import torch.nn as nn
import torch.nn.functional as F
class MultilayerPerceptron(nn.Module):
def __init__(self, input_dim, hidden_dim, output_dim):
"""
Args:
input_dim (int): the size of the input vectors
hidden_dim (int): the output size of the first Linear layer
output_dim (int): the output size of the second Linear layer
"""
super(MultilayerPerceptron, self).__init__()
self.fc1 = nn.Linear(input_dim, hidden_dim)
self.fc2 = nn.Linear(hidden_dim, output_dim)
def forward(self, x_in, apply_softmax=False):
"""The forward pass of the MLP
Args:
x_in (torch.Tensor): an input data tensor.
x_in.shape should be (batch, input_dim)
apply_softmax (bool): a flag for the softmax activation
should be false if used with the Cross Entropy losses
Returns:
the resulting tensor. tensor.shape should be (batch, output_dim)
"""
intermediate = F.relu(self.fc1(x_in))
output = self.fc2(intermediate)
if apply_softmax:
output = F.softmax(output, dim=1)
return output
batch_size = 2 # number of samples input at once
input_dim = 3
hidden_dim = 100
output_dim = 4
# Initialize model
mlp = MultilayerPerceptron(input_dim, hidden_dim, output_dim)
print(mlp)
MultilayerPerceptron( (fc1): Linear(in_features=3, out_features=100, bias=True) (fc2): Linear(in_features=100, out_features=4, bias=True) )
import torch
def describe(x):
print("Type: {}".format(x.type()))
print("Shape/size: {}".format(x.shape))
print("Values: \n{}".format(x))
x_input = torch.rand(batch_size, input_dim)
describe(x_input)
Type: torch.FloatTensor Shape/size: torch.Size([2, 3]) Values: tensor([[0.2394, 0.4419, 0.5734], [0.9339, 0.3021, 0.3990]])
y_output = mlp(x_input, apply_softmax=False)
describe(y_output)
Type: torch.FloatTensor Shape/size: torch.Size([2, 4]) Values: tensor([[-0.3379, 0.0256, 0.2527, -0.0742], [-0.4426, 0.0119, 0.0948, -0.0220]], grad_fn=<AddmmBackward>)
y_output = mlp(x_input, apply_softmax=True)
describe(y_output)
Type: torch.FloatTensor Shape/size: torch.Size([2, 4]) Values: tensor([[0.1803, 0.2594, 0.3255, 0.2348], [0.1721, 0.2712, 0.2946, 0.2621]], grad_fn=<SoftmaxBackward>)
from argparse import Namespace
from collections import Counter
import json
import os
import string
import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader
from tqdm import tqdm_notebook
class SurnameDataset(Dataset):
def __init__(self, surname_df, vectorizer):
"""
Args:
name_df (pandas.DataFrame): the dataset
vectorizer (SurnameVectorizer): vectorizer instatiated from dataset
"""
self.surname_df = surname_df
self._vectorizer = vectorizer
self.train_df = self.surname_df[self.surname_df.split=='train']
self.train_size = len(self.train_df)
self.val_df = self.surname_df[self.surname_df.split=='val']
self.validation_size = len(self.val_df)
self.test_df = self.surname_df[self.surname_df.split=='test']
self.test_size = len(self.test_df)
self._lookup_dict = {'train': (self.train_df, self.train_size),
'val': (self.val_df, self.validation_size),
'test': (self.test_df, self.test_size)}
self.set_split('train')
# Class weights
class_counts = surname_df.nationality.value_counts().to_dict()
def sort_key(item):
return self._vectorizer.nationality_vocab.lookup_token(item[0])
sorted_counts = sorted(class_counts.items(), key=sort_key)
frequencies = [count for _, count in sorted_counts]
self.class_weights = 1.0 / torch.tensor(frequencies, dtype=torch.float32)
@classmethod
def load_dataset_and_make_vectorizer(cls, surname_csv):
"""Load dataset and make a new vectorizer from scratch
Args:
surname_csv (str): location of the dataset
Returns:
an instance of SurnameDataset
"""
surname_df = pd.read_csv(surname_csv)
train_surname_df = surname_df[surname_df.split=='train']
return cls(surname_df, SurnameVectorizer.from_dataframe(train_surname_df))
@classmethod
def load_dataset_and_load_vectorizer(cls, surname_csv, vectorizer_filepath):
"""Load dataset and the corresponding vectorizer.
