How to create input samples from pandas dataframe

Question

I'm trying to create a LSTM model that gives me binary output buy or not. I have data that is in the format of: [date_time, close, volume], in millions of rows. I'm stuck at formatting the data as 3-D; Samples, Timesteps, features.

I have used pandas to read the data. I want to format it so I can get 4000 samples with 400 timesteps each, and two features (close and volume). Can someone advise on how to do this?

EDIT: I am using the TimeseriesGenerator as advised, but I am not sure how to check my sequences and replace the output Y with my own binary buy output.

df = normalize_data(df)

print("Creating sequences for NN \n")
targets = df.drop('date_time', 1)
train = keras.preprocessing.sequence.TimeseriesGenerator(df, targets, 1, sampling_rate=1, stride=1,
                                                         start_index=0, end_index=int(len(df.index)*0.8),
                                                         shuffle=True, reverse=False, batch_size=time_steps)

This is running without error, but now the output is the first close value after input timeseries.

EDIT 2: So thus far my code looks like this:

df = data.normalize_data(df)
targets = df.iloc[:, 3]  # Buy signal target

df.drop('y1', axis=1, inplace=True)
df.drop('y2', axis=1, inplace=True)

train = TimeseriesGenerator(df, targets, length=1, sampling_rate=1, stride=1,
                            start_index=0, end_index=int(len(df.index) * 0.8),
                            shuffle=True, reverse=False, batch_size=time_steps)

# number of samples
print("Samples: " + str(len(train)))
x, y = train[0]
print(str(x))

The output is as follows:

Samples: 8
Traceback (most recent call last):
File "/home/stian/.local/lib/python3.6/site- 
packages/pandas/core/indexes/base.py", line 3078, in get_loc
return self._engine.get_loc(key)
File "pandas/_libs/index.pyx", line 140, in 
pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: range(418, 419)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "./main.py", line 94, in <module>
data_menu()
File "./main.py", line 42, in data_menu
data_menu()
File "./main.py", line 56, in data_menu
nn_menu()
File "./main.py", line 76, in nn_menu
nn.nn_gen(pre_processed_data)
File "/home/stian/git/stian9k/nn.py", line 33, in nn_gen
x, y = train[0]
File "/home/stian/.local/lib/python3.6/site-packages/keras_preprocessing/sequence.py", line 378, in __getitem__
samples[j] = self.data[indices]
File "/home/stian/.local/lib/python3.6/site-packages/pandas/core/frame.py", line 2688, in __getitem__
return self._getitem_column(key)
File "/home/stian/.local/lib/python3.6/site-packages/pandas/core/frame.py", line 2695, in _getitem_column
return self._get_item_cache(key)
File "/home/stian/.local/lib/python3.6/site-packages/pandas/core/generic.py", line 2489, in _get_item_cache
values = self._data.get(item)
File "/home/stian/.local/lib/python3.6/site-packages/pandas/core/internals.py", line 4115, in get
loc = self.items.get_loc(item)
File "/home/stian/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py", line 3080, in get_loc
return self._engine.get_loc(self._maybe_cast_indexer(key))
File "pandas/_libs/index.pyx", line 140, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc
File "pandas/_libs/hashtable_class_helper.pxi", line 1492, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas/_libs/hashtable_class_helper.pxi", line 1500, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: range(418, 419)

So it seems that even tough I am getting 8 objects from the generator I am not able to look them up. If I test the type: print(str(type(train))) I get TimeseriesGenerator object. Any advise is much appreciated again.

EDIT 3: it turns out timeseriesgenerator did not like pandas dataframes. The issue was resolved by converting to numpy array as well as converting pandas timestamp type to float.

Answer 1

You can simply use Keras TimeseriesGenerator for this purpose. You can easily set the length (i.e. number of timesteps in each sample), sampling rate and stride to sub-sample the data.

It would return an instance of Sequence class which you can then pass to fit_generator to fit the model on the data generated by it. I highly recommend to read the documentation for more info about this class, its arguments and its usage.