UPDATE: 2022-12-24 17:25:11
お断り。昔運営していたブログ、勉強会の資料、メモなどわわまとめた物をコピーしただけ。
Rの{xgboost}についてまとめる。{xgboost}の使い方から、変数重要度({vip})、部分従属プロット({pdp})まで。
きっかけはkaggleで勝つデータ分析の技術を読んで、XGboostの特徴について、色々と勉強になったので、それも含めメモしておく。kaggleで勝つデータ分析の技術はすごくオススメです。
普段、意思決定系のデータ分析しかしてないとしても、ガチガチに予測できるモデルを作れる技術は、意思決定の予測モデリングでも存分に役立つと思う。
特に特徴量エンジニアリングの章は、意思決定のモデリングでも使える話が盛り沢山だと思う。
XGboostの理論的な側面については下記のサイトを参照。
kaggleで勝つデータ分析の技術に記載されていたGBDTの特徴を引用させていただく。本当、実際の経験をもとに書かれているので価値がある一冊だと思います。
まずは、p114の「3.2.1 モデルと特徴量」の部分。
- 数値の大きさ自体に意味がなく、大小関係のみが影響する
- 欠損値があっても、そのまま取り扱うことができる
- 決定木の分岐の繰り返しによって変数間の相互作用が反映する
数値の大小関係が変わらない変換をかけても結果はかわりませんし、欠損値を必ずしも埋める必要もありません。また、変数間の相互作用を明示的に与えなくてもある程度反映してくれます。カテゴリ変数については、one-hot encodingでなくlabel encodingによる変換としても、分岐の繰り返しによって各カテゴリの影響をある程度反映してくれます。
p140の「3.5.2 label encoding」の部分。
決定木をベースとした手法以外では、label encodingによる特徴量を直接学習に用いるのはあまり適切ではありません。一方で、決定木であれば、カテゴリ変数の特定の水準のみが目的変数に影響がある場合でも、分岐を繰り返すことで予測値に反映できるため、学習に用いることが出来ます。
p234の「4.3.2 GDBTの特徴」の部分。
- カテゴリ変数をone-hot encodingしなくても良い
数値にする必要があるためlabel encodingは行う必要がありますが、多くの場合、one-hot encodingを行う必要がありません。これは、例えばあるカテゴリ変数cが1から10まであるときに、cが5のときのみ効く特徴だった場合に、決定木の分岐を(c < 5, 5 <= c)と(c <= 5, 5 < c)と重ねることで、cが5であるという特徴が抽出されるためです。
{xgboost}と{vip}と{pdp}XGBoostのドキュメントのRのページにあるXGBoost R Feature Walkthroughをベースにしています。
サンプルデータはKaggleのHouse
Prices: Advanced Regression
Techniques。簡単に説明すると、アメリカのアイオワ州エイムスの住宅を説明する79の特徴量を使用して、各住宅の価格(SalePrice)を予測するためのデータセット。データの詳細説明は末尾に乗せている。
library(tidyverse)
library(xgboost)
library(pdp)
library(vip)
library(gridExtra)
train <- readr::read_csv("train.csv")
test <- readr::read_csv("test.csv")
df <- train %>%
dplyr::bind_rows(., test) %>%
dplyr::select(-Id) %>%
dplyr::mutate(SalePrice = log(SalePrice))
dplyr::glimpse(df)
Observations: 2,919
Variables: 80
$ MSSubClass <dbl> 60, 20, 60, 70, 60, 50, 20, 60, 50, 190, 20, 60, 20, 20, 20, 45, 20, 90, 20, 20, 60, 45, 20, 120, 20, 20,…
$ MSZoning <chr> "RL", "RL", "RL", "RL", "RL", "RL", "RL", "RL", "RM", "RL", "RL", "RL", "RL", "RL", "RL", "RM", "RL", "RL…
【略】
$ SaleCondition <chr> "Normal", "Normal", "Normal", "Abnorml", "Normal", "Normal", "Normal", "Normal", "Abnorml", "Normal", "No…
$ SalePrice <dbl> 12.24769, 12.10901, 12.31717, 11.84940, 12.42922, 11.87060, 12.63460, 12.20607, 11.77452, 11.67844, 11.77…欠損値とかを雑に確認しておく。
# NAを含む変数
df %>%
dplyr::select(-SalePrice) %>%
purrr::map_int(.x = .,
.f = function(x) {sum(is.na(x))} ) %>%
purrr::keep(.x = .,
.p = . > 0) %>%
names()
[1] "MSZoning" "LotFrontage" "Alley" "Utilities" "Exterior1st" "Exterior2nd" "MasVnrType" "MasVnrArea"
