def _train(train_data: DataFrame,
regressor: RegressorMixin,
clusterer: Clustering,
do_cv=False) -> dict:
models = dict()
train_data = clusterer.cluster_data(train_data)
for cluster in range(clusterer.n_clusters):
cluster_train_df = train_data[cluster]
if not cluster_train_df.empty:
cluster_targets_df = cluster_train_df['label']
if do_cv:
cross_validation_result = cross_validate(
regressor,
cluster_train_df.drop('label', 1),
cluster_targets_df.values.ravel(),
return_estimator=True,
cv=10 #TODO per Chiara check se vuoi 10 cv
)
validation_scores = cross_validation_result['test_score']
regressors = cross_validation_result['estimator']
regressor = regressors[dict(
zip(validation_scores, range(len(validation_scores)))
)[max(
validation_scores
)]] #TODO per Chiara check se vuoi il max o min o quello che sta in mezzo
else:
regressor.fit(cluster_train_df.drop('label', 1),
cluster_targets_df.values.ravel())
models[cluster] = regressor
try:
regressor = clone(regressor)
except TypeError:
regressor = clone(regressor, safe=False)
return {
ModelType.CLUSTERER.value: clusterer,
ModelType.REGRESSOR.value: models
}
def _train(train_data: DataFrame, regressor: RegressorMixin, clusterer: Clustering) -> dict:
models = dict()
train_data = clusterer.cluster_data(train_data)
for cluster in range(clusterer.n_clusters):
cluster_train_df = train_data[cluster]
if not cluster_train_df.empty:
cluster_targets_df = cluster_train_df['label']
regressor.fit(cluster_train_df.drop('label', 1), cluster_targets_df.values.ravel())
models[cluster] = regressor
try:
regressor = clone(regressor)
except TypeError:
regressor = clone(regressor, safe=False)
return {'clusterer': clusterer, PredictiveModels.REGRESSION.value: models}
def _cv_estimate(model: RegressorMixin,
train_data: pd.DataFrame,
features: List[str],
y: str,
n_splits: int) -> Tuple[pd.Series, List[RegressorMixin]]:
cv = KFold(n_splits=n_splits)
models = []
cv_pred = pd.Series(np.nan, index=train_data.index)
for train, test in cv.split(train_data):
m = model.fit(train_data[features].iloc[train], train_data[y].iloc[train])
cv_pred.iloc[test] = m.predict(train_data[features].iloc[test])
models += [m]
return cv_pred, models