时间序列分析: 探索季节性趋势和周期性模式

from pathlib import Path
from warnings import simplefilter

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from sklearn.linear_model import LinearRegression
from statsmodels.tsa.deterministic import CalendarFourier, DeterministicProcess

simplefilter('ignore')

# Set Matplotlib defaults
plt.style.use('seaborn-whitegrid')
plt.rc('figure', autolayout=True, figsize=(11, 5))
plt.rc(
    'axes',
    labelweight='bold',
    labelsize='large',
    titleweight='bold',
    titlesize=16,
    titlepad=10,
)
plot_params = dict(
    color='0.75',
    style='.-',
    markeredgecolor='0.25',
    markerfacecolor='0.25',
    legend=False,
)
%config InlineBackend.figure_format = 'retina'


# annotations: https://stackoverflow.com/a/49238256/5769929
def seasonal_plot(X, y, period, freq, ax=None):
    if ax is None:
        _, ax = plt.subplots()
    palette = sns.color_palette('husl', n_colors=X[period].nunique(),)
    ax = sns.lineplot(
        x=freq,
        y=y,
        hue=period,
        data=X,
        ci=False,
        ax=ax,
        palette=palette,
        legend=False,
    )
    ax.set_title(f'Seasonal Plot ({period}/{freq})')
    for line, name in zip(ax.lines, X[period].unique()):
        y_ = line.get_ydata()[-1]
        ax.annotate(
            name,
            xy=(1, y_),
            xytext=(6, 0),
            color=line.get_color(),
            xycoords=ax.get_yaxis_transform(),
            textcoords='offset points',
            size=14,
            va='center',
        )
    return ax


def plot_periodogram(ts, detrend='linear', ax=None):
    from scipy.signal import periodogram
    fs = pd.Timedelta('1Y') / pd.Timedelta('1D')
    freqencies, spectrum = periodogram(
        ts,
        fs=fs,
        detrend=detrend,
        window='boxcar',
        scaling='spectrum',
    )
    if ax is None:
        _, ax = plt.subplots()
    ax.step(freqencies, spectrum, color='purple')
    ax.set_xscale('log')
    ax.set_xticks([1, 2, 4, 6, 12, 26, 52, 104])
    ax.set_xticklabels(
        [
            'Annual (1)',
            'Semiannual (2)',
            'Quarterly (4)',
            'Bimonthly (6)',
            'Monthly (12)',
            'Biweekly (26)',
            'Weekly (52)',
            'Semiweekly (104)',
        ],
        rotation=30,
    )
    ax.ticklabel_format(axis='y', style='sci', scilimits=(0, 0))
    ax.set_ylabel('Variance')
    ax.set_title('Periodogram')
    return ax


data_dir = Path('../input/ts-course-data')
tunnel = pd.read_csv(data_dir / 'tunnel.csv', parse_dates=['Day'])
tunnel = tunnel.set_index('Day').to_period('D')
用中文解释代码palette = sns.color_palette('husl', n_colors=X[period].nunique(),)的意思

 这行代码的作用是为 seaborn 绘图库中的颜色调色板 palette 设置颜色序列，其中 'husl' 是调色板名称，n_colors 是需要的颜色数量，X[period].nunique() 是根据数据 X 中指定的周期 period 计算出唯一值的数量，用于生成相应数量的颜色。