def transform_pack6(df):
""" 0427 paper amplitude features"""
output = {}
percentiles = [1, 5, 10, 20, 25, 30]
# In absolute space
df = np.abs(df)
length = len(df)
x = np.sort(df.values)[::-1]
for p in percentiles:
bound = int((p / 100) * length)
other_bound = length - bound
output[f'ampl_p{p}'] = np.mean(np.power(2, x[:bound]))
output[f'ampl_p{100-p}'] = np.mean(np.power(2, x[other_bound:]))
output[f'ampl_p{p}_ratio'] = output[f'ampl_p{p}'] / output[
f'ampl_p{100-p}']
output[f'ampl_p{p}_diff'] = output[f'ampl_p{p}'] - output[
f'ampl_p{100-p}']
tmp = x
output['num_peaks_1'] = feature_calculators.number_peaks(tmp, 1)
output['num_peaks_5'] = feature_calculators.number_peaks(tmp, 5)
output['binned_entropy_5'] = feature_calculators.binned_entropy(x, 5)
return output
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 time_series_binned_entropy(x):
"""
:param x: the time series to calculate the feature of
:type x: pandas.Series
:param max_bins: the maximal number of bins
:type max_bins: int
:return: the value of this feature
:return type: float
"""
max_bins = [2, 4, 6, 8, 10, 20]
for value in max_bins:
temp__ = ts_feature_calculators.binned_entropy(x, value)
return temp__
def time_series_binned_entropy(x):
"""
First bins the values of x into max_bins equidistant bins.
Then calculates the value of
.. math::
- \\sum_{k=0}^{min(max\\_bins, len(x))} p_k log(p_k) \\cdot \\mathbf{1}_{(p_k > 0)}
where :math:`p_k` is the percentage of samples in bin :math:`k`.
:param x: the time series to calculate the feature of
:type x: pandas.Series
:param max_bins: the maximal number of bins
:type max_bins: int
:return: the value of this feature
:return type: float
"""
max_bins = [2, 4, 6, 8, 10, 20]
result = []
for value in max_bins:
result.append(ts_feature_calculators.binned_entropy(x, value))
return result
def time_series_binned_entropy(x):
"""
First bins the values of x into max_bins equidistant bins.
Then calculates the value of
.. math::
- \\sum_{k=0}^{min(max\\_bins, len(x))} p_k log(p_k) \\cdot \\mathbf{1}_{(p_k > 0)}
where :math:`p_k` is the percentage of samples in bin :math:`k`.
:param x: the time series to calculate the feature of
:type x: pandas.Series
:param max_bins: the maximal number of bins
:type max_bins: int
:return: the value of this feature
:return type: float
"""
max_bins = [2, 4, 6, 8, 10, 20]
result = []
for value in max_bins:
result.append(ts_feature_calculators.binned_entropy(x, value))
return result
def features(self, x, prefix):
feature_dict = dict()
# create features here
# numpy
feature_dict[prefix + '_' + 'mean'] = np.mean(x)
feature_dict[prefix + '_' + 'max'] = np.max(x)
feature_dict[prefix + '_' + 'min'] = np.min(x)
feature_dict[prefix + '_' + 'std'] = np.std(x)
feature_dict[prefix + '_' + 'var'] = np.var(x)
feature_dict[prefix + '_' + 'ptp'] = np.ptp(x)
feature_dict[prefix + '_' + 'percentile_10'] = np.percentile(x, 10)
feature_dict[prefix + '_' + 'percentile_20'] = np.percentile(x, 20)
feature_dict[prefix + '_' + 'percentile_30'] = np.percentile(x, 30)
feature_dict[prefix + '_' + 'percentile_40'] = np.percentile(x, 40)
feature_dict[prefix + '_' + 'percentile_50'] = np.percentile(x, 50)
feature_dict[prefix + '_' + 'percentile_60'] = np.percentile(x, 60)
feature_dict[prefix + '_' + 'percentile_70'] = np.percentile(x, 70)
feature_dict[prefix + '_' + 'percentile_80'] = np.percentile(x, 80)
feature_dict[prefix + '_' + 'percentile_90'] = np.percentile(x, 90)
# scipy
feature_dict[prefix + '_' + 'skew'] = sp.stats.skew(x)
feature_dict[prefix + '_' + 'kurtosis'] = sp.stats.kurtosis(x)
feature_dict[prefix + '_' + 'kstat_1'] = sp.stats.kstat(x, 1)
feature_dict[prefix + '_' + 'kstat_2'] = sp.stats.kstat(x, 2)
feature_dict[prefix + '_' + 'kstat_3'] = sp.stats.kstat(x, 3)
feature_dict[prefix + '_' + 'kstat_4'] = sp.stats.kstat(x, 4)
feature_dict[prefix + '_' + 'moment_1'] = sp.stats.moment(x, 1)
feature_dict[prefix + '_' + 'moment_2'] = sp.stats.moment(x, 2)
feature_dict[prefix + '_' + 'moment_3'] = sp.stats.moment(x, 3)
feature_dict[prefix + '_' + 'moment_4'] = sp.stats.moment(x, 4)
# tsfresh
feature_dict[prefix + '_' +
'abs_energy'] = feature_calculators.abs_energy(x)
feature_dict[
prefix + '_' +
'abs_sum_of_changes'] = feature_calculators.absolute_sum_of_changes(
x)
feature_dict[
prefix + '_' +
'count_above_mean'] = feature_calculators.count_above_mean(x)
feature_dict[
prefix + '_' +
'count_below_mean'] = feature_calculators.count_below_mean(x)
feature_dict[prefix + '_' +
'mean_abs_change'] = feature_calculators.mean_abs_change(
x)
feature_dict[prefix + '_' +
'mean_change'] = feature_calculators.mean_change(x)
feature_dict[
prefix + '_' +
'var_larger_than_std_dev'] = feature_calculators.variance_larger_than_standard_deviation(
x)
feature_dict[prefix + '_' +
'range_minf_m4000'] = feature_calculators.range_count(
x, -np.inf, -4000)
feature_dict[prefix + '_' +
'range_m4000_m3000'] = feature_calculators.range_count(
x, -4000, -3000)
feature_dict[prefix + '_' +
'range_m3000_m2000'] = feature_calculators.range_count(
x, -3000, -2000)
feature_dict[prefix + '_' +
'range_m2000_m1000'] = feature_calculators.range_count(
x, -2000, -1000)
feature_dict[prefix + '_' +
'range_m1000_0'] = feature_calculators.range_count(
x, -1000, 0)
feature_dict[prefix + '_' +
'range_0_p1000'] = feature_calculators.range_count(
x, 0, 1000)
feature_dict[prefix + '_' +
'range_p1000_p2000'] = feature_calculators.range_count(
x, 1000, 2000)
feature_dict[prefix + '_' +
'range_p2000_p3000'] = feature_calculators.range_count(
x, 2000, 3000)
feature_dict[prefix + '_' +
'range_p3000_p4000'] = feature_calculators.range_count(
x, 3000, 4000)
feature_dict[prefix + '_' +
'range_p4000_pinf'] = feature_calculators.range_count(
x, 4000, np.inf)
feature_dict[
prefix + '_' +
'ratio_unique_values'] = feature_calculators.ratio_value_number_to_time_series_length(
x)
feature_dict[
prefix + '_' +
'first_loc_min'] = feature_calculators.first_location_of_minimum(x)
feature_dict[
prefix + '_' +
'first_loc_max'] = feature_calculators.first_location_of_maximum(x)
feature_dict[
prefix + '_' +
'last_loc_min'] = feature_calculators.last_location_of_minimum(x)
feature_dict[
prefix + '_' +
'last_loc_max'] = feature_calculators.last_location_of_maximum(x)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_10'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 10)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_100'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 100)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_1000'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 1000)
feature_dict[
prefix + '_' +
'autocorrelation_1'] = feature_calculators.autocorrelation(x, 1)
feature_dict[
prefix + '_' +
'autocorrelation_2'] = feature_calculators.autocorrelation(x, 2)
feature_dict[
prefix + '_' +
'autocorrelation_3'] = feature_calculators.autocorrelation(x, 3)
feature_dict[
prefix + '_' +
'autocorrelation_4'] = feature_calculators.autocorrelation(x, 4)
feature_dict[
prefix + '_' +
'autocorrelation_5'] = feature_calculators.autocorrelation(x, 5)
feature_dict[
prefix + '_' +
'autocorrelation_6'] = feature_calculators.autocorrelation(x, 6)
feature_dict[
prefix + '_' +
'autocorrelation_7'] = feature_calculators.autocorrelation(x, 7)
feature_dict[
prefix + '_' +
'autocorrelation_8'] = feature_calculators.autocorrelation(x, 8)
feature_dict[
prefix + '_' +
'autocorrelation_9'] = feature_calculators.autocorrelation(x, 9)
feature_dict[
prefix + '_' +
'autocorrelation_10'] = feature_calculators.autocorrelation(x, 10)
feature_dict[
prefix + '_' +
'autocorrelation_50'] = feature_calculators.autocorrelation(x, 50)
feature_dict[
prefix + '_' +
'autocorrelation_100'] = feature_calculators.autocorrelation(
x, 100)
feature_dict[
prefix + '_' +
'autocorrelation_1000'] = feature_calculators.autocorrelation(
x, 1000)
feature_dict[prefix + '_' + 'c3_1'] = feature_calculators.c3(x, 1)
feature_dict[prefix + '_' + 'c3_2'] = feature_calculators.c3(x, 2)
feature_dict[prefix + '_' + 'c3_3'] = feature_calculators.c3(x, 3)
feature_dict[prefix + '_' + 'c3_4'] = feature_calculators.c3(x, 4)
feature_dict[prefix + '_' + 'c3_5'] = feature_calculators.c3(x, 5)
feature_dict[prefix + '_' + 'c3_10'] = feature_calculators.c3(x, 10)
feature_dict[prefix + '_' + 'c3_100'] = feature_calculators.c3(x, 100)
for c in range(1, 34):
feature_dict[prefix + '_' + 'fft_{0}_real'.format(c)] = list(
feature_calculators.fft_coefficient(x, [{
'coeff': c,
'attr': 'real'
}]))[0][1]
feature_dict[prefix + '_' + 'fft_{0}_imag'.format(c)] = list(
feature_calculators.fft_coefficient(x, [{
'coeff': c,
'attr': 'imag'
}]))[0][1]
feature_dict[prefix + '_' + 'fft_{0}_ang'.format(c)] = list(
feature_calculators.fft_coefficient(x, [{
'coeff': c,
'attr': 'angle'
}]))[0][1]
feature_dict[
prefix + '_' +
'long_strk_above_mean'] = feature_calculators.longest_strike_above_mean(
x)
feature_dict[
prefix + '_' +
'long_strk_below_mean'] = feature_calculators.longest_strike_below_mean(
x)
feature_dict[prefix + '_' + 'cid_ce_0'] = feature_calculators.cid_ce(
x, 0)
feature_dict[prefix + '_' + 'cid_ce_1'] = feature_calculators.cid_ce(
x, 1)
feature_dict[prefix + '_' +
'binned_entropy_5'] = feature_calculators.binned_entropy(
x, 5)
feature_dict[prefix + '_' +
'binned_entropy_10'] = feature_calculators.binned_entropy(
x, 10)
feature_dict[prefix + '_' +
'binned_entropy_20'] = feature_calculators.binned_entropy(
x, 20)
feature_dict[prefix + '_' +
'binned_entropy_50'] = feature_calculators.binned_entropy(
x, 50)
feature_dict[prefix + '_' +
'binned_entropy_80'] = feature_calculators.binned_entropy(
x, 80)
feature_dict[
prefix + '_' +
'binned_entropy_100'] = feature_calculators.binned_entropy(x, 100)
feature_dict[prefix + '_' +
'num_crossing_0'] = feature_calculators.number_crossing_m(
x, 0)
feature_dict[prefix + '_' +
'num_peaks_1'] = feature_calculators.number_peaks(x, 1)
feature_dict[prefix + '_' +
'num_peaks_3'] = feature_calculators.number_peaks(x, 3)
feature_dict[prefix + '_' +
'num_peaks_5'] = feature_calculators.number_peaks(x, 5)
feature_dict[prefix + '_' +
'num_peaks_10'] = feature_calculators.number_peaks(x, 10)
feature_dict[prefix + '_' +
'num_peaks_50'] = feature_calculators.number_peaks(x, 50)
feature_dict[prefix + '_' +
'num_peaks_100'] = feature_calculators.number_peaks(
x, 100)
feature_dict[prefix + '_' +
'num_peaks_500'] = feature_calculators.number_peaks(
x, 500)
feature_dict[prefix + '_' + 'spkt_welch_density_1'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 1
}]))[0][1]
feature_dict[prefix + '_' + 'spkt_welch_density_2'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 2
}]))[0][1]
feature_dict[prefix + '_' + 'spkt_welch_density_5'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 5
}]))[0][1]
feature_dict[prefix + '_' + 'spkt_welch_density_8'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 8
}]))[0][1]
feature_dict[prefix + '_' + 'spkt_welch_density_10'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 10
}]))[0][1]
feature_dict[prefix + '_' + 'spkt_welch_density_50'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 50
