Wann-Jiun

from scipy.stats import skew

skewed_features = train_df[numerical_features].apply(lambda x: skew(x.dropna().astype(float)))
skewed_features = skewed_features[skewed_features > 0.75]
skewed_features = skewed_features.index

train_df[skewed_features] = np.log1p(train_df[skewed_features])
test_df[skewed_features] = np.log1p(test_df[skewed_features])

Wann-Jiun

from sklearn.preprocessing import StandardScaler
scaling = StandardScaler()
scaling.fit(train_df[numerical_features])

scaling_result = scaling.transform(train_df[numerical_features])
for i, col in enumerate(numerical_features):
    train_df[col] = scaling_result[:, i]

scaling_result = scaler.transform(test_df_munged[numeric_features])
for i, col in enumerate(numeric_features):

Wann-Jiun

train_df["MasVnrArea"].fillna(0, inplace=True)

Wann-Jiun

all_df["CentralAir"] = (df["CentralAir"] == "Y") * 1.0

Wann-Jiun

dummies = pd.get_dummies(train_df[column_name], prefix = "_" + column_name)
train_df = train_df.join(dummies)
train_df = train_df.drop([column_name], axis=1)

Wann-Jiun

all_df["LotFrontage"] = df["LotFrontage"]   
for key, group in lot_frontage_by_neighborhood:
    idx = (df["Neighborhood"] == key) & (df["LotFrontage"].isnull())
    all_df.loc[idx, "LotFrontage"] = group.median()

Wann-Jiun

train_df["Is_Electrical_SBrkr"] = (df["Electrical"] == "SBrkr") * 1

Wann-Jiun

train_df["Aggregate_OverallQual"] = train_df.OverallQual.replace(
{1 : 1, 2 : 1, 3 : 1, 4 : 2, 5 : 2, 6 : 2, 7 : 3, 8 : 3, 9 : 3, 10 : 3})

Wann-Jiun

train_df["New_House"] = (train_df["YearRemodAdd"] == train_df["YrSold"]) * 1

Wann-Jiun

# Kernel Ridge GridSearch
from sklearn.kernel_ridge import KernelRidge

kridge_grid = KernelRidge()

parameter_grid = {'alpha': [0.0001,0.001,0.01,0.1],
                 'degree': [1,2,3,4],
                 'kernel': ['polynomial']
                 #'n_estimators': [200,210,240,250],
                 #'min_child_weight': [1,2,3,4]