK19L3rh/y1LsodL8udKtlnu+S7GtTypFfftZiXlwPkSbLFHohwqWWzyWdDwFGzT2se6DPSjGfv0BiqEbkSX9EHD+LUjoV68ACyAvxI+BPVevQAx37J78vhSJSniYMBbGuXR7918ez+N14796j5h5CKNron+jQuhnyyjsu1ucb6EzCDkZhxZPRcGSo1V6k3fVqN93Qfv5zYKtS/yaIMOgAfpD0p+/jXSR1A5L+IdQ09RgqlnkfjdzkvWIs7wJmLt07LTXzfO1qnaJEpNJk7xj9KwPPp2Nax4aiD+9AqWS+jVIgrU1nB65rkAHgxOR7g+hM3tbmXSuPHzpHv4xSyxyDHEmeYswii3cW7yE19eQtyXsIMqjthFJ9nBryv0iSgjHufQxxCbNWLfc4jNs1Mfc/QyOi4w7Gkqqljg3tE+8FronPTYnzWMdeAG6uWub/YdyGxzO4GY0o54XROfSyYm1DqWkOQI5P81StQ26t2yoXILcJPMBJqpUurhfE+RDkrXw2cDU6tG5PDQmhZNIvPEjGuomiQZx/hLxtnqCGhDkwRelz02rcybj1i8VvA0RKLkKQY8VmrA4bsiZjVmyUl0DFfjqAP9AkXD/5G0MTvSvXaVLQrSRjSi5viLzp10r0nRkRyZ8AW1LznOVN9LsI1TcYXLUs40GXdGN5PPJMXoGuvWZq+cyNRceUMN8fpR34I8rDO0bB51ZoiPBZGR08X6YU4YXIvK+A9YtxQwfvG4FVuhrfqlvoNW2pb8X4uXWsx88QxbSAGRAZ9h8aedufoAUM+MDOKPx3eKl/Txrey8sm/SkhVNv3sF31ajfdYi+xZvzerzRProH2v48BGyX9KXE+umBmnRuN/e2twF+i7//Zu/N4Xet58f+vtaem3aBZiNIk0qAiaUBHCZVSIcTRQaaKhDgcHBmOIQ4Sju8xpAg/h2M4SCVlyNBwKmmgQaNEs6O91u+P9/va9+e+1r3WXnu36/rc93o9H4/PY+913/faj897X9d9XZ/r/ZlWJJKUP6PXDj6UwcsYVnHc6G3AOm196LUPF8+MBTbPWH9c47Wf6IwqZ1Y+jRiwdFNe0zfN15u28/pEAvNq4L21HrMpYn0vMUvsCfnz0UTn1W15H2snzr9HsdRfrYXo2DgfeGH+/PS8Jn6emN12JZNHnO/Udb2XIr4PEksEPZFYKmcsj+V1ROfGtCPOayvEnlKnAT8vXmsPkJlDDMT4BjFgYYUHso7LENMqDBgISOQ87qS3z8/mxMCKk+nNOjqo+PxKXcdiGe7SeQUs98NBjYvh0yimIGZDeODo45obIgPqugbwAmDb4ucfAbvN4HcX5s3kEuqcUrsbMZ20SRx8gEgUVLHp0nI+ZqfTW7pke2KZi8uz4TKjh4cayijHNk0dX0Rs5HkKk9dfbhLntxPTpqvdsI/+ZMKR2XDeiRl2NObfq7t20p8wX5uYknjIkuIaptKK8atEwuvL9JYguHAm37eaCr3Opzl5L5iUOCdmdVyXDwWPIUamn0H/ptDVPdwRa/N+hl5C4TvEupOr5M8vJGbllInzVTLevYnO4KHYU4WYVXMHuWEu/Wuyv49IOHwdeFzXdTWu0Y2NSJ78kkhClh3eexHJrp/Tnzhv38uraRsvIc63EPukPIVoL/+c3iypdYnldv6DSvb0adV9KyLpv2P+PKP7FbHJ4iuIBPQv6SXSq7n2E5sOforYB+Yhxet7Ec9si/f3Kc83InF+CtE5fHjXcUwTX9kO3DDvyYfkz8dk/Z9HtJfH895W/T2MyTMcnkkklufkd+xu4I3EiOY3ZWwXMeA5dabnc4exrkQkxj9PjEZePHOI3lJO32dIEudF/Y/Iuh8y3bHIuC9uH/OaSp53Z1IshVa8t2fGuQkx0OLPxHNAs/zYHkQ7c7uu47CMRum8Apb74aDGeobfyMbjFkQS62qWsI5f+6Ja4w2P2JTvrIxtN6KX+4e0RrFN8/ur0BuxUdVDAbAPMSLhrLyZ3c0QrCm8jMfsNHLkBdGz/zgiafI7hijZNcqxFTG2R6qNEwmGDxevlw8QDyVmq4wD+3dd/xnEtxcxFf/1XddlOcd1ODFF8X+BTbquz/0U49H5ndu5uK6/IM+9o+jNAhm279wcYn3GQYnzF+bDwTgx/ftcekmTKuMEnpD1/XFeL68lZuKU15Yycb5t8XqVMU0T6wuJTsP9mDwLaU9i4+ebiUTeWl3V07hGLzZ6U9Sb5Mk7iD0qPsXUifPq17RttS/aSb098x5wB5E0b6bkLyQStn9kBoNqOorrZcTIyNOYYWIH2JhYMuhiYh+qGgcA7UTMbjsTeOeA9/fIc+9OYN/i9SaWDYB3UWmSsnXfelz++VJikMJTiY7tFxef+V7e/26nwo0jp4jxlcTgu/lEHmEe0dlxIr212OfTW87kBmJmy9Dcr4mZEFcAXyxem1/8/WcZ2/k1X/cHxLU90W48D9i9eL28Bzw4v59nEUvg7UOlA/SIJQibc26H4vWtieUMv0VvhHkzEGOdvD5+d5iOnaXu0nkFLPfTgY3G2BVEQ/964JFd12k5xvaSvFDelQ2vpZ5a1G5411KIhM+fiQ06juq6Pg/kMSPWAW+SJjsNS+NrFGOjN32vHNG7fv75Ynrr5+9U/k7x9w2Jjp8tuo5lCXG+gXjYvpWcxkdFD5/3Ia61iWTqjcDFxetDH1srzpOJdfVXy583ysbzF2lNxaz1O8fUS+bMIxLn51MkzokRXpsCryI2em6SfFUeW3oJvB2I0Xd3AP9UvF8+pDaJ8wupfFTvVG0IYrbRVcQMgC3oT7AcTGzk+mZis+4dH4i6GtfoxkYsx7IPOYo1f/4Ksf/B6sDrs96fZnLi/Cqi7bJz13FME195fXgxMeLweODA4vUj8x7+S2L/gxcQI8zvAQ7oOoYlxPdyYibimfQSsFPeq4h22T7EII2mo7ia5HJe528FPk7RWc/k9uSexEj5G+lPnM9v/XvVxDYg1lOJJeHWKe5z/5Ln4UOLz51MJO/OptI1lelvvx9L7AG2b3GOrUt0tB1TfG5n4l59eM3XkKzrwEGBwAlE+2rX9jlHtC3PJfYJe0TXMSxlvIcQz2m/YPAeFW8lNrS+k+jMuY2Kl+PNv7+HyGcdXLz29ozzd/Q2lH800cF9M7Bl1zFYRqd0XgHLcj6g/Y2SXxDJ1/Nn0hirvbRiu4YYiX1uEVuVifAZxtY0TA4kRg/eSGxu1ExVr2Jt8vvjmLU+s12er39hCTMjui4jHtvBxPJAzXl5JjFaphl9d2g2VL5K/yjYsuFd7cNOUcdtiOnR48BnBsUxrIVYvqMZ4fSeYY+t9V2aQ0ytvaQ5bsR6hs30zGa0yVuAt3Zd92liakbWrUI8xJxIbLrVLO80h1irvC9xPuDfqfK7Vlw/5hJLtIxnm+QnwC7F58rE2POJB6OfEx0E1d33iuO2IM+7XSmWt8ifb83r5gFEUuVJxMi1E4DViIfVN3cdy2yIa5RjI2Z//YJY0mIjIgn+Q3J0HbGUx9EMTpzvR8xKre76QST+n178/K9Eh9tPiY7RG4D3F+8fRiz7dHteK79DsfdD1/EMiK9cR/4oYoPnM8l9jAbVeYrXqrmfE8m4bxMdGwM3jqV/6aNn0EucVz+rlv4E3q7EKOud6b9/fYkYsNbc+9bM79ghTLGZa02FmKHxHmKkeRnvasRzzknE3gHrE8u0fI/ehpnVfc8GHLd5rZ/3ItbX/wb9Gz6vRczSP5BctqvG0v4/p7+dfCjR+XE7kUT+p7wXfIne3lMbEh1dNSbM27E9Mb9zv6bY6JqYlfKn/N79ihhhfzm5ubzFsrxK5xWw3A8HNR5QFwL/DhxHTF08m14v3KRGVq03u0H1JEbSvClLE9sOwxjbgJvC2sCW2WDpO27DWpb2mBE7Yn+JCh/kZkNs2ajcn3jI/hoxFfgPxBILZYPsZUQS7FSmSJzXVKaqFzH17wfZiHxj7XHMNK58b8uM7XrgDcMWW1Hf8iGnXGLr49mI3icbzV+hN+r8kfnze6h4oyNiI+dLiETP5UQyaBHxcDOX3lItvyESYtt2XedlOGabFn9/MjHi/CcUyybQn8zbl0pnx9EbhbYqkSC6nOgIvTLr3Zx/u+R18w5iFtJNRKfqXGIt4xuA53Qdz6jHNQtiW0Bsfnw9kSA5k1h2oPz+lYnzvqVa2v9HNRTinnwJMVL8qRnjr4jO/PnAw4mZbLcAHyl+byGxPNxqxTGtbsBJcT6uQSSzvprnY7OEVbNHTlX1nkFcDybuUYeX9QfWIzas/irRqX1s8Tt75zk7TtGRWnMhOuPfQezT0XTGNbHuSnSunUIklU/J68iGXdd7BnG9mhhN/kdg7+L1pr11aMZ2LTHC/G4qX4KxdR18GzF6/PT83q3biuvXecxelufqLdSZTP4ARSdT+zpB/3PaU/M8/RPRKXwd8cy2Z9dxTBHbHOKevH3x2heb84x4hr6cSIyXa7Y/C3gt8UxwyDB83yzDVzqvgGU5Hcj+G0P7AtokYM+hfz2oFRiCDRLof5hubwRRJpfL2NYFntJ13ZcQVzkqdzVa624R0++b2JoR53Oy8XngA1XPB/CYrUdr7UkqepCbDbEVdVuB3trQt9M/KrS81jSJ85OpOJnXqvMGwGOJ5GuzBuxWxOi8q+hPLld7jLJ+5TVkP2Ka+nuJqc/NpnZbZ2zXMISJ89axezeRIGquhwcQD3h/A75bfG4d4qHoUipMvrZiegvxENcsv7INsfzAOPC6fG0eMR3/OuDrXdd/KeM7gei4OZLeTJWn0EucN6Pq5+f/RbUP4fQSI6sQm5/9KL9rm+R18kri/tysv7k6sYTO6/LPJvnwJeLBr4oH8lGNaxbE1tRtNSIp8n/Af9HbuK4cAbsmsVTL3UTSpOrrP9GBcWbG9