Used in the case in the vectorizer has been cached for re-use
Args:
surname_csv (str): location of the dataset
vectorizer_filepath (str): location of the saved vectorizer
Returns:
an instance of SurnameDataset
"""
surname_df = pd.read_csv(surname_csv)
vectorizer = cls.load_vectorizer_only(vectorizer_filepath)
return cls(surname_df, vectorizer)
@staticmethod
def load_vectorizer_only(vectorizer_filepath):
"""a static method for loading the vectorizer from file
Args:
vectorizer_filepath (str): the location of the serialized vectorizer
Returns:
an instance of SurnameDataset
"""
with open(vectorizer_filepath) as fp:
return SurnameVectorizer.from_serializable(json.load(fp))
def save_vectorizer(self, vectorizer_filepath):
"""saves the vectorizer to disk using json
Args:
vectorizer_filepath (str): the location to save the vectorizer
"""
with open(vectorizer_filepath, "w") as fp:
json.dump(self._vectorizer.to_serializable(), fp)
def get_vectorizer(self):
""" returns the vectorizer """
return self._vectorizer
def set_split(self, split="train"):
""" selects the splits in the dataset using a column in the dataframe """
self._target_split = split
self._target_df, self._target_size = self._lookup_dict[split]
def __len__(self):
return self._target_size
def __getitem__(self, index):
"""the primary entry point method for PyTorch datasets
Args:
index (int): the index to the data point
Returns:
a dictionary holding the data point's features (x_data) and label (y_target)
"""
row = self._target_df.iloc[index]
surname_matrix = \
self._vectorizer.vectorize(row.surname)
nationality_index = \
self._vectorizer.nationality_vocab.lookup_token(row.nationality)
return {'x_surname': surname_matrix,
'y_nationality': nationality_index}
def get_num_batches(self, batch_size):
"""Given a batch size, return the number of batches in the dataset
Args:
batch_size (int)
Returns:
number of batches in the dataset
"""
return len(self) // batch_size
def generate_batches(dataset, batch_size, shuffle=True,
drop_last=True, device="cpu"):
"""
A generator function which wraps the PyTorch DataLoader. It will
ensure each tensor is on the write device location.
"""
dataloader = DataLoader(dataset=dataset, batch_size=batch_size,
shuffle=shuffle, drop_last=drop_last)
for data_dict in dataloader:
out_data_dict = {}
for name, tensor in data_dict.items():
out_data_dict[name] = data_dict[name].to(device)
yield out_data_dict
class SurnameVectorizer(object):
""" The Vectorizer which coordinates the Vocabularies and puts them to use"""
def __init__(self, surname_vocab, nationality_vocab):
self.surname_vocab = surname_vocab
self.nationality_vocab = nationality_vocab
def vectorize(self, surname):
"""Vectorize the provided surname
Args:
surname (str): the surname
Returns:
one_hot (np.ndarray): a collapsed one-hot encoding
"""
vocab = self.surname_vocab
one_hot = np.zeros(len(vocab), dtype=np.float32)
for token in surname:
one_hot[vocab.lookup_token(token)] = 1
return one_hot
@classmethod
def from_dataframe(cls, surname_df):
"""Instantiate the vectorizer from the dataset dataframe
Args:
surname_df (pandas.DataFrame): the surnames dataset
Returns:
an instance of the SurnameVectorizer
"""
surname_vocab = Vocabulary(unk_token="@")
nationality_vocab = Vocabulary(add_unk=False)
for index, row in surname_df.iterrows():
for letter in row.surname:
surname_vocab.add_token(letter)
nationality_vocab.add_token(row.nationality)
return cls(surname_vocab, nationality_vocab)
import torch.nn as nn
import torch.nn.functional as F
class SurnameClassifier(nn.Module):
""" A 2-layer Multilayer Perceptron for classifying surnames """
def __init__(self, input_dim, hidden_dim, output_dim):
"""
Args:
input_dim (int): the size of the input vectors
hidden_dim (int): the output size of the first Linear layer
output_dim (int): the output size of the second Linear layer
"""
super(SurnameClassifier, self).__init__()
self.fc1 = nn.Linear(input_dim, hidden_dim)
self.fc2 = nn.Linear(hidden_dim, output_dim)
def forward(self, x_in, apply_softmax=False):
"""The forward pass of the classifier
Args:
x_in (torch.Tensor): an input data tensor.