[9] "BsmtQual" "BsmtCond" "BsmtExposure" "BsmtFinType1" "BsmtFinSF1" "BsmtFinType2" "BsmtFinSF2" "BsmtUnfSF"
[17] "TotalBsmtSF" "Electrical" "BsmtFullBath" "BsmtHalfBath" "KitchenQual" "Functional" "FireplaceQu" "GarageType"
[25] "GarageYrBlt" "GarageFinish" "GarageCars" "GarageArea" "GarageQual" "GarageCond" "PoolQC" "Fence"
[33] "MiscFeature" "SaleType" ラベルエンコーディングしておく。集計値などをつかう特徴量エンジニアリングをする際は、学習用、テスト用で分けてやる。
# Label Encoding
df_labeled <- df %>%
mutate_if(is.character, as.factor) %>%
data.matrix() %>%
tidyr::as_tibble()
dplyr::glimpse(df_labeled)
Observations: 2,919
Variables: 80
$ MSSubClass <dbl> 60, 20, 60, 70, 60, 50, 20, 60, 50, 190, 20, 60, 20, 20, 20, 45, 20, 90, 20, 20, 60, 45, 20, 120, 20, 20,…
$ MSZoning <dbl> 4, 4, 4, 4, 4, 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 5, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, 4, 4, 5, 1, 4, 4, 4, 4, …
【略】
$ SaleCondition <dbl> 5, 5, 5, 1, 5, 5, 5, 5, 1, 5, 5, 6, 5, 6, 5, 5, 5, 5, 5, 1, 6, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, …
$ SalePrice <dbl> 12.24769, 12.10901, 12.31717, 11.84940, 12.42922, 11.87060, 12.63460, 12.20607, 11.77452, 11.67844, 11.77…ここでは、ローデータの段階で訓練データとテストデータが別れているので、下記のように分割している。そうではない場合に分割するときは{rsample}の関数が便利。
df_train <- df_labeled %>% dplyr::filter(!is.na(SalePrice))
df_test <- df_labeled %>% dplyr::filter(is.na(SalePrice))
# library(rsample)
# set.seed(1)
# df_split <- rsample::initial_split(data = df_labeled, prop = 0.7)
# df_train <- rsample::training(df_split)
# df_test <- rsample::testing(df_split){xgboost}でモデリングxgboost()を使うには、xgb.DMatrixというクラスにする必要があるので変換。
xgb_train <- xgboost::xgb.DMatrix(data = df_train %>% select(-SalePrice) %>% as.matrix(),
label = df_train %>% pull(SalePrice))
xgb_test <- xgboost::xgb.DMatrix(data = df_test %>% select(-SalePrice) %>% as.matrix(),
label = df_test %>% pull(SalePrice))
xgb_train
xgb.DMatrix dim: 1460 x 79 info: label colnames: yes
dimnames(xgb_train)
[[1]]
NULL
[[2]]
[1] "MSSubClass" "MSZoning" "LotFrontage" "LotArea" "Street" "Alley" "LotShape"
[8] "LandContour" "Utilities" "LotConfig" "LandSlope" "Neighborhood" "Condition1" "Condition2"
[15] "BldgType" "HouseStyle" "OverallQual" "OverallCond" "YearBuilt" "YearRemodAdd" "RoofStyle"
[22] "RoofMatl" "Exterior1st" "Exterior2nd" "MasVnrType" "MasVnrArea" "ExterQual" "ExterCond"
[29] "Foundation" "BsmtQual" "BsmtCond" "BsmtExposure" "BsmtFinType1" "BsmtFinSF1" "BsmtFinType2"
[36] "BsmtFinSF2" "BsmtUnfSF" "TotalBsmtSF" "Heating" "HeatingQC" "CentralAir" "Electrical"