}]))[0][1]
feature_dict[prefix + '_' + 'spkt_welch_density_100'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 100
}]))[0][1]
feature_dict[
prefix + '_' +
'time_rev_asym_stat_1'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 1)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_2'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 2)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_3'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 3)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_4'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 4)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_10'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 10)
feature_dict[
prefix + '_' +
'time_rev_asym_stat_100'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 100)
for r in range(20):
feature_dict[prefix + '_' + 'symmetry_looking_' +
str(r)] = feature_calculators.symmetry_looking(
x, [{
'r': r * 0.05
}])[0][1]
for r in range(1, 20):
feature_dict[
prefix + '_' + 'large_standard_deviation_' +
str(r)] = feature_calculators.large_standard_deviation(
x, r * 0.05)
for r in range(1, 10):
feature_dict[prefix + '_' + 'quantile_' +
str(r)] = feature_calculators.quantile(x, r * 0.1)
for r in ['mean', 'median', 'var']:
feature_dict[prefix + '_' + 'agg_autocorr_' +
r] = feature_calculators.agg_autocorrelation(
x, [{
'f_agg': r,
'maxlag': 40
}])[0][-1]
#for r in range(1, 6):
# feature_dict[prefix+'_'+'number_cwt_peaks_'+str(r)] = feature_calculators.number_cwt_peaks(x, r)
for r in range(1, 10):
feature_dict[prefix + '_' + 'index_mass_quantile_' +
str(r)] = feature_calculators.index_mass_quantile(
x, [{
'q': r
}])[0][1]
#for ql in [0., .2, .4, .6, .8]:
# for qh in [.2, .4, .6, .8, 1.]:
# if ql < qh:
# for b in [False, True]:
# for f in ["mean", "var"]:
# feature_dict[prefix+'_'+'change_quantiles_'+str(ql)+'_'+str(qh)+'_'+str(b)+'_'+str(f)] = feature_calculators.change_quantiles(x, ql, qh, b, f)
#for r in [.1, .3, .5, .7, .9]:
# feature_dict[prefix+'_'+'approximate_entropy_'+str(r)] = feature_calculators.approximate_entropy(x, 2, r)
feature_dict[
prefix + '_' +
'max_langevin_fixed_point'] = feature_calculators.max_langevin_fixed_point(
x, 3, 30)
for r in ['pvalue', 'rvalue', 'intercept', 'slope', 'stderr']:
feature_dict[prefix + '_' + 'linear_trend_' +
str(r)] = feature_calculators.linear_trend(
x, [{
'attr': r
}])[0][1]
for r in ['pvalue', 'teststat', 'usedlag']:
feature_dict[prefix + '_' + 'augmented_dickey_fuller_' +
r] = feature_calculators.augmented_dickey_fuller(
x, [{
'attr': r
}])[0][1]
for r in [0.5, 1, 1.5, 2, 2.5, 3, 5, 6, 7, 10]:
feature_dict[prefix + '_' + 'ratio_beyond_r_sigma_' +
str(r)] = feature_calculators.ratio_beyond_r_sigma(
x, r)
#for attr in ["pvalue", "rvalue", "intercept", "slope", "stderr"]:
# feature_dict[prefix+'_'+'linear_trend_timewise_'+attr] = feature_calculators.linear_trend_timewise(x, [{'attr': attr}])[0][1]
#for attr in ["rvalue", "intercept", "slope", "stderr"]:
# for i in [5, 10, 50]:
# for f in ["max", "min", "mean", "var"]:
# feature_dict[prefix+'_'+'agg_linear_trend_'+attr+'_'+str(i)+'_'+f] = feature_calculators.agg_linear_trend(x, [{'attr': attr, 'chunk_len': i, 'f_agg': f}])[0][-1]
#for width in [2, 5, 10, 20]:
# for coeff in range(15):
# for w in [2, 5, 10, 20]:
# feature_dict[prefix+'_'+'cwt_coefficients_'+str(width)+'_'+str(coeff)+'_'+str(w)] = list(feature_calculators.cwt_coefficients(x, [{'widths': width, 'coeff': coeff, 'w': w}]))[0][1]
#for r in range(10):
# feature_dict[prefix+'_'+'partial_autocorr_'+str(r)] = feature_calculators.partial_autocorrelation(x, [{'lag': r}])[0][1]
# "ar_coefficient": [{"coeff": coeff, "k": k} for coeff in range(5) for k in [10]],
# "fft_coefficient": [{"coeff": k, "attr": a} for a, k in product(["real", "imag", "abs", "angle"], range(100))],
# "fft_aggregated": [{"aggtype": s} for s in ["centroid", "variance", "skew", "kurtosis"]],
# "value_count": [{"value": value} for value in [0, 1, -1]],
# "range_count": [{"min": -1, "max": 1}, {"min": 1e12, "max": 0}, {"min": 0, "max": 1e12}],
# "friedrich_coefficients": (lambda m: [{"coeff": coeff, "m": m, "r": 30} for coeff in range(m + 1)])(3),
# "energy_ratio_by_chunks": [{"num_segments": 10, "segment_focus": i} for i in range(10)],
return feature_dict
def _f():
max_bins = [2, 4, 6, 8, 10, 20]
for value in max_bins:
temp__ = ts_feature_calculators.binned_entropy(x, value)
name = ("time_series_binned_entropy_max_bins_{}".format(value))
yield {'{}'.format(name):temp__}
def binned_entropy(current_observation: pd.DataFrame, raw_key: str):
return tsf.binned_entropy(current_observation[raw_key], 1280)
def features(self, x, y, seg_id):
feature_dict = dict()
feature_dict['target'] = y
feature_dict['seg_id'] = seg_id
# create features here
# numpy
feature_dict['mean'] = np.mean(x)
feature_dict['max'] = np.max(x)
feature_dict['min'] = np.min(x)
feature_dict['std'] = np.std(x)
feature_dict['var'] = np.var(x)
feature_dict['ptp'] = np.ptp(x)
feature_dict['percentile_10'] = np.percentile(x, 10)
feature_dict['percentile_20'] = np.percentile(x, 20)
feature_dict['percentile_30'] = np.percentile(x, 30)
feature_dict['percentile_40'] = np.percentile(x, 40)
feature_dict['percentile_50'] = np.percentile(x, 50)
feature_dict['percentile_60'] = np.percentile(x, 60)
feature_dict['percentile_70'] = np.percentile(x, 70)
feature_dict['percentile_80'] = np.percentile(x, 80)
feature_dict['percentile_90'] = np.percentile(x, 90)
# scipy
feature_dict['skew'] = sp.stats.skew(x)
feature_dict['kurtosis'] = sp.stats.kurtosis(x)
feature_dict['kstat_1'] = sp.stats.kstat(x, 1)
feature_dict['kstat_2'] = sp.stats.kstat(x, 2)
feature_dict['kstat_3'] = sp.stats.kstat(x, 3)
feature_dict['kstat_4'] = sp.stats.kstat(x, 4)
feature_dict['moment_1'] = sp.stats.moment(x, 1)
feature_dict['moment_2'] = sp.stats.moment(x, 2)
feature_dict['moment_3'] = sp.stats.moment(x, 3)
feature_dict['moment_4'] = sp.stats.moment(x, 4)
feature_dict['abs_energy'] = feature_calculators.abs_energy(x)
feature_dict['abs_sum_of_changes'] = feature_calculators.absolute_sum_of_changes(x)
feature_dict['count_above_mean'] = feature_calculators.count_above_mean(x)
feature_dict['count_below_mean'] = feature_calculators.count_below_mean(x)
feature_dict['mean_abs_change'] = feature_calculators.mean_abs_change(x)
feature_dict['mean_change'] = feature_calculators.mean_change(x)
feature_dict['var_larger_than_std_dev'] = feature_calculators.variance_larger_than_standard_deviation(x)
feature_dict['range_minf_m4000'] = feature_calculators.range_count(x, -np.inf, -4000)
feature_dict['range_m4000_m3000'] = feature_calculators.range_count(x, -4000, -3000)
feature_dict['range_m3000_m2000'] = feature_calculators.range_count(x, -3000, -2000)
feature_dict['range_m2000_m1000'] = feature_calculators.range_count(x, -2000, -1000)
feature_dict['range_m1000_0'] = feature_calculators.range_count(x, -1000, 0)
feature_dict['range_0_p1000'] = feature_calculators.range_count(x, 0, 1000)
feature_dict['range_p1000_p2000'] = feature_calculators.range_count(x, 1000, 2000)
feature_dict['range_p2000_p3000'] = feature_calculators.range_count(x, 2000, 3000)
feature_dict['range_p3000_p4000'] = feature_calculators.range_count(x, 3000, 4000)
feature_dict['range_p4000_pinf'] = feature_calculators.range_count(x, 4000, np.inf)
feature_dict['ratio_unique_values'] = feature_calculators.ratio_value_number_to_time_series_length(x)
feature_dict['first_loc_min'] = feature_calculators.first_location_of_minimum(x)
feature_dict['first_loc_max'] = feature_calculators.first_location_of_maximum(x)
feature_dict['last_loc_min'] = feature_calculators.last_location_of_minimum(x)
feature_dict['last_loc_max'] = feature_calculators.last_location_of_maximum(x)
feature_dict['time_rev_asym_stat_10'] = feature_calculators.time_reversal_asymmetry_statistic(x, 10)
feature_dict['time_rev_asym_stat_100'] = feature_calculators.time_reversal_asymmetry_statistic(x, 100)
feature_dict['time_rev_asym_stat_1000'] = feature_calculators.time_reversal_asymmetry_statistic(x, 1000)
feature_dict['autocorrelation_5'] = feature_calculators.autocorrelation(x, 5)
feature_dict['autocorrelation_10'] = feature_calculators.autocorrelation(x, 10)
feature_dict['autocorrelation_50'] = feature_calculators.autocorrelation(x, 50)
feature_dict['autocorrelation_100'] = feature_calculators.autocorrelation(x, 100)
feature_dict['autocorrelation_1000'] = feature_calculators.autocorrelation(x, 1000)
feature_dict['c3_5'] = feature_calculators.c3(x, 5)
feature_dict['c3_10'] = feature_calculators.c3(x, 10)
feature_dict['c3_100'] = feature_calculators.c3(x, 100)
feature_dict['fft_1_real'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 1, 'attr': 'real'}]))[0][1]
feature_dict['fft_1_imag'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 1, 'attr': 'imag'}]))[0][1]
feature_dict['fft_1_ang'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 1, 'attr': 'angle'}]))[0][1]
feature_dict['fft_2_real'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 2, 'attr': 'real'}]))[0][1]
feature_dict['fft_2_imag'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 2, 'attr': 'imag'}]))[0][1]
feature_dict['fft_2_ang'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 2, 'attr': 'angle'}]))[0][1]
feature_dict['fft_3_real'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 3, 'attr': 'real'}]))[0][1]
feature_dict['fft_3_imag'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 3, 'attr': 'imag'}]))[0][1]
feature_dict['fft_3_ang'] = list(feature_calculators.fft_coefficient(x, [{'coeff': 3, 'attr': 'angle'}]))[0][1]
feature_dict['long_strk_above_mean'] = feature_calculators.longest_strike_above_mean(x)
feature_dict['long_strk_below_mean'] = feature_calculators.longest_strike_below_mean(x)
feature_dict['cid_ce_0'] = feature_calculators.cid_ce(x, 0)
feature_dict['cid_ce_1'] = feature_calculators.cid_ce(x, 1)
feature_dict['binned_entropy_5'] = feature_calculators.binned_entropy(x, 5)
feature_dict['binned_entropy_10'] = feature_calculators.binned_entropy(x, 10)
feature_dict['binned_entropy_20'] = feature_calculators.binned_entropy(x, 20)
feature_dict['binned_entropy_50'] = feature_calculators.binned_entropy(x, 50)
feature_dict['binned_entropy_80'] = feature_calculators.binned_entropy(x, 80)
feature_dict['binned_entropy_100'] = feature_calculators.binned_entropy(x, 100)
feature_dict['num_crossing_0'] = feature_calculators.number_crossing_m(x, 0)
feature_dict['num_peaks_10'] = feature_calculators.number_peaks(x, 10)
feature_dict['num_peaks_50'] = feature_calculators.number_peaks(x, 50)
feature_dict['num_peaks_100'] = feature_calculators.number_peaks(x, 100)
feature_dict['num_peaks_500'] = feature_calculators.number_peaks(x, 500)
feature_dict['spkt_welch_density_1'] = list(feature_calculators.spkt_welch_density(x, [{'coeff': 1}]))[0][1]
feature_dict['spkt_welch_density_10'] = list(feature_calculators.spkt_welch_density(x, [{'coeff': 10}]))[0][1]
feature_dict['spkt_welch_density_50'] = list(feature_calculators.spkt_welch_density(x, [{'coeff': 50}]))[0][1]