x_in.shape should be (batch, input_dim)
apply_softmax (bool): a flag for the softmax activation
should be false if used with the Cross Entropy losses
Returns:
the resulting tensor. tensor.shape should be (batch, output_dim)
"""
intermediate_vector = F.relu(self.fc1(x_in))
prediction_vector = self.fc2(intermediate_vector)
if apply_softmax:
prediction_vector = F.softmax(prediction_vector, dim=1)
return prediction_vector
from argparse import Namespace
from collections import Counter
import json
import os
import string
import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader
from tqdm import tqdm_notebook
def set_seed_everywhere(seed, cuda):
np.random.seed(seed)
torch.manual_seed(seed)
if cuda:
torch.cuda.manual_seed_all(seed)
def handle_dirs(dirpath):
if not os.path.exists(dirpath):
os.makedirs(dirpath)
args = Namespace(
# Data and path information
surname_csv="data/surnames/surnames_with_splits.csv",
vectorizer_file="vectorizer.json",
model_state_file="model.pth",
save_dir="model_storage/ch4/surname_mlp",
# Model hyper parameters
hidden_dim=300,
# Training hyper parameters
seed=1337,
num_epochs=100,
early_stopping_criteria=5,
learning_rate=0.001,
batch_size=64,
# Runtime options
cuda=False,
reload_from_files=False,
expand_filepaths_to_save_dir=True,
)
if args.expand_filepaths_to_save_dir:
args.vectorizer_file = os.path.join(args.save_dir,
args.vectorizer_file)
args.model_state_file = os.path.join(args.save_dir,
args.model_state_file)
print("Expanded filepaths: ")
print("\t{}".format(args.vectorizer_file))
print("\t{}".format(args.model_state_file))
# Check CUDA
if not torch.cuda.is_available():
args.cuda = False
args.device = torch.device("cuda" if args.cuda else "cpu")
print("Using CUDA: {}".format(args.cuda))
# Set seed for reproducibility
set_seed_everywhere(args.seed, args.cuda)
# handle dirs
handle_dirs(args.save_dir)
Expanded filepaths: model_storage/ch4/surname_mlp/vectorizer.json model_storage/ch4/surname_mlp/model.pth Using CUDA: False
class SurnameDataset(Dataset):
def __init__(self, surname_df, vectorizer):
"""
Args:
surname_df (pandas.DataFrame): the dataset
vectorizer (SurnameVectorizer): vectorizer instatiated from dataset
"""
self.surname_df = surname_df
self._vectorizer = vectorizer
self.train_df = self.surname_df[self.surname_df.split=='train']
self.train_size = len(self.train_df)
self.val_df = self.surname_df[self.surname_df.split=='val']
self.validation_size = len(self.val_df)
self.test_df = self.surname_df[self.surname_df.split=='test']
self.test_size = len(self.test_df)
self._lookup_dict = {'train': (self.train_df, self.train_size),
'val': (self.val_df, self.validation_size),
'test': (self.test_df, self.test_size)}
self.set_split('train')
# Class weights
class_counts = surname_df.nationality.value_counts().to_dict()
def sort_key(item):
return self._vectorizer.nationality_vocab.lookup_token(item[0])
sorted_counts = sorted(class_counts.items(), key=sort_key)
frequencies = [count for _, count in sorted_counts]
self.class_weights = 1.0 / torch.tensor(frequencies, dtype=torch.float32)
@classmethod
def load_dataset_and_make_vectorizer(cls, surname_csv):
"""Load dataset and make a new vectorizer from scratch
Args:
surname_csv (str): location of the dataset
Returns:
an instance of SurnameDataset
"""
surname_df = pd.read_csv(surname_csv)
train_surname_df = surname_df[surname_df.split=='train']
return cls(surname_df, SurnameVectorizer.from_dataframe(train_surname_df))
@classmethod
def load_dataset_and_load_vectorizer(cls, surname_csv, vectorizer_filepath):
"""Load dataset and the corresponding vectorizer.
