RNN 人名分类案例 - 获取全局字母表和国家名

import string

all_letters = string.ascii_letters + " .,;'"

all_countries = [
    "Chinese", "English", "German", "French", "Spanish",
    "Italian", "Russian", "Japanese", "Korean", "Vietnamese",
    "Arabic", "Czech", "Dutch", "Greek", "Irish",
    "Polish", "Portuguese", "Scottish"
]

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
import string
import time
from tqdm import tqdm
import matplotlib.pyplot as plt

import string

# 1. 全局字母表
all_letters = string.ascii_letters + " .,;'"
n_letters = len(all_letters)

print(f"全局字母表: {all_letters}")
print(f"字母表大小: {n_letters}")

# 2. 国家名
all_countries = [
    "Chinese", "English", "German", "French", "Spanish",
    "Italian", "Russian", "Japanese", "Korean", "Vietnamese",
    "Arabic", "Czech", "Dutch", "Greek", "Irish",
    "Polish", "Portuguese", "Scottish"
]
n_countries = len(all_countries)

print(f"国家名: {all_countries}")
print(f"国家数量: {n_countries}")

# 3. 字符转索引
def letter_to_index(letter):
    """字符转索引"""
    return all_letters.find(letter)

# 4. 字符转 one-hot 张量
def letter_to_tensor(letter):
    """字符转 one-hot 张量"""
    tensor = torch.zeros(1, n_letters)
    tensor[0][letter_to_index(letter)] = 1
    return tensor

# 测试
print(f"\n字符 'A' 的索引: {letter_to_index('A')}")
print(f"字符 'A' 的 one-hot: {letter_to_tensor('A')}")