设置Python pandas autocorrelation_plot中的滞后数

Question

代码

import numpy as np
from pandas.tools.plotting import autocorrelation_plot
import matplotlib.pyplot as plt
nobs = 10000
xx = np.random.normal(size=nobs)
autocorrelation_plot(xx)
plt.show()

绘制xx的自相关，但它绘制所有10000个滞后。如何只绘制前10个？

函数autocorrelation_plot的启动方式如下：

def autocorrelation_plot(series, ax=None, **kwds):
    """Autocorrelation plot for time series.
    Parameters:
    -----------
    series: Time series
    ax: Matplotlib axis object, optional
    kwds : keywords
        Options to pass to matplotlib plotting method

有没有办法使用**kwds参数设置绘制的滞后数？

Answer 1

autocorrelation_plot返回一个matplotlib.axis对象。因此，您可以简单地使用set_xlim()方法来限制x轴：

autocorrelation_plot(xx).set_xlim([0, 10])

Reference

Answer 2

如果不需要使用pandas方法，就像备份解决方案一样。有一个statsmodels函数plot_acf，您可以在其中设置lags参数。

from statsmodels.graphics.tsaplots import plot_acf
import pandas as pd
d = dict()
d['value'] = [11, 22, 34, 22, 43, 23, 45, 32, 56, 40, 44, 33, 22, 56, 44]
df = pd.DataFrame.from_dict(d)
plot_acf(df, lags = 5)

Answer 3

autocorrelation_plot函数是一个高级函数。查看pandas库中的代码：

def autocorrelation_plot(series, ax=None, **kwds):
"""Autocorrelation plot for time series.

Parameters:
-----------
series: Time series
ax: Matplotlib axis object, optional
kwds : keywords
    Options to pass to matplotlib plotting method

Returns:
-----------
ax: Matplotlib axis object
"""
import matplotlib.pyplot as plt
n = len(series)
data = np.asarray(series)
if ax is None:
    ax = plt.gca(xlim=(1, n), ylim=(-1.0, 1.0))
mean = np.mean(data)
c0 = np.sum((data - mean) ** 2) / float(n)

def r(h):
    return ((data[:n - h] - mean) *
            (data[h:] - mean)).sum() / float(n) / c0
x = np.arange(n) + 1
y = lmap(r, x)
z95 = 1.959963984540054
z99 = 2.5758293035489004
ax.axhline(y=z99 / np.sqrt(n), linestyle='--', color='grey')
ax.axhline(y=z95 / np.sqrt(n), color='grey')
ax.axhline(y=0.0, color='black')
ax.axhline(y=-z95 / np.sqrt(n), color='grey')
ax.axhline(y=-z99 / np.sqrt(n), linestyle='--', color='grey')
ax.set_xlabel("Lag")
ax.set_ylabel("Autocorrelation")
ax.plot(x, y, **kwds)
if 'label' in kwds:
    ax.legend()
ax.grid()
return ax

函数中的所有行都缺少一个制表符。

添加到标题中：

from pandas.compat import lmap

在末尾前的第4行中，将ax.plot(x，y，**kwds)更改为ax.plot(x:10，y:10，**kwds)

我添加了一个n_samples变量：

from pandas.compat import lmap


def autocorrelation_plot(series, n_samples=None, ax=None, **kwds):
    """Autocorrelation plot for time series.

    Parameters:
    -----------
    series: Time series
    ax: Matplotlib axis object, optional
    kwds : keywords
        Options to pass to matplotlib plotting method

    Returns:
    -----------
    ax: Matplotlib axis object
    """
    import matplotlib.pyplot as plt
    n = len(series)
    data = np.asarray(series)
    if ax is None:
        ax = plt.gca(xlim=(1, n_samples), ylim=(-1.0, 1.0))
    mean = np.mean(data)
    c0 = np.sum((data - mean) ** 2) / float(n)

    def r(h):
        return ((data[:n - h] - mean) *
                (data[h:] - mean)).sum() / float(n) / c0
    x = (np.arange(n) + 1).astype(int)
    y = lmap(r, x)
    z95 = 1.959963984540054
    z99 = 2.5758293035489004
    ax.axhline(y=z99 / np.sqrt(n), linestyle='--', color='grey')
    ax.axhline(y=z95 / np.sqrt(n), color='grey')
    ax.axhline(y=0.0, color='black')
    ax.axhline(y=-z95 / np.sqrt(n), color='grey')
    ax.axhline(y=-z99 / np.sqrt(n), linestyle='--', color='grey')
    ax.set_xlabel("Lag")
    ax.set_ylabel("Autocorrelation")
    if n_samples:
        ax.plot(x[:n_samples], y[:n_samples], **kwds)
    else:
        ax.plot(x, y, **kwds)
    if 'label' in kwds:
        ax.legend()
    ax.grid()
    return ax