Used in the case in the vectorizer has been cached for re-use
Args:
surname_csv (str): location of the dataset
vectorizer_filepath (str): location of the saved vectorizer
Returns:
an instance of SurnameDataset
"""
surname_df = pd.read_csv(surname_csv)
vectorizer = cls.load_vectorizer_only(vectorizer_filepath)
return cls(surname_df, vectorizer)
@staticmethod
def load_vectorizer_only(vectorizer_filepath):
"""a static method for loading the vectorizer from file
Args:
vectorizer_filepath (str): the location of the serialized vectorizer
Returns:
an instance of SurnameVectorizer
"""
with open(vectorizer_filepath) as fp:
return SurnameVectorizer.from_serializable(json.load(fp))
def save_vectorizer(self, vectorizer_filepath):
"""saves the vectorizer to disk using json
Args:
vectorizer_filepath (str): the location to save the vectorizer
"""
with open(vectorizer_filepath, "w") as fp:
json.dump(self._vectorizer.to_serializable(), fp)
def get_vectorizer(self):
""" returns the vectorizer """
return self._vectorizer
def set_split(self, split="train"):
""" selects the splits in the dataset using a column in the dataframe """
self._target_split = split
self._target_df, self._target_size = self._lookup_dict[split]
def __len__(self):
return self._target_size
def __getitem__(self, index):
"""the primary entry point method for PyTorch datasets
Args:
index (int): the index to the data point
Returns:
a dictionary holding the data point's:
features (x_surname)
label (y_nationality)
"""
row = self._target_df.iloc[index]
surname_vector = \
self._vectorizer.vectorize(row.surname)
nationality_index = \
self._vectorizer.nationality_vocab.lookup_token(row.nationality)
return {'x_surname': surname_vector,
'y_nationality': nationality_index}
def get_num_batches(self, batch_size):
"""Given a batch size, return the number of batches in the dataset
Args:
batch_size (int)
Returns:
number of batches in the dataset
"""
return len(self) // batch_size
def generate_batches(dataset, batch_size, shuffle=True,
drop_last=True, device="cpu"):
"""
A generator function which wraps the PyTorch DataLoader. It will
ensure each tensor is on the write device location.
"""
dataloader = DataLoader(dataset=dataset, batch_size=batch_size,
shuffle=shuffle, drop_last=drop_last)
for data_dict in dataloader:
out_data_dict = {}
for name, tensor in data_dict.items():
out_data_dict[name] = data_dict[name].to(device)
yield out_data_dict
class Vocabulary(object):
"""Class to process text and extract vocabulary for mapping"""
def __init__(self, token_to_idx=None, add_unk=True, unk_token="<UNK>"):
"""
Args:
token_to_idx (dict): a pre-existing map of tokens to indices
add_unk (bool): a flag that indicates whether to add the UNK token
unk_token (str): the UNK token to add into the Vocabulary
"""
if token_to_idx is None:
token_to_idx = {}
self._token_to_idx = token_to_idx
self._idx_to_token = {idx: token
for token, idx in self._token_to_idx.items()}
self._add_unk = add_unk
self._unk_token = unk_token
self.unk_index = -1
if add_unk:
self.unk_index = self.add_token(unk_token)
def to_serializable(self):
""" returns a dictionary that can be serialized """
return {'token_to_idx': self._token_to_idx,
'add_unk': self._add_unk,
'unk_token': self._unk_token}
@classmethod
def from_serializable(cls, contents):
""" instantiates the Vocabulary from a serialized dictionary """
return cls(**contents)
def add_token(self, token):
"""Update mapping dicts based on the token.
Args:
token (str): the item to add into the Vocabulary
Returns:
index (int): the integer corresponding to the token
"""
try:
index = self._token_to_idx[token]
except KeyError:
index = len(self._token_to_idx)
self._token_to_idx[token] = index
self._idx_to_token[index] = token
return index
def add_many(self, tokens):
"""Add a list of tokens into the Vocabulary
Args:
tokens (list): a list of string tokens
Returns:
indices (list): a list of indices corresponding to the tokens
"""
return [self.add_token(token) for token in tokens]
def lookup_token(self, token):
"""Retrieve the index associated with the token
or the UNK index if token isn't present.
Args:
token (str): the token to look up
Returns:
index (int): the index corresponding to the token
Notes:
`unk_index` needs to be >=0 (having been added into the Vocabulary)
for the UNK functionality
"""
if self.unk_index >= 0:
return self._token_to_idx.get(token, self.unk_index)
else:
return self._token_to_idx[token]
def lookup_index(self, index):
"""Return the token associated with the index
Args:
index (int): the index to look up
Returns:
token (str): the token corresponding to the index
Raises:
KeyError: if the index is not in the Vocabulary
"""
if index not in self._idx_to_token:
raise KeyError("the index (%d) is not in the Vocabulary" % index)
return self._idx_to_token[index]
def __str__(self):
return "<Vocabulary(size=%d)>" % len(self)
def __len__(self):
return len(self._token_to_idx)
class SurnameVectorizer(object):
""" The Vectorizer which coordinates the Vocabularies and puts them to use"""
def __init__(self, surname_vocab, nationality_vocab):
"""
Args:
surname_vocab (Vocabulary): maps characters to integers
nationality_vocab (Vocabulary): maps nationalities to integers
"""
self.surname_vocab = surname_vocab
self.nationality_vocab = nationality_vocab
def vectorize(self, surname):
"""
Args:
surname (str): the surname
Returns:
one_hot (np.ndarray): a collapsed one-hot encoding
"""
vocab = self.surname_vocab
one_hot = np.zeros(len(vocab), dtype=np.float32)
for token in surname:
one_hot[vocab.lookup_token(token)] = 1
return one_hot
@classmethod
def from_dataframe(cls, surname_df):
"""Instantiate the vectorizer from the dataset dataframe
Args:
surname_df (pandas.DataFrame): the surnames dataset
Returns:
an instance of the SurnameVectorizer
"""
surname_vocab = Vocabulary(unk_token="@")
nationality_vocab = Vocabulary(add_unk=False)
for index, row in surname_df.iterrows():
for letter in row.surname:
surname_vocab.add_token(letter)
nationality_vocab.add_token(row.nationality)
return cls(surname_vocab, nationality_vocab)
@classmethod
def from_serializable(cls, contents):
surname_vocab = Vocabulary.from_serializable(contents['surname_vocab'])
nationality_vocab = Vocabulary.from_serializable(contents['nationality_vocab'])
return cls(surname_vocab=surname_vocab, nationality_vocab=nationality_vocab)
def to_serializable(self):
return {'surname_vocab': self.surname_vocab.to_serializable(),
'nationality_vocab': self.nationality_vocab.to_serializable()}
if args.reload_from_files:
# training from a checkpoint
print("Reloading!")
