終了済み: Re:不動産取引価格予測

評価指標をRMSLEと改めて開催します

賞金: 100,000 参加ユーザー数: 261 4ヶ月前に終了

LightGBMを使ったBase line

不動産取引価格予測

LightGBMを使ったBase lineです。ご参考までご活用ください。

CV= 0.438692 LB= 0.41466 でした。

# ライブラリのインポート
import pandas as pd
import numpy as np
import re
import lightgbm as lgb
from sklearn.model_selection import train_test_split
import warnings
warnings.filterwarnings('ignore')

# データの読込
train = pd.read_csv("./input/train_data.csv")
test = pd.read_csv('./input/test_data.csv')

前処理

# 間取りデータを変換
def change_to_madori(train):
    train['L'] = train['間取り'].map(lambda x: 1 if 'L' in str(x) else 0)
    train['D'] = train['間取り'].map(lambda x: 1 if 'D' in str(x) else 0)
    train['K'] = train['間取り'].map(lambda x: 1 if 'K' in str(x) else 0)
    train['S'] = train['間取り'].map(lambda x: 1 if 'S' in str(x) else 0)
    train['R'] = train['間取り'].map(lambda x: 1 if 'R' in str(x) else 0)
    train['Maisonette'] = train['間取り'].map(lambda x: 1 if 'メゾネット' in str(x) else 0)
    train['OpenFloor'] = train['間取り'].map(lambda x: 1 if 'オープンフロア' in str(x) else 0)
    train['Studio'] = train['間取り'].map(lambda x: 1 if 'スタジオ' in str(x) else 0)
    train['RoomNum'] = train['間取り'].map(lambda x: re.sub("\\D", "", str(x)))
    train['RoomNum'] = train['RoomNum'].map(lambda x:int(x) if x!='' else 0)
change_to_madori(train)
change_to_madori(test)
# 数値化
def change_to_number(df,input_column_name,output_column_name):
    df[output_column_name] = df[input_column_name].map(lambda x: re.sub(r'([0-9]+)m\^2未満', '9', str(x)))
    df[output_column_name] = df[output_column_name].map(lambda x: re.sub("\\D", "", str(x)))
    df[output_column_name] = df[output_column_name].map(lambda x:int(x) if x!='' else -1)
change_to_number(train,'延床面積(㎡)','TotalFloorArea')
change_to_number(test,'延床面積(㎡)','TotalFloorArea')
change_to_number(train,'面積(㎡)','Area')
change_to_number(test,'面積(㎡)','Area')
change_to_number(train,'取引時点',"Period")
change_to_number(test,'取引時点',"Period")
# 時間の変換
def change_to_minute(df,input_column_name,output_column_name):
    df[output_column_name] = df[input_column_name].map(lambda x: re.sub("30分\?60分", "30", str(x)))
    df[output_column_name] = df[output_column_name].map(lambda x: re.sub("2H\?", "120", str(x)))
    df[output_column_name] = df[output_column_name].map(lambda x: re.sub("1H30\?2H", "90", str(x)))
    df[output_column_name] = df[output_column_name].map(lambda x: re.sub("1H\?1H30", "60", str(x))) 
    df[output_column_name] = df[output_column_name].map(lambda x: re.sub("\\D", "", str(x)))
    df[output_column_name] = df[output_column_name].map(lambda x:int(x) if x!='' else -1)
change_to_minute(train,'最寄駅:距離(分)','TimeToNearestStation')
change_to_minute(test,'最寄駅:距離(分)','TimeToNearestStation')
# 数値化2
def change_to_float(df,input_column_name,output_column_name):
    # 50m以上は51にする
    df[output_column_name] = df[input_column_name].map(lambda x: re.sub("50.0m以上", "51.0", str(x)))
    #数値にする(Nullの場合はー1にする)
    df[output_column_name] = df[output_column_name].map(lambda x:float(x) if x!='nan' else -1)
change_to_float(train,'間口',"Frontage")
change_to_float(test,'間口',"Frontage")
change_to_float(train,'前面道路:幅員(m)',"Breadth")
change_to_float(test,'前面道路:幅員(m)',"Breadth")
change_to_float(train,'建ぺい率(%)',"CoverageRatio")
change_to_float(test,'建ぺい率(%)',"CoverageRatio")
change_to_float(train,'容積率(%)',"FloorAreaRatio")
change_to_float(test,'容積率(%)',"FloorAreaRatio")
# 年の西暦化
def change_to_year(df,input_column_name,output_column_name):
    # 戦前は昭和15年に置き換える
    df[output_column_name] = df[input_column_name].map(lambda x: re.sub(r'戦前', '昭和15年', str(x)))
    #昭和を西暦に変換する
    df[output_column_name] = df[output_column_name].map(lambda x:int(re.sub("\\D", "", str(x)))+1925 if '昭和' in str(x) else x)
    #平成を西暦に変換する
    df[output_column_name] = df[output_column_name].map(lambda x:int(re.sub("\\D", "", str(x)))+1988 if '平成' in str(x) else x)
    #nanを-1に変換する
    df[output_column_name] = df[output_column_name].map(lambda x: -1 if x=='nan' else x)
#    df = df.drop(input_column_name,axis=1)
change_to_year(train,'建築年','BuildingYear')
change_to_year(test,'建築年','BuildingYear')
# ターゲットエンコーディング
def change_to_target2(train_df,test_df,input_column_name,output_column_name):
    from sklearn.model_selection import KFold
    
