|
转自：DeepHub IMBA
在本文中，我们将介绍四个主要的Python库——statmodels、tslearn、tssearch、tsfresh——每个库都针对时间序列分析的不同方面进行了定制。这些库为从预测到模式识别的任务提供了强大的工具，使它们成为各种应用程序的宝贵资源。 我们使用来自Kaggle的数据集，通过加速度计数为各种身体活动进行分析。这些活动被分为12个不同的类别，每个类别对应一个特定的身体动作，如站立、坐着、行走，或从事更有活力的活动，如慢跑和骑自行车。每个活动都记录了一分钟的持续时间，提供了丰富的时间序列数据源。 用于此分析的库有: # statsmodels
from statsmodels.tsa.seasonal import seasonal_decompose
from statsmodels.tsa.stattools import adfuller
from statsmodels.graphics.tsaplots import plot_acf
#tslearn
from tslearn.barycenters import dtw_barycenter_averaging
# tssearch
from tssearch import get_distance_dict, time_series_segmentation, time_series_search, plot_search_distance_result
# tsfresh
from tsfresh import extract_features
from tsfresh.feature_selection.relevance import calculate_relevance_table
from tsfresh.feature_extraction import EfficientFCParameters
from tsfresh.utilities.dataframe_functions import impute Statsmodelsdef activity_stationary_test(dataframe, sensor, activity):
dataframe.reset_index(drop=True)
adft = adfuller(dataframe[(dataframe['Activity'] == activity)][sensor], autolag='AIC')
output_df = pd.DataFrame({'Values':[adft[0], adft[1], adft[4]['1%']], 'Metric':['Test Statistics', 'p-value', 'critical value (1%)']})
print('Statistics of {} sensor:\n'.format(sensor), output_df)
print()
if (adft[1] < 0.05) & (adft[0] < adft[4]['1%']):
print('The signal is stationary')
else:
print('The signal is non-stationary')
seasonal_decomposition函数提供了对时间序列数据结构的宝贵见解。它将时间序列分解为三个不同的组成部分:趋势、季节性和残差。这种分解使我们能够可视化和理解加速度数据中的潜在模式和异常。def activity_decomposition(dataframe, sensor, activity):
dataframe.reset_index(drop=True)
data = dataframe[(dataframe['Activity'] == activity)][sensor]
decompose = seasonal_decompose(data, model='additive', extrapolate_trend='freq', period=50)
fig = decompose.plot()
fig.set_size_inches((12, 7))
fig.axes[0].set_title('Seasonal Decomposition Plot')
fig.axes[3].set_xlabel('Indices')
plt.show() Tslearn template_length = 150
overlap = 50 # Adjust the overlap value as needed
segments = [signal[i:i + template_length] for i in range(0, len(signal) - template_length + 1, overlap)]
template_signal = dtw_barycenter_averaging(segments)
template_signal = template_signal.flatten() segment_distance = get_distance_dict(['Dynamic Time Warping'])
segment_results = time_series_segmentation(segment_distance, template_signal, signal_np)
for k in segment_results:
plt.figure(figsize=(15, 3))
plt.plot(signal_np, color='gray')
plt.vlines(segment_results[k], np.min(signal_np)-1, np.max(signal_np) + 1, 'C1')
plt.xlabel('Indices')
plt.ylabel('Amplitude')
plt.title(k)
dict_distances = {
'elastic': {
'Dynamic Time Warping': {
'function': 'dtw',
'parameters': {'dtw_type': 'sub-dtw', 'alpha': 0.5},
}
},
'lockstep': {
'Euclidean Distance': {
'function': 'euclidean_distance',
'parameters': '',
}
}
}
result = time_series_search(dict_distances, template_signal, signal_np, output=('number', 30))
plot_search_distance_result(result, signal_np) Tsfresh extraction_settings = EfficientFCParameters()
X_extracted = extract_features(final_df, column_id='Activity',
default_fc_parameters=extraction_settings,
# we impute = remove all NaN features automatically
impute_function=impute, show_warnings=False)
X_extracted= pd.DataFrame(X_extracted, index=X_extracted.index, columns=X_extracted.columns)
values = list(range(1, 13))
y = pd.Series(values, index=range(1, 13))
relevance_table_clf = calculate_relevance_table(X_extracted, y)
relevance_table_clf.sort_values('p_value', inplace=True)
relevance_table_clf.head(10)
top_features = relevance_table_clf['feature'].head(10)
x_features = X_extracted[top_features] 总结本文向您介绍了时间序列分析的四个基本Python库:statmodels、tslearn、tssearch和tsfresh。时间序列分析是金融和医疗保健等各个领域的重要工具，在这些领域，我们需要了解数据随时间的变化趋势，以便做出明智的决策和预测。每个库都专注于时间序列分析的不同方面，选择哪个库取决于具体问题。通过结合使用这些库，可以处理各种与时间相关的挑战，从预测财务趋势到对医疗保健中的活动进行分类。当要开始自己的时间序列分析项目时，请记住这些库，结合着使用它们可以帮助你解决很多的实际问题。kaggle数据集：https://www./datasets/gaurav2022/mobile-health/discussion/375938
|
