4649236213

Build Type

github

Committed by GitHub

Commit Message

Merge 0b894402b into 4646f5c3f

Pull Request Pull Request #44: Make imputation models `val_X_intact` and `val_indicating_mask` be included in input `val_set` originally

Run Details

15 of 15 new or added lines in 6 files covered. (100.0%)

2694 of 3170 relevant lines covered (84.98%)

0.85 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

17.65

/pypots/data/load_preprocessing.py

"""
Preprocessing functions to load supported open-source time-series datasets.
"""

# Created by Wenjie Du <wenjay.du@gmail.com>
# License: GLP-v3

import pandas as pd


def preprocess_physionet2012(data: dict) -> dict:
    """The preprocessing function for dataset PhysioNet-2012.

    Parameters
    ----------
    data : dict,
        A data dict from tsdb.load_dataset().

    Returns
    -------
    dataset : dict,
        A dict containing processed data, including:
            X : pandas.DataFrame,
                A dataframe contains all time series vectors from 11988 patients, distinguished by column `RecordID`.
            y : pandas.Series
                The 11988 classification labels of all patients, indicating whether they were deceased.
    """
    # remove the static features, e.g. age, gender
    X = data["X"].drop(data["static_features"], axis=1)

    def apply_func(df_temp):  # pad and truncate to set the max length of samples as 48
        missing = list(set(range(0, 48)).difference(set(df_temp["Time"])))
        missing_part = pd.DataFrame({"Time": missing})
        df_temp = pd.concat(
            [df_temp, missing_part], ignore_index=False, sort=False
        )  # pad the sample's length to 48 if it doesn't have enough time steps
        df_temp = df_temp.set_index("Time").sort_index().reset_index()
        df_temp = df_temp.iloc[:48]  # truncate
        return df_temp

    X = X.groupby("RecordID").apply(apply_func)
    X = X.drop("RecordID", axis=1)
    X = X.reset_index()
    X = X.drop(["level_1", "Time"], axis=1)

    dataset = {
        "X": X,
        "y": data["y"],
    }

    return dataset

1	"""	1✔
2	Preprocessing functions to load supported open-source time-series datasets.
3	"""
4
5	# Created by Wenjie Du <wenjay.du@gmail.com>
6	# License: GLP-v3
7
8	import pandas as pd	1✔
9
10
11	def preprocess_physionet2012(data: dict) -> dict:	1✔
12	"""The preprocessing function for dataset PhysioNet-2012.
13
14	Parameters
15	----------
16	data : dict,
17	A data dict from tsdb.load_dataset().
18
19	Returns
20	-------
21	dataset : dict,
22	A dict containing processed data, including:
23	X : pandas.DataFrame,
24	A dataframe contains all time series vectors from 11988 patients, distinguished by column `RecordID`.
25	y : pandas.Series
26	The 11988 classification labels of all patients, indicating whether they were deceased.
27	"""
28	# remove the static features, e.g. age, gender
29	X = data["X"].drop(data["static_features"], axis=1)	×
30
31	def apply_func(df_temp): # pad and truncate to set the max length of samples as 48	×
32	missing = list(set(range(0, 48)).difference(set(df_temp["Time"])))	×
33	missing_part = pd.DataFrame({"Time": missing})	×
34	df_temp = pd.concat(	×
35	[df_temp, missing_part], ignore_index=False, sort=False
36	) # pad the sample's length to 48 if it doesn't have enough time steps
37	df_temp = df_temp.set_index("Time").sort_index().reset_index()	×
38	df_temp = df_temp.iloc[:48] # truncate	×
39	return df_temp	×
40
41	X = X.groupby("RecordID").apply(apply_func)	×
42	X = X.drop("RecordID", axis=1)	×
43	X = X.reset_index()	×
44	X = X.drop(["level_1", "Time"], axis=1)	×
45
46	dataset = {	×
47	"X": X,
48	"y": data["y"],
49	}
50
51	return dataset	×

WenjieDu / PyPOTS / 4649236213

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous