def _train(train_data: DataFrame, classifier: ClassifierMixin,
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 = DataFrame(cluster_train_df['label'])
try:
classifier.fit(cluster_train_df.drop('label', 1),
cluster_targets_df.values.ravel())
except (NotImplementedError, KeyError):
classifier.partial_fit(
cluster_train_df.drop('label', 1).values,
cluster_targets_df.values.ravel())
except Exception as exception:
raise exception
models[cluster] = classifier
try:
classifier = clone(classifier)
except TypeError:
classifier = clone(classifier, safe=False)
classifier.reset()
return {
ModelType.CLUSTERER.value: clusterer,
ModelType.CLASSIFIER.value: models
}
def _train(train_data: DataFrame, time_series_predictor: Any, 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:
time_series_predictor.fit(cluster_train_df)
models[cluster] = time_series_predictor
time_series_predictor = clone(time_series_predictor, safe=False)
return {ModelType.CLUSTERER.value: clusterer, ModelType.TIME_SERIES_PREDICTOR.value: models}
def _train(train_data: DataFrame, time_series_predictor: Any,
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:
time_series_predictor.fit(cluster_train_df)
models[cluster] = time_series_predictor
time_series_predictor = clone(time_series_predictor, safe=False)
return {'clusterer': clusterer, 'time_series_predictor': models}
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}