随机森林 Random Forests

波士顿房价 

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
    
#载入数据
melbourne_file_path = '../input/melbourne-housing-snapshot/melb_data.csv'
melbourne_data = pd.read_csv(melbourne_file_path) 

# 哑变量处理
melbourne_data = melbourne_data.dropna(axis=0)
#选择y值，即要预测的值
y = melbourne_data.Price
#选择x值
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'BuildingArea', 
                        'YearBuilt', 'Lattitude', 'Longtitude']
X = melbourne_data[melbourne_features]

#训练+预测+模型验证（平均绝对误差）
train_X, val_X, train_y, val_y = train_test_split(X, y,random_state = 0)
forest_model = RandomForestRegressor(random_state=1)
forest_model.fit(train_X, train_y)
melb_preds = forest_model.predict(val_X)
print(mean_absolute_error(val_y, melb_preds))