feature_dict['spkt_welch_density_100'] = list(feature_calculators.spkt_welch_density(x, [{'coeff': 100}]))[0][1]
feature_dict['time_rev_asym_stat_1'] = feature_calculators.time_reversal_asymmetry_statistic(x, 1)
feature_dict['time_rev_asym_stat_10'] = feature_calculators.time_reversal_asymmetry_statistic(x, 10)
feature_dict['time_rev_asym_stat_100'] = feature_calculators.time_reversal_asymmetry_statistic(x, 100)
return feature_dict
def binned_entropy_nonan(srs, p):
srs_nonan = srs.copy().dropna()
return feature_calculators.binned_entropy(srs_nonan, max_bins=p)
def features(self, x, y, seg_id):
feature_dict = dict()
feature_dict['target'] = y
feature_dict['seg_id'] = seg_id
# create features here
# lists with parameters to iterate over them
percentiles = [
1, 5, 10, 20, 25, 30, 40, 50, 60, 70, 75, 80, 90, 95, 99
]
hann_windows = [50, 150, 1500, 15000]
spans = [300, 3000, 30000, 50000]
windows = [10, 50, 100, 500, 1000, 10000]
borders = list(range(-4000, 4001, 1000))
peaks = [10, 20, 50, 100]
coefs = [1, 5, 10, 50, 100]
lags = [10, 100, 1000, 10000]
autocorr_lags = [5, 10, 50, 100, 500, 1000, 5000, 10000]
# basic stats
feature_dict['mean'] = x.mean()
feature_dict['std'] = x.std()
feature_dict['max'] = x.max()
feature_dict['min'] = x.min()
# basic stats on absolute values
feature_dict['mean_change_abs'] = np.mean(np.diff(x))
feature_dict['abs_max'] = np.abs(x).max()
feature_dict['abs_mean'] = np.abs(x).mean()
feature_dict['abs_std'] = np.abs(x).std()
# geometric and harminic means
feature_dict['hmean'] = stats.hmean(np.abs(x[np.nonzero(x)[0]]))
feature_dict['gmean'] = stats.gmean(np.abs(x[np.nonzero(x)[0]]))
# k-statistic and moments
for i in range(1, 5):
feature_dict[f'kstat_{i}'] = stats.kstat(x, i)
feature_dict[f'moment_{i}'] = stats.moment(x, i)
for i in [1, 2]:
feature_dict[f'kstatvar_{i}'] = stats.kstatvar(x, i)
# aggregations on various slices of data
for agg_type, slice_length, direction in product(
['std', 'min', 'max', 'mean'], [1000, 10000, 50000],
['first', 'last']):
if direction == 'first':
feature_dict[
f'{agg_type}_{direction}_{slice_length}'] = x[:
slice_length].agg(
agg_type)
elif direction == 'last':
feature_dict[f'{agg_type}_{direction}_{slice_length}'] = x[
-slice_length:].agg(agg_type)
feature_dict['max_to_min'] = x.max() / np.abs(x.min())
feature_dict['max_to_min_diff'] = x.max() - np.abs(x.min())
feature_dict['count_big'] = len(x[np.abs(x) > 500])
feature_dict['sum'] = x.sum()
feature_dict['mean_change_rate'] = calc_change_rate(x)
# calc_change_rate on slices of data
for slice_length, direction in product([1000, 10000, 50000],
['first', 'last']):
if direction == 'first':
feature_dict[
f'mean_change_rate_{direction}_{slice_length}'] = calc_change_rate(
x[:slice_length])
elif direction == 'last':
feature_dict[
f'mean_change_rate_{direction}_{slice_length}'] = calc_change_rate(
x[-slice_length:])
# percentiles on original and absolute values
for p in percentiles:
feature_dict[f'percentile_{p}'] = np.percentile(x, p)
feature_dict[f'abs_percentile_{p}'] = np.percentile(np.abs(x), p)
feature_dict['trend'] = add_trend_feature(x)
feature_dict['abs_trend'] = add_trend_feature(x, abs_values=True)
feature_dict['mad'] = x.mad()
feature_dict['kurt'] = x.kurtosis()
feature_dict['skew'] = x.skew()
feature_dict['med'] = x.median()
feature_dict['Hilbert_mean'] = np.abs(hilbert(x)).mean()
for hw in hann_windows:
feature_dict[f'Hann_window_mean_{hw}'] = (
convolve(x, hann(hw), mode='same') / sum(hann(hw))).mean()
feature_dict['classic_sta_lta1_mean'] = classic_sta_lta(x, 500,
10000).mean()
feature_dict['classic_sta_lta2_mean'] = classic_sta_lta(
x, 5000, 100000).mean()
feature_dict['classic_sta_lta3_mean'] = classic_sta_lta(x, 3333,
6666).mean()
feature_dict['classic_sta_lta4_mean'] = classic_sta_lta(
x, 10000, 25000).mean()
feature_dict['classic_sta_lta5_mean'] = classic_sta_lta(x, 50,
1000).mean()
feature_dict['classic_sta_lta6_mean'] = classic_sta_lta(x, 100,
5000).mean()
feature_dict['classic_sta_lta7_mean'] = classic_sta_lta(x, 333,
666).mean()
feature_dict['classic_sta_lta8_mean'] = classic_sta_lta(
x, 4000, 10000).mean()
# exponential rolling statistics
ewma = pd.Series.ewm
for s in spans:
feature_dict[f'exp_Moving_average_{s}_mean'] = (ewma(
x, span=s).mean(skipna=True)).mean(skipna=True)
feature_dict[f'exp_Moving_average_{s}_std'] = (ewma(
x, span=s).mean(skipna=True)).std(skipna=True)
feature_dict[f'exp_Moving_std_{s}_mean'] = (ewma(
x, span=s).std(skipna=True)).mean(skipna=True)
feature_dict[f'exp_Moving_std_{s}_std'] = (ewma(
x, span=s).std(skipna=True)).std(skipna=True)
feature_dict['iqr'] = np.subtract(*np.percentile(x, [75, 25]))
feature_dict['iqr1'] = np.subtract(*np.percentile(x, [95, 5]))
feature_dict['ave10'] = stats.trim_mean(x, 0.1)
for slice_length, threshold in product([50000, 100000, 150000],
[5, 10, 20, 50, 100]):
feature_dict[f'count_big_{slice_length}_threshold_{threshold}'] = (
np.abs(x[-slice_length:]) > threshold).sum()
feature_dict[
f'count_big_{slice_length}_less_threshold_{threshold}'] = (
np.abs(x[-slice_length:]) < threshold).sum()
# tfresh features take too long to calculate, so I comment them for now
# feature_dict['abs_energy'] = feature_calculators.abs_energy(x)
# feature_dict['abs_sum_of_changes'] = feature_calculators.absolute_sum_of_changes(x)
# feature_dict['count_above_mean'] = feature_calculators.count_above_mean(x)
# feature_dict['count_below_mean'] = feature_calculators.count_below_mean(x)
# feature_dict['mean_abs_change'] = feature_calculators.mean_abs_change(x)
# feature_dict['mean_change'] = feature_calculators.mean_change(x)
# feature_dict['var_larger_than_std_dev'] = feature_calculators.variance_larger_than_standard_deviation(x)
feature_dict['range_minf_m4000'] = feature_calculators.range_count(
x, -np.inf, -4000)
feature_dict['range_p4000_pinf'] = feature_calculators.range_count(
x, 4000, np.inf)
for i, j in zip(borders, borders[1:]):
feature_dict[f'range_{i}_{j}'] = feature_calculators.range_count(
x, i, j)
# feature_dict['ratio_unique_values'] = feature_calculators.ratio_value_number_to_time_series_length(x)
# feature_dict['first_loc_min'] = feature_calculators.first_location_of_minimum(x)
# feature_dict['first_loc_max'] = feature_calculators.first_location_of_maximum(x)
# feature_dict['last_loc_min'] = feature_calculators.last_location_of_minimum(x)
# feature_dict['last_loc_max'] = feature_calculators.last_location_of_maximum(x)
# for lag in lags:
# feature_dict[f'time_rev_asym_stat_{lag}'] = feature_calculators.time_reversal_asymmetry_statistic(x, lag)
for autocorr_lag in autocorr_lags:
feature_dict[
f'autocorrelation_{autocorr_lag}'] = feature_calculators.autocorrelation(
x, autocorr_lag)
feature_dict[f'c3_{autocorr_lag}'] = feature_calculators.c3(
x, autocorr_lag)
# for coeff, attr in product([1, 2, 3, 4, 5], ['real', 'imag', 'angle']):
# feature_dict[f'fft_{coeff}_{attr}'] = list(feature_calculators.fft_coefficient(x, [{'coeff': coeff, 'attr': attr}]))[0][1]
# feature_dict['long_strk_above_mean'] = feature_calculators.longest_strike_above_mean(x)
# feature_dict['long_strk_below_mean'] = feature_calculators.longest_strike_below_mean(x)
# feature_dict['cid_ce_0'] = feature_calculators.cid_ce(x, 0)
# feature_dict['cid_ce_1'] = feature_calculators.cid_ce(x, 1)
for p in percentiles:
feature_dict[
f'binned_entropy_{p}'] = feature_calculators.binned_entropy(
x, p)
feature_dict['num_crossing_0'] = feature_calculators.number_crossing_m(
x, 0)
for peak in peaks:
feature_dict[
f'num_peaks_{peak}'] = feature_calculators.number_peaks(
x, peak)
for c in coefs:
feature_dict[f'spkt_welch_density_{c}'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': c
}]))[0][1]
feature_dict[
f'time_rev_asym_stat_{c}'] = feature_calculators.time_reversal_asymmetry_statistic(
x, c)
# statistics on rolling windows of various sizes
for w in windows:
x_roll_std = x.rolling(w).std().dropna().values
x_roll_mean = x.rolling(w).mean().dropna().values
feature_dict[f'ave_roll_std_{w}'] = x_roll_std.mean()
feature_dict[f'std_roll_std_{w}'] = x_roll_std.std()
feature_dict[f'max_roll_std_{w}'] = x_roll_std.max()
feature_dict[f'min_roll_std_{w}'] = x_roll_std.min()
for p in percentiles:
feature_dict[
f'percentile_roll_std_{p}_window_{w}'] = np.percentile(
x_roll_std, p)
feature_dict[f'av_change_abs_roll_std_{w}'] = np.mean(
np.diff(x_roll_std))
feature_dict[f'av_change_rate_roll_std_{w}'] = np.mean(
np.nonzero((np.diff(x_roll_std) / x_roll_std[:-1]))[0])
feature_dict[f'abs_max_roll_std_{w}'] = np.abs(x_roll_std).max()
feature_dict[f'ave_roll_mean_{w}'] = x_roll_mean.mean()
feature_dict[f'std_roll_mean_{w}'] = x_roll_mean.std()
feature_dict[f'max_roll_mean_{w}'] = x_roll_mean.max()
feature_dict[f'min_roll_mean_{w}'] = x_roll_mean.min()
for p in percentiles:
feature_dict[
f'percentile_roll_mean_{p}_window_{w}'] = np.percentile(
x_roll_mean, p)
feature_dict[f'av_change_abs_roll_mean_{w}'] = np.mean(
np.diff(x_roll_mean))
feature_dict[f'av_change_rate_roll_mean_{w}'] = np.mean(
np.nonzero((np.diff(x_roll_mean) / x_roll_mean[:-1]))[0])
feature_dict[f'abs_max_roll_mean_{w}'] = np.abs(x_roll_mean).max()
return feature_dict
def create_features(seg_id, seg, X, st, end):
"""
create features including fft features, statistical features and time series features
:param seg_id: the ID for a sample
:param seg: s signal segment
:param X: train set features before creating these features
:param st: the start index of the signal segment
:param end: the end index of the signal segment
:return: train set features after creating these features
"""
try:
# test set won't create these features because its seg_id is string
X.loc[seg_id, 'seg_id'] = np.int32(seg_id)
X.loc[seg_id, 'seg_start'] = np.int32(st)
X.loc[seg_id, 'seg_end'] = np.int32(end)
except ValueError:
pass
xc = pd.Series(seg['acoustic_data'].values)
xcdm = xc - np.mean(xc)
b, a = des_bw_filter_lp(cutoff=18000)
xcz = sg.lfilter(b, a, xcdm)
zc = np.fft.fft(xcz)
zc = zc[:MAX_FREQ]
# FFT transform values
realFFT = np.real(zc)
imagFFT = np.imag(zc)
freq_bands = [x for x in range(0, MAX_FREQ, FREQ_BAND)]
magFFT = np.sqrt(realFFT ** 2 + imagFFT ** 2)
phzFFT = np.arctan(imagFFT / realFFT)
phzFFT[phzFFT == -np.inf] = -np.pi / 2.0
phzFFT[phzFFT == np.inf] = np.pi / 2.0
phzFFT = np.nan_to_num(phzFFT)
for freq in freq_bands:
X.loc[seg_id, 'FFT_Mag_01q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_BAND], 0.01)
X.loc[seg_id, 'FFT_Mag_10q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_BAND], 0.1)
X.loc[seg_id, 'FFT_Mag_90q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_BAND], 0.9)
X.loc[seg_id, 'FFT_Mag_99q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_BAND], 0.99)
X.loc[seg_id, 'FFT_Mag_mean%d' % freq] = np.mean(magFFT[freq: freq + FREQ_BAND])
X.loc[seg_id, 'FFT_Mag_std%d' % freq] = np.std(magFFT[freq: freq + FREQ_BAND])
X.loc[seg_id, 'FFT_Mag_max%d' % freq] = np.max(magFFT[freq: freq + FREQ_BAND])
X.loc[seg_id, 'FFT_Phz_mean%d' % freq] = np.mean(phzFFT[freq: freq + FREQ_BAND])
X.loc[seg_id, 'FFT_Phz_std%d' % freq] = np.std(phzFFT[freq: freq + FREQ_BAND])
