Given a list where each element is a dataframe, i want to create sliding windows in order to train a lstm model, but the problem is an error occurs. Each dataframe is a time series with the 4 columns but different length.
import import_ipynb
import split_data
import numpy as np
train, val, test = split_data.split_datasets()
window_size = 5
window_datasets = []
for i in range(len(train)):
window_datasets.append(create_sliding_windows(train[i], window_size=5, n_future=1))
def create_sliding_windows(df, window_size=5, n_future=1):
trainX = []
trainY = []
for i in range(window_size, len(df) - n_future + 1):
trainX.append(df[i - window_size:i, 0:df.shape[1]])
trainY.append(df[i + n_future - 1, i + n_future, 0])
return np.array(trainX), np.array(trainY)
The error i achieve is :
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
3802 try:
-> 3803 return self._engine.get_loc(casted_key)
3804 except KeyError as err:
~/anaconda3/lib/python3.8/site-packages/pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
~/anaconda3/lib/python3.8/site-packages/pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
TypeError: '(slice(0, 5, None), slice(0, 4, None))' is an invalid key
During handling of the above exception, another exception occurred:
InvalidIndexError Traceback (most recent call last)
<ipython-input-68-7cd0d5e7624d> in <module>
6 window_datasets = []
7 for i in range(len(train)):
----> 8 window_datasets.append(create_sliding_windows(train[i], window_size=5, n_future=1))
9
10
<ipython-input-66-9d44549be273> in create_sliding_windows(df, window_size, n_future)
3 trainY = []
4 for i in range(window_size, len(df) - n_future + 1):
----> 5 trainX.append(df[i - window_size:i, 0:df.shape[1]])
6 trainY.append(df[i + n_future - 1, i + n_future, 0])
7
~/anaconda3/lib/python3.8/site-packages/pandas/core/frame.py in getitem(self, key)
3803 if self.columns.nlevels > 1:
3804 return self._getitem_multilevel(key)
-> 3805 indexer = self.columns.get_loc(key)
3806 if is_integer(indexer):
3807 indexer = [indexer]
~/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
3808 # InvalidIndexError. Otherwise we fall through and re-raise
3809 # the TypeError.
-> 3810 self._check_indexing_error(key)
3811 raise
3812
~/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py in _check_indexing_error(self, key)
5966 # if key is not a scalar, directly raise an error (the code below
5967 # would convert to numpy arrays and raise later any way) - GH29926
-> 5968 raise InvalidIndexError(key)
5969
5970 @cache_readonly
InvalidIndexError: (slice(0, 5, None), slice(0, 4, None))