[43] "1stFlrSF" "2ndFlrSF" "LowQualFinSF" "GrLivArea" "BsmtFullBath" "BsmtHalfBath" "FullBath"
[50] "HalfBath" "BedroomAbvGr" "KitchenAbvGr" "KitchenQual" "TotRmsAbvGrd" "Functional" "Fireplaces"
[57] "FireplaceQu" "GarageType" "GarageYrBlt" "GarageFinish" "GarageCars" "GarageArea" "GarageQual"
[64] "GarageCond" "PavedDrive" "WoodDeckSF" "OpenPorchSF" "EnclosedPorch" "3SsnPorch" "ScreenPorch"
[71] "PoolArea" "PoolQC" "Fence" "MiscFeature" "MiscVal" "MoSold" "YrSold"
[78] "SaleType" "SaleCondition"
xgb_test
xgb.DMatrix dim: 1459 x 79 info: label colnames: yes
dimnames(xgb_test)
[[1]]
NULL
[[2]]
[1] "MSSubClass" "MSZoning" "LotFrontage" "LotArea" "Street" "Alley" "LotShape"
[8] "LandContour" "Utilities" "LotConfig" "LandSlope" "Neighborhood" "Condition1" "Condition2"
[15] "BldgType" "HouseStyle" "OverallQual" "OverallCond" "YearBuilt" "YearRemodAdd" "RoofStyle"
[22] "RoofMatl" "Exterior1st" "Exterior2nd" "MasVnrType" "MasVnrArea" "ExterQual" "ExterCond"
[29] "Foundation" "BsmtQual" "BsmtCond" "BsmtExposure" "BsmtFinType1" "BsmtFinSF1" "BsmtFinType2"
[36] "BsmtFinSF2" "BsmtUnfSF" "TotalBsmtSF" "Heating" "HeatingQC" "CentralAir" "Electrical"
[43] "1stFlrSF" "2ndFlrSF" "LowQualFinSF" "GrLivArea" "BsmtFullBath" "BsmtHalfBath" "FullBath"
[50] "HalfBath" "BedroomAbvGr" "KitchenAbvGr" "KitchenQual" "TotRmsAbvGrd" "Functional" "Fireplaces"
[57] "FireplaceQu" "GarageType" "GarageYrBlt" "GarageFinish" "GarageCars" "GarageArea" "GarageQual"
[64] "GarageCond" "PavedDrive" "WoodDeckSF" "OpenPorchSF" "EnclosedPorch" "3SsnPorch" "ScreenPorch"
[71] "PoolArea" "PoolQC" "Fence" "MiscFeature" "MiscVal" "MoSold" "YrSold"
[78] "SaleType" "SaleCondition"パラメタをとりあえず(よしなに調整くだされ、Kaggleだったら他のユーザーが公開しているものとか)設定し、クロスバリデーションでnroundsの数を調整する。損失が減らないのであれば、それ以上学習する必要はないので、過学習する前に学習を打ち切る。nroundsのような木の数はハイパーパラメータのチューニングに入れる必要はないそうで、詳細は下記のサイトを参照。
-なぜn_estimatorsやepochsをパラメータサーチしてはいけないのか
また、Kaggle本のp309の「6.1.2 パラメータチューニングで設定すること」の部分では、下記のようにある。
モデルのデフォルト値には、速度や単純さを重視しており、分析コンペには向いていないものもあります。例えば、xgboostのetaのデフォルト値は0.3となっていますが、これは大きすぎます。
Package ‘xgboost’を確認すると、Rのパッケージでも0.3がetaのデフォルトのようです。
eta control the learning rate: scale the contribution of each tree by a factor of 0 < eta < 1 when it is added to the current approximation. Used to prevent overfitting by making the boosting process more conservative. Lower value for eta implies larger value for nrounds: low eta value means model more robust to overfitting but slower to compute. Default: 0.3
主なパラメタは下記の通り。
eta:
学習率で、予測値をアップデートする際に掛け合わされる値。デフォルトは0.3。max_depth :
木の深さ。深くすればするほど、複雑な関係を表現できるが過学習にもなる。デフォルトは6。min_child_weight
