计算时间序列周期的三种方法

from google.colab import drive
 drive.mount('/content/gdrive')
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
 import numpy as np
 
 file_path = '/content/gdrive/My Drive/Colab Notebooks/Data/SR-2019.xlsx'
 records2019 = pd.read_excel(file_path)#,encoding='utf16')
 
 file_path = '/content/gdrive/My Drive/Colab Notebooks/Data/SR-2020.xlsx'
 records2020 = pd.read_excel(file_path)#,encoding='utf16')
 
 file_path = '/content/gdrive/My Drive/Colab Notebooks/Data/2021_Monthly_Service_Requests_EN.xlsx'
 records2021 = pd.read_excel(file_path)#,encoding='utf16')
 
 file_path = '/content/gdrive/My Drive/Colab Notebooks/Data/2022_Monthly_Service_Requests.csv'
 records2022 =pd.read_csv(file_path)
 
 records=pd.concat([records2019,records2020,records2021,records2022],axis=0)

records["DATE_RAISED"]=pd.to_datetime(records.DATE_RAISED)
 record_by_date=records.groupby("DATE_RAISED")["TYPE"].count().sort_index()
 record_by_date.plot(figsize = (25, 10))
 plt.ylabel('Number of requests')
 plt.grid(visible=True,which='both')
 plt.figure()
 
 record_by_date.iloc[100:130].plot(figsize = (25, 10))
 plt.ylabel('Number of requests')
 plt.grid(visible=True,which='both')

start_date = record_by_date.index.min()
 end_date = record_by_date.index.max()
 
 # create a complete date range for the period of interest
 date_range = pd.date_range(start=start_date, end=end_date, freq='D')
 
 # compare the date range to the index of the time series
 missing_dates = date_range[~date_range.isin(record_by_date.index)]
 
 if len(missing_dates) > 0:
     print("Missing dates:", missing_dates)
 else:
     print("No missing dates")

# Reindex to fill missing dates
 idx = pd.date_range(start=record_by_date.index.min(), end=record_by_date.index.max(), freq='D')
 record_by_date = record_by_date.reindex(idx, fill_value=0)
 
 # Add missing dates with average of surrounding values
 for date in missing_dates:
     prev_date = date - pd.DateOffset(days=1)
     next_date = date + pd.DateOffset(days=1)
     prev_val = record_by_date.loc[prev_date] if prev_date in record_by_date.index else np.nan
     next_val = record_by_date.loc[next_date] if next_date in record_by_date.index else np.nan
     avg_val = np.nanmean([prev_val, next_val])
     record_by_date.loc[date] = avg_val

from statsmodels.graphics.tsaplots import plot_acf
 
 fig, ax = plt.subplots(figsize=(14,7))
 plot_acf(record_by_date.values.squeeze(), lags=50,ax=ax,title='Autocorrelation', use_vlines=True);
 lags = list(range(51))
 ax.set_xticks(lags);
 ax.set_xticklabels(lags);

from scipy.fft import fft
 
 # Calculate the Fourier transform
 yf = np.fft.fft(record_by_date)
 xf = np.linspace(0.0, 1.0/(2.0), len(record_by_date)//2)
 
 # Find the dominant frequency
 # We have to drop the first element of the fft as it corresponds to the
 # DC component or the average value of the signal
 idx = np.argmax(np.abs(yf[1:len(record_by_date)//2]))
 freq = xf[idx]
 
 period =(1/freq)
 print(f"The period of the time series is {period}")

from scipy.signal import periodogram
 
 freq, power = periodogram(record_by_date)
 period = 1/freq[np.argmax(power)]
 print(f"The period of the time series is {period}")
 
 plt.plot(freq, power)
 plt.xlabel('Frequency (Hz)')
 plt.ylabel('Power spectral density')
 plt.show()