def prepare_datatraining(self):
"""
Step to build the training and testing set
"""
self.array_features_totrain, self.array_labels_totrain , self.df_totrain = ext.prepare_data(self.df_decks_totrain, self.features)
self.next(self.prepare_mlmagic)
def prepare_datascoring(self):
"""
Step to build the scoring set
"""
self.array_features_toscore, self.array_labels_toscore, self.df_toscore = ext.prepare_data(self.df_decks_toscore, self.features)
self.next(self.prepare_mlmagic)
for idx, features in enumerate(features_cardid[:-1]):
features_cardid.append(features)
informations_topcards[archetypes[idx]] = features
features = list(itertools.chain.from_iterable(features_cardid))
features = list(dict.fromkeys(features))
dict_df_decks_dataset = {
"train" : df_decks_totrain,
"test" : df_decks_totest,
"score" : df_decks_toscore,
}
dict_df_decks_dataset_rtu = {}
for dataset in dict_df_decks_dataset:
array_features, array_labels, df = ext.prepare_data(dict_df_decks_dataset[dataset], features)
dict_df_decks_dataset_rtu[dataset] = {
"array_features" : array_features,
"array_labels" : array_labels,
"df" : df
}
parameters_model = random.choices(combinations_parameters_randomforest, k = 5)
"""
trigger_build_model + build_model steps
"""
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score