def generate_standard_deviation_data(
self, model: RegressorMixin) -> RegressorMixin:
# Define some variables
predicted = None
self.standard_deviation = pd.DataFrame()
# Loop over horizons and ask prediction for each specific horizon
for horizon in self.validation_data.horizon.unique():
# Make subset for this specific horizon
sub_val = self.validation_data[self.validation_data.horizon ==
horizon]
try:
predicted = model.predict(sub_val.iloc[:, 1:-1])
except Exception as e:
print("Could not get prediction from new model!", e)
# Calculate confidence interval for this horizon
confidence_interval_horizon = self._calculate_standard_deviation(
sub_val.iloc[:, 0], predicted)
confidence_interval_horizon[
"horizon"] = horizon # Label with respective horizon
self.standard_deviation = pd.concat(
[self.standard_deviation, confidence_interval_horizon])
model.standard_deviation = self.standard_deviation
return model
def _fit_and_predict_oof_model(
self,
estimator: RegressorMixin,
X: ArrayLike,
y: ArrayLike,
train_index: ArrayLike,
val_index: ArrayLike,
sample_weight: Optional[ArrayLike] = None,
) -> Tuple[RegressorMixin, NDArray, ArrayLike]:
"""
Fit a single out-of-fold model on a given training set and
perform predictions on a test set.
Parameters
----------
estimator : RegressorMixin
Estimator to train.
X : ArrayLike of shape (n_samples, n_features)
Input data.
y : ArrayLike of shape (n_samples,)
Input labels.
train_index : ArrayLike of shape (n_samples_train)
Training data indices.
val_index : ArrayLike of shape (n_samples_val)
Validation data indices.
sample_weight : Optional[ArrayLike] of shape (n_samples,)
Sample weights. If None, then samples are equally weighted.
By default ``None``.
Returns
-------
Tuple[RegressorMixin, NDArray, ArrayLike]
- [0]: RegressorMixin, fitted estimator
- [1]: NDArray of shape (n_samples_val,),
estimator predictions on the validation fold.
- [3]: ArrayLike of shape (n_samples_val,),
validation data indices.
"""
X_train = _safe_indexing(X, train_index)
y_train = _safe_indexing(y, train_index)
X_val = _safe_indexing(X, val_index)
if sample_weight is None:
estimator = fit_estimator(estimator, X_train, y_train)
else:
sample_weight_train = _safe_indexing(sample_weight, train_index)
estimator = fit_estimator(
estimator, X_train, y_train, sample_weight_train
)
if _num_samples(X_val) > 0:
y_pred = estimator.predict(X_val)
else:
y_pred = np.array([])
return estimator, y_pred, val_index
def produce_submission(model: RegressorMixin):
td = load_test_data()
out: pd.DataFrame = model.predict(td)
submission_data = pd.DataFrame([td.index, out]).T
submission_data.columns = ['Id', 'SalePrice']
submission_data = submission_data.astype({'Id': int, 'SalePrice': float})
submission_data['SalePrice'].round(decimals=2)
submission_data.to_csv('../data/submissions/nearest-neighbors.csv', header=['Id', 'SalePrice'], index=False)
def bootstrap_regressor(
f: RegressorMixin,
X, # numpy array
y, # numpy array
num_samples: int = 100,
random_state: int = random.randint(0, 2 ** 32 - 1),
) -> List[float]:
"""
Take the regressor f, and compute it's bootstrapped accuracy over the dataset `X`,`y`.
Generate `num_samples` samples; and seed the resampler with `random_state`.
"""
dist: List[float] = []
y_pred = f.predict(X) # type:ignore
# do the bootstrap:
for trial in range(num_samples):
sample_pred, sample_truth = resample(
y_pred, y, random_state=trial + random_state
) # type:ignore
score = mean_squared_error(y_true=sample_truth, y_pred=sample_pred) # type:ignore
dist.append(score)
return dist
def bootstrap_mae(
f: RegressorMixin,
X, # numpy array
y, # numpy array
num_samples: int = 100,
random_state: int = random.randint(0, 2 ** 32 - 1),
) -> List[float]:
"""
Take the regressor ``f``, and compute it's bootstrapped mse over the dataset ``X``,``y``.
Generate ``num_samples`` samples; and seed the resampler with ``random_state``.
"""
dist: List[float] = []
y_pred = f.predict(X) # type:ignore (predict not on ClassifierMixin)
# do the bootstrap:
for trial in range(num_samples):
sample_pred, sample_truth = resample(
y_pred, y, random_state=trial + random_state
) # type:ignore
score = mean_absolute_error(y_true=sample_truth, y_pred=sample_pred) # type:ignore
dist.append(score)
return dist