X.loc[seg_id, 'FFT_Rmean'] = realFFT.mean()
X.loc[seg_id, 'FFT_Rstd'] = realFFT.std()
X.loc[seg_id, 'FFT_Rmax'] = realFFT.max()
X.loc[seg_id, 'FFT_Rmin'] = realFFT.min()
X.loc[seg_id, 'FFT_Imean'] = imagFFT.mean()
X.loc[seg_id, 'FFT_Istd'] = imagFFT.std()
X.loc[seg_id, 'FFT_Imax'] = imagFFT.max()
X.loc[seg_id, 'FFT_Imin'] = imagFFT.min()
X.loc[seg_id, 'FFT_Rmean_first_6000'] = realFFT[:6000].mean()
X.loc[seg_id, 'FFT_Rstd__first_6000'] = realFFT[:6000].std()
X.loc[seg_id, 'FFT_Rmax_first_6000'] = realFFT[:6000].max()
X.loc[seg_id, 'FFT_Rmin_first_6000'] = realFFT[:6000].min()
X.loc[seg_id, 'FFT_Rmean_first_18000'] = realFFT[:18000].mean()
X.loc[seg_id, 'FFT_Rstd_first_18000'] = realFFT[:18000].std()
X.loc[seg_id, 'FFT_Rmax_first_18000'] = realFFT[:18000].max()
X.loc[seg_id, 'FFT_Rmin_first_18000'] = realFFT[:18000].min()
del xcz
del zc
b, a = des_bw_filter_lp(cutoff=2500)
xc0 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=2500, high=5000)
xc1 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=5000, high=7500)
xc2 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=7500, high=10000)
xc3 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=10000, high=12500)
xc4 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=12500, high=15000)
xc5 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=15000, high=17500)
xc6 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_bp(low=17500, high=20000)
xc7 = sg.lfilter(b, a, xcdm)
b, a = des_bw_filter_hp(cutoff=20000)
xc8 = sg.lfilter(b, a, xcdm)
sigs = [xc, pd.Series(xc0), pd.Series(xc1), pd.Series(xc2), pd.Series(xc3),
pd.Series(xc4), pd.Series(xc5), pd.Series(xc6), pd.Series(xc7), pd.Series(xc8)]
for i, sig in enumerate(sigs):
X.loc[seg_id, 'mean_%d' % i] = sig.mean()
X.loc[seg_id, 'std_%d' % i] = sig.std()
X.loc[seg_id, 'max_%d' % i] = sig.max()
X.loc[seg_id, 'min_%d' % i] = sig.min()
X.loc[seg_id, 'mean_change_abs_%d' % i] = np.mean(np.diff(sig))
X.loc[seg_id, 'mean_change_rate_%d' % i] = calc_mean_change_rate(sig)
X.loc[seg_id, 'abs_max_%d' % i] = np.abs(sig).max()
X.loc[seg_id, 'std_first_50000_%d' % i] = sig[:50000].std()
X.loc[seg_id, 'std_last_50000_%d' % i] = sig[-50000:].std()
X.loc[seg_id, 'std_first_10000_%d' % i] = sig[:10000].std()
X.loc[seg_id, 'std_last_10000_%d' % i] = sig[-10000:].std()
X.loc[seg_id, 'avg_first_50000_%d' % i] = sig[:50000].mean()
X.loc[seg_id, 'avg_last_50000_%d' % i] = sig[-50000:].mean()
X.loc[seg_id, 'avg_first_10000_%d' % i] = sig[:10000].mean()
X.loc[seg_id, 'avg_last_10000_%d' % i] = sig[-10000:].mean()
X.loc[seg_id, 'min_first_50000_%d' % i] = sig[:50000].min()
X.loc[seg_id, 'min_last_50000_%d' % i] = sig[-50000:].min()
X.loc[seg_id, 'min_first_10000_%d' % i] = sig[:10000].min()
X.loc[seg_id, 'min_last_10000_%d' % i] = sig[-10000:].min()
X.loc[seg_id, 'max_first_50000_%d' % i] = sig[:50000].max()
X.loc[seg_id, 'max_last_50000_%d' % i] = sig[-50000:].max()
X.loc[seg_id, 'max_first_10000_%d' % i] = sig[:10000].max()
X.loc[seg_id, 'max_last_10000_%d' % i] = sig[-10000:].max()
X.loc[seg_id, 'max_to_min_%d' % i] = sig.max() / np.abs(sig.min())
X.loc[seg_id, 'max_to_min_diff_%d' % i] = sig.max() - np.abs(sig.min())
X.loc[seg_id, 'count_big_%d' % i] = len(sig[np.abs(sig) > 500])
X.loc[seg_id, 'mean_change_rate_first_50000_%d' % i] = calc_mean_change_rate(sig[:50000])
X.loc[seg_id, 'mean_change_rate_last_50000_%d' % i] = calc_mean_change_rate(sig[-50000:])
X.loc[seg_id, 'mean_change_rate_first_10000_%d' % i] = calc_mean_change_rate(sig[:10000])
X.loc[seg_id, 'mean_change_rate_last_10000_%d' % i] = calc_mean_change_rate(sig[-10000:])
X.loc[seg_id, 'q95_%d' % i] = np.quantile(sig, 0.95)
X.loc[seg_id, 'q99_%d' % i] = np.quantile(sig, 0.99)
X.loc[seg_id, 'q05_%d' % i] = np.quantile(sig, 0.05)
X.loc[seg_id, 'q01_%d' % i] = np.quantile(sig, 0.01)
X.loc[seg_id, 'abs_q95_%d' % i] = np.quantile(np.abs(sig), 0.95)
X.loc[seg_id, 'abs_q99_%d' % i] = np.quantile(np.abs(sig), 0.99)
X.loc[seg_id, 'abs_q05_%d' % i] = np.quantile(np.abs(sig), 0.05)
X.loc[seg_id, 'abs_q01_%d' % i] = np.quantile(np.abs(sig), 0.01)
X.loc[seg_id, 'trend_%d' % i] = add_trend_feature(sig)
X.loc[seg_id, 'abs_trend_%d' % i] = add_trend_feature(sig, abs_values=True)
X.loc[seg_id, 'abs_mean_%d' % i] = np.abs(sig).mean()
X.loc[seg_id, 'abs_std_%d' % i] = np.abs(sig).std()
X.loc[seg_id, 'mad_%d' % i] = sig.mad()
X.loc[seg_id, 'kurt_%d' % i] = sig.kurtosis()
X.loc[seg_id, 'skew_%d' % i] = sig.skew()
X.loc[seg_id, 'med_%d' % i] = sig.median()
X.loc[seg_id, 'Hilbert_mean_%d' % i] = np.abs(hilbert(sig)).mean()
X.loc[seg_id, 'Hann_window_mean'] = (convolve(xc, hann(150), mode='same') / sum(hann(150))).mean()
X.loc[seg_id, 'classic_sta_lta1_mean_%d' % i] = classic_sta_lta(sig, 500, 10000).mean()
X.loc[seg_id, 'classic_sta_lta2_mean_%d' % i] = classic_sta_lta(sig, 5000, 100000).mean()
X.loc[seg_id, 'classic_sta_lta3_mean_%d' % i] = classic_sta_lta(sig, 3333, 6666).mean()
X.loc[seg_id, 'classic_sta_lta4_mean_%d' % i] = classic_sta_lta(sig, 10000, 25000).mean()
X.loc[seg_id, 'Moving_average_700_mean_%d' % i] = sig.rolling(window=700).mean().mean(skipna=True)
X.loc[seg_id, 'Moving_average_1500_mean_%d' % i] = sig.rolling(window=1500).mean().mean(skipna=True)
X.loc[seg_id, 'Moving_average_3000_mean_%d' % i] = sig.rolling(window=3000).mean().mean(skipna=True)
X.loc[seg_id, 'Moving_average_6000_mean_%d' % i] = sig.rolling(window=6000).mean().mean(skipna=True)
ewma = pd.Series.ewm
X.loc[seg_id, 'exp_Moving_average_300_mean_%d' % i] = ewma(sig, span=300).mean().mean(skipna=True)
X.loc[seg_id, 'exp_Moving_average_3000_mean_%d' % i] = ewma(sig, span=3000).mean().mean(skipna=True)
X.loc[seg_id, 'exp_Moving_average_30000_mean_%d' % i] = ewma(sig, span=30000).mean().mean(skipna=True)
no_of_std = 3
X.loc[seg_id, 'MA_700MA_std_mean_%d' % i] = sig.rolling(window=700).std().mean()
X.loc[seg_id, 'MA_700MA_BB_high_mean_%d' % i] = (
X.loc[seg_id, 'Moving_average_700_mean_%d' % i] + no_of_std * X.loc[
seg_id, 'MA_700MA_std_mean_%d' % i]).mean()
X.loc[seg_id, 'MA_700MA_BB_low_mean_%d' % i] = (
X.loc[seg_id, 'Moving_average_700_mean_%d' % i] - no_of_std * X.loc[
seg_id, 'MA_700MA_std_mean_%d' % i]).mean()
X.loc[seg_id, 'MA_400MA_std_mean_%d' % i] = sig.rolling(window=400).std().mean()
X.loc[seg_id, 'MA_400MA_BB_high_mean_%d' % i] = (
X.loc[seg_id, 'Moving_average_700_mean_%d' % i] + no_of_std * X.loc[
seg_id, 'MA_400MA_std_mean_%d' % i]).mean()
X.loc[seg_id, 'MA_400MA_BB_low_mean_%d' % i] = (
X.loc[seg_id, 'Moving_average_700_mean_%d' % i] - no_of_std * X.loc[
seg_id, 'MA_400MA_std_mean_%d' % i]).mean()
X.loc[seg_id, 'MA_1000MA_std_mean_%d' % i] = sig.rolling(window=1000).std().mean()
X.loc[seg_id, 'iqr_%d' % i] = np.subtract(*np.percentile(sig, [75, 25]))
X.loc[seg_id, 'q999_%d' % i] = np.quantile(sig, 0.999)
X.loc[seg_id, 'q001_%d' % i] = np.quantile(sig, 0.001)
X.loc[seg_id, 'ave10_%d' % i] = stats.trim_mean(sig, 0.1)
X.loc[seg_id, 'num_peaks_10_%d' % i] = feature_calculators.number_peaks(sig, 10)
X.loc[seg_id, 'cid_ce_1_%d' % i] = feature_calculators.cid_ce(sig, 1) # time series complexity
X.loc[seg_id, 'count_1000_0_%d' % i] = feature_calculators.range_count(sig, -1000, 0)
X.loc[seg_id, 'binned_entropy_5_%d' % i] = feature_calculators.binned_entropy(sig, 5)
X.loc[seg_id, 'binned_entropy_15_%d' % i] = feature_calculators.binned_entropy(sig, 15)
# sliding window is a kind of filter, so this code is out of the cycle of band pass
for windows in [10, 100, 1000]:
x_roll_std = xc.rolling(windows).std().dropna()
x_roll_mean = xc.rolling(windows).mean().dropna()
X.loc[seg_id, 'ave_roll_std_' + str(windows)] = x_roll_std.mean()
X.loc[seg_id, 'std_roll_std_' + str(windows)] = x_roll_std.std()
X.loc[seg_id, 'max_roll_std_' + str(windows)] = x_roll_std.max()
X.loc[seg_id, 'min_roll_std_' + str(windows)] = x_roll_std.min()
X.loc[seg_id, 'q01_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.01)
X.loc[seg_id, 'q05_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.05)
X.loc[seg_id, 'q95_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.95)
X.loc[seg_id, 'q99_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.99)
X.loc[seg_id, 'av_change_abs_roll_std_' + str(windows)] = np.mean(np.diff(x_roll_std))
X.loc[seg_id, 'av_change_rate_roll_std_' + str(windows)] = calc_mean_change_rate(x_roll_std)
X.loc[seg_id, 'abs_max_roll_std_' + str(windows)] = np.abs(x_roll_std).max()
X.loc[seg_id, 'ave_roll_mean_' + str(windows)] = x_roll_mean.mean()
X.loc[seg_id, 'std_roll_mean_' + str(windows)] = x_roll_mean.std()
X.loc[seg_id, 'max_roll_mean_' + str(windows)] = x_roll_mean.max()
X.loc[seg_id, 'min_roll_mean_' + str(windows)] = x_roll_mean.min()
X.loc[seg_id, 'q01_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.01)
X.loc[seg_id, 'q05_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.05)
X.loc[seg_id, 'q95_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.95)
X.loc[seg_id, 'q99_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.99)
X.loc[seg_id, 'av_change_abs_roll_mean_' + str(windows)] = np.mean(np.diff(x_roll_mean))
X.loc[seg_id, 'av_change_rate_roll_mean_' + str(windows)] = calc_mean_change_rate(x_roll_mean)
X.loc[seg_id, 'abs_max_roll_mean_' + str(windows)] = np.abs(x_roll_mean).max()
return X
def function(x):
return binned_entropy(x, max_bins=self.max_bins)
def binned_entropy(seg, k):
res = [
feature_calculators.binned_entropy(seg[i], k)
for i in range(config.seg_size[0])
]
return np.asarray(res)
)
for i in range(series_dat_all.shape[-1]):
avg = series_dat_all[:, :, i].mean()
std = series_dat_all[:, :, i].std()
series_dat_all[:, :, i] = (series_dat_all[:, :, i] - avg) / std
print('progress: {:02d} / {:02d}; '.format(i+1, series_dat_all.shape[-1]), end='\r')
series_dat_all = np.concatenate([series_dat_all[4*unit:5*unit], series_dat_all[9*unit:10*unit]], 0)
series_lbl_all = np.concatenate([series_lbl_all[4*unit:5*unit], series_lbl_all[9*unit:10*unit]], 0)series_dat_all.shape
bin_ent = [feature_calculators.binned_entropy(lst, max_bins=20) for lst in series_dat_all[:, :, 0].tolist()]
bin_ent = pd.qcut(pd.Series(bin_ent), q=10, duplicates='drop')
skf_trgt = [str(a) + '_' + str(b) for a, b in zip(series_bch_all, bin_ent)]
us = np.unique(skf_trgt)
umap = {u: i for u, i in zip(us, range(len(us)))}
skf_trgt = [umap[u] for u in skf_trgt]
us, cs = np.unique(skf_trgt, return_counts=True)
for u, c in zip(us, cs):
print(u, c)
class Waveset(Dataset):
def __init__(self, data, labels=None):
self.data = data
'trn_srs_lbl_all_s{}_w{}_feat_target_encoded.bp'.format(step, wndw)))
print(series_lbl_all.shape)
series_bch_all = np.concatenate([
np.ones(shape=(series_lbl_all.shape[0] // 10, )) * i
for i in [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
],
axis=0).astype(int)
print(np.unique(series_bch_all, return_counts=True))
avg = series_dat_all[:, :, 0].mean()
std = series_dat_all[:, :, 0].std()
series_dat_all[:, :, 0] = (series_dat_all[:, :, 0] - avg) / std
bin_ent = [
feature_calculators.binned_entropy(lst, max_bins=20)
for lst in series_dat_all[:, :, 0].tolist()
]
