def main():
download_robot_execution_failures()
df_ts, y = load_robot_execution_failures()
# We create an empty feature matrix that has the proper index
X = pd.DataFrame(index=y.index)
# Split data into train and test set
X_train, X_test, y_train, y_test = train_test_split(X, y)
print(df_ts)
# We have a pipeline that consists of a feature extraction step with a subsequent Random Forest Classifier
ppl = Pipeline([('fresh',
RelevantFeatureAugmenter(column_id='id',
column_sort='time')),
('clf', RandomForestClassifier())])
# Here comes the tricky part, due to limitations of the sklearn pipeline API, we can not pass the dataframe
# containing the time series dataframe but instead have to use the set_params method
# In this case, df_ts contains the time series of both train and test set, if you have different dataframes for
# train and test set, you have to call set_params two times (see the notebook pipeline_with_two_datasets.ipynb)
ppl.set_params(fresh__timeseries_container=df_ts)
# We fit the pipeline
ppl.fit(X_train, y_train)
# Predicting works as well
y_pred = ppl.predict(X_test)
# So, finally we inspect the performance
print(classification_report(y_test, y_pred))
def setUp(self):
download_robot_execution_failures()
self.timeseries, self.y = load_robot_execution_failures()
self.df = pd.DataFrame(index=self.timeseries.id.unique())
# shrink the time series for this test
self.timeseries = self.timeseries[["id", "time", "a"]]
def setUp(self):
download_robot_execution_failures()
self.timeseries, self.y = load_robot_execution_failures()
self.df = pd.DataFrame(index=self.timeseries.id.unique())
# shrink the time series for this test
self.timeseries = self.timeseries[["id", "time", "F_x"]]
def setUp(self):
self.temporary_folder = tempfile.mkdtemp()
temporary_file = os.path.join(self.temporary_folder, "data")
download_robot_execution_failures(file_name=temporary_file)
self.timeseries, self.y = load_robot_execution_failures(file_name=temporary_file)
self.df = pd.DataFrame(index=self.timeseries.id.unique())
# shrink the time series for this test
self.timeseries = self.timeseries[["id", "time", "F_x"]]
def testLocalTSFresh(self):
robot_execution_failures.download_robot_execution_failures()
df, y = robot_execution_failures.load_robot_execution_failures()
dist = MarsDistributor()
df = df.iloc[:200]
extraction_settings = ComprehensiveFCParameters()
extract_features(df, column_id='id', column_sort='time',
default_fc_parameters=extraction_settings,
# we impute = remove all NaN features automatically
impute_function=impute, distributor=dist)
def test_distributed_ts_fresh(setup):
robot_execution_failures.download_robot_execution_failures()
df, y = robot_execution_failures.load_robot_execution_failures()
default_session = get_default_session()
sync_session = new_session(default_session.address)
dist = MarsDistributor(session=sync_session)
df = df.iloc[:200].copy()
extraction_settings = ComprehensiveFCParameters()
extract_features(df, column_id='id', column_sort='time',
default_fc_parameters=extraction_settings,
# we impute = remove all NaN features automatically
impute_function=impute, distributor=dist)
def testDistributedTSFresh(self):
robot_execution_failures.download_robot_execution_failures()
df, y = robot_execution_failures.load_robot_execution_failures()
service_ep = 'http://127.0.0.1:' + self.web_port
with new_session(service_ep) as sess:
dist = MarsDistributor(sess)
df = df.iloc[:200]
extraction_settings = ComprehensiveFCParameters()
extract_features(df, column_id='id', column_sort='time',
default_fc_parameters=extraction_settings,
# we impute = remove all NaN features automatically
impute_function=impute, distributor=dist)
def test_timing():
from tsfresh.examples.robot_execution_failures import download_robot_execution_failures, \
load_robot_execution_failures
download_robot_execution_failures()
df, y = load_robot_execution_failures()
commit_hash = check_output(["git", "log", "--format=\"%H\"", "-1"
]).decode("ascii").strip().replace("\"", "")
lengths_to_test = [1, 5, 10, 60, 100, 400, 600, 1000, 2000]
results = []
for length in lengths_to_test:
results.append(test_with_length(length, df))
results.append(test_with_length(length, df))
results.append(test_with_length(length, df))
results = pd.DataFrame(results)
results.to_csv("{hash}.dat".format(hash=commit_hash))
def main():
# download and load the data
download_robot_execution_failures()
timeseries, y = load_robot_execution_failures()
# plot healthy example
timeseries[timeseries['id'] == 3].plot(subplots=True, sharex=True, figsize=(10,10))
# plot failure example
timeseries[timeseries['id'] == 21].plot(subplots=True, sharex=True, figsize=(10,10))
plt.show()
# extract features
extracted_features = extract_features(timeseries, column_id="id", column_sort="time")
print('shape of extracted features: {},{}'.format(*extracted_features.shape))
# fill NaNs based on rules
impute(extracted_features)
# filter for significant features
features_filtered = select_features(extracted_features, y)
print('shape of selected features: {},{}'.format(*features_filtered.shape))
import pdb; pdb.set_trace()
import numpy as np
import pickle
import matplotlib.pyplot as plt
import random
import math
from scipy.fftpack import fft, irfft, rfft
from scipy.optimize import curve_fit
import tsfresh.feature_extraction.feature_calculators as ts
from tsfresh.examples.robot_execution_failures import download_robot_execution_failures, load_robot_execution_failures
from tsfresh import extract_features
download_robot_execution_failures()
timeseries, y = load_robot_execution_failures()
def normalize(signal, range=None, offset=None):
'''
# If range = None and Offset = None:
- return normalized signal with values in range (0,1)
# Range squeezes the signal between range(-range, +range)
# Offet adds offset...
'''
norm_sig = (signal - np.min(signal)) / (np.max(signal) - np.min(signal))
if range is not None:
norm_sig = (2 * norm_sig - 1) * range
if offset is not None:
norm_sig = norm_sig + offset
return norm_sig
# with open('/Users/jiayun/PycharmProjects/D'
def setUp(self):
download_robot_execution_failures()
self.X, self.y = load_robot_execution_failures()
# -*- coding: utf-8 -*- from tsfresh.examples.robot_execution_failures import download_robot_execution_failures, load_robot_execution_failures import matplotlib.pyplot as plt from tsfresh import extract_features from tsfresh import select_features from tsfresh import extract_relevant_features from tsfresh.utilities.dataframe_functions import impute import pandas as pd import numpy as np from classifiers.base_classification import Base_Classification from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score ### First test, delet after real test work ### ''' download_robot_execution_failures() timeseries, y = load_robot_execution_failures() print(timeseries.head()) timeseries[timeseries['id'] == 3].plot(subplots=True, sharex=True, figsize=(10,10)) plt.show() extracted_features = extract_features(timeseries, column_id="id", column_sort="time") impute(extracted_features) features_filtered = select_features(extracted_features, y) ''' ### Real Work ### # First load hmp data in extratrees_classification.py dataframe_1 = hmp.data_with_window["f1"]["training"] dataframe_2 = pd.DataFrame()
def setUp(self):
download_robot_execution_failures()
self.X, self.y = load_robot_execution_failures()