dataset = SurnameDataset.load_dataset_and_load_vectorizer(args.surname_csv,
args.vectorizer_file)
else:
# create dataset and vectorizer
print("Creating fresh!")
dataset = SurnameDataset.load_dataset_and_make_vectorizer(args.surname_csv)
dataset.save_vectorizer(args.vectorizer_file)
vectorizer = dataset.get_vectorizer()
classifier = SurnameClassifier(input_dim=len(vectorizer.surname_vocab),
hidden_dim=args.hidden_dim,
output_dim=len(vectorizer.nationality_vocab))
Creating fresh!
def make_train_state(args):
return {'stop_early': False,
'early_stopping_step': 0,
'early_stopping_best_val': 1e8,
'learning_rate': args.learning_rate,
'epoch_index': 0,
'train_loss': [],
'train_acc': [],
'val_loss': [],
'val_acc': [],
'test_loss': -1,
'test_acc': -1,
'model_filename': args.model_state_file}
def update_train_state(args, model, train_state):
"""Handle the training state updates.
Components:
- Early Stopping: Prevent overfitting.
- Model Checkpoint: Model is saved if the model is better
:param args: main arguments
:param model: model to train
:param train_state: a dictionary representing the training state values
:returns:
a new train_state
"""
# Save one model at least
if train_state['epoch_index'] == 0:
torch.save(model.state_dict(), train_state['model_filename'])
train_state['stop_early'] = False
# Save model if performance improved
elif train_state['epoch_index'] >= 1:
loss_tm1, loss_t = train_state['val_loss'][-2:]
# If loss worsened
if loss_t >= train_state['early_stopping_best_val']:
# Update step
train_state['early_stopping_step'] += 1
# Loss decreased
else:
# Save the best model
if loss_t < train_state['early_stopping_best_val']:
torch.save(model.state_dict(), train_state['model_filename'])
