python库Tsmoothie模块数据平滑化异常点抓取

pip install tsmoothie

import numpy as np
import matplotlib.pyplot as plt
from tsmoothie.utils_func import sim_randomwalk
from tsmoothie.smoother import LowessSmoother
# 生成 3 个长度为200的随机数据组
np.random.seed(123)
data = sim_randomwalk(n_series=3, timesteps=200,
                      process_noise=10, measure_noise=30)

# 平滑
smoother = LowessSmoother(smooth_fraction=0.1, iterations=1)
smoother.smooth(data)

print(smoother.smooth_data)
# [[ 5.21462928 3.07898076 0.93933646 -1.19847767 -3.32294934
# -5.40678762 -7.42425709 -9.36150892 -11.23591897 -13.05271523
# ....... ....... ....... ....... ....... ]]

_low, _up = smoother.get_intervals('sigma_interval', n_sigma=2)
series['low'] = np.hstack([series['low'], _low[:,[-1]]])
series['up'] = np.hstack([series['up'], _up[:,[-1]]])
is_anomaly = np.logical_or(
    series['original'][:,-1] > series['up'][:,-1],
    series['original'][:,-1] < series['low'][:,-1]
).reshape(-1,1)

# Origin: https://github.com/cerlymarco/MEDIUM_NoteBook/blob/master/Anomaly_Detection_RealTime/Anomaly_Detection_RealTime.ipynb
import numpy as np
import matplotlib.pyplot as plt
from celluloid import Camera
from collections import defaultdict
from functools import partial
from tqdm import tqdm
from tsmoothie.utils_func import sim_randomwalk, sim_seasonal_data
from tsmoothie.smoother import *
def plot_history(ax, i, is_anomaly, window_len, color='blue', **pltargs):
    posrange = np.arange(0,i)
    ax.fill_between(posrange[window_len:],
                    pltargs['low'][1:], pltargs['up'][1:],
                    color=color, alpha=0.2)
    if is_anomaly:
        ax.scatter(i-1, pltargs['original'][-1], c='red')
    else:
        ax.scatter(i-1, pltargs['original'][-1], c='black')
    ax.scatter(i-1, pltargs['smooth'][-1], c=color)
    ax.plot(posrange, pltargs['original'][1:], '.k')
    ax.plot(posrange[window_len:],
            pltargs['smooth'][1:], color=color, linewidth=3)
    if 'ano_id' in pltargs.keys():
        if pltargs['ano_id'].sum()>0:
            not_zeros = pltargs['ano_id'][pltargs['ano_id']!=0] -1
            ax.scatter(not_zeros, pltargs['original'][1:][not_zeros],
                       c='red', alpha=1.)
np.random.seed(42)
n_series, timesteps = 3, 200
data = sim_randomwalk(n_series=n_series, timesteps=timesteps,
                      process_noise=10, measure_noise=30)
window_len = 20
fig = plt.figure(figsize=(18,10))
camera = Camera(fig)
axes = [plt.subplot(n_series,1,ax+1) for ax in range(n_series)]
series = defaultdict(partial(np.ndarray, shape=(n_series,1), dtype='float32'))
for i in tqdm(range(timesteps+1), total=(timesteps+1)):
    if i>window_len:
        smoother = ConvolutionSmoother(window_len=window_len, window_type='ones')
        smoother.smooth(series['original'][:,-window_len:])
        series['smooth'] = np.hstack([series['smooth'], smoother.smooth_data[:,[-1]]])
        _low, _up = smoother.get_intervals('sigma_interval', n_sigma=2)
        series['low'] = np.hstack([series['low'], _low[:,[-1]]])
        series['up'] = np.hstack([series['up'], _up[:,[-1]]])
        is_anomaly = np.logical_or(
            series['original'][:,-1] > series['up'][:,-1],
            series['original'][:,-1] < series['low'][:,-1]
        ).reshape(-1,1)
        if is_anomaly.any():
            series['ano_id'] = np.hstack([series['ano_id'], is_anomaly*i]).astype(int)
        for s in range(n_series):
            pltargs = {k:v[s,:] for k,v in series.items()}
            plot_history(axes[s], i, is_anomaly[s], window_len,
                         **pltargs)
        camera.snap()
    if i>=timesteps:
        continue
    series['original'] = np.hstack([series['original'], data[:,[i]]])
print('CREATING GIF...') # it may take a few seconds
camera._photos = [camera._photos[-1]] + camera._photos
animation = camera.animate()
animation.save('animation1.gif', codec="gif", writer='imagemagick')
plt.close(fig)
print('DONE')