:分岐した後の葉の最低限必要なデータの数。大きくすると、葉に必要なデータ数が足りにくくなるので、分岐しにくくなる。デフォルトは1。subsample :
決定木ごとに行数をサンプリングする割合。デフォルトは1。colsample_bytree :
決定木ごとに特徴量の数をサンプリングする割合。デフォルトは1。gamma :
決定木を分岐させるために最低限必要な目的関数の減少量。デフォルトは0。alpha :
決定木の葉のウェイトに対するL1正則化項の重み。デフォルトは0。lambda :
決定木の葉のウェイトに対するL2正則化項の重み。デフォルトは1。nrounds : 構築する決定木の数。Kaggle本のp316の「6.1.5 GBDTのパラメータおよびそのチューニング」の「Author’s Opinion」の部分では、下記のようにある。
max_depthが最も重要で、subsample、colsample_bytree、min_child_weightも重要という意見が多いようです。gamma、alpha、lambdaについてはそれぞれ好みよって優先度が異なるように思います。(T)
# booster: c("gbtree", "gblinear", "dart")
# objective: Regression = "reg:linear", Classification = "binary:logistic", MultiClass = c("multi:softmax", "multi:softprob")
# eval_metric: Regression = c("rmse", "mae"), Classification = c("logloss", "error", "auc"), MultiClass = c("merror", "mlogloss")
params <- list(
booster = "gbtree",
objective = "reg:linear",
eval_metric = "rmse",
eta = 0.1, # etaが小さいと学習に時間がかかる。
gamma = 0,
max_depth = 5
# min_child_weight = 2,
# colsample_bytree = 0.8
)
# 繰り返し回数。
# クロスバリデーションの分割数。
# 評価関数の値が改善しないときの継続数。その継続数を満たすとストップ。
# Fit
set.seed(1989)
xgb_cv <- xgboost::xgb.cv(
data = xgb_train,
nrounds = 1000, # 1000とか10000くらいでいいらしい
nfold = 5,
params = params,
early_stopping_rounds = 50
)
[1] train-rmse:10.380313+0.002714 test-rmse:10.380307+0.012391
Multiple eval metrics are present. Will use test_rmse for early stopping.
Will train until test_rmse hasn't improved in 50 rounds.
[2] train-rmse:9.344792+0.002420 test-rmse:9.344783+0.012631
[3] train-rmse:8.412910+0.002161 test-rmse:8.412902+0.012840
[4] train-rmse:7.574156+0.001924 test-rmse:7.574147+0.012563
【略】
[228] train-rmse:0.025341+0.001142 test-rmse:0.131419+0.014428
[229] train-rmse:0.025216+0.001122 test-rmse:0.131407+0.014415
Stopping. Best iteration:
[179] train-rmse:0.033059+0.000671 test-rmse:0.131305+0.014494これがnroundsの現状での設定での最適な回数。evaluation_logにはクロスバリデーションの経過過程の結果が入っている。
xgb_cv$best_iteration
[1] 179
head(xgb_cv$evaluation_log, 5)
iter train_rmse_mean train_rmse_std test_rmse_mean test_rmse_std
1: 1 10.380313 0.002713865 10.380307 0.01239056
2: 2 9.344792 0.002419657 9.344783 0.01263102
3: 3 8.412910 0.002161464 8.412902 0.01283981
4: 4 7.574156 0.001924287 7.574147 0.01256348
5: 5 6.819253 0.001710014 6.819239 0.01231013
tail(xgb_cv$evaluation_log, 5)
iter train_rmse_mean train_rmse_std test_rmse_mean test_rmse_std
1: 225 0.0256168 0.001081275 0.1314350 0.01439371
2: 226 0.0255420 0.001095117 0.1314284 0.01439814
3: 227 0.0254436 0.001153605 0.1314152 0.01441775
4: 228 0.0253414 0.001142210 0.1314194 0.01442756