# Reset early stopping step
train_state['early_stopping_step'] = 0
# Stop early ?
train_state['stop_early'] = \
train_state['early_stopping_step'] >= args.early_stopping_criteria
return train_state
def compute_accuracy(y_pred, y_target):
_, y_pred_indices = y_pred.max(dim=1)
n_correct = torch.eq(y_pred_indices, y_target).sum().item()
return n_correct / len(y_pred_indices) * 100
classifier = classifier.to(args.device)
dataset.class_weights = dataset.class_weights.to(args.device)
loss_func = nn.CrossEntropyLoss(dataset.class_weights)
optimizer = optim.Adam(classifier.parameters(), lr=args.learning_rate)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer=optimizer,
mode='min', factor=0.5,
patience=1)
train_state = make_train_state(args)
epoch_bar = tqdm_notebook(desc='training routine',
total=args.num_epochs,
position=0)
dataset.set_split('train')
train_bar = tqdm_notebook(desc='split=train',
total=dataset.get_num_batches(args.batch_size),
position=1,
leave=True)
dataset.set_split('val')
val_bar = tqdm_notebook(desc='split=val',
total=dataset.get_num_batches(args.batch_size),
position=1,
leave=True)
try:
for epoch_index in range(args.num_epochs):
train_state['epoch_index'] = epoch_index
# Iterate over training dataset
# setup: batch generator, set loss and acc to 0, set train mode on
dataset.set_split('train')
batch_generator = generate_batches(dataset,
batch_size=args.batch_size,
device=args.device)
running_loss = 0.0
running_acc = 0.0
classifier.train()
for batch_index, batch_dict in enumerate(batch_generator):
# the training routine is these 5 steps:
# --------------------------------------
# step 1. zero the gradients
optimizer.zero_grad()
# step 2. compute the output
y_pred = classifier(batch_dict['x_surname'])
# step 3. compute the loss
loss = loss_func(y_pred, batch_dict['y_nationality'])
loss_t = loss.item()
running_loss += (loss_t - running_loss) / (batch_index + 1)
# step 4. use loss to produce gradients
loss.backward()
# step 5. use optimizer to take gradient step
optimizer.step()
# -----------------------------------------
# compute the accuracy
acc_t = compute_accuracy(y_pred, batch_dict['y_nationality'])
running_acc += (acc_t - running_acc) / (batch_index + 1)
# update bar
train_bar.set_postfix(loss=running_loss, acc=running_acc,
epoch=epoch_index)
train_bar.update()
train_state['train_loss'].append(running_loss)
train_state['train_acc'].append(running_acc)
# Iterate over val dataset
# setup: batch generator, set loss and acc to 0; set eval mode on
dataset.set_split('val')
batch_generator = generate_batches(dataset,
batch_size=args.batch_size,
device=args.device)
running_loss = 0.
running_acc = 0.
classifier.eval()
for batch_index, batch_dict in enumerate(batch_generator):
# compute the output
y_pred = classifier(batch_dict['x_surname'])
# step 3. compute the loss
loss = loss_func(y_pred, batch_dict['y_nationality'])
loss_t = loss.to("cpu").item()
running_loss += (loss_t - running_loss) / (batch_index + 1)
# compute the accuracy
acc_t = compute_accuracy(y_pred, batch_dict['y_nationality'])
running_acc += (acc_t - running_acc) / (batch_index + 1)
val_bar.set_postfix(loss=running_loss, acc=running_acc,
epoch=epoch_index)
val_bar.update()
train_state['val_loss'].append(running_loss)
train_state['val_acc'].append(running_acc)
train_state = update_train_state(args=args, model=classifier,
train_state=train_state)
scheduler.step(train_state['val_loss'][-1])
if train_state['stop_early']:
break
train_bar.n = 0
val_bar.n = 0
epoch_bar.update()
except KeyboardInterrupt:
print("Exiting loop")
def predict_nationality(name, classifier, vectorizer):
vectorized_name = vectorizer.vectorize(name)
vectorized_name = torch.tensor(vectorized_name).view(1, -1)
result = classifier(vectorized_name, apply_softmax=True)
probability_values, indices = result.max(dim=1)
index = indices.item()
predicted_nationality = vectorizer.nationality_vocab.lookup_index(index)
probability_value = probability_values.item()
return {'nationality': predicted_nationality,
'probability': probability_value}
def predict_topk_nationality(name, classifier, vectorizer, k=5):
vectorized_name = vectorizer.vectorize(name)
vectorized_name = torch.tensor(vectorized_name).view(1, -1)
prediction_vector = classifier(vectorized_name, apply_softmax=True)
probability_values, indices = torch.topk(prediction_vector, k=k)
# returned size is 1,k
probability_values = probability_values.detach().numpy()[0]
indices = indices.detach().numpy()[0]
results = []
for prob_value, index in zip(probability_values, indices):
nationality = vectorizer.nationality_vocab.lookup_index(index)
results.append({'nationality': nationality,
'probability': prob_value})
return results
import torch.nn as nn
import torch.nn.functional as F
class MultilayerPerceptron(nn.Module):
def __init__(self, input_dim, hidden_dim, output_dim):
"""
Args:
input_dim (int): the size of the input vectors
hidden_dim (int): the output size of the first Linear layer
output_dim (int): the output size of the second Linear layer
"""
super(MultilayerPerceptron, self).__init__()
self.fc1 = nn.Linear(input_dim, hidden_dim)
self.fc2 = nn.Linear(hidden_dim, output_dim)
def forward(self, x_in, apply_softmax=False):
"""The forward pass of the MLP
Args:
x_in (torch.Tensor): an input data tensor.
