regression.py 文件源码

def __init__(self, csv_file = './data/king_county_data_geocoded.csv', data = None, values = None):
    if (data is None and csv_file is not None):
      df = pd.read_csv(csv_file)
      self.values = df['AppraisedValue']
      df = df.drop('AppraisedValue', 1)
      df = (df - df.mean()) / (df.max() - df.min())
      self.df = df
      self.df = self.df[['lat', 'long', 'SqFtLot']]

    elif (data is not None and values is not None):
      self.df = data
      self.values = values
    else:
      raise ValueError("Must have either csv_file or data set")

    self.n = len(self.df)

    self.kdtree = KDTree(self.df)
    self.metric = np.mean

    # TODO: set k to a number, try a few numbers out
    # self.k = None