    # nan埋め処理
    train[input_column_name] = train[input_column_name].fillna('-1').isnull().sum()
    test[input_column_name] = test[input_column_name].fillna('-1').isnull().sum()

    kf = KFold(n_splits=5, shuffle=True, random_state=71)
    #=========================================================#
    c=input_column_name
    # 学習データ全体で各カテゴリにおけるyの平均を計算
    data_tmp = pd.DataFrame({c: train_df[c],'target':train_df['y']})
    target_mean = data_tmp.groupby(c)['target'].mean()
    #テストデータのカテゴリを置換
    test_df[output_column_name] = test_df[c].map(target_mean)
    
    # 変換後の値を格納する配列を準備
    tmp = np.repeat(np.nan, train_df.shape[0])

    for i, (train_index, test_index) in enumerate(kf.split(train_df)): # NFOLDS回まわる
        #学習データについて、各カテゴリにおける目的変数の平均を計算
        target_mean = data_tmp.iloc[train_index].groupby(c)['target'].mean()
        #バリデーションデータについて、変換後の値を一時配列に格納
        tmp[test_index] = train_df[c].iloc[test_index].map(target_mean) 

    #変換後のデータで元の変数を置換
    train_df[output_column_name] = tmp
#========================================================#   
change_to_target2(train,test,"種類","Type")
change_to_target2(train,test,"地域","Region")
change_to_target2(train,test,"市区町村コード","MunicipalityCode")
change_to_target2(train,test,"都道府県名","Prefecture")
change_to_target2(train,test,"市区町村名","Municipality")
change_to_target2(train,test,"地区名","DistrictName")
change_to_target2(train,test,"最寄駅:名称","NearestStation")
change_to_target2(train,test,"土地の形状","LandShape")
change_to_target2(train,test,"建物の構造","Structure")
change_to_target2(train,test,"用途","Use")
change_to_target2(train,test,"今後の利用目的","Purpose")
change_to_target2(train,test,"前面道路:方位","Direction")
change_to_target2(train,test,"前面道路:種類","Classification")
change_to_target2(train,test,"都市計画","CityPlanning")
change_to_target2(train,test,"改装", "Renovation")
change_to_target2(train,test,"取引の事情等","Remarks")
# 変換前の列を削除
jap_col = ['id', '種類', '地域', '市区町村コード', '都道府県名', '市区町村名', '地区名', '最寄駅:名称',
       '最寄駅:距離(分)', '間取り', '面積(㎡)', '土地の形状', '間口', '延床面積(㎡)', '建築年', '建物の構造',
       '用途', '今後の利用目的', '前面道路:方位', '前面道路:種類', '前面道路:幅員(m)', '都市計画', '建ぺい率(%)',
       '容積率(%)', '取引時点', '改装', '取引の事情等']
train = train.drop(jap_col,axis=1)
test = test.drop(jap_col,axis=1)

