This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
from torch import LongTensor | |
from torch.nn import Embedding, LSTM | |
from torch.autograd import Variable | |
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence | |
## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium'] | |
# | |
# Step 1: Construct Vocabulary | |
# Step 2: Load indexed data (list of instances, where each instance is list of character indices) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
def shrink_df(df, categorize=False, verbose=False): | |
"""Reduces the memory use of a data frame by using more compact types. | |
Args: | |
df (pandas.DataFrame): The dataframe | |
categorize (bool): Whether strings should be converted to categorical values. | |
Note this may cause memory use to increase slightly. | |
verbose (bool): Whether to print memory savings to stdout. |