5: 229 0.0252158 0.001122084 0.1314066 0.01441493
# Learning Curve
# xgb_cv$evaluation_log %>%
# ggplot(aes(x = iter)) +
# geom_line(aes(y = train_rmse_mean, col = "train")) +
# geom_line(aes(y = test_rmse_mean, col = "test")) +
# ggtitle("rmse") + ylab("rmse_mean")現状最適なnroundsを使ってモデルを学習し直す。
# Fit
set.seed(1989)
xgb_fit <- xgboost::xgboost(param = params,
data = xgb_train,
nrounds = xgb_cv$best_iteration)
[1] train-rmse:10.380111
[2] train-rmse:9.344444
【略】
[178] train-rmse:0.039547
[179] train-rmse:0.039418
# Prediction
xgb_pred <- exp(predict(xgb_fit, xgb_test))
# テストデータの正解ラベルをもっているようなバリデーションの仕方であれば
# library(MLmetrics)
# MLmetrics::RMSE(y_pred = xgb_pred,
# y_true = <test label>)
{vip}で変数重要度を可視化する{vip}を使って変数重要度を確認する。変数重要度の計算に関する説明はこちらを参照。{tidymodels}を使って一連の説明をされていおり、しかも非常にわかりやすいです。
Permutationベースの変数重要度の計算は、簡単?に言ってしまうと、興味のある特徴量を1つ選び、それ以外の特徴量は固定しながら、興味のある特徴量はランダムにシャッフルする。予測値と興味のある特徴量の組み合わせが有効な場合、つまり予測に役立つ特徴量である場合、予測精度は良いわけだが、その組み合わせをシャッフルすることで、組み合わせが壊されると、その結果として予測精度が悪くなるのであれば、その興味のある特徴量というのは重要な特徴とみなせる一方で、そもそも、予測値と特徴量の組み合わせが有効ではない場合、シャッフルしようが、しまいが予測精度には影響しない、という考え方。
# Variable Importance Plot
vip_plot <- vip::vip(xgb_fit, num_features = 30)
head(vip_plot$data)
# A tibble: 6 x 2
Variable Importance
<chr> <dbl>
1 OverallQual 0.196
2 GrLivArea 0.193
3 TotalBsmtSF 0.118
4 GarageCars 0.0708
5 GarageFinish 0.0376
6 YearRemodAdd 0.0368
print(vip_plot)[f:id:AZUMINO:20191130141530p:plain]
{pdp}で部分従属プロットを可視化する{pdp}を使って部分従属プロットを確認する。住宅の全体的な品質Overall_QualとGr_Liv_Areaは、Sale_Priceを予測する上で重要な特徴なので、これらがSale_Priceに与える影響を可視化する。trainは訓練データのターゲット抜きを渡す。先程と同様にこちらを参照。
部分従属プロットは簡単?に言ってしまうと、興味のある特徴量を1つ選び、その特徴量の最小値から最大値までを使って、それ以外の特徴量は固定しながら順番に興味ある特徴量のみを数値を変化させたときに、予測値がどう変化するのかを見たもの。{pdp}の部分従属プロットの赤い線は平均的な予測値で、黒い線(Individual
Conditional Expectation : ICE)は各レコードの予測値。
# Partial Dependence Plot
p1 <- pdp::partial(
xgb_fit,
pred.var = "OverallQual",
ice = TRUE,
center = TRUE,
plot = TRUE,
rug = TRUE,
alpha = 0.1,
plot.engine = "ggplot2",
train = df_train %>% select(-SalePrice) %>% as.matrix()
)
p2 <- pdp::partial(
xgb_fit,
pred.var = "GrLivArea",
ice = TRUE,
center = TRUE,
plot = TRUE,
rug = TRUE,
alpha = 0.1,
plot.engine = "ggplot2",
train = df_train %>% select(-SalePrice) %>% as.matrix()
)
p3 <- pdp::partial(
xgb_fit,
pred.var = c("OverallQual", "GrLivArea"),
plot = TRUE,
chull = TRUE,
plot.engine = "ggplot2",
train = df_train %>% select(-SalePrice) %>% as.matrix()
)
grid.arrange(p1, p2, p3, ncol = 3)[f:id:AZUMINO:20191130142040p:plain]
MSSubClass: Identifies the type of dwelling involved in the sale.
