kagglegym.py 文件源码

def __init__(self):
        with pd.HDFStore("../input/train.h5", "r") as hfdata:
            self.timestamp = 0
            fullset = hfdata.get("train")
            self.unique_timestamp = fullset["timestamp"].unique()
            # Get a list of unique timestamps
            # use the first half for training and
            # the second half for the test set
            n = len(self.unique_timestamp)
            i = int(n/2)
            timesplit = self.unique_timestamp[i]
            self.n = n
            self.unique_idx = i
            self.train = fullset[fullset.timestamp < timesplit]
            self.test = fullset[fullset.timestamp >= timesplit]

            # Needed to compute final score
            self.full = self.test.loc[:, ['timestamp', 'y']]
            self.full['y_hat'] = 0.0
            self.temp_test_y = None