【Kaggle】Intermediate Machine Learning（管道+交叉验证）

from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder

# Preprocessing for numerical data 数字数据插值
numerical_transformer = SimpleImputer(strategy='constant')

# Preprocessing for categorical data 文字特征处理，插值+编码转换
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])

# Bundle preprocessing for numerical and categorical data
# 上面两者合并起来，形成完整的数据处理流程
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, numerical_cols),
        ('cat', categorical_transformer, categorical_cols)
    ])

from sklearn.ensemble import RandomForestRegressor

model = RandomForestRegressor(n_estimators=100, random_state=0)

# Bundle preprocessing and modeling code in a pipeline
# 将 前处理管道 + 模型管道，再次叠加形成新管道
my_pipeline = Pipeline(steps=[('preprocessor', preprocessor),
                              ('model', model)
                             ])

# Preprocessing of training data, fit model 
my_pipeline.fit(X_train, y_train)

# Preprocessing of validation data, get predictions
preds = my_pipeline.predict(X_valid)

# 用定义好的pipeline 对test进行预测，提交，代码很简洁，不易出错
preds_test = my_pipeline.predict(X_test)
# Save test predictions to file
output = pd.DataFrame({'Id': X_test.index,
                       'SalePrice': preds_test})
output.to_csv('submission.csv', index=False)

from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer

my_pipeline = Pipeline(steps=[
		('preprocessor', SimpleImputer()),
		('model', RandomForestRegressor(n_estimators=50,random_state=0))
])

from sklearn.model_selection import cross_val_score
# Multiply by -1 since sklearn calculates *negative* MAE
scores = -1 * cross_val_score(my_pipeline, X, y,
                              cv=5,
                              scoring='neg_mean_absolute_error')
print("MAE scores:\n", scores)
print("Average MAE score (across experiments):")
print(scores.mean())

# 树的棵数不同情况下，交叉验证的得分均值
def get_score(n_estimators):
    """Return the average MAE over 3 CV folds of random forest model.
    Keyword argument:
    n_estimators -- the number of trees in the forest
    """
    my_pipeline = Pipeline(steps=[
        ('preprocessing',SimpleImputer()),
        ('model',RandomForestRegressor(n_estimators=n_estimators,random_state=0))
    ])
    scores = -1*cross_val_score(my_pipeline,X,y,cv=3,scoring='neg_mean_absolute_error')
    return scores.mean()

results = {}
for i in range(1,9):# 获取树的棵树是50，100，。。。，400时，模型的效果
    results[50*i] = get_score(50*i)

# 可视化不同参数下的模型效果
import matplotlib.pyplot as plt
%matplotlib inline

plt.plot(list(results.keys()), list(results.values()))
plt.show()
n_estimators_best = min(results, key=results.get) #最合适的参数