如何随着时间的推移重现滚动窗口的动画？

Question

我正在试验一维时间序列数据，并尝试通过动画在 GoogleColab 笔记本中我自己的数据上重现以下方法。

它是关于再现STS变换的动画（由

series_to_supervised()

函数实现，具有回溯过去时间

n_in=9

的步骤）等于带有改装和固定训练大小（滚动原点）的回溯测试介绍了动画方法skforecast 包。更多的是关于实际时间序列数据

train

和

test

选择。可视化固定的列车尺寸并改装并预测下一步。

y

STS改造

:

多步或序列预测 另一种类型的预测问题是使用过去的观察来预测一系列未来的观察。这可以称为序列预测或多步预测。

到目前为止，我得到的输出是如此丑陋且不正确。

Answer 1

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
from matplotlib.animation import FuncAnimation
from IPython.display import HTML
print(pd.__version__)


# Generate univariate (1D) time-series data into pandas DataFrame
import numpy as np
np.random.seed(123) # for reproducibility and get reproducible results

df = pd.DataFrame({
    "TS_24hrs": np.arange(0, 274),
    "count"   : np.abs(np.sin(2 * np.pi * np.arange(0, 274) / 7) + np.random.normal(0, 100.1, size=274)) # generate sesonality
})
#df = pd.read_csv('/content/U2996_24hrs_.csv', header=0, index_col=0).values
print(f"The raw data {df.shape}")
#print(f"The raw data columns {df.columns}")


# visulize data
import matplotlib.pyplot as plt
fig, ax = plt.subplots( figsize=(10,4))

# plot data
df['count'].plot(label=f'data or y', c='red' )
#df['count'].plot(label=f'data',  linestyle='--')
plt.xticks([0, 50, 100, 150, 200, 250, df['TS_24hrs'].iloc[-1]], visible=True, rotation="horizontal")

plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
plt.title('Plot of data')
plt.ylabel('count', fontsize=15)
plt.xlabel('Timestamp [24hrs]', fontsize=15)
plt.grid()
plt.show()

# slecet train/test data using series_to_supervised (STS)
from pandas import DataFrame, concat
def series_to_supervised( data, n_in, n_out=1, dropnan=True):
    """
    Frame a time series as a supervised learning dataset.
    Arguments:
        data: Sequence of observations as a list or NumPy array.
        n_in: Number of lag observations as input (X).
        n_out: Number of observations as output (y).
        dropnan: Boolean whether or not to drop rows with NaN values.
    Returns:
        Pandas DataFrame of series framed for supervised learning.
    """
    n_vars = 1 if type(data) is list else data.shape[1]
    df = pd.DataFrame(data)
    cols = list()
    # input sequence (t-n, ... t-1)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
    # forecast sequence (t, t+1, ... t+n)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
    # put it all together
    agg = concat(cols, axis=1)
    # drop rows with NaN values
    if dropnan:
        agg.dropna(inplace=True)
    return agg.values


values=series_to_supervised(df, n_in=9)
data_x,data_y =values[:, :-1], values[:, -1]

print(data_x.shape)
print(data_y.shape)


# define animation function
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.animation import FuncAnimation

fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(40, 8))
plt.subplots_adjust(bottom=0.25)
plt.xticks(fontsize=12)
ax.set_xticks(range(0, len(data_y), 9))
ax.set_yticks(range(0, 2500, 200))

data_y = pd.Series(data_y)
data_y.plot(color='r', linestyle='-', label="y")
ax.set_title('Time Series')
ax.set_xlabel('Time')
ax.set_ylabel('Value')
ax.legend(loc="upper left")
ax.grid(True, which='both', linestyle='-', linewidth=3)
ax.set_facecolor('gainsboro')

ax.spines['bottom'].set_position('zero')
ax.spines['left'].set_position('zero')
ax.spines['right'].set_color('none')
ax.spines['top'].set_color('none')

nested_list = list(trainX_tss)
lines = [ax.plot([], [], color='g', linestyle='-')[0] for _ in range(len(trainX_tss))]

def init():
    for line in lines:
        line.set_data([], [])
    return lines

def update(frame):
    for i, line in enumerate(lines):
        data = pd.Series(nested_list[i], index=range(frame + i, frame + i + 9))
        line.set_data([], [])
        line.set_data(data.index, data)
    return lines


# define animation setup
anim = FuncAnimation(fig, update,
                    frames=len(nested_list) - 9,
                    init_func=init,
                    interval=500,
                    blit=True,
                    repeat=False)


# Save animation (.gif))
anim.save('BrowniamMotion.gif', writer = "pillow", fps=10 )

# visulize animation in GoogleColab Notebook
# suppress final output
plt.close(0)
HTML(anim.to_html5_video())

函数应该反映它。

所以你需要的是按照你想要的方式设置初始图形，创建你想要动画的部分（使用

update()

），然后使用

init()

创建框架：update()