Coi+bhu8f4jiJHzfwaOL14fin0siI6Ni4h780HEOsQfzHiGMnFODKy4Gzi09dr5REfwLUTibhz4bPGZfYj7RNXtrazrPxCdU3cBJ+Rr5fdsZWLWw03ECPoLydkDtRdiWZZL8rr4lAGxLSTWoz8F+Ajw1Hy9+nOU3obxnyU2db6MSP4/Ld/fh9hI/m95La3yuBEdhuNEJ+I/FK9PuyddXv8fSQzMW3Gqz3VdiEFoJxHPK9sRMwD+SuyB09zvysT587usr2V2lc4rYFkOB7H/AfXFxNqLz2w1MJsE7E/ygjOf6JG7AFij6xiWFBvxwPNOopH8fIpexFZsuxBJsbOINeSquiFMEeObiSmn1xBT9MtRu01sPyemUr2JaHzu3VV978dj9pPaj9kox5Z1L5OwryVGP92TDZdVivfKa85h2Yj7T4qpt7WUVl0/Q6wrP56Nrk+Qm9/QS5xfzZBtCkokym8l1oO+hXg4+A7wkHz/0RnblVS8XMmAuMoRM6cSDzrvon+90Ddn7D8jptIemZ+9Fdi66ximiW2VjOVTZHK8eG9t4qF0EfDEfG0OkVCvPrFQxPFlYuThC5pjRu/Bpxlx/jNidNen83u5edf1XkJM84gOme/Tm5b+1bxu/IR4wPtHMnHZ+t1n5v/Jn2s7N0c1rlkQ21he3z+a15LriKRWE2fZyb86MUL2x1SaNKf/fr0rsc78ONFGnp/XwaYd9vC8btwIfKLrui9lnC8k1tzt2xweOCLvXT9mmqVaai15vK4iOgA+RySXrybudSsQs9++kq/vNt3xr7Hk+fc6oi11I7DBoHoTScqNqHRpj0HnVMZ2BJE0/j25aSmTBwctnr1BhTM5BsT1WiZvGH9AXlfeSm+2wKrEbImNazxuRd23ymvEb8ik/1THdLrXayrF+TSP2Ffk1xnjjfSPOh+UOD+o6/pbZkfpvAKW5Xgwo6F8e97wxvPnHYv3X0UkHf5CJGFvp+LRoUW9VyGSQdfkjbxZS7lcf+xVxEYQdxHTay+ktaFMjSUbX38mHuhOJZIk3yQTJfmZlwMXZ2w309uwsNob4Ygfs5GMjf6H1fWJ0dibEEnx24nE+arFZ8oE+0uAR3cdwxLi+0Iei1cSUxY/SIwG+jWwen5mS2KNxjuB13Rd5xnGdVheQ55N7yHn3XlevofeA8GjidlG1wMbd13vpYzxXcSooJ3JpVboTwa9jFhG6Lb8bn6ZyjcAIpZL+Dsxsuml+Vq5zu12eb0/ZsDvVp1YKI7JdURyvLxWjNF78NmN6OD5I9E2qXINyta1cXXgQ+QIJ2JU1NXEg+yDidGjfyAGMKxR/N5qwDHE6NkqrpWjGtcsiG2qpcbmAB/O792X6SXO5xAdcRvmz2PT/Ts1xUXcq79D7IXw7ObYFteQDYnp+7cDj+o6hqWItdmgtZntVl77P0Tcv0+n2Gy95lIcj02J2RyLMr6Pk7OJis8+LePbq+t6LyGmqTbpLpPLv6I38KJvqZZaS/t7Rv86801sfyTyBOtP938xDIUYXf4/zbWdSIoP3DC+9kKvw/CxRHt3RonzmgvxTP0/wMOL15r9mK4prx/0tx93JGZGXNXcGyyW+7N0XgHLcjqQMWXHzyfeAAAgAElEQVTsXGLjog2JUQzjeSHaufjcgcQIts/X3sAsGvYvIqacbkxMD3texvb9Vmz7ECOx31E0Xiat3VhJTM2fHyPWU2tuhAcVsZWJ8+2IBMPikSc13hxH8ZjNktjKBMNHibXM98qfVyU2kGkS5yvl6wuI5RQ26rr+M4hvV6KDY7+i/lvQ2xxtpeL4bkOse7hpV/VdmnOS2HTrFPqTPRcTI8ubkebNg/ljKDpSh6EQDeofE3t0tB/25rd+figxUmXFB6p+9yGu9YnkyB3Aj4vXy+TJVcBHu67rMsb3MWIU+YLW630JO2I03lYUM+NqKsW9eW3g5fn3xxKjXvclNp/ao4jnxLwfjAPPbP1b86lkZt+oxjULYis3NN2G2MhureL9ucTyTtcRy6Y9mFge7sfAF4vPVdV+pL9j7WD6l/jYld5SLU8u4myO38OZYpPk2kpx/XsGMajiBcV7TYfwzkRH+F+Aj3dd52WMc0taS6MR7ZW5xKCSqjfqo79N/GTimXoPsvOMSC4fRdyjf8GQJJdb37NXErmA3xCdbc3GuU1sVw9TbIPqmNfJXwKn5s+bMXnD+GMoNhWuvRT3gJFInOf1/iRgYfHai4jl0c4j7te7ts7d5tq/E9FxNVQDgSzDWTqvgGUZD9zkG8NBROKkHH33bHqJ8ydO9/s1FSZvrPJW4GOtz0wZW60xti74DyY2AToHeEb5fiu2YRllMpLHbNRjK+PKv59KPMy8nmLtVnqJ89uIEb3PJpY6GQe26DqG6WLKn/8xG8rr5M+PIkYJfRlYOV/bq2hEV7fMTNarPU12ZSJB/vmm3vnzz+lNG342MROg6pkO08T8YGKa5tsH/R/ka5u07n1VPTRM9d0nklkfIkZRntJ6bztiVsCkkea1FyI58k3gl9N85gByhkftBViRWJf3fPqXvXs7Me27TFp+NF9/26BztaYyqnGNamz0OgNWJUbiXUGMmLyZWAKpmWk0N68rNxAzdC7OUuU9gP42yLuJROS3KZZqIpa6O4tInDfrLS9OnA/6t2oo01z7H5pxnkX/jOAxYiO7LxLJpCrbjdPEO2i2QJmAfiTRPvnaoM/WUOh/VjuF6ID6C9HJ8TvgJc3niFHZVxPPcht0XfeliPE4oj1/ch6L8zK+V+T7YxnbFcRMnAd3XeeljO959EaWv5sYsfx8eu3+ZqPgjfIYf5BKB1tM9z0h9iwahcR5s9/NO8lZonl935oicV58fmXg8fn3FR7Iulpmb+m8ApZlOGj9DZDXEA39jwEfyNcWMDkB+x2GYGdyeg8FC4kR8Z/MG/pR+foKA2L7bnkxrbHQ/1Dw1myEnE8kKPeY4rg1G6U94YGur8ds9GMbEOvrsmG5exF3ed6uSvT+/4lIQP+eykYKMbkzsUmSH5INy3WIGQJ/JhrKC/P9/YkRN5u0466hAA8jk/v589PztTlEcuG7ROP/YmJ0b7N+9EOJB4RjGdKGJZH8ugT4RvFauTnVvsTmoGt3Xdcp6t90uq1IzAg7jFjHtunUWJ8Y5bWISKC8kljj+xxi6aBqk3hZ/3YH1RzigftjxOyUJw34zFZEB90/PFD1XIa4Fl8DiVlD3ydmp5QJlbcR09j3IGY4bJrH7Z/ax7+WMqpxzYLYyg1NLySWwNgNeAhxT76e2M+huefNAV5NtFk+RuWz3bJuryfWl39OEUfZBmkS53fWfO1on0fETLbnAofn+dYk7J6YsfyEmHG6KtH+OpvcZDI/V13ifKZ1ap23e2SsFxT/N1UmzrNuHyfauXsTs1a2I2ZsjJPPZXmteS0xY+yHRKKvqvbjgLieSXSoHUBvA+TdMq7v0WsXjxFtkesoZtHWXoglTcfJ0cd5/K4inqm/X3yu2TD+crLtX1tp3bt2yWP2CmJFgeY4bcOQJc7zevAKcjZsvrYr0Tl1ATkYi7hHb0Mkzi/La8hGxAzha6hw7XnL6JbOK2C5DwcvHjr/SmyUME70Ej8q35tHL5m3b77/NSrtSW3FtTKRJLkib2bjeUPYfEBs++X7H+663tPEU970Xk0kEo4nloC4l3iAa2KbX8R2YMZW/XIKo3bMZktsrThPJRKw7SUv2iO5HkY0uqsZVUMkCA6i2BCGWMP8jfn3J+R37UQiwfAVesu0rE2M6vovKpqGX8SxE/B14PD8+YPEA0DTqHxJnnO3EpulrZWvrwz8M/HQV/2MFaZfP/TojPHY1ntrE5uNnUmFjWf6R4b+Jo/F34nRob8Ctsv318njeke+/1GiE2ul8t+prdDfgT+P/gTXhsSD+Y8oOteIToLP5DX1IQ9UXZcxvhWJDqmTgZPKczL/3JhIKPyeSOZdlMe12sTkKMc1C2Kbm/ewH9Bbr/xr9EZm30Mkzteb4verjJFIzq1LLDF5HJOXdCqvM7sQnYnjxGaL1SaGsr6rEkmgm7POtxB7dDRLXuyU5+JdRBvlFmI5iepmBRDJ/3Jwz0osoR2Yx3Zj4v73qzxPh6EDZ4M8bq+lNxvxoUQ76/NE0m/xUmNEArD6Jf2yvkcRHW/NWuzzib1gzqC3pN8jitge0XWdlzK+NYgZNp8pXntFfgfPI5Lqbyba1VVu8Jx1LttT/5ox3U7MtrmO6ABujmGTOP8FsHfXdZ9BbEfm9fDt9M8Ee2neky+k94wzF9g2r4vjwKXEc9wOXcdhmV2l8wpYluJg9Tcc9yamuO2eN4hXEw3nS+glzssE7DOoeGO0VmyHZcNq02xwvYKYTnvxFLHtWnPjq4hrTWLkwquKxtZhxHS/i+jvWW1iG/jwU0MZ5WM2yrENiHUOkWC9iEwyMOCBDdieYiPQ2gqxtvffiKVYvkU0kLct3n9XNrj+l96I8s2IkSY3UukeD3k9+AUxIu37RGJ179Y52mz8eQK9/Q8+TCRR9u86hhnEWMZyOJHsP5rew/VmxIj5RcQIkz2IWQ9fJR5iH9N1DNPEtiLRmfF9YtT1KkRH9q1EgqQZUbkO0Zl6LfC54ver3KiK/s7g9xDLNp0JPIt8CCLaHTcTmyx+NuM7k3hQfWzXMcwgxg2JRE+zKV+5EXLTIbIFMWvlv4lRvfPK92ssoxrXLIhtNWL6+ovy5y8QS0M8FngQMcvoRuJ5oMo9AopYmvZS0xbehOgwPKR8f4rf3Z2KO4Jb97NPEKN3n0gkYk8hEj4foZfweiiwJzFzePGSLFTUjiQS5McAb8ifFxIbqb9+CcdqjGg7/zsxi6q62MrzsPh5h7yG7JI/PyrvW1+hl0R/OZUmXIs4Bi2X83Hg6uLnZoZiM/vt6cTslKqvIVPFS3TsfIgY6LRd8V6zjO1NRPK8+r3dst6vI9r9h+Z5+Shi9YDbicEWzUCZrfKcvZBKZ1624nov0aZ/B0XnG/HM/Vv6E+dz8h73ziybdV1/y+wrnVfAsgwHLXqJjyVGnJTruP4j0QN3SXGhmd9uDNRaiMTdCcRDzLtb7y0xttoaYa36H0GMJvk1uRxLK7bfZWyLR5znn30PFrWVET9mIxlbq45l4uskYop3M7q13JBwd2Lk3qO7rv8SYjs7G5d/JqeT0nsoX5NecvnM/OzZRNKhqmVminjKh+9biCT4CfQe2prY1iASzbdl7H8kOlX3aR/zmgsx2+EGIvFzD/Ewt1G+tyXRyP4TkVy5nlhWoerkK/AUopPtKfQ2ZH1uxvem/LlJ2jVLtdwK/GfXdZ8mpvIa8mVi1NO3iZF59xAPQc36yo8h9nq4lOyYYwgeVIv4tiBmodxDPHSXba4mAdSenVPltX82xDXKsRGJgy2JtsbTiZlvT6PXTvwgvQ1ND+66vlPE0N6Xo1lK7GHlNbE8Vvn3g4DXDPj3qry3Ee3HFxCd8vu3rpmfpZU4H/D7VXXgEInIN+a59b68p53BDGccto5lbbGVx6aZwbEhkVx9GbA5vc0jm+VMnpjXmL1qPQdbMe5NL7n6SqIz+yB6CfOH5XtrEs88n6fC2XutmKbcz4BYC/vv5GzT1ufWzD+r3LuojCePxxlER0d7Bs7JxAyVvYvXHgvs2XXdp4hnIfCs1mvvz2vKEhPnxXtVXT8ss6d0XgHLUh6wuHnfnReZLw14/yXEw+mFDMlu8kXdtyeSPuPA8VPE9ltipGjtiZLy5j1GrGX724ztZe2LfsZ2EbFGV7UzAkb5mM2G2Aacd+Xa0HtkvD9svb4+Mbr3PHJKcU2FSCQ0iZBv5fG6PR8MJi1HRaw9/15ilN4/kUnZ2gq9RMhcYhTy3cTImdsytr7Eef59U2BHYiRKk7Qco9KHOvofpJ+X59guRALlwPx+XUmvY2oBsTHo04jE2JpdxzAgpiYB3mxs9DJiBkTz8yF5jr45f16VGK3XPKyvTazRPg6c2HU8SzhmmxFLYexAr0PgxKz7e+lN9Z5DdOwspNIH1fa1sXh9jGh3/YhIojyD/iRs3/ertu/aqMY1i2Nr7gtHEx2H5Zqw7yemu7+GCjsBgCcTI0BXz58/QiTt1iRG0X+HXLe29XsrE7NUfshwjKAcI9pMd+QxemS+vlLxmf8gEpcfZog2WQQ+QCwjcwUVbgJ/H2P7LPBv+feFxMCDPxAJ81OLY7smMbPxnGE4dsSzzDi9QRTrEc+a40Sbq5nxsDox+OImcrPdYSh5Th7cvjYQy9xdSzHYp/br/oDYHkQMSji+eK18Pvsd8OX8e9k2qyo2og34JWKD+PYAs/flufhO+hPnLyUGpv2GimeTWmZP6bwCliUcoMlJrgXEqM8LiNGET2hfHIkpPDfnDX9BbRfPJcS2WzairwS2H/A7LyY2ipjUYVBLoX/0bpMoaWK7LI/dpCQrMdXvCmC3rmOYbcds1GNrx0fMVDklrxHHkFPdiJFEf83z9AhiSZP/zhir6xhoNbxWJZYm2Z54mLmNWAppUnJ5mArwfGKJjyaOMrZVmmNLPMwt7Lq+yxjjgXkefohe0nk+8FSiM/FKchZOzaU5x4gE0HuBRxAjQm8n1mQ8iP6E+RiRRP860dHR/P66xKyIamMm1tj8EjFKbfXWd/HjGed7yJGkNZfinFuJGJF3JLGUTpP0HyM6CM6gl4StfrTTqMY1i2JbmWhj/Csx8u6xRWyvy7j2J5Z8ajY0PbL979RQss4HE0nkHxPLP9xBsXwYsbTTdXlNeV6+tjWRTLkTeHrXcSxFvDsSSf5x4Lji9XIG36fy/SMf6Prdh7i+QIySX0S0D1fruk7LMbZPEbPcmvbwZsSyp/8HvJBI/O1MJMyrXhauFdfq+Z37Lr3BFNsQifMr6XW0fSG/k8/pus5LEdsOxF4Ii4hO0jfSa0ftQnR4vCp/Horrfyu+dYjBI98jOxvz9abz9HvAOV3Xc4axbEPvmeXxrfemSpy/JL+TZ1NxPssyO0rnFbBMc3D6k1zlbvJzicT5VcRat5NGlBMP4o/sOoZpYisfCo6ktwZqE9vV08RW7cMP/Qnzw4H/LGIba8U2KHHeTFWt7sYwqsds1GNrn0/EOtBXA98glsO4i9hg5RnE+tnPy8bnX4lRNt+k/mVZPg98oPXaT+kll5tRsM160g/rus4zjOtJ2ZDcZIrYDi9iezWxidrKXdd7KWPcnd6SAu9vvTeXXuL8t1Q8C4feQ8z8/D6dAzyE3lqo5xEjzpslWZqk3ll5nxhr/TtTrhPbdSFGw1+T5+BPitfLhNDHiRGJH6XCGSrlOZZ/rprfq0uJJYKuITZZfEzreP2ISOwdUPkxGsm4ZkFszfd/1bzuXUoMkLmO6Lx+Qb6/dl4TbyBG4v2WWP6vmkR5EVPTnpqT96xmM7tm/fJyFsDBxMCSRUSypIn9Oc0x7TqeAfFNteTdY4hOmxuAI4rXy+vkm6i4/diKbR7REbwx0ZEznn+u3vqdqr9j08T6DGIZvFcUr21FLIP0RyKhfDFxL69uEMkSYntzfu92KF7bmBgUcz7R1v8S8A/t415TGVQvouN0T2Kmyh3E6ORjicELnyVGY1c5w62IYbp9AV6d18PXtK4vqxNL332WumeUtpfROSavHc9rvT5V4vwFVJzPssye0nkFLFMcmP6E+f8j1sM+nl5ybw6RbLiGKRKwtRb6H3h+RjwYvJkiadCKbeAyM7U1NFuNy+OykfVZYMeyzjOJrbYyqsds1GMbUMfXE51tT6LX439oNlSOaX12i2x0rtJ1vWcQ19nAyfn3FYvXzyESDa8DHk2s1Xg1QzClNuu/CdGpsVv+XE7LbGL7D2KK9ziwX9d1XoYYVyJGU/45v1/tDoK5xLT+64mk0KRNarsu9CfMdyU6pLYuriHNCPNLiNkrC4gR6D8lNi2cV/47tZVB1zbg4XkO9l07KB5Oic6sv5Ad/rUWorP0V8BpZAchsezWbflaOwl7IfDfXdd7tsY1C2JbkDH8kNxvg0hwXUQkm7fM19YjRseeQix1Ut2GpsBPiPbUCvnzoXlN+HO+96B8vUwkb0UMFPoQMcK3+T+oLjFEr/04l7iXbdB6fxsicf4H+hPnK7Y+V2Nnx+LzKc/JdYr3ViRmEi0iEucL8/UHEx0B1bax2t8P+jttvkUkxsvk5IOINsjLiJHN63UdwxRxDdr0s9kfa96gayDRZlmRWI6m+Wx137P2ccs6rtZ6f02io+obRDv/JmJ0/Tg52rzG0jrX9szz7C15zq2Sx+5zxCCE9wM7ETNqjyOeD4ZpKZ15xAyA04g2/VSJ87czBLMULbOrdF4ByxIOUGz08AdiDdcNW+81I5evJR5et+26vksR1yp5Az+NSC6sNOAzu+eN76cUO2DXXoiNWm8hGv2rT/GZ3YmOkIsYkg6PET9mIxXboMZzvn4y8BV6D7BbEKOgTqa3AWgzo6W6RnM7NnrLH30NOLN4vXwIOpN4sLs+G9GP6zqGmR4z4iH8L8Dri9fKxPm3iOm1lwHPrvm4TRVjvr6QWH7gHiLR+uDW+3OJZHQ1o01obZJFJBV+SEwVPp9ewrxJqhxEJIqaEdr/S4wSml9+ruZCPMitX/y8ITGq/kqKh1L6E+dVjjKnv1P0XcTD9Qb52qlEu+pD9JKwWxaff1itx2tU4xrV2IqYykEXj8rv1IH07tUHEzNV3pg/NzOM2htrVpV8Bd5Gb4P7BXnNeDwx2vBaInHebFDY3uiu2ntZ1q+5ti8kBjf9mhiV/Gkigdd0pm5LL3E+aTPTGksrtv8kZjNcDXwxj99cIuF6HLHh4seIpeTOIQZmVNkB3Ipx5wGvPY1YfuZ15f/DMBViqc+30d9Wnk/cv68DdhkUW83fN/oT5scSbd9zic7CSQN7iI1a35/XzJupqO041f850Ql1M/Gccm/ex04lBi8tpLdp5j3ELJxrgANqPHZ5fdifYkktYoDPy/PvuxL36BuZnDg/LuN88zB+/yyjWzqvgGWagxOj7/6QF/+m8bU6MUp0O3qb6exGrPd3WrvRWWshdkr+DfDw4rXHENNnn0qvEb0bMbLm013XeQYxjRGjlc+gWGYAWAF4KzHK9ZX0HvL2IBJ5kxpuNZZRPGajGBsxauQcYN/W6wuIB9RmRPbmRBLvFHqjzo8ikpfVPfDk92uqzdGOIUYHrUXvYa8cuXZ4fveGoeG8D/DYPD5rE6Ov/7X1+fIBYuPimlLlCKEBdX4ysSHr4uUSiMTWy4mHnEmJ85oKMWvhr7SWiyE6n/6W36tHFHE1ibEtiE2hXwI8roi9qkTXFDE/jniQOZv+EYcbESN+BybOazofiXvxKsAardePBI7Nv3+S6NBuRi83G5v+gNa+FlNdj4zL2GYY27bEqMJmlG5zndgn69+sz/4C+vdCWEhsfrdx69+r6bt2eOvnt+Rxae5V84A30EucNyPO5xIbdO/4QNZ3GeJrrt0LiRlEZxIz2l6Rx+orxDrzzTHdlnhGuwc4sOv6LyG2ps4LiWV/fg58IsvNRPL8BXmsVs5jO04MwDiLXkdwde3IIsYm2f89ol3fbMS9FjEw5kft/49hKMTsk98QS7FcRiSYmzXaH0J0CHys63ouZUxl8v9UYu+vjxNJ1XGi3bXJFL+7IxWOWG6fU8TzyW3E4IqN8rv30fxO/Q+wan5u+/zu7QM8qvm3ajtHiU6abxAdAPsSy3z+iWJwZ37vpkqc/0sTn8VSS+m8ApZpDk5Mcfs10cs4h0g0XEL0FI8TjeYV8r0nAZt2XeeliO3T2VhZgegIOIpINNyUsb0345qbjc1qHnSKGFagNe2c2MDt2jx2DyE2qLqS6