20 1-STORY 1946 & NEWER ALL STYLES
30 1-STORY 1945 & OLDER
40 1-STORY W/FINISHED ATTIC ALL AGES
45 1-1/2 STORY - UNFINISHED ALL AGES
50 1-1/2 STORY FINISHED ALL AGES
60 2-STORY 1946 & NEWER
70 2-STORY 1945 & OLDER
75 2-1/2 STORY ALL AGES
80 SPLIT OR MULTI-LEVEL
85 SPLIT FOYER
90 DUPLEX - ALL STYLES AND AGES
120 1-STORY PUD (Planned Unit Development) - 1946 & NEWER
150 1-1/2 STORY PUD - ALL AGES
160 2-STORY PUD - 1946 & NEWER
180 PUD - MULTILEVEL - INCL SPLIT LEV/FOYER
190 2 FAMILY CONVERSION - ALL STYLES AND AGES
MSZoning: Identifies the general zoning classification of the sale.
A Agriculture
C Commercial
FV Floating Village Residential
I Industrial
RH Residential High Density
RL Residential Low Density
RP Residential Low Density Park
RM Residential Medium Density
LotFrontage: Linear feet of street connected to property
LotArea: Lot size in square feet
Street: Type of road access to property
Grvl Gravel
Pave Paved
Alley: Type of alley access to property
Grvl Gravel
Pave Paved
NA No alley access
LotShape: General shape of property
Reg Regular
IR1 Slightly irregular
IR2 Moderately Irregular
IR3 Irregular
LandContour: Flatness of the property
Lvl Near Flat/Level
Bnk Banked - Quick and significant rise from street grade to building
HLS Hillside - Significant slope from side to side
Low Depression
Utilities: Type of utilities available
AllPub All public Utilities (E,G,W,& S)
NoSewr Electricity, Gas, and Water (Septic Tank)
NoSeWa Electricity and Gas Only
ELO Electricity only
LotConfig: Lot configuration
Inside Inside lot
Corner Corner lot
CulDSac Cul-de-sac
FR2 Frontage on 2 sides of property
FR3 Frontage on 3 sides of property
LandSlope: Slope of property
Gtl Gentle slope
Mod Moderate Slope
Sev Severe Slope
Neighborhood: Physical locations within Ames city limits
Blmngtn Bloomington Heights
Blueste Bluestem
BrDale Briardale
BrkSide Brookside
ClearCr Clear Creek
CollgCr College Creek
Crawfor Crawford
Edwards Edwards
Gilbert Gilbert
IDOTRR Iowa DOT and Rail Road
MeadowV Meadow Village
Mitchel Mitchell
Names North Ames
NoRidge Northridge
NPkVill Northpark Villa
NridgHt Northridge Heights
NWAmes Northwest Ames
OldTown Old Town
SWISU South & West of Iowa State University
Sawyer Sawyer
SawyerW Sawyer West
Somerst Somerset
StoneBr Stone Brook
Timber Timberland
Veenker Veenker
Condition1: Proximity to various conditions
Artery Adjacent to arterial street
Feedr Adjacent to feeder street
Norm Normal
RRNn Within 200' of North-South Railroad
RRAn Adjacent to North-South Railroad
PosN Near positive off-site feature--park, greenbelt, etc.
PosA Adjacent to postive off-site feature
RRNe Within 200' of East-West Railroad
RRAe Adjacent to East-West Railroad
Condition2: Proximity to various conditions (if more than one is present)
Artery Adjacent to arterial street
Feedr Adjacent to feeder street
Norm Normal
RRNn Within 200' of North-South Railroad
RRAn Adjacent to North-South Railroad
PosN Near positive off-site feature--park, greenbelt, etc.
