def feature_extract(dt):
import tsfresh.feature_extraction.feature_calculators as fc
ft = {
'abs_energy': fc.abs_energy(dt),
'sum_values': fc.sum_values(dt),
'mean': fc.mean(dt),
'maximum': fc.maximum(dt),
'minimum': fc.minimum(dt),
'median': fc.median(dt),
'quantile_0.1': fc.quantile(dt, 0.1),
'quantile_0.2': fc.quantile(dt, 0.2),
'quantile_0.3': fc.quantile(dt, 0.3),
'quantile_0.4': fc.quantile(dt, 0.4),
'quantile_0.5': fc.quantile(dt, 0.5),
'quantile_0.6': fc.quantile(dt, 0.6),
'quantile_0.7': fc.quantile(dt, 0.7),
'quantile_0.8': fc.quantile(dt, 0.8),
'quantile_0.9': fc.quantile(dt, 0.9),
#
# TODO:
# Below functions dont works well -> need to be checked!!
#
#'fft_coefficient__coeff_0__attr_real': fc.fft_coefficient(dt {"coeff": 0, "attr": "real"}),
#'fft_coefficient__coeff_0__attr_imag': fc.fft_coefficient(dt {"coeff": 0, "attr": "imag"}),
#'fft_coefficient__coeff_0__attr_abs': fc.fft_coefficient(dt {"coeff": 0, "attr": "abs"}),
#'fft_coefficient__coeff_0__attr_angle': fc.fft_coefficient(dt {"coeff": 0, "attr": "angle"}),
#
#=> Mr. Huy just fix this issue with above function fft_ft !!
}
ft.update(fft_ft(dt))
return ft
def get_sta_features(self, data):
"""
Calculate the value of 9 kinds of selected statistical features
:param data:
:return:
"""
def _cal_trend(data):
time_list = np.arange(len(data))
# create linear regression object
regr = linear_model.LinearRegression()
regr.fit(time_list.reshape(-1, 1), np.array(data).reshape(-1, 1))
return regr.coef_[0][0]
E = ts.abs_energy(data)
S = ts.binned_entropy(data, max_bins=5)
ro = ts.autocorrelation(data, lag=4)
skewness = ts.skewness(data)
kurtosis = ts.kurtosis(data)
trend = _cal_trend(data)
mean = ts.mean(data)
min = ts.minimum(data)
max = ts.maximum(data)
return [E, S, ro, skewness, kurtosis, trend, mean, min, max]
def TS_feature3(signal):
max_ts = ts.maximum(signal)
mean_rs = ts.mean(signal)
mean_abs_change = ts.mean_abs_change(signal)
mean_change = ts.mean_change(signal)
median_ts = ts.median(signal)
minimum_ts = ts.minimum(signal)
return max_ts, mean_rs, mean_abs_change, mean_change, median_ts, minimum_ts
def time_series_minimum(x):
"""
:param x: the time series to calculate the feature of
:type x: pandas.Series
:return: the value of this feature
:return type: float
"""
return ts_feature_calculators.minimum(x)
def min_max_points(df):
diff_lwx = np.diff(split_leftwrist_x(df))
diff_rwx = np.diff(split_rightwrist_x(df))
diff_lwy = np.diff(split_leftwrist_y(df))
diff_rwy = np.diff(split_rightwrist_y(df))
x = [diff_lwx, diff_lwy, diff_rwx, diff_rwy]
min_max = []
for i in x:
l = len(i)
j = 0
while j < l:
min1 = fc.minimum(i[j:j + math.ceil(l / 3)])
max1 = fc.minimum(i[j:j + math.ceil(l / 3)])
dev = dc(max1) - dc(min1)
min_max.append(dev)
j = j + math.ceil(l / 3)
return pd.DataFrame(min_max).transpose()
def scalar_feature_extraction(column):
retval = np.zeros([1, 10], dtype=float)
retval[0][0] = tffe.count_above_mean(column.values)
retval[0][1] = tffe.mean(column.values)
retval[0][2] = tffe.maximum(column.values)
retval[0][3] = tffe.median(column.values)
retval[0][4] = tffe.minimum(column.values)
retval[0][5] = tffe.sample_entropy(column.values)
if (isNaN(retval[0][5])):
retval[0][5] = 0
retval[0][6] = tffe.skewness(column.values)
retval[0][7] = tffe.variance(column.values)
retval[0][8] = tffe.longest_strike_above_mean(column.values)
retval[0][9] = tffe.longest_strike_below_mean(column.values)
return retval
def extract_features(data):
day = 24 * 60
return list(
numpy.nan_to_num(
numpy.array([
feature.symmetry_looking(data, [{
'r': 0.3
}])[0][1],
feature.variance_larger_than_standard_deviation(data).bool(),
feature.ratio_beyond_r_sigma(data, 2),
feature.has_duplicate_max(data),
feature.has_duplicate_min(data),
feature.has_duplicate(data),
feature.agg_autocorrelation(numpy.array(data.value),
[{
'f_agg': 'mean',
'maxlag': day
}])[0][1],
feature.partial_autocorrelation(data, [{
'lag': day
}])[0][1],
feature.abs_energy(numpy.array(data.value)),
feature.mean_change(data),
feature.mean_second_derivative_central(data),
feature.median(data),
float(feature.mean(data)),
float(feature.standard_deviation(data)),
float(feature.longest_strike_below_mean(data)),
float(feature.longest_strike_above_mean(data)),
int(feature.number_peaks(data, 10)),
feature.linear_trend(numpy.array(data.value), [{
'attr': 'rvalue'
}])[0][1],
feature.c3(data, day),
float(feature.maximum(data)),
float(feature.minimum(data))
])))