BG+JGM7Ij87F1iz6zhm0zGbDbER02N/Q4xQ3rP13knE+n7bZQPm1KIxtiGxvuFxVNT5RnREPaH12ueIB7dvEyNqTgXuJmYJDM1mmMQajOXyTc/L821RxvOD/Pkq4LlEovnBeS4OU5xlwvxLxEPPHcSD3QXEUiUr5vfrZUTi+bNk0qimAqxBTNE+PH9ur9f4wTxmJ9FLEM1lioea9u/XWvL4HEBvZtugxPnvgKO7rusU9X808aB9UV4/2uvwrkB0VF1JPJQ2M2+eQWz69lfgo13HMVviGvXYsp7NRpGvoBgtSSwn81diKZNmaadji/efBXyfSgdcEKOuL2699pmM433k4AQisdIkzn9OTNs/Nj/3zK7jmEGcC4jE0A/ozdD7KtG2uj2P0ab0Euw7EiOyq20/FrHNye/er8ika77+UGKAwlUUHVJE22t3KusIJjpnHgQ8IY/Fmvn6I4lO+gvyeJ0N7JPv7US0QQ7puv5LiG3f/L58mmi3Pz5fX4mYrfJ1YuDdn4mBW48h2lfXA0/suv7LEO/7iTbGE/LnY+hvK29SfLbq7xj9s6ZWJGbLfp3ohGrem08sU3JrHufq24pEB/eRGddKRFv/r0Rn245NzMXny8T5wV3X32KZrnRegdle8qJyKDHV9LkUU76Bo/PGfRwxJe5OIuGwB9HwXEROe6yxAFvmjfoUYuTIusV778p4vgCcnn9/I7GG74eJBmd7bcBqboJEh8WZ2dh6B8XSOcQak/cS0zSvJZInzYih0/LmXkWDcpYds5GNLeuzOnBi/n0rYur6HcBexWe2I0YuNKMzmsbZ+sTUucupaDQ2kTC/gRil0IxeWoXYKOYDxGiuK7Le40Tj7H8z9o8Tjerduo5jith+RCT+Ny9eW5UY6fRE4n7wPmLk1jix5NPd+edfiPX316OyESZFLCvSSnoTIw2vJpJa2+Z38lJilOh2+ZkViNkO48AJNX3PgKcQy5FsWtT1bCbP6vgE8aDzSXqJ82F44FmR6OwdeH/KeJ9DPHS3E+ePIJKX59FauqbrAuxM3Iu/TTx4P4re7JryAW4/ol21Sf48RowA+w8ieVnNuTjKcY16bEXdx4j2xm1Z5ya+dYnRrtfTv3nwHCLx9xPgy7VeU4gE0Gn593KppqZD8d/oT5wfSSRh7yDa1Ac2/z9dx7KEOLcm2lFPyZ9PJQbIPI5YqqQZcb5Z+1jVfF4Wdfwx8PXi52aN84cR7ZDPTfF7VcRGjNb9Ir0BS/fmNeUY+p/ZjqC39vUZeX6eTiwBUuV+HESC9RKi7XQx0fb9O/H8WY7mfXLG89f87PnEbIe3UO9z6Hyiw3RHYKN8bZO85v1j/vyGjPd5xDJWf8vrTtWDB4kVBN6b18Im+b8q0RlwSvl/kH/OIzoUz+i67jOM7+X5Pfpg/nwGvVkoz6X3zFkuobkbMZp+EbncjMVSY+m8ArO50Nt48DJ6I1o/RY78zM98iugp/kZzs8jX9ySSRVUmzYmR79cSI14vzYvhJ+lfj/cj2Sj7BP2jLQ8n1ipb94Gu9wxj+yGRmDuRGA35f8D7Wp85itjxer/itTWIB8APUeHDzogfs5GNLeu4Wl4PzqU3cnxrYvT84sQ58RBxBPGA+mtizbk3EA3wW4Ctu46lFdOVxGitKROPRGfBo4nRiF8D/jkbYBcQs3Kqu0YSDclLaS3vMcVnX5rXm8cSI4UOIUbX73V/1/M+HrsbyBEn+drmeYxeTG/pjo2J5PIX6N/AdWWiM7ma6ZnEKMh7iHtys87wZvmdGzSr45MZ2wnF+VttEqg8ZsVr+zN4dO8B+dkz6e983JB8yK2lEA/edxBTnTcqXh90LXkUMSrvU3kObp/3hPcWn6klITSScY16bEWdmgTkGJEEvxN4Fb1lF7fL68eNxEj0dYgE0U+Jdky1mwcT7dzvNfWjf6ZRs2l1mTifSySan02v87S6JQcGxLkOsUzCHKK9fyU5+p9Y07xJ1p5LhUtETBPXHOL59Hzgv1rna/Pnp4k251qVnoOrEkvLnA68ntiQ9VVEG3GcmOX3pFbM+xHP2tfkZy5lin2pOo6t2az0qfRGzm+T36lx4hn1ia3f2YFYzuSK/MxTu45jitgWZnyXEZ0cNxNJ8bnEbKI1iYGDNwEvyd9ZI6+L48Qgk6raIEVs3yTyOVcTA2DGgUPzvW8Qg38eU3y++a59nEiqT9prq7ZCtCP/OY/dm4iZDU/La+O1xD1s8ebJxe/tmv8/m3VRb4tlJqXzCszWkheW3xMjj7cHNiCSI+MUGyfkZ9emf+rmOsTGLOdQ2YiurN8uRCL5eGL02Yr0eh8f3/rsCvQSKPOIUTRnEyPqq2swZwPsd0QCq7mhvY/YwXqNaX5v3Wyw3ALs3nUcs+yYjWxsWc8mufxDJm+guDUxs+GO5rpCNDCfQTQyryQeLE5iBgncDmI6rYmJwQmTseLztzJ5HdXVuo5lQJ1Pp0iY07+e+YYDPr9HnquTNgyu8ZzMY3EZkVDdoHj9CcRooN3z53JN/ZXztZdWGlNzDfkQrQcXoiOj+Y7t1XrvBOKh7xRyzdQay6BjRm9d5XdTdOTne6sQnW3jxANurZt9rks8RP8Hxf2Z/tGvHwW2yr+vQYxqvp1IYt5ILE9Q1Yi8UY1r1GMbEGs52u584l78GvoT5z8D/kiMqvxfooO7aXtW1RlAJLrnELOovtV6b6rE+aR73jAVep3CXwb+q3VMv5P3gP+vtmM1w9jeQSS/njTgGFu+tqUAACAASURBVH6aGAFbXVzESOVvEe3Hh9PfxppDDGoaJ0aXb9X63bWJBPRJ7fdqKMSgg0uZYmkmomNgPM/HSfvCEEnpbfPvVbW16G+HvDyP0y8znj2Lz72fYh+EfO3zRNL1Eoq9qWopxECZi4kljFYi2vVnZGyPJpbcGicGb5UdxavmdeVrFIO8ai55jr0j43lPvrYmvcT581uffSrxvL1CF/W1WGZaOq/AbCx5EbycGA1ZJhUeRowAfRYxRXpSwoeYxvJZIvla4w29WQvu3+hP9G+dse1EJJwf2vq9tYiptD8hRsAuHoXTdUxFHX9A9BJv1nr95cRmfQcRy348dcD7nyGSes+pMK5RPmYjG1vWp+x8Gzgam0hO/g+R1Nu79d4jstGy4gNR3xnGNOn6SO/BdAHxEFo2KptRC2cAn8m/N1MbaztezTWkWd6jXGbg60Rn6Aqt39mGSAg9pf07tZXW+dh0djQdG9sQMzz2yM/9mXiwa2ZGPJ4YQblnF3WfJqbyGtIk95vzcb38cwtaszqK3z8536vyuA06Zvn6SsSMhv8D3kO2R4rj+RDiIagZ2VZdfMTo1Ssp1kemP/FzCr2lj5ok7LrEGvtvI0aPNteXapKwoxrXKMdGjIhvL1fV1HNTIuF/C7GMQjnifD1i/eWnUSQAK4tt8ajx/Pl/gG/m38t7XPn3DxP3g3+n0lHYg47ZgM80a/eeQXQWNMdtK6L9uFv7eNdQZhjbpsTgir8AuxSvb0ksw3Vi13FMUe8tiA6m59O7V7fbxUfkdeSt+XM136clxPYJYsDcvNbrZcfAWzO2Z5ext88/Kmof02v3f788L4lZwr8nZo6uTYw4/1Lzc37mIUQb60Aq2o+piGFxu791nJpE+T/nz2/Pn79BzPJ7Sl5b76GydvGAGNsbmy7MeBYBH8rX1ibu7VcRnT8bEjP2L6XimdwWS1M6r8BsK3nBPykvjI/L15qE3MOJRMKviQfVX5FrGeb7L82byi+pM2G+BjEqd5xeUqiJbS9ixMJv8/3LmsZKvv/mjO1rtKYB1lCIhM4NxPIC7Qef04ik1qV53G4F3pHvrUI8HHwf2CNfq2ba6Ygfs5GNrTi3/pDnVpOgbB7CVyBGaxyaP09aqqXGMsX1sYzpt8TD6VoDfvdTxINcFd+tAfWb7hryLWI04aTrOvFQfi3ZsK61zOB83IdY3/WqvF5+jt4avmsTm8edRUWjllvXkGbN5Cam7YhRrfvlz+V3rL1Uy8AH967LFMds8ShWYkbKUcSDz7vpH/m7OzECal8q2gehFd8Rea5N2jSXSGhdRawlfR7TLE9FRcmuUY5rVGMjlhC7LEuzv015HbmTGD2/Sl4DbyMS56tO8e9Vcx0hltL5OzFw5GH52mn0r4VdJorKkdgn5LV1i67jmMkxW8Lnm5nCXyb2Wzk3z9dqzsNliY3orDkn7wHfzGv+hcTMiFoHkxyYx2LSUg+tc/GLxEywDab7XA2FeG5ckN+tZsmcBe3P5J/rEUnlHzHNJuS1FAa3+8vj9JU855pZwIfQW8729cTyftdQ5wjzSe1+eoN61iOWkDy6+Pyrib0sxolcwuXA/pWekyuTg3kG1Y/+xPm/5Wvr5nXnHuJe/ieKDYUtlppL5xWYbYVIHjyP3vrDD8/XV8yL6i+JxvJziVF39wCvzc+sQ6z5t8QGXEexrQgcTPQk/rKI7XH0Nll8BrExyS+I0Xsvzc+sSYyir2rn9SK2lYj17q4iOjPWytf/O197csa/JTEy4056I0NXJDeToaKE+Sw4ZiMbW9bp8GxYNY2Rpq4r5LXk5/TPZGmSercC+3Rd/ylimur6uAIxcugcJs8KaB4UjiMaYwMTDV2XGVxDpkr+rJGx/0PXMSwhvunOxwuJUfT/mMf2JnrLBe1AJNBvAR7ddRytmKa6hjSJrk8xeQbLd4mRee3NQatJdM3gmK2Yx+wkokPj7UQn44eJmTkbESOEvlbr9y3jeFUepwflz821Ym4TS/68K/Fw+pf8vlV3rGZDXKMaG5HsOqi4jjwiX2+uIydSzCwlEud/ye/npM6Dmkpe3/cl7mHnEqPizwJOyvdXyuvJgizziXZwM2unuj1HpjhmA0fD05/cO4pIeF1O/+blVZ2bM4mtFdfGxCyOXxGzij