自动提取时序特征 tsfresh(1)

import matplotlib.pylab as plt
import seaborn as sns
from tsfresh.examples.robot_execution_failures import download_robot_execution_failures,load_robot_execution_failures
from tsfresh import extract_features, extract_relevant_features, select_features
from tsfresh.utilities.dataframe_functions import impute
from tsfresh.feature_extraction import ComprehensiveFCParameters
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import numpy as np
from  pandas import Series 

download_robot_execution_failures()#导入案例数据
df, y = load_robot_execution_failures()
df.head()
df[df.id == 3][['time', 'F_x', 'F_y', 'F_z', 'T_x', 'T_y', 'T_z']].plot(x='time', title='Success example (id 3)', figsize=(12, 6));
df[df.id == 20][['time', 'F_x', 'F_y', 'F_z', 'T_x', 'T_y', 'T_z']].plot(x='time', title='Failure example (id 20)', figsize=(12, 6));
dff=df.drop(1319)
dff=df.drop(29)
extraction_settings = ComprehensiveFCParameters()
X = extract_features(dff, 
                     column_id='id', column_sort='time',
                     default_fc_parameters=extraction_settings,
                     impute_function= impute)

X_filtered = extract_relevant_features(df, y,column_id='id', column_sort='time', default_fc_parameters=extraction_settings)
X_filtered.info()
X_train, X_test, X_filtered_train, X_filtered_test, y_train, y_test = train_test_split(X, X_filtered, y, test_size=4)

relevant_features = set()
for label in y.unique():
    y_train_binary = y_train == label
    X_train_filtered = select_features(X_train, y_train_binary)
    print("Number of relevant features for class {}: {}/{}".format(label, X_train_filtered.shape[1],
                                                                       X_train.shape[1]))
    relevant_features = relevant_features.union(set(X_train_filtered.columns))
    X_train_filtered = X_train[list(relevant_features)]
    X_test_filtered = X_test[list(relevant_features)]

cl =DecisionTreeClassifier()
cl.fit(X_train, y_train)
print(classification_report(y_test, cl.predict(X_test)))
cl.n_features_
cl2 = DecisionTreeClassifier()
cl2.fit(X_filtered_train, y_train)
print(classification_report(y_test, cl2.predict(X_filtered_test)))