x_in.shape should be (batch, input_dim)
apply_softmax (bool): a flag for the softmax activation
should be false if used with the Cross Entropy losses
Returns:
the resulting tensor. tensor.shape should be (batch, output_dim)
"""
intermediate = F.relu(self.fc1(x_in))
output = self.fc2(F.dropout(intermediate, p=0.5))
if apply_softmax:
output = F.softmax(output, dim=1)
return output
import torch
import torch.nn as nn
import torch.nn.functional as F
seed = 1337
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
def describe(x):
print("Type: {}".format(x.type()))
print("Shape/size: {}".format(x.shape))
print("Values: \n{}".format(x))
# Inputs
x_input = torch.rand(batch_size, input_dim)
describe(x_input)
y_output = mlp(x_input, apply_softmax=False)
describe(y_output)
y_output = mlp(x_input, apply_softmax=True)
describe(y_output)
Type: torch.FloatTensor Shape/size: torch.Size([2, 4]) Values: tensor([[0.2015, 0.2402, 0.2109, 0.3474], [0.2189, 0.1998, 0.2781, 0.3031]], grad_fn=<SoftmaxBackward>)
class MultilayerPerceptron(nn.Module):
def __init__(self, input_dim, hidden_dim, output_dim):
"""
Args:
input_dim (int): the size of the input vectors
hidden_dim (int): the output size of the first Linear layer
output_dim (int): the output size of the second Linear layer
"""
super(MultilayerPerceptron, self).__init__()
self.fc1 = nn.Linear(input_dim, hidden_dim)
self.fc2 = nn.Linear(hidden_dim, output_dim)
def forward(self, x_in, apply_softmax=False):
"""The forward pass of the MLP
Args:
x_in (torch.Tensor): an input data tensor.
x_in.shape should be (batch, input_dim)
apply_softmax (bool): a flag for the softmax activation
should be false if used with the Cross Entropy losses
Returns:
the resulting tensor. tensor.shape should be (batch, output_dim)
"""
intermediate = F.relu(self.fc1(x_in))
output = self.fc2(F.dropout(intermediate, p=0.5))
if apply_softmax:
output = F.softmax(output, dim=1)
return output
batch_size = 2 # number of samples input at once
input_dim = 3
hidden_dim = 100
output_dim = 4
# Initialize model
mlp = MultilayerPerceptron(input_dim, hidden_dim, output_dim)
print(mlp)
y_output = mlp(x_input, apply_softmax=False)
describe(y_output)
MultilayerPerceptron( (fc1): Linear(in_features=3, out_features=100, bias=True) (fc2): Linear(in_features=100, out_features=4, bias=True) ) Type: torch.FloatTensor Shape/size: torch.Size([2, 4]) Values: tensor([[-0.0665, -0.1061, -0.1754, 0.1274], [ 0.2514, -0.3060, -0.2361, -0.3319]], grad_fn=<AddmmBackward>)
batch_size = 2
one_hot_size = 10
sequence_width = 7
data = torch.randn(batch_size, one_hot_size, sequence_width)
conv1 = nn.Conv1d(in_channels=one_hot_size, out_channels=16, kernel_size=3)
intermediate1 = conv1(data)
print(data.size())
print(intermediate1.size())
torch.Size([2, 10, 7]) torch.Size([2, 16, 5])
conv2 = nn.Conv1d(in_channels=16, out_channels=32, kernel_size=3)
conv3 = nn.Conv1d(in_channels=32, out_channels=64, kernel_size=3)
intermediate2 = conv2(intermediate1)
intermediate3 = conv3(intermediate2)
print(intermediate2.size())
print(intermediate3.size())
torch.Size([2, 32, 3]) torch.Size([2, 64, 1])
y_output = intermediate3.squeeze()
print(y_output.size())
torch.Size([2, 64])
# Method 2 of reducing to feature vectors
print(intermediate1.view(batch_size, -1).size())
# Method 3 of reducing to feature vectors
print(torch.mean(intermediate1, dim=2).size())
# print(torch.max(intermediate1, dim=2).size())
# print(torch.sum(intermediate1, dim=2).size())
torch.Size([2, 80]) torch.Size([2, 16])
class SurnameDataset(Dataset):
# ... existing implementation from Section 4.2
def __getitem__(self, index):
row = self._target_df.iloc[index]
surname_matrix = \
self._vectorizer.vectorize(row.surname, self._max_seq_length)
nationality_index = \
self._vectorizer.nationality_vocab.lookup_token(row.nationality)
return {'x_surname': surname_matrix,
'y_nationality': nationality_index}
class SurnameVectorizer(object):
""" The Vectorizer which coordinates the Vocabularies and puts them to use"""
def vectorize(self, surname):
"""
Args:
surname (str): the surname
Returns:
one_hot_matrix (np.ndarray): a matrix of one-hot vectors
"""
one_hot_matrix_size = (len(self.character_vocab), self.max_surname_length)
