Intro and intermediate Machine Learning 课程总结

describe() #描述每一列的计数、均值、标准差等数据
head() #列出前X行的数据

from sklearn.tree import Dmelbourne_model.predict(X.head()ecisionTreeRegressor

# Define model. Specify a number for random_state to ensure same results each run
melbourne_model = DecisionTreeRegressor(random_state=1)

# Fit model
melbourne_model.fit(X, y)

#predict data
melbourne_model.predict(X.head()

from sklearn.metrics import mean_absolute_error

predicted_home_prices = melbourne_model.predict(X)
mean_absolute_error(y, predicted_home_prices)

#确定存在缺失值的列名
cols_with_missing = [col for col in X.columns if X[col].isnull().any()]

#快速插值
from sklearn.impute import SimpleImputer

# Imputation
my_imputer = SimpleImputer()
imputed_X_train = pd.DataFrame(my_imputer.fit_transform(X_train))
imputed_X_valid = pd.DataFrame(my_imputer.transform(X_valid))

#确定哪一列是类别型变量：
s = (X.dtypes == 'object')
object_cols = list(s[s].index)

from sklearn.preprocessing import OrdinalEncoder

# Make copy to avoid changing original data
label_X_train = X_train.copy()
label_X_valid = X_valid.copy()

# Apply ordinal encoder to each column with categorical data
ordinal_encoder = OrdinalEncoder()
label_X_train[object_cols] = ordinal_encoder.fit_transform(X_train[object_cols])
label_X_valid[object_cols] = ordinal_encoder.transform(X_valid[object_cols])

from sklearn.preprocessing import OneHotEncoder

# Apply one-hot encoder to each column with categorical data
OH_encoder = OneHotEncoder(handle_unknown='ignore', sparse=False)
OH_cols_train = pd.DataFrame(OH_encoder.fit_transform(X_train[object_cols]))
OH_cols_valid = pd.DataFrame(OH_encoder.transform(X_valid[object_cols]))

# One-hot encoding removed index; put it back
OH_cols_train.index = X_train.index
OH_cols_valid.index = X_valid.index

# Remove categorical columns (will replace with one-hot encoding)
num_X_train = X_train.drop(object_cols, axis=1)
num_X_valid = X_valid.drop(object_cols, axis=1)

# Add one-hot encoded columns to numerical features
OH_X_train = pd.concat([num_X_train, OH_cols_train], axis=1)
OH_X_valid = pd.concat([num_X_valid, OH_cols_valid], axis=1)

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

# 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)
    ])

from sklearn.ensemble import RandomForestRegressor

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

from sklearn.metrics import mean_absolute_error

# Bundle preprocessing and modeling code in a pipeline
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)

# Evaluate the model
score = mean_absolute_error(y_valid, preds)

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')

from xgboost import XGBRegressor

my_model = XGBRegressor()
my_model.fit(X_train, y_train)