データの確認

# 訓練データとテストデータの列を確認
print(train.columns)
print(test.columns)
Index(['y', 'L', 'D', 'K', 'S', 'R', 'Maisonette', 'OpenFloor', 'Studio',
       'RoomNum', 'TotalFloorArea', 'Area', 'Period', 'TimeToNearestStation',
       'Frontage', 'Breadth', 'CoverageRatio', 'FloorAreaRatio',
       'BuildingYear', 'Type', 'Region', 'MunicipalityCode', 'Prefecture',
       'Municipality', 'DistrictName', 'NearestStation', 'LandShape',
       'Structure', 'Use', 'Purpose', 'Direction', 'Classification',
       'CityPlanning', 'Renovation', 'Remarks'],
      dtype='object')
Index(['L', 'D', 'K', 'S', 'R', 'Maisonette', 'OpenFloor', 'Studio', 'RoomNum',
       'TotalFloorArea', 'Area', 'Period', 'TimeToNearestStation', 'Frontage',
       'Breadth', 'CoverageRatio', 'FloorAreaRatio', 'BuildingYear', 'Type',
       'Region', 'MunicipalityCode', 'Prefecture', 'Municipality',
       'DistrictName', 'NearestStation', 'LandShape', 'Structure', 'Use',
       'Purpose', 'Direction', 'Classification', 'CityPlanning', 'Renovation',
       'Remarks'],
      dtype='object')
# 訓練データに欠損がないことの確認
train.isnull().sum()
y                       0
L                       0
D                       0
K                       0
S                       0
R                       0
Maisonette              0
OpenFloor               0
Studio                  0
RoomNum                 0
TotalFloorArea          0
Area                    0
Period                  0
TimeToNearestStation    0
Frontage                0
Breadth                 0
CoverageRatio           0
FloorAreaRatio          0
BuildingYear            0
Type                    0
Region                  0
MunicipalityCode        0
Prefecture              0
Municipality            0
DistrictName            0
NearestStation          0
LandShape               0
Structure               0
Use                     0
Purpose                 0
Direction               0
Classification          0
CityPlanning            0
Renovation              0
Remarks                 0
dtype: int64
# テストデータに欠損がないことの確認
test.isnull().sum()
L                       0
D                       0
K                       0
S                       0
R                       0
Maisonette              0
OpenFloor               0
Studio                  0
RoomNum                 0
TotalFloorArea          0
Area                    0
Period                  0
TimeToNearestStation    0
Frontage                0
Breadth                 0
CoverageRatio           0
FloorAreaRatio          0
BuildingYear            0
Type                    0
Region                  0
MunicipalityCode        0
Prefecture              0
Municipality            0
DistrictName            0
NearestStation          0
LandShape               0
Structure               0
Use                     0
Purpose                 0
Direction               0
Classification          0
CityPlanning            0
Renovation              0
Remarks                 0
dtype: int64

学習の準備

# 訓練データを説明変数と目的変数に分割
target = np.log(train['y']) # RMSLEを求めるためにlogをとる
train_x = train.drop('y',axis=1)
# 訓練データから検証用データを作成
X_train, X_test, y_train, y_test = train_test_split(train_x, target, test_size=0.1, random_state=42)
lgb_train = lgb.Dataset(X_train, y_train)
lgb_valid = lgb.Dataset(X_test, y_test, reference=lgb_train)
# LGBMのパラメータを設定
params = {
    'boosting_type': 'gbdt',
    'objective': 'regression',
    'metric': 'rmse',
    'num_leaves': 31,
    'learning_rate': 0.01,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0,
    'n_estimators':20000,
    'early_stopping_rounds':1000,
    'seed': 42    
}