bin_ent = pd.qcut(pd.Series(bin_ent), q=10, duplicates='drop')
skf_trgt = [str(a) + '_' + str(b) for a, b in zip(series_bch_all, bin_ent)]
us = np.unique(skf_trgt)
umap = {u: i for u, i in zip(us, range(len(us)))}
skf_trgt = [umap[u] for u in skf_trgt]
class Waveset(Dataset):
def __init__(self, data, labels=None):
self.data = data
self.labels = labels
def generate_time_series_feats(x_dataset, dataset_name="raw", test=False):
make_dir_if_not_exists(os.path.join(FEATURES_PATH, 'tsfeats'))
time_length = x_dataset.shape[1]
features_function_dict = {
"mean":
mean,
"median":
median,
"length":
length,
"minimum":
minimum,
"maximum":
maximum,
"variance":
variance,
"skewness":
skewness,
"kurtosis":
kurtosis,
"sum_values":
sum_values,
"abs_energy":
abs_energy,
"mean_change":
mean_change,
"mean_abs_change":
mean_abs_change,
"count_below_mean":
count_below_mean,
"count_above_mean":
count_above_mean,
"has_duplicate_min":
has_duplicate_min,
"has_duplicate_max":
has_duplicate_max,
"standard_deviation":
standard_deviation,
"absolute_sum_of_changes":
absolute_sum_of_changes,
"last_location_of_minimum":
last_location_of_minimum,
"last_location_of_maximum":
last_location_of_maximum,
"first_location_of_maximum":
first_location_of_maximum,
"longest_strike_below_mean":
longest_strike_below_mean,
"longest_strike_above_mean":
longest_strike_above_mean,
"sum_of_reoccurring_values":
sum_of_reoccurring_values,
"first_location_of_minimum":
first_location_of_minimum,
"sum_of_reoccurring_data_points":
sum_of_reoccurring_data_points,
"variance_larger_than_standard_deviation":
variance_larger_than_standard_deviation,
"ratio_value_number_to_time_series_length":
ratio_value_number_to_time_series_length,
"percentage_of_reoccurring_values_to_all_values":
percentage_of_reoccurring_values_to_all_values,
"binned_entropy_max300":
lambda x: binned_entropy(x, 300),
"binned_entropy_max400":
lambda x: binned_entropy(x, 400),
"cid_ce_true":
lambda x: cid_ce(x, True),
"cid_ce_false":
lambda x: cid_ce(x, False),
"percentage_of_reoccurring_datapoints_to_all_datapoints":
percentage_of_reoccurring_datapoints_to_all_datapoints
}
for feature_name, function_call in features_function_dict.iteritems():
print "{:.<70s}".format("- Processing feature: %s" % feature_name),
feature_name = 'tsfeats/%s_%s' % (dataset_name, feature_name)
if not features_exists(feature_name, test):
feats = x_dataset.apply(function_call, axis=1, raw=True).values
save_features(feats, feature_name, test)
print("Done")
else:
print("Already generated")
ar_param_k100 = [{"coeff": i, "k": 100} for i in range(100 + 1)]
ar_param_k500 = [{"coeff": i, "k": 500} for i in range(500 + 1)]
agg50_mean_linear_trend = [{
"attr": val,
"chunk_len": 50,
"f_agg": "mean"
} for val in ("pvalue", "rvalue", "intercept", "slope", "stderr")]
aug_dickey_fuler_params = [{
"attr": "teststat"
}, {
"attr": "pvalue"
}, {
"attr": "usedlag"
}]
energy_ratio_num10_focus5 = [{"num_segments": 10, "segment_focus": 5}]
fft_aggr_spectrum = [{
"aggtype": "centroid"
}, {
"aggtype": "variance"
}, {
"aggtype": "skew"
}, {
"aggtype": "kurtosis"
}]
fft_coefficient_real = [{
"coeff": i,
"attr": "real"
} for i in range((time_length + 1) // 2)]
fft_coefficient_imag = [{
"coeff": i,
"attr": "imag"
} for i in range((time_length + 1) // 2)]
fft_coefficient_abs = [{
"coeff": i,
"attr": "abs"
} for i in range((time_length + 1) // 2)]
fft_coefficient_angle = [{
"coeff": i,
"attr": "angle"
} for i in range((time_length + 1) // 2)]
linear_trend_params = [{
"attr": val
} for val in ("pvalue", "rvalue", "intercept", "slope", "stderr")]
other_feats_dict = {
"ar_coeff100":
lambda x: dict(ar_coefficient(x, ar_param_k100)),
"ar_coeff500":
lambda x: dict(ar_coefficient(x, ar_param_k500)),
"agg50_mean_lin_trend":
lambda x: dict(agg_linear_trend(x, agg50_mean_linear_trend)),
"aug_dickey_fuler":
lambda x: dict(augmented_dickey_fuller(x, aug_dickey_fuler_params)),
"energy_ratio_num10_focus5":
lambda x: dict(energy_ratio_by_chunks(x, energy_ratio_num10_focus5)),
"fft_aggr_spectrum":
lambda x: dict(fft_aggregated(x, fft_aggr_spectrum)),
"fft_coeff_real":
lambda x: dict(fft_coefficient(x, fft_coefficient_real)),
"fft_coeff_imag":
lambda x: dict(fft_coefficient(x, fft_coefficient_imag)),
"fft_coeff_abs":
lambda x: dict(fft_coefficient(x, fft_coefficient_abs)),
"fft_coeff_angle":
lambda x: dict(fft_coefficient(x, fft_coefficient_angle)),
"linear_trend":
lambda x: dict(linear_trend(x, linear_trend_params)),
}
for feature_name, function_call in other_feats_dict.iteritems():
print "{:.<70s}".format("- Processing features: %s" % feature_name),
feature_name = 'tsfeats/%s_%s' % (dataset_name, feature_name)
if not features_exists(feature_name, test):
feats_dict = x_dataset.apply(function_call, axis=1,
raw=True).values.tolist()
feats = pd.DataFrame.from_dict(feats_dict)
save_features(feats.values, feature_name, test)
print("Done")
else:
print("Already generated")
# Auto-correlations as features
print("- Processing Auto-correlation features...")
corr_dataset = x_dataset.apply(autocorrelation_all, axis=1, raw=True)
save_features(corr_dataset.values,
'%s_auto_correlation_all' % dataset_name, test)
print("- Processing ARIMA(5,5,1) Features...")
arima_features = parallelize_row(x_dataset.values,
generate_arima_feats,
n_jobs=2)
assert arima_features.shape[0] == x_dataset.shape[0] # Assert the axis
save_features(arima_features, '%s_arima_5_5_1' % dataset_name, test)
def features(self, x, y, seg_id):
feature_dict = dict()
feature_dict['target'] = y
feature_dict['seg_id'] = seg_id
# lists with parameters to iterate over them
percentiles = [
1, 5, 10, 20, 25, 30, 40, 50, 60, 70, 75, 80, 90, 95, 99
]
hann_windows = [50, 150, 1500, 15000]
spans = [300, 3000, 30000, 50000]
windows = [10, 50, 100, 500, 1000, 10000]
borders = list(range(-4000, 4001, 1000))
peaks = [10, 20, 50, 100]
coefs = [1, 5, 10, 50, 100]
autocorr_lags = [5, 10, 50, 100, 500, 1000, 5000, 10000]
# basic stats
feature_dict['mean'] = x.mean()
feature_dict['std'] = x.std()
feature_dict['max'] = x.max()
feature_dict['min'] = x.min()
# basic stats on absolute values
feature_dict['mean_change_abs'] = np.mean(np.diff(x))
feature_dict['abs_max'] = np.abs(x).max()
feature_dict['abs_mean'] = np.abs(x).mean()
feature_dict['abs_std'] = np.abs(x).std()
# geometric and harmonic means
feature_dict['hmean'] = stats.hmean(np.abs(x[np.nonzero(x)[0]]))
feature_dict['gmean'] = stats.gmean(np.abs(x[np.nonzero(x)[0]]))
# k-statistic and moments
for i in range(1, 5):
feature_dict[f'kstat_{i}'] = stats.kstat(x, i)
feature_dict[f'moment_{i}'] = stats.moment(x, i)
for i in [1, 2]:
feature_dict[f'kstatvar_{i}'] = stats.kstatvar(x, i)
# aggregations on various slices of data
for agg_type, slice_length, direction in product(
['std', 'min', 'max', 'mean'], [1000, 10000, 50000],
['first', 'last']):
if direction == 'first':
feature_dict[
f'{agg_type}_{direction}_{slice_length}'] = x[:
slice_length].agg(
agg_type)
elif direction == 'last':
feature_dict[f'{agg_type}_{direction}_{slice_length}'] = x[
-slice_length:].agg(agg_type)
feature_dict['max_to_min'] = x.max() / np.abs(x.min())
feature_dict['max_to_min_diff'] = x.max() - np.abs(x.min())
feature_dict['count_big'] = len(x[np.abs(x) > 500])
feature_dict['sum'] = x.sum()
feature_dict['mean_change_rate'] = self.calc_change_rate(x)
# calc_change_rate on slices of data
for slice_length, direction in product([1000, 10000, 50000],
['first', 'last']):
if direction == 'first':
feature_dict[
f'mean_change_rate_{direction}_{slice_length}'] = self.calc_change_rate(
x[:slice_length])
elif direction == 'last':
feature_dict[
f'mean_change_rate_{direction}_{slice_length}'] = self.calc_change_rate(
x[-slice_length:])
# percentiles on original and absolute values
for p in percentiles:
feature_dict[f'percentile_{p}'] = np.percentile(x, p)
feature_dict[f'abs_percentile_{p}'] = np.percentile(np.abs(x), p)
feature_dict['trend'] = self.add_trend_feature(x)
feature_dict['abs_trend'] = self.add_trend_feature(x, abs_values=True)
feature_dict['mad'] = x.mad()
feature_dict['kurt'] = x.kurtosis()
feature_dict['skew'] = x.skew()
feature_dict['med'] = x.median()
feature_dict['Hilbert_mean'] = np.abs(signal.hilbert(x)).mean()
for hw in hann_windows:
feature_dict[f'Hann_window_mean_{hw}'] = (
signal.convolve(x, signal.hann(hw), mode='same') /
sum(signal.hann(hw))).mean()
feature_dict['classic_sta_lta1_mean'] = self.classic_sta_lta(
x, 500, 10000).mean()
feature_dict['classic_sta_lta2_mean'] = self.classic_sta_lta(
x, 5000, 100000).mean()
feature_dict['classic_sta_lta3_mean'] = self.classic_sta_lta(
x, 3333, 6666).mean()
feature_dict['classic_sta_lta4_mean'] = self.classic_sta_lta(
x, 10000, 25000).mean()
feature_dict['classic_sta_lta5_mean'] = self.classic_sta_lta(
x, 50, 1000).mean()
feature_dict['classic_sta_lta6_mean'] = self.classic_sta_lta(
x, 100, 5000).mean()
feature_dict['classic_sta_lta7_mean'] = self.classic_sta_lta(
x, 333, 666).mean()
feature_dict['classic_sta_lta8_mean'] = self.classic_sta_lta(
x, 4000, 10000).mean()
# exponential rolling statistics
ewma = pd.Series.ewm
for s in spans:
feature_dict[f'exp_Moving_average_{s}_mean'] = (ewma(
x, span=s).mean(skipna=True)).mean(skipna=True)
feature_dict[f'exp_Moving_average_{s}_std'] = (ewma(
x, span=s).mean(skipna=True)).std(skipna=True)
feature_dict[f'exp_Moving_std_{s}_mean'] = (ewma(
x, span=s).std(skipna=True)).mean(skipna=True)
feature_dict[f'exp_Moving_std_{s}_std'] = (ewma(
x, span=s).std(skipna=True)).std(skipna=True)
feature_dict['iqr'] = np.subtract(*np.percentile(x, [75, 25]))
feature_dict['iqr1'] = np.subtract(*np.percentile(x, [95, 5]))
feature_dict['ave10'] = stats.trim_mean(x, 0.1)
for slice_length, threshold in product([50000, 100000, 150000],
[5, 10, 20, 50, 100]):
feature_dict[f'count_big_{slice_length}_threshold_{threshold}'] = (
np.abs(x[-slice_length:]) > threshold).sum()
feature_dict[
f'count_big_{slice_length}_less_threshold_{threshold}'] = (
np.abs(x[-slice_length:]) < threshold).sum()
feature_dict['range_minf_m4000'] = feature_calculators.range_count(
x, -np.inf, -4000)
feature_dict['range_p4000_pinf'] = feature_calculators.range_count(
x, 4000, np.inf)
for i, j in zip(borders, borders[1:]):
feature_dict[f'range_{i}_{j}'] = feature_calculators.range_count(
x, i, j)
for autocorr_lag in autocorr_lags:
feature_dict[
f'autocorrelation_{autocorr_lag}'] = feature_calculators.autocorrelation(
x, autocorr_lag)
feature_dict[f'c3_{autocorr_lag}'] = feature_calculators.c3(
x, autocorr_lag)
for p in percentiles:
feature_dict[
f'binned_entropy_{p}'] = feature_calculators.binned_entropy(
x, p)
feature_dict['num_crossing_0'] = feature_calculators.number_crossing_m(
x, 0)
for peak in peaks:
feature_dict[
f'num_peaks_{peak}'] = feature_calculators.number_peaks(
x, peak)
for c in coefs:
feature_dict[f'spkt_welch_density_{c}'] = \
list(feature_calculators.spkt_welch_density(x, [{'coeff': c}]))[0][1]
feature_dict[
f'time_rev_asym_stat_{c}'] = feature_calculators.time_reversal_asymmetry_statistic(
x, c)
for w in windows:
x_roll_std = x.rolling(w).std().dropna().values
x_roll_mean = x.rolling(w).mean().dropna().values