5IpYNJsk4HE+35zaf7/yfWyB6ntf53zYXYbPZ3g45T63OfBy7qur4zjKnd7m+Sy0175AdEZ8HKxe8cQ3Su3kw871SzH1MrtrLdfy79G9C+kqKjoHj9kcRG2I+n1+asLXcwRqx6sHhGQ/N663PNUi2LgFfla2sBx2apeuNWi6UsnVdgNpa8QexH9Iz+LBskFxAJoQ2LG8WWRA/l9xiCDSCyzguK2M4mpszeTjwULKT3ALQFMSLvC+0GTW0NzAGxXUskJH9ITBvbpvW57fNG8oqu6+wxG+nYHkSspz9Ob2bDpOQy/Q8/j81z91qKZF9NZZrr408Z/HDXPLxtTYUj1qY4H6e9hjRxkRth0kog1VimOR8vpNhIlxiR91NiVs5lxBqUF1LvQ89015CVB3x+64z3h13X/T4es5/Te3hdhRjRtYjodLuaaJtMWme/pgI8kRgF+7bitXKpj+b6v4CY8n1q13WezXGNcmwzuY604jwjv5f7d133pYjtj3mvvjCP4eVEIuxCYgbtecQAhXOJBOz6xb9R3b2tdcymTJyX9Sc6CNYqfq4uqTzT2OjNhpgqMVtrbI8i9pn6YPv45N+bZ+wH53ds3weyfssYU3M+NYnWVw6KrXjtxPwuVve9miK+st3/K3ptj7cRm2Y2S3GV18jNiQ78aveLyXouaMU2l9hM/V7g5fmZOVT6rDlNXJsRezTdVN6n2uccMeDzFGJm5iO6rrfFsqyl8wrM1tK6QYxno2W9AZ/7LjFqYyg2gGjF9vuM7YsMmMaXDej/13V9lzK25uZ3Ycb2tOK9plHz+Lw5PLOLOnrMZlVsqxFTgceBdxFTZqdKLs8nkl+PpPLNt6a4Pk5a845YB/FT5F4Bw1Cmu4YUn5mXDwvjxF4Xw/LgM+X52PqubULMmnoDsCcDNqyqqUx3DZni85swJA9AS3kN2Rn45zxuVS7J0qrvOhnP75l6jew5wLbEw9/ru67zbI5rFsS2xOsIRaKSWL+4ysTkNLFdQG9d3o8RAxFOJkbIfp0Ygf09itGJNRemSS7Ta/PPyWvjNyk6Emu/ByxDbNu036+xEDNPziKWvti3eL09IOb5REfPRg9k/e5jbA/POl9MztZrjmXx93XzO3b8oLhrLUzuWPwAMdu+2Qus6eyo9tybJrbm+ngdMehgEXD0MMbSimtj4MfEiP/pEucHEx1ZkwYIWSzDUjqvwGwueRHdn97IjA1a7z+MeHg9ngrXxZthbBcTI0zaSypsA/wOOKrrui5DbCtmbL8nRsyUDc0FxFSky6h02uksPWajHFuT9LqbqddnXEisC/iDYbmWzOD6uJBIKowD23Vd36WMbbpryHzgTcT04hd0XddliG3K83FYzr0p4pr2GpKfaT8oDMvD6nTHbKz8c9gKMfPrDmKEV3vJnHnE5lznEHtADM35OapxzYLYZnIdaSfShyVx3tzXLiFGlK+xhM8PxTWF/k78dnJ5DrFZ9EXELL+hOFajHhvRpm+uIc8a8P6DiA6d08iZfMNSgF0ytvOA5w+I61hiubsndV3XZYitSZw3+00d3nWdlnNsz85z8iYqXIN9GeOaKnFednS/iFiipvrBFhbLVKXzCsz2ko3MSQ0WYgTlicQ0/qFc82ma2B6eDzxVbpIzw9jaDc1mKtmbiClX1U/3m4XHbJRjW53YqG+cYlp7vrcq8EliKviOXdd1OR2z5vo4tCMXlnANGQcOzp+rWstwhrFNeT4OcxlwPj6s6zp5zGYU215EkuE6Yj3eLYlldI4iloD6Db31h4fmHjCqcc2C2Eb5OtLEdn0eo2Zz0MXrezMknYmtuNqjstfP15uk8gVDfD6OZGzFNeRqYhbVekRS+SnExuN/AR7TdT2XMbY9sv53At8mlm15J7ER7e3AgV3X8T7E1nQsXk7RNh6FktfHZzODJZ+GqdCfOD+g9d66xP43ZwCrd11Xi2VZS+cVsAxMnmxOjKC8G9i26/rdx9jKxtgviKVLziJG2QxdI2ya4/Zz4L1EwnxxsqvrOnrMZlVs5TILb8/XFtJLLg/ltWSa6+PQxjRFbM01ZBFDnDAvYpt0Po5CaV1DFm9aNQplVI9ZxrZ1PtTdSUz5HidG+v4/Kt7UbrbGNQtiG+XrSBnbTxmRTgH69yQ5l9gA9QL6k8rDfj6OVGzA4/Ka8fdsM95JzAT+FZXvyTGD2DYnBsRcSiwJeg2xAege+f5Qth2z7lPOgBj2wuR9m0bl+rgxkRi/G3gNsUffU4kZHUPbQWWxNKWZdquOjY2NrUBsDPRBYmOLu4BdJiYmftNpxZaDjG0v4ENEbBcRyyn8fWxsbN7ExMS9nVbwPsjY9gROIDaVOXhiYuLUsbGxMYCJIf2CzYJjNqqxrUashf06YtTo2sChwM7DfC2ZBdfHkbuGwKTz8W0TExP/2nGVloviGvIRomNj+4mJiZu7rdXyMarHDGBsbGx1YH1i4+e/E9Pbr5+YmJgYGxubOzExsajTCi6jUY0LRj62Ub6ONPe1zwN/AB4/MTHxt04rtRyMjY0tINoiHyD2h7kA2GFE2o8jGdvY2NjaxD4jOxDLO50L/G5iYuKmTiu2HIyNjc0jOjw2IJZkuWtiYuJvI9J+XADsTTyrjQO7TkxMXNdtrZaPEb4+bggcR6xh/jdi4/hbgBdNTExc0GXdpPvKpHlF8gaxP/By4IhRusDkDeIAYlrcKyYmJu4d5kZYaWxsbEXgGcSD3Dmj0FiBkT9moxzbasBbiM36xomHnlFILo/y9XEkryEw6Xx808TExPs7rtJyUZyPBxMbVQ1t8q5tVI/ZVMbGxuZMTEyMd12P5W1U44LRiW3EryMrEEmvv05MTPyo6/osLyPefhzZ2DR88vq4H9GR/6yJiYnfd1yl5WbEr4+PJfYVuBy4eGJi4sZuayXddybNK5PJk/kTExO3d12X5W1sbGzBxMTE/+XfR6oRVj7AjY2NjY1CsgtG/piNcmxrEGscfn1iYuK3XddneRnx6+NIXkNg8WjRo4GTJyYmLu66PsvL2NjY/ImJib/n34d61GvbqB4zqTYjfh0Zy1kBo3ZPG+X248jGpuGTifMFExMTd3Rdl+VtVK+P0igyaS5JI2hURuJpNHg+Dh+PmSRJkqTZzKS5JEmSJEmSJElpTtcVuK/GxsaeMzY29u9jY2NnjY2N3TY2NjYxNjb2xa7rJUmSJEmSJEkaPvO6rsBy8FZga+AO4Fpgi26rI0mSJEmSJEkaVkM/0hw4CtgMWA04vOO6SJIkSZIkSZKG2NCPNJ+YmDi9+fvY2FiXVZEkSZIkSZIkDblRGGkuSZIkSZIkSdJyYdJckiRJkiRJkqQ09MuzLA+77777RNd1uD8cf/zxABx55JEd12T5G9XYRjUuMLZhNKpxgbENo1GNC4xtGI1qXGBsw2hU4wJjG0ajGhcY2zAa1bhgtGMDOOOMM0Zx/eWRzD3O1BVXXMFhhx3GO97xDnbdddfl8U/e7+eII80lSZIkSZIkSUomzSVJkiRJkiRJSibNJUmSJEmSJElKJs0lSZIkSZIkSUomzSVJkiRJkiRJSvO6rsB9NTY2th+wX/64fv6509jY2H/m3/80MTFx9ANeMUmSJEmSJEnS0Bn6pDmwDXBo67WNswBcBZg0lyRJkiRJkiQt0dAvzzIxMfEvExMTY9OUR3RdR0mSJEmSJEnScBj6pLkkSZIkSZIkScuLSXNJkiRJkiRJktIorGkuSZIkSZIkSXqAXXHFFRx22GEz+uxdd911P9dm+XGkuSRJkiRJkiRpqf3tb3+b8WfHx8fvx5osX440lyRJkiRJkiQttS233JLTTz992s80o9EXLlz4ANXqvnOkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJaV7XFZA0e2yzzTacccYZXVdjuTvvvPO6roIkSZIkSdID7oYbbuClL30pd9111xI/e++99z4ANVo+TJpLesCcd955HHnkkV1XY7k7/vjju66CJEmSJEnSA+6aa66ZUcIc4Pbbb7+fa7P8mDSXJEmSJEmSJC21HXbYgdNPP33xz4sWLWLRokXce++9i8uVV17JG97wBh70oAd1WNOlY9JckiRJkiRJknSfzZ07l7lz57JgwYLFr916660d1mjZuBGoJEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5JEmSJEmSJEnJpLkkSZIkSZIkScmkuSRJkiRJkiRJyaS5/v/27j3I7rOu4/jnm03SIqUFChHUYZShOOUydBCCLQzYUFsY5aYygg63Uh25CgKp4oAw9dIBpEXAQWCYClIHqKJWLsVCCgMSFhkiYgOk4VIobUOT2hZMotk8/nG+kWWbTTab7aaX12vmzMn5/Z7f83vO/vnOb54DAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAA5lFVj66qf6qqq6pqVNWz55w/pqreXFXfqaqdVfXVqnrpEVouS2DlkV4AAAAAAMCt2DFJvpzk3f2a641JTkvyjCTfSPLoJO+oquvGGO9ZtlWyZERzAAAAAIB5jDE+nOTDSVJVF+xnyClJ3jPG2NCfv1lVz03yiCRLEs1nZmYyPT2dLVu25IQTTsjatWszNTW1FFOzH6I5AAAAAMDifTrJE6rqnWOMb1fVKUlOSvL6pZh8ZmYm69evz+bNm7Nr166sXr06973vffOKV7wiK1Yc3u7bY4yMMX7k34v9vHfv3v2eu/rqqw9rjUeCaA4AAAAAsHgvTvJXSa6sqj197EVjjH9eismnp6ezefPm7Ny5M0mye/fubN68OWeeeeZSTL9srrvuuiO9hAUTzQEAAAAAFu9FmWzR8sQk38pkT/M3VNU3xxgfPdzJt2zZkl27dt3s+HHHHZfjjjvucKdfEvueMN+fG2+8MTfccEOOP/74ZVzR4RHNAQAAAAAWoarulOTPkjx1jHFxH/5SVZ2U5OVJDjuan3DCCTn66KP//0nzJDn66KNz9tln5+STTz7c6Q/Lnj178t73vjfbt2+fd8yOHTvymc98JlW1jCs7PKI5AAAAAMDirOrXzJzjM0kOb8Pxtnbt2px44om5/PLLs3v37hx11FF5wAMekLVr1y7F9Ifl0ksvzQUXXLCgsdu2bbtlF7OERHMAAAAAgHlU1TFJ7tcfVyS5Tz9JvmOMcWVVfTLJuVX1/Uy2Z3lMkmcmWb8U95+amsrrXve6TE9P54orrsj97ne/rF27NlNTU0sx/WE544wzsnr16tx0001Jst+nya+99tpceOGFWbNmzXIvb9FEcwAAAACA+T0syYZZn1/br79O8uwkT8tki5b3Jrl7JuH8VUneslQLmJqaysknn3zEt2OZq6qybt26A47ZunVrLrzwwmVa0dIQzQEAAAAA5jHGuCzJvBtyjzGuSfKcZVsQt7gl2VcHAAAAAABuD0RzAAAAAABoojkAAAAAADTRHAAAAAAAmmgOAAAAAABNNAcAAAAAgCaaAwAAAABAE80BAAAAAKCJ5gAAAAAA0ERzAAAAAABoojkAAAAAADTRHAAAAAAAmmgOAAAAAABNNAcAAAAAgCaaAwAAAABAE80BAAAAAKCJ5gAAAAAA0ERzAAAAAABoojkAAAAAADTRHAAAAAAAmmgOAAAAAABNNAcAAAAAgCaaAwAAAABAE80BAAAAAKCJFN3SQAAAEENJREFU5gAAAAAA0ERzAAAAAABoojkAAAAAADTRHAAAAAAAmmgOAAAAAABNNAcAAAAAgCaaAwAAAABAE80BAAAAAKCJ5gAAAAAA0ERzAAAAAABoojkAAAAAADTRHAAAAAAA2sojvQAAAAAAAG579uzZkw984APZvn37vGMOdO7WSjQHAAAAAOCQXXrppXn729++oLHbtm27hVezdERzAAAAAAAO2emnn56qyg033JAkqaqbjdm2bVsuuuiirFmzZrmXt2iiOQAAAAAAh2zFihU544wzDjhm69atueiii5ZpRUvDD4ECAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAAtJVHegHcsk466aRcdtllR3oZS27Tpk1HegkAAAAAcId25ZVX5lnPetaCxu7evfsWXs3SEc1v5zZt2pSXvOQlR3oZS+78888/0ksAAAAAgDu066+/fsFjRXMAAAAAAG7XHvKQh2TDhg3znp+ZmcmWLVvyvOc9L8cee+wyruzw2NMcAAAAAIAlNzU1lVWrVh3pZRwy0RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgrTzSCwAAAAAA4MgZY/zIa+/evfN+Pti5JD9y7JprrjnC3+7QieYAAAAAAHcQMzMzOe2005b9vjt27Fj2ey6W7VkAAAAAAO4gVqxYkcc//vHLft9jjz122e+5WJ40BwAAAAC4g6iqrF+/PuvXr1+W+23dujVnnXVWVq687aRoT5oDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEATzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAEBbeaQXAAAAAADAbc8YI5/61Kdy4403zjvme9/73jKuaGmI5gAAAAAAHLKPfexjOffccxc0dtu2bbfwapaOaA4AAAAAwCFbt25drrrqqmzfvj1JUlU3G7N9+/Zs3Lgxa9asWe7lLZpoDgAAAADAIVu1alXOPPPMA47ZunVrNm7cuEwrWhp+CBQAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQBPNAQAAAACgieYAAAAAANBEcwAAAAAAaKI5AAAAAAA00RwAAAAAAJpoDgAAAAAATTQHAAAAAIAmmgMAAAAAQFtQNK+q46vqrKr6YFVdUVU7q+qGqvp0VT23qm42T1Xdpar+pKq+UlW7qur6qrqkqh47zz2eXFXv6/HX9z22VNXfVtXDDrC2u1fV+VX1zaraXVXfrap3VdVPLfzPAAAAAADAbUFV/UFVfb6qbqyq71XVxVX1oDljzunW/IPuzR+vqlMWMv9CnzR/apJ3JHlEks8lOT/J3yV5UJJ3Jnl/VdWsBd0tycYkr0yyJ8nbevxDk1xaVc/dzz2elOThSf49yQVJ/iLJl5I8Jcl0VZ0194KqOj7JZ5P8bpKtSc5LMp3kOUm+UFX3XeD3AwAAAADgtuEXkvxlklOSrMukQV9aVXefNearSV6Q5MFJHpXkG0k+WlU/frDJVy5wEV9L8sQkHxpj7N13sKpemUmk/tUkv5JJGE+S1yR5QJK/T/LrY4w9s8b/W5I3V9UlY4zvzLrH88YYu+beuKoenOTzSd5QVe8eY/zPrNN/muT+Sd44xnjZrGtenORNmfzhHrfA7wgAAAAAwBLau3eSky+77LKsWrUqa9euzdTU1GHNOcY4Y/bnqnpGkhuSPDLJxT3mb+aM+b0kz01yUpJLDjT/gp40H2N8Yoxx8exg3sevyeQp8mRS9/d5Sr+/el8w7/HbkrwxyZ2SnDlnrpsF8z7+H0k2JzkuyT33Ha+qY5I8I8kPMon0s70lybeSnOFpcwAAAACA5TczM5PzzjsvSbJhw4acc845Wb9+fWZmZpb6VnfJpHVfv7+TVbU6yW8nuTHJpoNNthQ/BPq//b5n1rF79fvX9zN+37H97m0+V1XdP8nPJrkuydWzTv18JvH9M2OMm2Zf03F/3/8WnLqQ+wAAAAAAsHSmp6fz9a//MBHv3Lkzl19+eaanp5f6Vm/KJIZ/dvbBqvrlqvp+kl1JXprkF8cY1x5sshpjLHolVbUyyRcz2dv8cWOMS/r4d5PcO8kDxxiXz7nmJZnsPX7tGONec6ZMVZ2WyR4zq5P8TJInZBL3nz7G+MdZ416QyRPlbxljvGg/87w8yeuTvG6McfaivyQAAAAAAIfs1FNPfVUmu4TMfnh7b5I/2rBhwx8vxT2q6o1JnpbkUWOMr885d+dMOvU9kvxWJg9ynzzGuPpmE82y0D3N53NuJsH8w/uCeftQkrOSvLaqnjbGmOlF3jOTop8kd5tnztOSzI7c1yR59pz5k8l2Lclkr5r92Xf8rgf9FgAAAAAALKkNGzack+ScW2r+qjovk2B+6txgniRjjB8kuaJfG6tqSybd+oBrWvT2LP1jmy9L8pVM9haf7dVJvp3k15Jsqqrzq+odSf4zyY4eszf7Mcb4/TFGJTkmyUOTfCLJR6rqDxe7VgAAAAAAbj+q6k1Jnp5k3RjjKwu8bEWSoxYyaDELemEm+8RcnknF3zH7fD/e/vAkb81kE/bnJ/mlJO9L8tQetu1A9xhj/GCM8cUxxm9msj/5OVX18FlD9j1JftzNr/6R4/+1oC8FAAAAAMCtXlW9NclzkvxGkuur6l79OqbPH1tVf1xVj6iq+1TVz1XVu5L8VJL3H2z+Q47mvSf5m5N8OZNgfs3+xo0xrh1jvHCM8dNjjNVjjJ/ovcfv00M+fwi3/WiSSvKYWce+2u/3n+eaE/r9a4dwHwAAAAAAbt2en8nD2h9PcvWs18v7/J4kD0zywSRbklyc5Pgkjx5jfOlgkx/SnuZVdXYm+5hvyuSXRq87lOvbM/v9wkO45if7fc+sYxuT7EzyyKq6yxjjplnrXJHk9P64YRFrBAAAAADgVqi39z7Q+f9O8pTFzr/gJ82r6lWZBPMvJHnsgYJ5Va3Y9yj8nOPPyCSa/2uSf5h1/Kiqesg8cz08ye8kmcnkifMkyRjj+0nek+TOmfwC62wvTPLTSS7Z3wbwAAAAAACwPzXGOPigqmcluSCTcP3m/HA/8dm+Oca4oMcfk+TaJP+SZGsmP/r5yCQnJ9mc5LQxxndnzX/XJNcn+VIm2758J8mPJTkxyboe9ooxxp/PWdfxmQT4+2fyg6HTfc2TMtkz/ZQxxtaDfkEAAAAAAMjCo/lrkvzRQYZ9cozxCz1+VZK3JXlUJpurJ5O9Y96f5Px+PH72/KuSnJ3JnuUnJrlHkpHkqkyi+FvHGJ+bZ21377U9Ocm9k2xP8pEkrx5jfOegXw4AAAAAANqCojkAAAAAANwRLHhPcwAAAAAAuL0TzQEAAAAAoInmAAAAAADQRHMAAAAAAGiiOQAAAAAANNEcAAAAAACaaA4AAAAAAE00BwAAAACAJpoDAAAAAED7P0RPi8+NfqsjAAAAAElFTkSuQmCC\n",
"text/plain": [
"<Figure size 1800x720 with 2 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"msno.matrix(df[ORDINAL_VARIABLES]);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Cleansing"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Since only about 1% of the overall number of observations exhibit variables with missing data (disregarding the columns *Lot Frontage* and *Garage Yr Blt*), the decision is made to discard these rows entirely to not have to deal with interpolating meaningful replacements for the missing values."