PosA Adjacent to postive off-site feature
RRNe Within 200' of East-West Railroad
RRAe Adjacent to East-West Railroad
BldgType: Type of dwelling
1Fam Single-family Detached
2FmCon Two-family Conversion; originally built as one-family dwelling
Duplx Duplex
TwnhsE Townhouse End Unit
TwnhsI Townhouse Inside Unit
HouseStyle: Style of dwelling
1Story One story
1.5Fin One and one-half story: 2nd level finished
1.5Unf One and one-half story: 2nd level unfinished
2Story Two story
2.5Fin Two and one-half story: 2nd level finished
2.5Unf Two and one-half story: 2nd level unfinished
SFoyer Split Foyer
SLvl Split Level
OverallQual: Rates the overall material and finish of the house
10 Very Excellent
9 Excellent
8 Very Good
7 Good
6 Above Average
5 Average
4 Below Average
3 Fair
2 Poor
1 Very Poor
OverallCond: Rates the overall condition of the house
10 Very Excellent
9 Excellent
8 Very Good
7 Good
6 Above Average
5 Average
4 Below Average
3 Fair
2 Poor
1 Very Poor
YearBuilt: Original construction date
YearRemodAdd: Remodel date (same as construction date if no remodeling or additions)
RoofStyle: Type of roof
Flat Flat
Gable Gable
Gambrel Gabrel (Barn)
Hip Hip
Mansard Mansard
Shed Shed
RoofMatl: Roof material
ClyTile Clay or Tile
CompShg Standard (Composite) Shingle
Membran Membrane
Metal Metal
Roll Roll
Tar&Grv Gravel & Tar
WdShake Wood Shakes
WdShngl Wood Shingles
Exterior1st: Exterior covering on house
AsbShng Asbestos Shingles
AsphShn Asphalt Shingles
BrkComm Brick Common
BrkFace Brick Face
CBlock Cinder Block
CemntBd Cement Board
HdBoard Hard Board
ImStucc Imitation Stucco
MetalSd Metal Siding
Other Other
Plywood Plywood
PreCast PreCast
Stone Stone
Stucco Stucco
VinylSd Vinyl Siding
Wd Sdng Wood Siding
WdShing Wood Shingles
Exterior2nd: Exterior covering on house (if more than one material)
AsbShng Asbestos Shingles
AsphShn Asphalt Shingles
BrkComm Brick Common
BrkFace Brick Face
CBlock Cinder Block
CemntBd Cement Board
HdBoard Hard Board
ImStucc Imitation Stucco
MetalSd Metal Siding
Other Other
Plywood Plywood
PreCast PreCast
Stone Stone
Stucco Stucco
VinylSd Vinyl Siding
Wd Sdng Wood Siding
WdShing Wood Shingles
MasVnrType: Masonry veneer type
BrkCmn Brick Common
BrkFace Brick Face
CBlock Cinder Block
None None
Stone Stone
MasVnrArea: Masonry veneer area in square feet
ExterQual: Evaluates the quality of the material on the exterior
Ex Excellent
Gd Good
TA Average/Typical
Fa Fair
Po Poor
ExterCond: Evaluates the present condition of the material on the exterior
Ex Excellent
Gd Good
TA Average/Typical
Fa Fair
Po Poor
Foundation: Type of foundation
BrkTil Brick & Tile
CBlock Cinder Block
PConc Poured Contrete
Slab Slab
Stone Stone
Wood Wood
BsmtQual: Evaluates the height of the basement
Ex Excellent (100+ inches)
Gd Good (90-99 inches)
TA Typical (80-89 inches)
Fa Fair (70-79 inches)
Po Poor (<70 inches
NA No Basement
BsmtCond: Evaluates the general condition of the basement
Ex Excellent
Gd Good
TA Typical - slight dampness allowed
Fa Fair - dampness or some cracking or settling
Po Poor - Severe cracking, settling, or wetness
NA No Basement
BsmtExposure: Refers to walkout or garden level walls
Gd Good Exposure
Av Average Exposure (split levels or foyers typically score average or above)
Mn Mimimum Exposure
No No Exposure
NA No Basement
BsmtFinType1: Rating of basement finished area
GLQ Good Living Quarters
ALQ Average Living Quarters
BLQ Below Average Living Quarters
Rec Average Rec Room
LwQ Low Quality
Unf Unfinshed
NA No Basement
BsmtFinSF1: Type 1 finished square feet
BsmtFinType2: Rating of basement finished area (if multiple types)
GLQ Good Living Quarters
ALQ Average Living Quarters
BLQ Below Average Living Quarters
Rec Average Rec Room
LwQ Low Quality
Unf Unfinshed
NA No Basement
BsmtFinSF2: Type 2 finished square feet
BsmtUnfSF: Unfinished square feet of basement area
TotalBsmtSF: Total square feet of basement area
Heating: Type of heating