one_hot_matrix = np.zeros(one_hot_matrix_size, dtype=np.float32)
for position_index, character in enumerate(surname):
character_index = self.character_vocab.lookup_token(character)
one_hot_matrix[character_index][position_index] = 1
return one_hot_matrix
@classmethod
def from_dataframe(cls, surname_df):
"""Instantiate the vectorizer from the dataset dataframe
Args:
surname_df (pandas.DataFrame): the surnames dataset
Returns:
an instance of the SurnameVectorizer
"""
character_vocab = Vocabulary(unk_token="@")
nationality_vocab = Vocabulary(add_unk=False)
max_surname_length = 0
for index, row in surname_df.iterrows():
max_surname_length = max(max_surname_length, len(row.surname))
for letter in row.surname:
character_vocab.add_token(letter)
nationality_vocab.add_token(row.nationality)
return cls(character_vocab, nationality_vocab, max_surname_length)
import torch.nn as nn
import torch.nn.functional as F
class SurnameClassifier(nn.Module):
def __init__(self, initial_num_channels, num_classes, num_channels):
"""
Args:
initial_num_channels (int): size of the incoming feature vector
num_classes (int): size of the output prediction vector
num_channels (int): constant channel size to use throughout network
"""
super(SurnameClassifier, self).__init__()
self.convnet = nn.Sequential(
nn.Conv1d(in_channels=initial_num_channels,
out_channels=num_channels, kernel_size=3),
nn.ELU(),
nn.Conv1d(in_channels=num_channels, out_channels=num_channels,
kernel_size=3, stride=2),
nn.ELU(),
nn.Conv1d(in_channels=num_channels, out_channels=num_channels,
kernel_size=3, stride=2),
nn.ELU(),
nn.Conv1d(in_channels=num_channels, out_channels=num_channels,
kernel_size=3),
nn.ELU()
)
self.fc = nn.Linear(num_channels, num_classes)
def forward(self, x_surname, apply_softmax=False):
"""The forward pass of the classifier
Args:
x_surname (torch.Tensor): an input data tensor.
x_surname.shape should be (batch, initial_num_channels,
max_surname_length)
apply_softmax (bool): a flag for the softmax activation
should be false if used with the Cross Entropy losses
Returns:
the resulting tensor. tensor.shape should be (batch, num_classes)
"""
features = self.convnet(x_surname).squeeze(dim=2)
prediction_vector = self.fc(features)
if apply_softmax:
prediction_vector = F.softmax(prediction_vector, dim=1)
return prediction_vector
args = Namespace(
# Data and Path information
surname_csv="data/surnames/surnames_with_splits.csv",
vectorizer_file="vectorizer.json",
model_state_file="model.pth",
save_dir="model_storage/ch4/cnn",
# Model hyper parameters
hidden_dim=100,
num_channels=256,
# Training hyper parameters
seed=1337,
learning_rate=0.001,
batch_size=128,
num_epochs=100,
early_stopping_criteria=5,
dropout_p=0.1,
# Runtime omitted for space ...
)
def predict_nationality(surname, classifier, vectorizer):
"""Predict the nationality from a new surname
Args:
surname (str): the surname to classifier
classifier (SurnameClassifer): an instance of the classifier
vectorizer (SurnameVectorizer): the corresponding vectorizer
Returns:
a dictionary with the most likely nationality and its probability
"""
vectorized_surname = vectorizer.vectorize(surname)
vectorized_surname = torch.tensor(vectorized_surname).unsqueeze(0)
result = classifier(vectorized_surname, apply_softmax=True)
probability_values, indices = result.max(dim=1)
index = indices.item()
predicted_nationality = vectorizer.nationality_vocab.lookup_index(index)
probability_value = probability_values.item()
return {'nationality': predicted_nationality, 'probability': probability_value}
conv1 = nn.Conv1d(in_channels=one_hot_size, out_channels=16, kernel_size=3)
conv2 = nn.Conv1d(in_channels=16, out_channels=32, kernel_size=3)
conv3 = nn.Conv1d(in_channels=32, out_channels=64, kernel_size=3)
conv1_bn = nn.BatchNorm1d(num_features=16)
conv2_bn = nn.BatchNorm1d(num_features=32)
intermediate1 = conv1_bn(F.relu(conv1(data)))
intermediate2 = conv2_bn(F.relu(conv2(intermediate1)))
intermediate3 = conv3(intermediate2)
print(intermediate1.size())
print(intermediate2.size())
print(intermediate3.size())
torch.Size([2, 16, 5]) torch.Size([2, 32, 3]) torch.Size([2, 64, 1])