def learn(self, from_data, test_data=None):
"""
Train and save a model (you can use this to retrain model from data).
:param from_data: DataFrame or DataSource
The data to learn from
:param test_data: DataFrame or DataSource
The data to test accuracy and learn_error from
"""
device, _available_devices = get_devices()
log.info(f'Computing device used: {device}')
# generate the configuration and set the order for the input and output columns
if self._generate_config is True:
self._input_columns = [col for col in from_data if col not in self._output_columns]
self.config = {
'input_features': [{'name': col, 'type': self._type_map(from_data, col)} for col in self._input_columns],
'output_features': [{'name': col, 'type': self._type_map(from_data, col)} for col in self._output_columns]
}
self.config = predictor_config_schema.validate(self.config)
log.info('Automatically generated a configuration')
log.info(self.config)
else:
self._output_columns = [col['name'] for col in self.config['output_features']]
self._input_columns = [col['name'] for col in self.config['input_features']]
if isinstance(from_data, pandas.DataFrame):
train_ds = DataSource(from_data, self.config)
elif isinstance(from_data, DataSource):
train_ds = from_data
else:
raise TypeError(':from_data: must be either DataFrame or DataSource')
nr_subsets = 3 if len(train_ds) > 100 else 1
if test_data is None:
test_ds = train_ds.subset(0.1)
elif isinstance(test_data, pandas.DataFrame):
test_ds = train_ds.make_child(test_data)
elif isinstance(test_data, DataSource):
test_ds = test_data
else:
raise TypeError(':test_data: must be either DataFrame or DataSource')
train_ds.create_subsets(nr_subsets)
test_ds.create_subsets(nr_subsets)
train_ds.train()
test_ds.train()
mixer_class = self.config['mixer']['class']
mixer_kwargs = self.config['mixer']['kwargs']
self._mixer = mixer_class(**mixer_kwargs)
self._mixer.fit(train_ds=train_ds, test_ds=test_ds)
self.train_accuracy = self._mixer.calculate_accuracy(test_ds)
return self
def test_fit_and_predict(self):
config = {
'input_features': [{
'name': 'x',
'type': 'numeric'
}, {
'name': 'y',
'type': 'numeric'
}],
'output_features': [{
'name': 'z',
'type': 'numeric'
}, {
'name': 'z`',
'type': 'categorical'
}]
}
config = predictor_config_schema.validate(config)
N = 100
data = {
'x': [i for i in range(N)],
'y': [random.randint(i, i + 20) for i in range(N)]
}
nums = [data['x'][i] * data['y'][i] for i in range(N)]
data['z'] = [i + 0.5 for i in range(N)]
data['z`'] = ['low' if i < 50 else 'high' for i in nums]
data_frame = pandas.DataFrame(data)
train_ds = DataSource(data_frame, config)
test_ds = train_ds.subset(0.25)
mixer = BoostMixer()
mixer.fit(train_ds, test_ds)
predictions = mixer.predict(train_ds.make_child(data_frame[['x',
'y']]))