Floor Floor Furnace
GasA Gas forced warm air furnace
GasW Gas hot water or steam heat
Grav Gravity furnace
OthW Hot water or steam heat other than gas
Wall Wall furnace
HeatingQC: Heating quality and condition
Ex Excellent
Gd Good
TA Average/Typical
Fa Fair
Po Poor
CentralAir: Central air conditioning
N No
Y Yes
Electrical: Electrical system
SBrkr Standard Circuit Breakers & Romex
FuseA Fuse Box over 60 AMP and all Romex wiring (Average)
FuseF 60 AMP Fuse Box and mostly Romex wiring (Fair)
FuseP 60 AMP Fuse Box and mostly knob & tube wiring (poor)
Mix Mixed
1stFlrSF: First Floor square feet
2ndFlrSF: Second floor square feet
LowQualFinSF: Low quality finished square feet (all floors)
GrLivArea: Above grade (ground) living area square feet
BsmtFullBath: Basement full bathrooms
BsmtHalfBath: Basement half bathrooms
FullBath: Full bathrooms above grade
HalfBath: Half baths above grade
Bedroom: Bedrooms above grade (does NOT include basement bedrooms)
Kitchen: Kitchens above grade
KitchenQual: Kitchen quality
Ex Excellent
Gd Good
TA Typical/Average
Fa Fair
Po Poor
TotRmsAbvGrd: Total rooms above grade (does not include bathrooms)
Functional: Home functionality (Assume typical unless deductions are warranted)
Typ Typical Functionality
Min1 Minor Deductions 1
Min2 Minor Deductions 2
Mod Moderate Deductions
Maj1 Major Deductions 1
Maj2 Major Deductions 2
Sev Severely Damaged
Sal Salvage only
Fireplaces: Number of fireplaces
FireplaceQu: Fireplace quality
Ex Excellent - Exceptional Masonry Fireplace
Gd Good - Masonry Fireplace in main level
TA Average - Prefabricated Fireplace in main living area or Masonry Fireplace in basement
Fa Fair - Prefabricated Fireplace in basement
Po Poor - Ben Franklin Stove
NA No Fireplace
GarageType: Garage location
2Types More than one type of garage
Attchd Attached to home
Basment Basement Garage
BuiltIn Built-In (Garage part of house - typically has room above garage)
CarPort Car Port
Detchd Detached from home
NA No Garage
GarageYrBlt: Year garage was built
GarageFinish: Interior finish of the garage
Fin Finished
RFn Rough Finished
Unf Unfinished
NA No Garage
GarageCars: Size of garage in car capacity
GarageArea: Size of garage in square feet
GarageQual: Garage quality
Ex Excellent
Gd Good
TA Typical/Average
Fa Fair
Po Poor
NA No Garage
GarageCond: Garage condition
Ex Excellent
Gd Good
TA Typical/Average
Fa Fair
Po Poor
NA No Garage
PavedDrive: Paved driveway
Y Paved
P Partial Pavement
N Dirt/Gravel
WoodDeckSF: Wood deck area in square feet
OpenPorchSF: Open porch area in square feet
EnclosedPorch: Enclosed porch area in square feet
3SsnPorch: Three season porch area in square feet
ScreenPorch: Screen porch area in square feet
PoolArea: Pool area in square feet
PoolQC: Pool quality
Ex Excellent
Gd Good
TA Average/Typical
Fa Fair
NA No Pool
Fence: Fence quality
GdPrv Good Privacy
MnPrv Minimum Privacy
GdWo Good Wood
MnWw Minimum Wood/Wire
NA No Fence
MiscFeature: Miscellaneous feature not covered in other categories
Elev Elevator
Gar2 2nd Garage (if not described in garage section)
Othr Other
Shed Shed (over 100 SF)
TenC Tennis Court
NA None
MiscVal: $Value of miscellaneous feature
MoSold: Month Sold (MM)
YrSold: Year Sold (YYYY)
SaleType: Type of sale
WD Warranty Deed - Conventional
CWD Warranty Deed - Cash
VWD Warranty Deed - VA Loan
New Home just constructed and sold
COD Court Officer Deed/Estate
Con Contract 15% Down payment regular terms
ConLw Contract Low Down payment and low interest
ConLI Contract Low Interest
ConLD Contract Low Down
Oth Other
SaleCondition: Condition of sale
Normal Normal Sale
Abnorml Abnormal Sale - trade, foreclosure, short sale
AdjLand Adjoining Land Purchase
Alloca Allocation - two linked properties with separate deeds, typically condo with a garage unit
Family Sale between family members
Partial Home was not completed when last assessed (associated with New Homes)