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"remaining_columns = sorted(set(ALL_VARIABLES) - set(missing_a_lot)) + TARGET_VARIABLES\n",
"mask = df[remaining_columns].isnull().any(axis=1)\n",
"assert (100 * mask.sum() / df.shape[0]) < 1.1 # percent\n",
"df = df[~mask]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The two columns with a lot of missing values regard the age of a house's optional garage and the length of the intersection with the street where the house is located. The first is assumed as not important for the house appraisal and the second is assumed to be captured in other variables (e.g. overall size of the house). Therefore, for sake of simplicity both columns are dropped from the DataFrame."
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Garage Yr Blt Year garage was built\n",
"Lot Frontage Linear feet of street connected to property\n"
]
}
],
"source": [
"print_column_list(missing_a_lot)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"df = df[remaining_columns]"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"# Remove the discarded columns from the helper dictionaries / lists.\n",
"update_column_descriptions(df.columns)\n",
"# Without any more missing data, cast all numeric\n",
"# columns as floats or integers respectively.\n",
"for column in CONTINUOUS_VARIABLES + TARGET_VARIABLES:\n",
" df[column] = df[column].astype(np.float64)\n",
"for column in DISCRETE_VARIABLES:\n",
" df[column] = df[column].astype(np.int64)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Clean Data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The cleaned data comes as a 2898 rows x 78 columns matrix."
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(2898, 78)"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 38,
"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></th>\n",
" <th>1st Flr SF</th>\n",
" <th>2nd Flr SF</th>\n",
" <th>3Ssn Porch</th>\n",
" <th>Alley</th>\n",
" <th>Bedroom AbvGr</th>\n",
" <th>Bldg Type</th>\n",
" <th>Bsmt Cond</th>\n",
" <th>Bsmt Exposure</th>\n",
" <th>Bsmt Full Bath</th>\n",
" <th>Bsmt Half Bath</th>\n",
" <th>Bsmt Qual</th>\n",
" <th>Bsmt Unf SF</th>\n",
" <th>BsmtFin SF 1</th>\n",
" <th>BsmtFin SF 2</th>\n",
" <th>BsmtFin Type 1</th>\n",
" <th>BsmtFin Type 2</th>\n",
" <th>Central Air</th>\n",
" <th>Condition 1</th>\n",
" <th>Condition 2</th>\n",
" <th>Electrical</th>\n",
" <th>Enclosed Porch</th>\n",
" <th>Exter Cond</th>\n",
" <th>Exter Qual</th>\n",
" <th>Exterior 1st</th>\n",
" <th>Exterior 2nd</th>\n",
" <th>Fence</th>\n",
" <th>Fireplace Qu</th>\n",
" <th>Fireplaces</th>\n",
" <th>Foundation</th>\n",
" <th>Full Bath</th>\n",
" <th>Functional</th>\n",
" <th>Garage Area</th>\n",
" <th>Garage Cars</th>\n",
" <th>Garage Cond</th>\n",
" <th>Garage Finish</th>\n",
" <th>Garage Qual</th>\n",
" <th>Garage Type</th>\n",
" <th>Gr Liv Area</th>\n",
" <th>Half Bath</th>\n",
" <th>Heating</th>\n",
" <th>Heating QC</th>\n",
" <th>House Style</th>\n",
" <th>Kitchen AbvGr</th>\n",
" <th>Kitchen Qual</th>\n",
" <th>Land Contour</th>\n",
" <th>Land Slope</th>\n",
" <th>Lot Area</th>\n",
" <th>Lot Config</th>\n",
" <th>Lot Shape</th>\n",
" <th>Low Qual Fin SF</th>\n",
" <th>MS SubClass</th>\n",
" <th>MS Zoning</th>\n",
" <th>Mas Vnr Area</th>\n",
" <th>Mas Vnr Type</th>\n",
" <th>Misc Feature</th>\n",
" <th>Misc Val</th>\n",
" <th>Mo Sold</th>\n",
" <th>Neighborhood</th>\n",
" <th>Open Porch SF</th>\n",
" <th>Overall Cond</th>\n",
" <th>Overall Qual</th>\n",
" <th>Paved Drive</th>\n",
" <th>Pool Area</th>\n",
" <th>Pool QC</th>\n",
" <th>Roof Matl</th>\n",
" <th>Roof Style</th>\n",
" <th>Sale Condition</th>\n",
" <th>Sale Type</th>\n",
" <th>Screen Porch</th>\n",
" <th>Street</th>\n",
" <th>TotRms AbvGrd</th>\n",
" <th>Total Bsmt SF</th>\n",
" <th>Utilities</th>\n",
" <th>Wood Deck SF</th>\n",
" <th>Year Built</th>\n",
" <th>Year Remod/Add</th>\n",
" <th>Yr Sold</th>\n",
" <th>SalePrice</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Order</th>\n",
" <th>PID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <th>526301100</th>\n",
" <td>1656.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>Gd</td>\n",
" <td>Gd</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>TA</td>\n",
" <td>441.0</td>\n",
" <td>639.0</td>\n",
" <td>0.0</td>\n",
" <td>BLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>BrkFace</td>\n",
" <td>Plywood</td>\n",
" <td>NA</td>\n",
" <td>Gd</td>\n",
" <td>2</td>\n",
" <td>CBlock</td>\n",
" <td>1</td>\n",
" <td>Typ</td>\n",
" <td>528.0</td>\n",
" <td>2</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1656.0</td>\n",
" <td>0</td>\n",
" <td>GasA</td>\n",
" <td>Fa</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>31770.0</td>\n",
" <td>Corner</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>112.0</td>\n",
" <td>Stone</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" <td>Names</td>\n",
" <td>62.0</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>P</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>7</td>\n",
" <td>1080.0</td>\n",
" <td>AllPub</td>\n",
" <td>210.0</td>\n",
" <td>1960</td>\n",
" <td>1960</td>\n",
" <td>2010</td>\n",
" <td>215000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <th>526350040</th>\n",
" <td>896.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>2</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>TA</td>\n",
" <td>270.0</td>\n",
" <td>468.0</td>\n",
" <td>144.0</td>\n",
" <td>Rec</td>\n",
" <td>LwQ</td>\n",
" <td>Y</td>\n",
" <td>Feedr</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>MnPrv</td>\n",
" <td>NA</td>\n",
" <td>0</td>\n",
" <td>CBlock</td>\n",
" <td>1</td>\n",
" <td>Typ</td>\n",
" <td>730.0</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>896.0</td>\n",
" <td>0</td>\n",
" <td>GasA</td>\n",
" <td>TA</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>11622.0</td>\n",
" <td>Inside</td>\n",
" <td>Reg</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RH</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>6</td>\n",
" <td>Names</td>\n",
" <td>0.0</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>120.0</td>\n",
" <td>Pave</td>\n",
" <td>5</td>\n",
" <td>882.0</td>\n",
" <td>AllPub</td>\n",
" <td>140.0</td>\n",
" <td>1961</td>\n",
" <td>1961</td>\n",
" <td>2010</td>\n",
" <td>105000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <th>526351010</th>\n",
" <td>1329.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>TA</td>\n",
" <td>406.0</td>\n",
" <td>923.0</td>\n",
" <td>0.0</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>Wd Sdng</td>\n",
" <td>Wd Sdng</td>\n",
" <td>NA</td>\n",
" <td>NA</td>\n",
" <td>0</td>\n",
" <td>CBlock</td>\n",
" <td>1</td>\n",
" <td>Typ</td>\n",
" <td>312.0</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Unf</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1329.0</td>\n",
" <td>1</td>\n",
" <td>GasA</td>\n",
" <td>TA</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Gd</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>14267.0</td>\n",
" <td>Corner</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>108.0</td>\n",
" <td>BrkFace</td>\n",
" <td>Gar2</td>\n",
" <td>12500.0</td>\n",
" <td>6</td>\n",
" <td>Names</td>\n",
" <td>36.0</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>6</td>\n",
" <td>1329.0</td>\n",
" <td>AllPub</td>\n",
" <td>393.0</td>\n",
" <td>1958</td>\n",
" <td>1958</td>\n",
" <td>2010</td>\n",
" <td>172000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <th>526353030</th>\n",
" <td>2110.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>TA</td>\n",
