def train_script_2():
dbreader = DbReader(PATH, split_size=ONE_PERSON_SPLIT)
training_commands = getting_commands_from_signals(
dbreader.training_signals[:2], dbreader.training_text[:2])
valid_commands = getting_commands_from_signals(
dbreader.training_signals[2:], dbreader.training_text[2:])
training_mfcc_data = simple_mfcc(training_commands)
valid_mfcc_data = simple_mfcc(valid_commands)
y_train = training_mfcc_data['command']
X_train = training_mfcc_data.drop(columns=['command'])
y_valid = valid_mfcc_data['command']
X_valid = valid_mfcc_data.drop(columns=['command'])
rf_model = RandomForestModel()
model_to_fit = rf_model.gridsearchCV()
model_to_fit.fit(X_train, y_train)
rf_model.set_internal_model(model_to_fit.best_estimator_)
print(model_to_fit.best_estimator_)
rf_model.save_model()
joblib.dump(dbreader, "dbreader.mdl")
predictions = rf_model.predict(X_valid)
plot_confusion_matrix(y_valid, predictions)
def train_script():
dbreader = DbReader(PATH, split_size=ONE_PERSON_SPLIT)
commands = getting_commands_from_signals(dbreader.training_signals,
dbreader.training_text)
mfcc_data = simple_mfcc(commands)
y_train = mfcc_data['command']
X_train = mfcc_data.drop(columns=['command'])
rf_model = RandomForestModel()
model_to_fit = rf_model.gridsearchCV()
model_to_fit.fit(X_train, y_train)
rf_model.set_internal_model(model_to_fit.best_estimator_)
print(model_to_fit.best_estimator_)
rf_model.save_model()
joblib.dump(dbreader, "dbreader.mdl")
def train_script():
db_reader = DbReader()
hyper_dataset = db_reader.load_csv("../allhyper.data")
hypo_dataset = db_reader.load_csv("../allhypo.data")
X, y = create_dataset_for_training(hyper_dataset, hypo_dataset)
X = preprocess_the_data(X)
rf_model = RandomForestModel()
filtered_features = feature_selection(X, y, rf_model.internal_model)
with open('selected_best_features.data', 'wb') as filehandle:
pickle.dump(filtered_features,filehandle)
model_to_fit = rf_model.gridsearchCV()
model_to_fit.fit(X[filtered_features], y)
print(model_to_fit.best_score_)
print(model_to_fit.best_params_)
print(filtered_features)
rf_model.set_internal_model(model_to_fit.best_estimator_)
rf_model.save_model()