utils.py：NLP学习记录相关的类和函数

import numpy as np
import torch
import time
from matplotlib_inline import backend_inline
from matplotlib import pyplot as plt
from IPython import display
from torch.utils import data


class Timer:
    """Record multiple running times."""
    def __init__(self):
        """Defined in :numref:`subsec_linear_model`"""
        self.times = []
        self.start()

    def start(self):
        """Start the timer."""
        self.tik = time.time()

    def stop(self):
        """Stop the timer and record the time in a list."""
        self.times.append(time.time() - self.tik)
        return self.times[-1]

    def avg(self):
        """Return the average time."""
        return sum(self.times) / len(self.times)

    def sum(self):
        """Return the sum of time."""
        return sum(self.times)

    def cumsum(self):
        """Return the accumulated time."""
        return np.array(self.times).cumsum().tolist()


class Accumulator:
    """For accumulating sums over `n` variables."""
    def __init__(self, n):
        """Defined in :numref:`sec_softmax_scratch`"""
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]


def use_svg_display():
    backend_inline.set_matplotlib_formats('svg')


def set_figsize(figsize=(3.5, 2.5)):
    use_svg_display()
    plt.rcParams['figure.figsize'] = figsize


def set_axes(axes, xlabel, ylabel, xlim, ylim, xscale, yscale, legend):
    axes.set_xlabel(xlabel)
    axes.set_ylabel(ylabel)
    axes.set_xscale(xscale)
    axes.set_yscale(yscale)
    axes.set_xlim(xlim)
    axes.set_ylim(ylim)

    if legend:
        axes.legend(legend)

    axes.grid()


def show():
    plt.show()


# 绘制列表长度对的直方图
def show_list_len_pair_hist(legend, xlabel, ylabel, xlist, ylist):
    set_figsize()
    _, _, patches = plt.hist(
        [[len(l) for l in xlist], [len(l) for l in ylist]])
    plt.xlabel(xlabel)
    plt.ylabel(ylabel)
    for patch in patches[1].patches:
        patch.set_hatch('/')
    plt.legend(legend)
    show()


class Animator:
    """For plotting data in animation."""
    def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
                 ylim=None, xscale='linear', yscale='linear',
                 fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
                 figsize=(3.5, 2.5)):
        """Defined in :numref:`sec_softmax_scratch`"""

        # Incrementally plot multiple lines
        if legend is None:
            legend = []

        use_svg_display()
        self.fig, self.axes = plt.subplots(nrows, ncols, figsize=figsize)

        if nrows * ncols == 1:
            self.axes = [self.axes, ]

        # Use a lambda function to capture arguments
        self.config_axes = lambda: set_axes(
            self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)

        self.X, self.Y, self.fmts = None, None, fmts

    def add(self, x, y):
        # Add multiple data points into the figure
        if not hasattr(y, "__len__"):
            y = [y]

        n = len(y)

        if not hasattr(x, "__len__"):
            x = [x] * n
        if not self.X:
            self.X = [[] for _ in range(n)]
        if not self.Y:
            self.Y = [[] for _ in range(n)]

        for i, (a, b) in enumerate(zip(x, y)):
            if a is not None and b is not None:
                self.X[i].append(a)
                self.Y[i].append(b)

        self.axes[0].cla()

        for x, y, fmt in zip(self.X, self.Y, self.fmts):
            self.axes[0].plot(x, y, fmt)

        self.config_axes()
        display.display(self.fig)
        display.clear_output(wait=True)


def sgd(params, lr, batch_size):
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()


def load_array(data_arrays, batch_size, is_train=True):
    dataset = data.TensorDataset(*data_arrays)
    return data.DataLoader(dataset, batch_size, shuffle=is_train)