" <td>1045.0</td>\n",
" <td>1065.0</td>\n",
" <td>0.0</td>\n",
" <td>ALQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>Gd</td>\n",
" <td>BrkFace</td>\n",
" <td>BrkFace</td>\n",
" <td>NA</td>\n",
" <td>TA</td>\n",
" <td>2</td>\n",
" <td>CBlock</td>\n",
" <td>2</td>\n",
" <td>Typ</td>\n",
" <td>522.0</td>\n",
" <td>2</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>2110.0</td>\n",
" <td>1</td>\n",
" <td>GasA</td>\n",
" <td>Ex</td>\n",
" <td>1Story</td>\n",
" <td>1</td>\n",
" <td>Ex</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>11160.0</td>\n",
" <td>Corner</td>\n",
" <td>Reg</td>\n",
" <td>0.0</td>\n",
" <td>020</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>4</td>\n",
" <td>Names</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Hip</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>8</td>\n",
" <td>2110.0</td>\n",
" <td>AllPub</td>\n",
" <td>0.0</td>\n",
" <td>1968</td>\n",
" <td>1968</td>\n",
" <td>2010</td>\n",
" <td>244000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <th>527105010</th>\n",
" <td>928.0</td>\n",
" <td>701.0</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>3</td>\n",
" <td>1Fam</td>\n",
" <td>TA</td>\n",
" <td>No</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>Gd</td>\n",
" <td>137.0</td>\n",
" <td>791.0</td>\n",
" <td>0.0</td>\n",
" <td>GLQ</td>\n",
" <td>Unf</td>\n",
" <td>Y</td>\n",
" <td>Norm</td>\n",
" <td>Norm</td>\n",
" <td>SBrkr</td>\n",
" <td>0.0</td>\n",
" <td>TA</td>\n",
" <td>TA</td>\n",
" <td>VinylSd</td>\n",
" <td>VinylSd</td>\n",
" <td>MnPrv</td>\n",
" <td>TA</td>\n",
" <td>1</td>\n",
" <td>PConc</td>\n",
" <td>2</td>\n",
" <td>Typ</td>\n",
" <td>482.0</td>\n",
" <td>2</td>\n",
" <td>TA</td>\n",
" <td>Fin</td>\n",
" <td>TA</td>\n",
" <td>Attchd</td>\n",
" <td>1629.0</td>\n",
" <td>1</td>\n",
" <td>GasA</td>\n",
" <td>Gd</td>\n",
" <td>2Story</td>\n",
" <td>1</td>\n",
" <td>TA</td>\n",
" <td>Lvl</td>\n",
" <td>Gtl</td>\n",
" <td>13830.0</td>\n",
" <td>Inside</td>\n",
" <td>IR1</td>\n",
" <td>0.0</td>\n",
" <td>060</td>\n",
" <td>RL</td>\n",
" <td>0.0</td>\n",
" <td>None</td>\n",
" <td>NA</td>\n",
" <td>0.0</td>\n",
" <td>3</td>\n",
" <td>Gilbert</td>\n",
" <td>34.0</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>Y</td>\n",
" <td>0.0</td>\n",
" <td>NA</td>\n",
" <td>CompShg</td>\n",
" <td>Gable</td>\n",
" <td>Normal</td>\n",
" <td>WD</td>\n",
" <td>0.0</td>\n",
" <td>Pave</td>\n",
" <td>6</td>\n",
" <td>928.0</td>\n",
" <td>AllPub</td>\n",
" <td>212.0</td>\n",
" <td>1997</td>\n",
" <td>1998</td>\n",
" <td>2010</td>\n",
" <td>189900.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 1st Flr SF 2nd Flr SF 3Ssn Porch Alley Bedroom AbvGr \\\n",
"Order PID \n",
"1 526301100 1656.0 0.0 0.0 NA 3 \n",
"2 526350040 896.0 0.0 0.0 NA 2 \n",
"3 526351010 1329.0 0.0 0.0 NA 3 \n",
"4 526353030 2110.0 0.0 0.0 NA 3 \n",
"5 527105010 928.0 701.0 0.0 NA 3 \n",
"\n",
" Bldg Type Bsmt Cond Bsmt Exposure Bsmt Full Bath \\\n",
"Order PID \n",
"1 526301100 1Fam Gd Gd 1 \n",
"2 526350040 1Fam TA No 0 \n",
"3 526351010 1Fam TA No 0 \n",
"4 526353030 1Fam TA No 1 \n",
"5 527105010 1Fam TA No 0 \n",
"\n",
" Bsmt Half Bath Bsmt Qual Bsmt Unf SF BsmtFin SF 1 \\\n",
"Order PID \n",
"1 526301100 0 TA 441.0 639.0 \n",
"2 526350040 0 TA 270.0 468.0 \n",
"3 526351010 0 TA 406.0 923.0 \n",
"4 526353030 0 TA 1045.0 1065.0 \n",
"5 527105010 0 Gd 137.0 791.0 \n",
"\n",
" BsmtFin SF 2 BsmtFin Type 1 BsmtFin Type 2 Central Air \\\n",
"Order PID \n",
"1 526301100 0.0 BLQ Unf Y \n",
"2 526350040 144.0 Rec LwQ Y \n",
"3 526351010 0.0 ALQ Unf Y \n",
"4 526353030 0.0 ALQ Unf Y \n",
"5 527105010 0.0 GLQ Unf Y \n",
"\n",
" Condition 1 Condition 2 Electrical Enclosed Porch Exter Cond \\\n",
"Order PID \n",
"1 526301100 Norm Norm SBrkr 0.0 TA \n",
"2 526350040 Feedr Norm SBrkr 0.0 TA \n",
"3 526351010 Norm Norm SBrkr 0.0 TA \n",
"4 526353030 Norm Norm SBrkr 0.0 TA \n",
"5 527105010 Norm Norm SBrkr 0.0 TA \n",
"\n",
" Exter Qual Exterior 1st Exterior 2nd Fence Fireplace Qu \\\n",
"Order PID \n",
"1 526301100 TA BrkFace Plywood NA Gd \n",
"2 526350040 TA VinylSd VinylSd MnPrv NA \n",
"3 526351010 TA Wd Sdng Wd Sdng NA NA \n",
"4 526353030 Gd BrkFace BrkFace NA TA \n",
"5 527105010 TA VinylSd VinylSd MnPrv TA \n",
"\n",
" Fireplaces Foundation Full Bath Functional Garage Area \\\n",
"Order PID \n",
"1 526301100 2 CBlock 1 Typ 528.0 \n",
"2 526350040 0 CBlock 1 Typ 730.0 \n",
"3 526351010 0 CBlock 1 Typ 312.0 \n",
"4 526353030 2 CBlock 2 Typ 522.0 \n",
"5 527105010 1 PConc 2 Typ 482.0 \n",
"\n",
" Garage Cars Garage Cond Garage Finish Garage Qual \\\n",
"Order PID \n",
"1 526301100 2 TA Fin TA \n",
"2 526350040 1 TA Unf TA \n",
"3 526351010 1 TA Unf TA \n",
"4 526353030 2 TA Fin TA \n",
"5 527105010 2 TA Fin TA \n",
"\n",
" Garage Type Gr Liv Area Half Bath Heating Heating QC \\\n",
"Order PID \n",
"1 526301100 Attchd 1656.0 0 GasA Fa \n",
"2 526350040 Attchd 896.0 0 GasA TA \n",
"3 526351010 Attchd 1329.0 1 GasA TA \n",
"4 526353030 Attchd 2110.0 1 GasA Ex \n",
"5 527105010 Attchd 1629.0 1 GasA Gd \n",
"\n",
" House Style Kitchen AbvGr Kitchen Qual Land Contour \\\n",
"Order PID \n",
"1 526301100 1Story 1 TA Lvl \n",
"2 526350040 1Story 1 TA Lvl \n",
"3 526351010 1Story 1 Gd Lvl \n",
"4 526353030 1Story 1 Ex Lvl \n",
"5 527105010 2Story 1 TA Lvl \n",
"\n",
" Land Slope Lot Area Lot Config Lot Shape Low Qual Fin SF \\\n",
"Order PID \n",
"1 526301100 Gtl 31770.0 Corner IR1 0.0 \n",
"2 526350040 Gtl 11622.0 Inside Reg 0.0 \n",
"3 526351010 Gtl 14267.0 Corner IR1 0.0 \n",
"4 526353030 Gtl 11160.0 Corner Reg 0.0 \n",
"5 527105010 Gtl 13830.0 Inside IR1 0.0 \n",
"\n",
" MS SubClass MS Zoning Mas Vnr Area Mas Vnr Type Misc Feature \\\n",
"Order PID \n",
"1 526301100 020 RL 112.0 Stone NA \n",
"2 526350040 020 RH 0.0 None NA \n",
"3 526351010 020 RL 108.0 BrkFace Gar2 \n",
"4 526353030 020 RL 0.0 None NA \n",
"5 527105010 060 RL 0.0 None NA \n",
"\n",
" Misc Val Mo Sold Neighborhood Open Porch SF Overall Cond \\\n",
"Order PID \n",
"1 526301100 0.0 5 Names 62.0 5 \n",
"2 526350040 0.0 6 Names 0.0 6 \n",
"3 526351010 12500.0 6 Names 36.0 6 \n",
"4 526353030 0.0 4 Names 0.0 5 \n",
"5 527105010 0.0 3 Gilbert 34.0 5 \n",
"\n",
" Overall Qual Paved Drive Pool Area Pool QC Roof Matl \\\n",
"Order PID \n",
"1 526301100 6 P 0.0 NA CompShg \n",
"2 526350040 5 Y 0.0 NA CompShg \n",
"3 526351010 6 Y 0.0 NA CompShg \n",
"4 526353030 7 Y 0.0 NA CompShg \n",
"5 527105010 5 Y 0.0 NA CompShg \n",
"\n",
" Roof Style Sale Condition Sale Type Screen Porch Street \\\n",
"Order PID \n",
"1 526301100 Hip Normal WD 0.0 Pave \n",
"2 526350040 Gable Normal WD 120.0 Pave \n",
"3 526351010 Hip Normal WD 0.0 Pave \n",
"4 526353030 Hip Normal WD 0.0 Pave \n",
"5 527105010 Gable Normal WD 0.0 Pave \n",
"\n",
" TotRms AbvGrd Total Bsmt SF Utilities Wood Deck SF \\\n",
"Order PID \n",
"1 526301100 7 1080.0 AllPub 210.0 \n",
"2 526350040 5 882.0 AllPub 140.0 \n",
"3 526351010 6 1329.0 AllPub 393.0 \n",
"4 526353030 8 2110.0 AllPub 0.0 \n",
"5 527105010 6 928.0 AllPub 212.0 \n",
"\n",
" Year Built Year Remod/Add Yr Sold SalePrice \n",
"Order PID \n",
"1 526301100 1960 1960 2010 215000.0 \n",
"2 526350040 1961 1961 2010 105000.0 \n",
"3 526351010 1958 1958 2010 172000.0 \n",
"4 526353030 1968 1968 2010 244000.0 \n",
"5 527105010 1997 1998 2010 189900.0 "
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv(\"data/data_clean.csv\")"
]
}
],
"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": "3.7.8"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in a new issue View git blame Copy permalink