def load_features(self):
# retrieve values from config, assign_category does this
self.set('df', pd.read_csv(self.get('file')))
df = self.get('df')
df.reset_index(inplace=True, drop=True)
categories, unique_values, default_list, frequent_values2frequency = self.assign_category(
df)
default_values = [str(v) for v in default_list.values()]
self.set(
'data',
preprocessing.insert_data(df, categories, unique_values,
default_list, frequent_values2frequency,
SAMPLE_DATA_SIZE))
self.set('defaults',
dict(zip(self.get('data').index.tolist(), default_values)))
self.set('category_list', categories)
return categories
default_list = {
'sepal_length': 5.8,
'sepal_width': 3.0,
'petal_length': 4.35,
'petal_width': 1.3,
'class': 'Iris-setosa'
}
frequent_values2frequency = {
'sepal_length': (5.0, 10),
'sepal_width': (3.0, 26),
'petal_length': (1.5, 14),
'petal_width': (0.2, 28),
'class': ('Iris-setosa', 50)
}
SAMPLE_DATA_SIZE = 5
data = preprocessing.insert_data(df, categories, unique_values, default_list,
frequent_values2frequency, SAMPLE_DATA_SIZE)
data.Category = categories
labels = feature_util.get_target_labels(target, data.Category[target], fs)
all_params_config = config_reader.read_config(config_file)
export_dir = all_params_config.export_dir()
dtypes = fs.group_by(categories)
category_list = [
'numerical', 'numerical', 'numerical', 'numerical', 'categorical'
]
features = fs.create_tf_features(categories, target)
def test_add_and_get_port():
t.add_port(username, config_file, port)
assert t.get_port(username, config_file) == port
def test_insert_data():
data = preprocessing.insert_data(df, categories, unique_values, default_list, frequent_values2frequency,
SAMPLE_DATA_SIZE)
assert data.values.size == 45
assert data.shape == (5, 9)