def complete_build(x_train, x_test, y_train, y_test):
#Called function post label encoding
lab_stats = create_stats(x_train,
x_test,
y_train,
y_test,
enc='labelencoder')
#Prepare data for one hot encoding
x_train, x_test, y_train, y_test = split_dataset(df)
category_index = [
x for x in range(len(df.columns))
if df[df.columns[x]].dtype == 'object'
]
#one hot encoding
x_train, x_test = ohe_encode(x_train, x_test, category_index)
#Called function post one hot encoding
ohe_stats = create_stats(x_train,
x_test,
y_train,
y_test,
enc='oheencoder')
final_stats = pd.concat([lab_stats, ohe_stats], axis=0)
final_stats = final_stats[['c_val', 'rmse', 'mae', 'r2']]
return final_stats
def complete_build(x_train, x_test, y_train, y_test):
stats_label = create_stats(x_train, x_test, y_train, y_test)
all_indices = list(range(0, x_train.shape[-1]))
all_indices.remove(2)
x_train_ohe, x_test_ohe = ohe_encode(x_train, x_test, all_indices)
stats_ohe = create_stats(pd.DataFrame(x_train_ohe),
pd.DataFrame(x_test_ohe),
y_train,
y_test,
enc="ohe")
model_plot = pd.concat([stats_label, stats_ohe])
model_plot.sort_values(['r2', 'rmse'], ascending=[0, 1])
return model_plot
def complete_build(x_train, x_test, y_train, y_test):
category_index = [
x for x in range(len(x_train.columns))
if x_train[x_train.columns[x]].dtype == 'object'
]
x_train_t, x_test_t = ohe_encode(x_train, x_test, category_index)
train = pd.DataFrame(x_train_t)
test = pd.DataFrame(x_test_t)
train.columns = x_train.columns.values
test.columns = x_test.columns.values
complete_stats1 = create_stats(x_train, x_test, y_train, y_test)
complete_stats = create_stats(train, test, y_train, y_test)
return pd.concat([complete_stats1, complete_stats], axis=0)