House Priceの分析4

XGBRegressorっていう、回帰モデルがあるので確認。 そもそも xgboost が結構界隈では有名らしい。

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import Imputer

data = pd.read_csv('kaggle/kaggle1/train.csv')
data.isnull().any(axis=0)

# Imputerは欠損値を mean（平均）, median（中央値）, mode（最頻値）のどれかに置き換える

data.dropna(axis=0, subset=['SalePrice'], inplace=True)
y = data.SalePrice
X = data.drop(['SalePrice'], axis=1).select_dtypes(exclude=['object'])

train_X, test_X, train_y, test_y = train_test_split(X.as_matrix(), y.as_matrix(), test_size=0.25)

my_imputer = Imputer()
train_X = my_imputer.fit_transform(train_X)
test_X = my_imputer.transform(test_X)

from xgboost import XGBRegressor

my_model = XGBRegressor()
# Add silent=True to avoid printing out updates with each cycle
my_model.fit(train_X, train_y, verbose=False)

# make predictions
predictions = my_model.predict(test_X)

from sklearn.metrics import mean_absolute_error
print("Mean Absolute Error : " + str(mean_absolute_error(predictions, test_y)))

my_model = XGBRegressor(n_estimators=1000)
my_model.fit(train_X, train_y, early_stopping_rounds=5, 
             eval_set=[(test_X, test_y)], verbose=False)

my_model = XGBRegressor(n_estimators=1000, learning_rate=0.05)
my_model.fit(train_X, train_y, early_stopping_rounds=5, 
             eval_set=[(test_X, test_y)], verbose=False)