feature_dict[f'ave_roll_std_{w}'] = x_roll_std.mean()
feature_dict[f'std_roll_std_{w}'] = x_roll_std.std()
feature_dict[f'max_roll_std_{w}'] = x_roll_std.max()
feature_dict[f'min_roll_std_{w}'] = x_roll_std.min()
for p in percentiles:
feature_dict[
f'percentile_roll_std_{p}_window_{w}'] = np.percentile(
x_roll_std, p)
feature_dict[f'av_change_abs_roll_std_{w}'] = np.mean(
np.diff(x_roll_std))
feature_dict[f'av_change_rate_roll_std_{w}'] = np.mean(
np.nonzero((np.diff(x_roll_std) / x_roll_std[:-1]))[0])
feature_dict[f'abs_max_roll_std_{w}'] = np.abs(x_roll_std).max()
feature_dict[f'ave_roll_mean_{w}'] = x_roll_mean.mean()
feature_dict[f'std_roll_mean_{w}'] = x_roll_mean.std()
feature_dict[f'max_roll_mean_{w}'] = x_roll_mean.max()
feature_dict[f'min_roll_mean_{w}'] = x_roll_mean.min()
for p in percentiles:
feature_dict[
f'percentile_roll_mean_{p}_window_{w}'] = np.percentile(
x_roll_mean, p)
feature_dict[f'av_change_abs_roll_mean_{w}'] = np.mean(
np.diff(x_roll_mean))
feature_dict[f'av_change_rate_roll_mean_{w}'] = np.mean(
np.nonzero((np.diff(x_roll_mean) / x_roll_mean[:-1]))[0])
feature_dict[f'abs_max_roll_mean_{w}'] = np.abs(x_roll_mean).max()
# Mel-frequency cepstral coefficients (MFCCs)
x = x.values.astype('float32')
mfcc = librosa.feature.mfcc(y=x)
for i in range(len(mfcc)):
feature_dict[f'mfcc_{i}_avg'] = np.mean(np.abs(mfcc[i]))
# spectral features
feature_dict['spectral_centroid'] = np.mean(
np.abs(librosa.feature.spectral_centroid(y=x)[0]))
feature_dict['zero_crossing_rate'] = np.mean(
np.abs(librosa.feature.zero_crossing_rate(y=x)[0]))
feature_dict['spectral_flatness'] = np.mean(
np.abs(librosa.feature.spectral_flatness(y=x)[0]))
feature_dict['spectral_contrast'] = np.mean(
np.abs(
librosa.feature.spectral_contrast(
S=np.abs(librosa.stft(x)))[0]))
feature_dict['spectral_bandwidth'] = np.mean(
np.abs(librosa.feature.spectral_bandwidth(y=x)[0]))
return feature_dict
def create_features2(seg, ):
data_row = {}
xcz = des_filter(seg, high=CUTOFF)
zc = np.fft.fft(xcz)
zc = zc[:MAX_FREQ]
# FFT transform values
realFFT = np.real(zc)
imagFFT = np.imag(zc)
freq_bands = list(range(0, MAX_FREQ, FREQ_STEP))
magFFT = np.abs(zc)
phzFFT = np.angle(zc)
phzFFT[phzFFT == -np.inf] = -np.pi / 2.0
phzFFT[phzFFT == np.inf] = np.pi / 2.0
phzFFT = np.nan_to_num(phzFFT)
for freq in freq_bands:
data_row['FFT_Mag_01q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_STEP], 0.01)
data_row['FFT_Mag_10q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_STEP], 0.1)
data_row['FFT_Mag_90q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_STEP], 0.9)
data_row['FFT_Mag_99q%d' % freq] = np.quantile(magFFT[freq: freq + FREQ_STEP], 0.99)
data_row['FFT_Mag_mean%d' % freq] = np.mean(magFFT[freq: freq + FREQ_STEP])
data_row['FFT_Mag_std%d' % freq] = np.std(magFFT[freq: freq + FREQ_STEP])
data_row['FFT_Mag_max%d' % freq] = np.max(magFFT[freq: freq + FREQ_STEP])
data_row['FFT_Mag_min%d' % freq] = np.min(magFFT[freq: freq + FREQ_STEP])
data_row['FFT_Phz_mean%d' % freq] = np.mean(phzFFT[freq: freq + FREQ_STEP])
data_row['FFT_Phz_std%d' % freq] = np.std(phzFFT[freq: freq + FREQ_STEP])
data_row['FFT_Phz_max%d' % freq] = np.max(phzFFT[freq: freq + FREQ_STEP])
data_row['FFT_Phz_min%d' % freq] = np.min(phzFFT[freq: freq + FREQ_STEP])
data_row['FFT_Rmean'] = realFFT.mean()
data_row['FFT_Rstd'] = realFFT.std()
data_row['FFT_Rmax'] = realFFT.max()
data_row['FFT_Rmin'] = realFFT.min()
data_row['FFT_Imean'] = imagFFT.mean()
data_row['FFT_Istd'] = imagFFT.std()
data_row['FFT_Imax'] = imagFFT.max()
data_row['FFT_Imin'] = imagFFT.min()
data_row['FFT_Rmean_first_6000'] = realFFT[:6000].mean()
data_row['FFT_Rstd__first_6000'] = realFFT[:6000].std()
data_row['FFT_Rmax_first_6000'] = realFFT[:6000].max()
data_row['FFT_Rmin_first_6000'] = realFFT[:6000].min()
data_row['FFT_Rmean_first_18000'] = realFFT[:18000].mean()
data_row['FFT_Rstd_first_18000'] = realFFT[:18000].std()
data_row['FFT_Rmax_first_18000'] = realFFT[:18000].max()
data_row['FFT_Rmin_first_18000'] = realFFT[:18000].min()
del xcz
del zc
# gc.collect()
sigs = [seg]
for freq in range(0, MAX_FREQ + FREQ_STEP, FREQ_STEP):
if freq == 0:
xc_ = des_filter(seg, high=FREQ_STEP)
elif freq == MAX_FREQ:
xc_ = des_filter(seg, low=freq)
else:
xc_ = des_filter(seg, low=freq, high=freq + FREQ_STEP)
sigs.append(pd.Series(xc_))
for window in [50, 200, 1000]:
roll_mean = seg.rolling(window).mean().dropna()
roll_std = seg.rolling(window).std().dropna()
sigs.append(pd.Series(roll_mean))
sigs.append(pd.Series(roll_std))
for span in [30, 300, 3000]:
exp_mean = seg.ewm(span).mean().dropna()
exp_std = seg.ewm(span).std().dropna()
sigs.append(pd.Series(exp_mean))
sigs.append(pd.Series(exp_std))
for i, sig in enumerate(sigs):
data_row['mean_%d' % i] = sig.mean()
data_row['std_%d' % i] = sig.std()
data_row['max_%d' % i] = sig.max()
data_row['min_%d' % i] = sig.min()
data_row['mean_change_abs_%d' % i] = np.mean(np.diff(sig))
data_row['mean_change_rate_%d' % i] = np.mean(np.nonzero((np.diff(sig) / sig[:-1]))[0])
data_row['abs_max_%d' % i] = np.abs(sig).max()
data_row['abs_min_%d' % i] = np.abs(sig).min()
data_row['std_first_50000_%d' % i] = sig[:50000].std()
data_row['std_last_50000_%d' % i] = sig[-50000:].std()
data_row['std_first_10000_%d' % i] = sig[:10000].std()
data_row['std_last_10000_%d' % i] = sig[-10000:].std()
data_row['avg_first_50000_%d' % i] = sig[:50000].mean()
data_row['avg_last_50000_%d' % i] = sig[-50000:].mean()
data_row['avg_first_10000_%d' % i] = sig[:10000].mean()
data_row['avg_last_10000_%d' % i] = sig[-10000:].mean()
data_row['min_first_50000_%d' % i] = sig[:50000].min()
data_row['min_last_50000_%d' % i] = sig[-50000:].min()
data_row['min_first_10000_%d' % i] = sig[:10000].min()
data_row['min_last_10000_%d' % i] = sig[-10000:].min()
data_row['max_first_50000_%d' % i] = sig[:50000].max()
data_row['max_last_50000_%d' % i] = sig[-50000:].max()
data_row['max_first_10000_%d' % i] = sig[:10000].max()
data_row['max_last_10000_%d' % i] = sig[-10000:].max()
data_row['max_to_min_%d' % i] = sig.max() / np.abs(sig.min())
data_row['max_to_min_diff_%d' % i] = sig.max() - np.abs(sig.min())
data_row['count_big_%d' % i] = len(sig[np.abs(sig) > 500])
data_row['sum_%d' % i] = sig.sum()
data_row['mean_change_rate_first_50000_%d' % i] = np.mean(
np.nonzero((np.diff(sig[:50000]) / sig[:50000][:-1]))[0])
data_row['mean_change_rate_last_50000_%d' % i] = np.mean(
np.nonzero((np.diff(sig[-50000:]) / sig[-50000:][:-1]))[0])
data_row['mean_change_rate_first_10000_%d' % i] = np.mean(
np.nonzero((np.diff(sig[:10000]) / sig[:10000][:-1]))[0])
data_row['mean_change_rate_last_10000_%d' % i] = np.mean(
np.nonzero((np.diff(sig[-10000:]) / sig[-10000:][:-1]))[0])
for p in [1, 5, 10, 25, 50, 75, 90, 95, 99]:
data_row['percentile_p{}_{}'.format(p, i)] = np.percentile(sig, p)
data_row['abd_percentile_p{}_{}'.format(p, i)] = np.percentile(np.abs(sig), p)
data_row['trend_%d' % i] = add_trend_feature(sig)
data_row['abs_trend_%d' % i] = add_trend_feature(sig, abs_values=True)
data_row['abs_mean_%d' % i] = np.abs(sig).mean()
data_row['abs_std_%d' % i] = np.abs(sig).std()
data_row['mad_%d' % i] = sig.mad()
data_row['kurt_%d' % i] = sig.kurtosis()
data_row['skew_%d' % i] = sig.skew()
data_row['med_%d' % i] = sig.median()
# data_row['Hilbert_mean_%d' % i] = np.abs(hilbert(sig)).mean()
data_row['Hann_window50_%d' % i] = (convolve(sig, hann(50), mode='same') / sum(hann(50))).mean()
data_row['Hann_window500_%d' % i] = (convolve(sig, hann(500), mode='same') / sum(hann(500))).mean()
data_row['classic_sta_lta0_mean_%d' % i] = classic_sta_lta(sig, 50, 1000).mean()
data_row['classic_sta_lta1_mean_%d' % i] = classic_sta_lta(sig, 500, 10000).mean()
data_row['classic_sta_lta2_mean_%d' % i] = classic_sta_lta(sig, 5000, 100000).mean()
data_row['classic_sta_lta3_mean_%d' % i] = classic_sta_lta(sig, 3333, 6666).mean()
data_row['classic_sta_lta4_mean_%d' % i] = classic_sta_lta(sig, 10000, 25000).mean()
no_of_std = 2
for w in [10, 100, 500]:
signal_mean = sig.rolling(window=w).mean()
signal_std = sig.rolling(window=w).std()
data_row['high_bound_mean_win{}_{}'.format(w, i)] = (signal_mean + no_of_std * signal_std).mean()
data_row['low_bound_mean_win{}_{}'.format(w, i)] = (signal_mean - no_of_std * signal_std).mean()
data_row['range_inf_4000_%d' % i] = feature_calculators.range_count(sig, -np.inf, -4000)
data_row['range_4000_inf_%d' % i] = feature_calculators.range_count(sig, 4000, np.inf)
for l, h in [[-4000, -2000], [-2000, 0], [0, 2000], [2000, 4000]]:
data_row['range_{}_{}_{}'.format(np.abs(l), np.abs(h), i)] = feature_calculators.range_count(sig, l, h)
data_row['iqr0_%d' % i] = np.subtract(*np.percentile(sig, [75, 25]))
data_row['iqr1_%d' % i] = np.subtract(*np.percentile(sig, [95, 5]))
data_row['ave10_%d' % i] = stats.trim_mean(sig, 0.1)
data_row['num_cross_0_%d' % i] = feature_calculators.number_crossing_m(sig, 0)
data_row['ratio_value_number_%d' % i] = feature_calculators.ratio_value_number_to_time_series_length(sig)
# data_row['var_larger_than_std_dev_%d' % i] = feature_calculators.variance_larger_than_standard_deviation(sig)
data_row['ratio_unique_values_%d' % i] = feature_calculators.ratio_value_number_to_time_series_length(sig)
data_row['abs_energy_%d' % i] = feature_calculators.abs_energy(sig)
data_row['abs_sum_of_changes_%d' % i] = feature_calculators.absolute_sum_of_changes(sig)
data_row['count_above_mean_%d' % i] = feature_calculators.count_above_mean(sig)
data_row['count_below_mean_%d' % i] = feature_calculators.count_below_mean(sig)
data_row['mean_abs_change_%d' % i] = feature_calculators.mean_abs_change(sig)
data_row['mean_change_%d' % i] = feature_calculators.mean_change(sig)
data_row['first_loc_min_%d' % i] = feature_calculators.first_location_of_minimum(sig)
data_row['first_loc_max_%d' % i] = feature_calculators.first_location_of_maximum(sig)
data_row['last_loc_min_%d' % i] = feature_calculators.last_location_of_minimum(sig)
data_row['last_loc_max_%d' % i] = feature_calculators.last_location_of_maximum(sig)
data_row['long_strk_above_mean_%d' % i] = feature_calculators.longest_strike_above_mean(sig)
data_row['long_strk_below_mean_%d' % i] = feature_calculators.longest_strike_below_mean(sig)
# data_row['cid_ce_0_%d' % i] = feature_calculators.cid_ce(sig, 0)
# data_row['cid_ce_1_%d' % i] = feature_calculators.cid_ce(sig, 1)
for j in [10, 50, ]:
data_row['peak_num_p{}_{}'.format(j, i)] = feature_calculators.number_peaks(sig, j)
for j in [1, 10, 50, 100]:
data_row['spkt_welch_density_coeff{}_{}'.format(j, i)] = \
list(feature_calculators.spkt_welch_density(sig, [{'coeff': j}]))[0][1]
for j in [5, 10, 100]:
data_row['c3_c{}_{}'.format(j, i)] = feature_calculators.c3(sig, j)
for j in [5, 10, 50, 100, 1000]:
data_row['autocorrelation_auto{}_{}'.format(j, i)] = feature_calculators.autocorrelation(sig, j)
for j in [10, 100, 1000]:
data_row['time_rev_asym_stat_t{}_{}'.format(j, i)] = feature_calculators.time_reversal_asymmetry_statistic(
sig, j)
for j in range(1, 5):
data_row['kstat_k{}_{}'.format(j, i)] = stats.kstat(sig, j)
