Function get_data

supervised_class2/rf_classification.py:87–102

()

def get_data():
  df = pd.read_csv('../large_files/mushroom.data', header=None)

  # replace label column: e/p --> 0/1
  # e = edible = 0, p = poisonous = 1
  df[0] = df.apply(lambda row: 0 if row[0] == 'e' else 1, axis=1)

  # check if there is missing data
  replace_missing(df)

  # transform the data
  transformer = DataTransformer()

  X = transformer.fit_transform(df)
  Y = df[0].values
  return X, Y


if __name__ == '__main__':