Kaggle教程

缺失值

抛弃条目；填补；填补并额外添加新的Boolean列示意是否缺失

from sklearn.impute import SimpleImputer
my_imputer = SimpleImputer()
imputed_X_train = pd.DataFrame(my_imputer.fit_transform(X_train))
imputed_X_valid = pd.DataFrame(my_imputer.transform(X_valid))

误差

from sklearn.metrics import mean_absolute_error
mean_absolute_error(y_valid, preds)

非数值类型的类别变量

from sklearn.preprocessing import LabelEncoder
# Make copy to avoid changing original data 
label_X_train = X_train.copy()
label_X_valid = X_valid.copy()

# Apply label encoder to each column with categorical data
label_encoder = LabelEncoder()
for col in object_cols:
    label_X_train[col] = label_encoder.fit_transform(X_train[col])
    label_X_valid[col] = label_encoder.transform(X_valid[col])

print("MAE from Approach 2 (Label Encoding):") 
print(score_dataset(label_X_train, label_X_valid, y_train, y_valid))

或以下同一目的的不同实现

from sklearn.preprocessing import OneHotEncoder

管道（类似于建造者模式）

from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error

# Preprocessing for numerical data
numerical_transformer = SimpleImputer(strategy='constant')

# Preprocessing for categorical data
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])

# Bundle preprocessing for numerical and categorical data
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, numerical_cols),
        ('cat', categorical_transformer, categorical_cols)
    ])

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

# Bundle preprocessing and modeling code in a pipeline
clf = Pipeline(steps=[('preprocessor', preprocessor),
                      ('model', model)
                     ])

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

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

print('MAE:', mean_absolute_error(y_valid, preds))