data_row['moment_m{}_{}'.format(j, i)] = stats.moment(sig, j)
for j in range(1, 3):
data_row['kstatvar_k{}_{}'.format(j, i)] = stats.kstatvar(sig, j)
for j in [5, 10, 50, 100]:
data_row['binned_entropy_b{}_{}'.format(j, i)] = feature_calculators.binned_entropy(sig, j)
return data_row
def compute_standard_features_block(xc, seg_id, X, fs, prefix=''):
# Generic stats
X.loc[seg_id, prefix + 'mean'] = xc.mean()
X.loc[seg_id, prefix + 'std'] = xc.std()
X.loc[seg_id, prefix + 'max'] = xc.max()
X.loc[seg_id, prefix + 'min'] = xc.min()
X.loc[seg_id, prefix + 'hmean'] = stats.hmean(np.abs(xc[np.nonzero(xc)[0]]))
X.loc[seg_id, prefix + 'gmean'] = stats.gmean(np.abs(xc[np.nonzero(xc)[0]]))
X.loc[seg_id, prefix + 'mad'] = xc.mad()
X.loc[seg_id, prefix + 'kurt'] = xc.kurtosis()
X.loc[seg_id, prefix + 'skew'] = xc.skew()
X.loc[seg_id, prefix + 'med'] = xc.median()
for p in [1, 5, 10, 20, 25, 30, 40, 50, 60, 70, 75, 80, 90, 95, 99]:
X.loc[seg_id, prefix + f'percentile_{p}'] = np.percentile(xc, p)
X.loc[seg_id, prefix + f'abs_percentile_{p}'] = np.percentile(np.abs(xc), p)
X.loc[seg_id, prefix + 'num_crossing_0'] = feature_calculators.number_crossing_m(xc, 0)
for p in [95,99]:
X.loc[seg_id, prefix + f'binned_entropy_{p}'] = feature_calculators.binned_entropy(xc, p)
# Andrew stats
X.loc[seg_id, prefix + 'mean_diff'] = np.mean(np.diff(xc))
X.loc[seg_id, prefix + 'mean_abs_diff'] = np.mean(np.abs(np.diff(xc)))
X.loc[seg_id, prefix + 'mean_change_rate'] = change_rate(xc, method='original')
X.loc[seg_id, prefix + 'mean_change_rate_v2'] = change_rate(xc, method='modified')
X.loc[seg_id, prefix + 'abs_max'] = np.abs(xc).max()
X.loc[seg_id, prefix + 'abs_min'] = np.abs(xc).min()
X.loc[seg_id, prefix + 'mean_change_abs'] = np.mean(np.diff(xc))
# Classical stats by segment
for agg_type, slice_length, direction in product(['std', 'min', 'max', 'mean'], [1000, 10000, 50000], ['first', 'last']):
if direction == 'first':
X.loc[seg_id, prefix + f'{agg_type}_{direction}_{slice_length}'] = xc[:slice_length].agg(agg_type)
elif direction == 'last':
X.loc[seg_id, prefix + f'{agg_type}_{direction}_{slice_length}'] = xc[-slice_length:].agg(agg_type)
X.loc[seg_id, prefix + 'avg_first_50000'] = xc[:50000].mean()
X.loc[seg_id, prefix + 'avg_last_50000'] = xc[-50000:].mean()
X.loc[seg_id, prefix + 'avg_first_10000'] = xc[:10000].mean()
X.loc[seg_id, prefix + 'avg_last_10000'] = xc[-10000:].mean()
# k-statistic and moments
for i in range(1, 5):
X.loc[seg_id, prefix + f'kstat_{i}'] = stats.kstat(xc, i)
X.loc[seg_id, prefix + f'moment_{i}'] = stats.moment(xc, i)
for i in [1, 2]:
X.loc[seg_id, prefix + f'kstatvar_{i}'] = stats.kstatvar(xc, i)
X.loc[seg_id, prefix + 'range_minf_m4000'] = feature_calculators.range_count(xc, -np.inf, -4000)
X.loc[seg_id, prefix + 'range_p4000_pinf'] = feature_calculators.range_count(xc, 4000, np.inf)
for i, j in zip(borders, borders[1:]):
X.loc[seg_id, prefix + f'range_{i}_{j}'] = feature_calculators.range_count(xc, i, j)
X.loc[seg_id, prefix + 'ratio_unique_values'] = feature_calculators.ratio_value_number_to_time_series_length(xc)
X.loc[seg_id, prefix + 'max_to_min'] = xc.max() / np.abs(xc.min())
X.loc[seg_id, prefix + 'max_to_min_diff'] = xc.max() - np.abs(xc.min())
X.loc[seg_id, prefix + 'count_big'] = len(xc[np.abs(xc) > 500])
X.loc[seg_id, prefix + 'sum'] = xc.sum()
# calc_change_rate on slices of data
for slice_length, direction in product([1000, 10000, 50000], ['first', 'last']):
if direction == 'first':
X.loc[seg_id, prefix + f'mean_change_rate_{direction}_{slice_length}'] = change_rate(xc[:slice_length], method='original')
X.loc[seg_id, prefix + f'mean_change_rate_{direction}_{slice_length}_v2'] = change_rate(xc[:slice_length], method='modified')
elif direction == 'last':
X.loc[seg_id, prefix + f'mean_change_rate_{direction}_{slice_length}'] = change_rate(xc[-slice_length:], method='original')
X.loc[seg_id, prefix + f'mean_change_rate_{direction}_{slice_length}_v2'] = change_rate(xc[-slice_length:], method='modified')
X.loc[seg_id, prefix + 'q95'] = np.quantile(xc, 0.95)
X.loc[seg_id, prefix + 'q99'] = np.quantile(xc, 0.99)
X.loc[seg_id, prefix + 'q05'] = np.quantile(xc, 0.05)
X.loc[seg_id, prefix + 'q01'] = np.quantile(xc, 0.01)
X.loc[seg_id, prefix + 'abs_q95'] = np.quantile(np.abs(xc), 0.95)
X.loc[seg_id, prefix + 'abs_q99'] = np.quantile(np.abs(xc), 0.99)
X.loc[seg_id, prefix + 'abs_q05'] = np.quantile(np.abs(xc), 0.05)
X.loc[seg_id, prefix + 'abs_q01'] = np.quantile(np.abs(xc), 0.01)
X.loc[seg_id, prefix + 'trend'] = add_trend_feature(xc)
X.loc[seg_id, prefix + 'abs_trend'] = add_trend_feature(xc, abs_values=True)
X.loc[seg_id, prefix + 'abs_mean'] = np.abs(xc).mean()
X.loc[seg_id, prefix + 'abs_std'] = np.abs(xc).std()
X.loc[seg_id, prefix + 'Hilbert_mean'] = np.abs(hilbert(xc)).mean()
X.loc[seg_id, prefix + 'Hann_window_mean'] = (convolve(xc, hann(150), mode='same') / sum(hann(150))).mean()
for hw in [50, 150, 1500, 15000]:
X.loc[seg_id, prefix + f'Hann_window_mean_{hw}'] = (convolve(xc, hann(hw), mode='same') / sum(hann(hw))).mean()
sta_lta_method = 'original'
classic_sta_lta1 = sta_lta_ratio(xc, 500, 10000, method=sta_lta_method)
classic_sta_lta2 = sta_lta_ratio(xc, 5000, 100000, method=sta_lta_method)
classic_sta_lta3 = sta_lta_ratio(xc, 3333, 6666, method=sta_lta_method)
classic_sta_lta4 = sta_lta_ratio(xc, 10000, 25000, method=sta_lta_method)
classic_sta_lta5 = sta_lta_ratio(xc, 50, 1000, method=sta_lta_method)
classic_sta_lta6 = sta_lta_ratio(xc, 100, 5000, method=sta_lta_method)
classic_sta_lta7 = sta_lta_ratio(xc, 333, 666, method=sta_lta_method)
classic_sta_lta8 = sta_lta_ratio(xc, 4000, 10000, method=sta_lta_method)
X.loc[seg_id, prefix + 'classic_sta_lta1_mean'] = classic_sta_lta1.mean()
X.loc[seg_id, prefix + 'classic_sta_lta2_mean'] = classic_sta_lta2.mean()
X.loc[seg_id, prefix + 'classic_sta_lta3_mean'] = classic_sta_lta3.mean()
X.loc[seg_id, prefix + 'classic_sta_lta4_mean'] = classic_sta_lta4.mean()
X.loc[seg_id, prefix + 'classic_sta_lta5_mean'] = classic_sta_lta5.mean()
X.loc[seg_id, prefix + 'classic_sta_lta6_mean'] = classic_sta_lta6.mean()
X.loc[seg_id, prefix + 'classic_sta_lta7_mean'] = classic_sta_lta7.mean()
X.loc[seg_id, prefix + 'classic_sta_lta8_mean'] = classic_sta_lta8.mean()
X.loc[seg_id, prefix + 'classic_sta_lta1_q95'] = np.quantile(classic_sta_lta1, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta2_q95'] = np.quantile(classic_sta_lta2, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta3_q95'] = np.quantile(classic_sta_lta3, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta4_q95'] = np.quantile(classic_sta_lta4, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta5_q95'] = np.quantile(classic_sta_lta5, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta6_q95'] = np.quantile(classic_sta_lta6, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta7_q95'] = np.quantile(classic_sta_lta7, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta8_q95'] = np.quantile(classic_sta_lta8, 0.95)
X.loc[seg_id, prefix + 'classic_sta_lta1_q05'] = np.quantile(classic_sta_lta1, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta2_q05'] = np.quantile(classic_sta_lta2, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta3_q05'] = np.quantile(classic_sta_lta3, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta4_q05'] = np.quantile(classic_sta_lta4, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta5_q05'] = np.quantile(classic_sta_lta5, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta6_q05'] = np.quantile(classic_sta_lta6, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta7_q05'] = np.quantile(classic_sta_lta7, 0.05)
X.loc[seg_id, prefix + 'classic_sta_lta8_q05'] = np.quantile(classic_sta_lta8, 0.05)
sta_lta_method = 'modified'
classic_sta_lta1 = sta_lta_ratio(xc, 500, 10000, method=sta_lta_method)
classic_sta_lta2 = sta_lta_ratio(xc, 5000, 100000, method=sta_lta_method)
classic_sta_lta3 = sta_lta_ratio(xc, 3333, 6666, method=sta_lta_method)
classic_sta_lta4 = sta_lta_ratio(xc, 10000, 25000, method=sta_lta_method)
classic_sta_lta5 = sta_lta_ratio(xc, 50, 1000, method=sta_lta_method)
classic_sta_lta6 = sta_lta_ratio(xc, 100, 5000, method=sta_lta_method)
classic_sta_lta7 = sta_lta_ratio(xc, 333, 666, method=sta_lta_method)
classic_sta_lta8 = sta_lta_ratio(xc, 4000, 10000, method=sta_lta_method)
X.loc[seg_id, prefix + 'modified_sta_lta1_mean'] = classic_sta_lta1.mean()
X.loc[seg_id, prefix + 'modified_sta_lta2_mean'] = classic_sta_lta2.mean()
X.loc[seg_id, prefix + 'modified_sta_lta3_mean'] = classic_sta_lta3.mean()
X.loc[seg_id, prefix + 'modified_sta_lta4_mean'] = classic_sta_lta4.mean()
X.loc[seg_id, prefix + 'modified_sta_lta5_mean'] = classic_sta_lta5.mean()
X.loc[seg_id, prefix + 'modified_sta_lta6_mean'] = classic_sta_lta6.mean()
X.loc[seg_id, prefix + 'modified_sta_lta7_mean'] = classic_sta_lta7.mean()
X.loc[seg_id, prefix + 'modified_sta_lta8_mean'] = classic_sta_lta8.mean()
X.loc[seg_id, prefix + 'modified_sta_lta1_q95'] = np.quantile(classic_sta_lta1, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta2_q95'] = np.quantile(classic_sta_lta2, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta3_q95'] = np.quantile(classic_sta_lta3, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta4_q95'] = np.quantile(classic_sta_lta4, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta5_q95'] = np.quantile(classic_sta_lta5, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta6_q95'] = np.quantile(classic_sta_lta6, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta7_q95'] = np.quantile(classic_sta_lta7, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta8_q95'] = np.quantile(classic_sta_lta8, 0.95)
X.loc[seg_id, prefix + 'modified_sta_lta1_q05'] = np.quantile(classic_sta_lta1, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta2_q05'] = np.quantile(classic_sta_lta2, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta3_q05'] = np.quantile(classic_sta_lta3, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta4_q05'] = np.quantile(classic_sta_lta4, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta5_q05'] = np.quantile(classic_sta_lta5, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta6_q05'] = np.quantile(classic_sta_lta6, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta7_q05'] = np.quantile(classic_sta_lta7, 0.05)
X.loc[seg_id, prefix + 'modified_sta_lta8_q05'] = np.quantile(classic_sta_lta8, 0.05)
X.loc[seg_id, prefix + 'Moving_average_700_mean'] = xc.rolling(window=700).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'Moving_average_1500_mean'] = xc.rolling(window=1500).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'Moving_average_3000_mean'] = xc.rolling(window=3000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'Moving_average_6000_mean'] = xc.rolling(window=6000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'Moving_average_30000_mean'] = xc.rolling(window=30000).mean().mean(skipna=True)
ewma = pd.Series.ewm