学習の実行

# 学習の実行
model = lgb.train(params,
                  lgb_train,
                  valid_names=['train', 'valid'],
                  valid_sets=[lgb_train, lgb_valid],
                  verbose_eval=200)
Training until validation scores don't improve for 1000 rounds
[200]	train's rmse: 0.510617	valid's rmse: 0.512846
[400]	train's rmse: 0.467615	valid's rmse: 0.471829
[600]	train's rmse: 0.454878	valid's rmse: 0.460003
[800]	train's rmse: 0.448517	valid's rmse: 0.454627
[1000]	train's rmse: 0.444594	valid's rmse: 0.451654
[1200]	train's rmse: 0.441706	valid's rmse: 0.44966
[1400]	train's rmse: 0.43958	valid's rmse: 0.4483
[1600]	train's rmse: 0.437561	valid's rmse: 0.44712
[1800]	train's rmse: 0.435834	valid's rmse: 0.446286
[2000]	train's rmse: 0.434292	valid's rmse: 0.445535
[2200]	train's rmse: 0.432887	valid's rmse: 0.444923
[2400]	train's rmse: 0.431582	valid's rmse: 0.444364
[2600]	train's rmse: 0.430375	valid's rmse: 0.444005
[2800]	train's rmse: 0.429199	valid's rmse: 0.443627
[3000]	train's rmse: 0.428064	valid's rmse: 0.443247
[3200]	train's rmse: 0.426985	valid's rmse: 0.442905
[3400]	train's rmse: 0.426062	valid's rmse: 0.442629
[3600]	train's rmse: 0.425058	valid's rmse: 0.442326
[3800]	train's rmse: 0.424232	valid's rmse: 0.442072
[4000]	train's rmse: 0.423273	valid's rmse: 0.441794
[4200]	train's rmse: 0.422327	valid's rmse: 0.441642
[4400]	train's rmse: 0.421518	valid's rmse: 0.441471
[4600]	train's rmse: 0.420683	valid's rmse: 0.441286
[4800]	train's rmse: 0.419912	valid's rmse: 0.441178
[5000]	train's rmse: 0.419078	valid's rmse: 0.441014
[5200]	train's rmse: 0.418339	valid's rmse: 0.440855
[5400]	train's rmse: 0.417618	valid's rmse: 0.440717
[5600]	train's rmse: 0.416885	valid's rmse: 0.440615
[5800]	train's rmse: 0.416171	valid's rmse: 0.440444
[6000]	train's rmse: 0.415472	valid's rmse: 0.440298
[6200]	train's rmse: 0.414765	valid's rmse: 0.440191
[6400]	train's rmse: 0.414065	valid's rmse: 0.440094
[6600]	train's rmse: 0.413412	valid's rmse: 0.440025
[6800]	train's rmse: 0.412772	valid's rmse: 0.43997
[7000]	train's rmse: 0.412178	valid's rmse: 0.439854
[7200]	train's rmse: 0.411563	valid's rmse: 0.439766
[7400]	train's rmse: 0.410977	valid's rmse: 0.439697
[7600]	train's rmse: 0.410427	valid's rmse: 0.439674
[7800]	train's rmse: 0.409802	valid's rmse: 0.439618
[8000]	train's rmse: 0.409166	valid's rmse: 0.43949
[8200]	train's rmse: 0.408573	valid's rmse: 0.439464
[8400]	train's rmse: 0.408041	valid's rmse: 0.439386
[8600]	train's rmse: 0.407454	valid's rmse: 0.439233
[8800]	train's rmse: 0.406891	valid's rmse: 0.439193
[9000]	train's rmse: 0.40632	valid's rmse: 0.439086
[9200]	train's rmse: 0.405757	valid's rmse: 0.439065
[9400]	train's rmse: 0.405243	valid's rmse: 0.438984
[9600]	train's rmse: 0.404755	valid's rmse: 0.438947
[9800]	train's rmse: 0.404201	valid's rmse: 0.438996
[10000]	train's rmse: 0.40369	valid's rmse: 0.438976
[10200]	train's rmse: 0.40317	valid's rmse: 0.438967
[10400]	train's rmse: 0.402662	valid's rmse: 0.438933
[10600]	train's rmse: 0.402217	valid's rmse: 0.438961
[10800]	train's rmse: 0.40169	valid's rmse: 0.438879
[11000]	train's rmse: 0.401236	valid's rmse: 0.438865
[11200]	train's rmse: 0.400762	valid's rmse: 0.438877
[11400]	train's rmse: 0.400244	valid's rmse: 0.438806
[11600]	train's rmse: 0.399784	valid's rmse: 0.438796
[11800]	train's rmse: 0.399317	valid's rmse: 0.438767
[12000]	train's rmse: 0.398832	valid's rmse: 0.438731
[12200]	train's rmse: 0.398355	valid's rmse: 0.438712
[12400]	train's rmse: 0.397905	valid's rmse: 0.438737
[12600]	train's rmse: 0.39749	valid's rmse: 0.438715
[12800]	train's rmse: 0.397064	valid's rmse: 0.438728
[13000]	train's rmse: 0.396657	valid's rmse: 0.438706
[13200]	train's rmse: 0.396231	valid's rmse: 0.438713
[13400]	train's rmse: 0.39578	valid's rmse: 0.43873
[13600]	train's rmse: 0.395341	valid's rmse: 0.438728
Early stopping, best iteration is:
[12660]	train's rmse: 0.397355	valid's rmse: 0.438692

予測の実行

# 予測の実行
predicts = model.predict(test)
predicts.shape
(34844,)
# 学習時に目的変数のlogをとっているのでもとに戻す
predicts = np.exp(predicts)
# 提出用ファイルを作成する
pd.DataFrame({"id": range(len(predicts)), "y": predicts }).to_csv("001_submission.csv", index=False)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from matplotlib import pyplot as plt

"""LightGBM を使った特徴量の重要度の可視化"""
# 特徴量の重要度をプロットする
lgb.plot_importance(model, figsize=(12, 6))
plt.show()

添付データ

  • LGBM_01.ipynb?X-Amz-Expires=600&X-Amz-Date=20201204T145415Z&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIP7GCBGMWPMZ42PQ
  • Favicon
    new user
    コメントするには 新規登録 もしくは ログイン が必要です。