X.loc[seg_id, prefix + 'exp_Moving_average_300_mean'] = ewma(xc, span=300).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_3000_mean'] = ewma(xc, span=3000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_6000_mean'] = ewma(xc, span=6000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_30000_mean'] = ewma(xc, span=30000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_50000_mean'] = ewma(xc, span=50000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_300_std'] = ewma(xc, span=300).mean().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_3000_std'] = ewma(xc, span=3000).mean().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_6000_std'] = ewma(xc, span=6000).mean().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_30000_std'] = ewma(xc, span=30000).mean().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_average_50000_std'] = ewma(xc, span=50000).mean().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_300_mean'] = ewma(xc, span=300).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_3000_mean'] = ewma(xc, span=3000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_6000_mean'] = ewma(xc, span=6000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_30000_mean'] = ewma(xc, span=30000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_50000_mean'] = ewma(xc, span=50000).mean().mean(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_300_std'] = ewma(xc, span=300).std().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_3000_std'] = ewma(xc, span=3000).std().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_6000_std'] = ewma(xc, span=6000).std().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_30000_std'] = ewma(xc, span=30000).std().std(skipna=True)
X.loc[seg_id, prefix + 'exp_Moving_std_50000_std'] = ewma(xc, span=50000).std().std(skipna=True)
no_of_std = 2
X.loc[seg_id, prefix + 'MA_700MA_std_mean'] = xc.rolling(window=700).std().mean()
X.loc[seg_id, prefix + 'MA_700MA_BB_high_mean'] = (X.loc[seg_id, prefix + 'Moving_average_700_mean'] + no_of_std * X.loc[seg_id, prefix + 'MA_700MA_std_mean']).mean()
X.loc[seg_id, prefix + 'MA_700MA_BB_low_mean'] = (X.loc[seg_id, prefix + 'Moving_average_700_mean'] - no_of_std * X.loc[seg_id, prefix + 'MA_700MA_std_mean']).mean()
X.loc[seg_id, prefix + 'MA_400MA_std_mean'] = xc.rolling(window=400).std().mean()
X.loc[seg_id, prefix + 'MA_400MA_BB_high_mean'] = (X.loc[seg_id, prefix + 'Moving_average_700_mean'] + no_of_std * X.loc[seg_id, prefix + 'MA_400MA_std_mean']).mean()
X.loc[seg_id, prefix + 'MA_400MA_BB_low_mean'] = (X.loc[seg_id, prefix + 'Moving_average_700_mean'] - no_of_std * X.loc[seg_id, prefix + 'MA_400MA_std_mean']).mean()
X.loc[seg_id, prefix + 'MA_1000MA_std_mean'] = xc.rolling(window=1000).std().mean()
X.loc[seg_id, prefix + 'iqr'] = np.subtract(*np.percentile(xc, [75, 25]))
X.loc[seg_id, prefix + 'iqr1'] = np.subtract(*np.percentile(xc, [95, 5]))
X.loc[seg_id, prefix + 'q999'] = np.quantile(xc, 0.999)
X.loc[seg_id, prefix + 'q001'] = np.quantile(xc, 0.001)
X.loc[seg_id, prefix + 'ave10'] = stats.trim_mean(xc, 0.1)
X.loc[seg_id, prefix + 'freq_cross_first_50000'] = freq_from_crossings(xc.values[:50000], fs)
X.loc[seg_id, prefix + 'freq_cross_last_50000'] = freq_from_crossings(xc.values[-50000:], fs)
X.loc[seg_id, prefix + 'freq_cross_first_10000'] = freq_from_crossings(xc.values[:10000], fs)
X.loc[seg_id, prefix + 'freq_cross_last_10000'] = freq_from_crossings(xc.values[-10000:], fs)
for peak in [10, 20, 50, 100]:
X.loc[seg_id, prefix + f'num_peaks_{peak}'] = feature_calculators.number_peaks(xc, peak)
for c in [1, 5, 10, 50, 100]:
X.loc[seg_id, prefix + f'spkt_welch_density_{c}'] = list(feature_calculators.spkt_welch_density(xc, [{'coeff': c}]))[0][1]
X.loc[seg_id, prefix + f'time_rev_asym_stat_{c}'] = feature_calculators.time_reversal_asymmetry_statistic(xc, c)
for autocorr_lag in [5, 10, 50, 100, 500, 1000, 5000, 10000]:
X.loc[seg_id, prefix + f'autocorrelation_{autocorr_lag}'] = feature_calculators.autocorrelation(xc, autocorr_lag)
X.loc[seg_id, prefix + f'c3_{autocorr_lag}'] = feature_calculators.c3(xc, autocorr_lag)
for windows in [10, 50, 100, 500, 1000, 10000]:
x_roll_std = xc.rolling(windows).std().dropna().values
x_roll_mean = xc.rolling(windows).mean().dropna().values
for p in [1, 5, 10, 20, 25, 30, 40, 50, 60, 70, 75, 80, 90, 95, 99]:
X.loc[seg_id, prefix + f'percentile_roll_std_{p}_window_{windows}'] = np.percentile(x_roll_std, p)
X.loc[seg_id, prefix + f'percentile_roll_mean_{p}_window_{windows}'] = np.percentile(x_roll_mean, p)
X.loc[seg_id, prefix + 'ave_roll_std_' + str(windows)] = x_roll_std.mean()
X.loc[seg_id, prefix + 'std_roll_std_' + str(windows)] = x_roll_std.std()
X.loc[seg_id, prefix + 'max_roll_std_' + str(windows)] = x_roll_std.max()
X.loc[seg_id, prefix + 'min_roll_std_' + str(windows)] = x_roll_std.min()
X.loc[seg_id, prefix + 'q01_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.01)
X.loc[seg_id, prefix + 'q05_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.05)
X.loc[seg_id, prefix + 'q95_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.95)
X.loc[seg_id, prefix + 'q99_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.99)
X.loc[seg_id, prefix + 'av_change_abs_roll_std_' + str(windows)] = np.mean(np.abs(np.diff(x_roll_std)))
X.loc[seg_id, prefix + 'av_change_rate_roll_std_' + str(windows)] = change_rate(pd.Series(x_roll_std), method='original')
X.loc[seg_id, prefix + 'av_change_rate_roll_std_' + str(windows) + 'v2'] = change_rate(pd.Series(x_roll_std), method='modified')
X.loc[seg_id, prefix + 'abs_max_roll_std_' + str(windows)] = np.abs(x_roll_std).max()
X.loc[seg_id, prefix + 'ave_roll_mean_' + str(windows)] = x_roll_mean.mean()
X.loc[seg_id, prefix + 'std_roll_mean_' + str(windows)] = x_roll_mean.std()
X.loc[seg_id, prefix + 'max_roll_mean_' + str(windows)] = x_roll_mean.max()
X.loc[seg_id, prefix + 'min_roll_mean_' + str(windows)] = x_roll_mean.min()
X.loc[seg_id, prefix + 'q01_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.01)
X.loc[seg_id, prefix + 'q05_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.05)
X.loc[seg_id, prefix + 'q95_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.95)
X.loc[seg_id, prefix + 'q99_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.99)
X.loc[seg_id, prefix + 'av_change_abs_roll_mean_' + str(windows)] = np.mean(np.abs(np.diff(x_roll_mean)))
X.loc[seg_id, prefix + 'av_change_rate_roll_mean_' + str(windows)] = change_rate(pd.Series(x_roll_mean), method='original')
X.loc[seg_id, prefix + 'av_change_rate_roll_mean_' + str(windows) + '_v2'] = change_rate(pd.Series(x_roll_mean), method='modified')
X.loc[seg_id, prefix + 'abs_max_roll_mean_' + str(windows)] = np.abs(x_roll_mean).max()
for p in [1, 5, 10, 20, 25, 30, 40, 50, 60, 70, 75, 80, 90, 95, 99]:
X.loc[seg_id, prefix + f'percentile_roll_std_{p}'] = X.loc[seg_id, prefix + f'percentile_roll_std_{p}_window_10000']
X.loc[seg_id, prefix + f'percentile_roll_mean_{p}'] = X.loc[seg_id, prefix + f'percentile_roll_mean_{p}_window_10000']
def transform_pack3(df):
""" augment X from tsfresh features"""
x = df.values
output = {}
output['kstat_1'] = stats.kstat(x, 1)
output['kstat_2'] = stats.kstat(x, 2)
output['kstat_3'] = stats.kstat(x, 3)
output['kstat_4'] = stats.kstat(x, 4)
output['abs_energy'] = feature_calculators.abs_energy(x)
output['abs_sum_of_changes'] = feature_calculators.absolute_sum_of_changes(
x)
output['count_above_mean'] = feature_calculators.count_above_mean(x)
output['count_below_mean'] = feature_calculators.count_below_mean(x)
output['range_minf_m4000'] = feature_calculators.range_count(
x, -np.inf, -4000)
output['range_m4000_m3000'] = feature_calculators.range_count(
x, -4000, -3000)
output['range_m3000_m2000'] = feature_calculators.range_count(
x, -3000, -2000)
output['range_m2000_m1000'] = feature_calculators.range_count(
x, -2000, -1000)
output['range_m1000_0'] = feature_calculators.range_count(x, -1000, 0)
output['range_0_p1000'] = feature_calculators.range_count(x, 0, 1000)
output['range_p1000_p2000'] = feature_calculators.range_count(
x, 1000, 2000)
output['range_p2000_p3000'] = feature_calculators.range_count(
x, 2000, 3000)
output['range_p3000_p4000'] = feature_calculators.range_count(
x, 3000, 4000)
output['range_p4000_pinf'] = feature_calculators.range_count(
x, 4000, np.inf)
output[
'ratio_unique_values'] = feature_calculators.ratio_value_number_to_time_series_length(
x)
output['first_loc_min'] = feature_calculators.first_location_of_minimum(x)
output['first_loc_max'] = feature_calculators.first_location_of_maximum(x)
output['last_loc_min'] = feature_calculators.last_location_of_minimum(x)
output['last_loc_max'] = feature_calculators.last_location_of_maximum(x)
output[
'time_rev_asym_stat_10'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 10)
output[
'time_rev_asym_stat_100'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 100)
output[
'time_rev_asym_stat_1000'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 1000)
output['autocorrelation_10'] = feature_calculators.autocorrelation(x, 10)
output['autocorrelation_100'] = feature_calculators.autocorrelation(x, 100)
output['autocorrelation_1000'] = feature_calculators.autocorrelation(
x, 1000)
output['autocorrelation_5000'] = feature_calculators.autocorrelation(
x, 5000)
output['c3_5'] = feature_calculators.c3(x, 5)
output['c3_10'] = feature_calculators.c3(x, 10)
output['c3_100'] = feature_calculators.c3(x, 100)
output[
'long_strk_above_mean'] = feature_calculators.longest_strike_above_mean(
x)
output[
'long_strk_below_mean'] = feature_calculators.longest_strike_below_mean(
x)
output['cid_ce_0'] = feature_calculators.cid_ce(x, 0)
output['cid_ce_1'] = feature_calculators.cid_ce(x, 1)
output['binned_entropy_10'] = feature_calculators.binned_entropy(x, 10)
output['binned_entropy_50'] = feature_calculators.binned_entropy(x, 50)
output['binned_entropy_80'] = feature_calculators.binned_entropy(x, 80)
output['binned_entropy_100'] = feature_calculators.binned_entropy(x, 100)
tmp = np.abs(x)
output['num_crossing_0'] = feature_calculators.number_crossing_m(tmp, 0)
output['num_crossing_10'] = feature_calculators.number_crossing_m(tmp, 10)
output['num_crossing_100'] = feature_calculators.number_crossing_m(
tmp, 100)
output['num_peaks_10'] = feature_calculators.number_peaks(tmp, 10)
output['num_peaks_50'] = feature_calculators.number_peaks(tmp, 50)
output['num_peaks_100'] = feature_calculators.number_peaks(tmp, 100)
output['num_peaks_500'] = feature_calculators.number_peaks(tmp, 500)
output['spkt_welch_density_1'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 1
}]))[0][1]
output['spkt_welch_density_10'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 10
}]))[0][1]
output['spkt_welch_density_50'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 50
}]))[0][1]
output['spkt_welch_density_100'] = list(
feature_calculators.spkt_welch_density(x, [{
'coeff': 100
}]))[0][1]
output[
'time_rev_asym_stat_1'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 1)
output[
'time_rev_asym_stat_10'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 10)
output[
'time_rev_asym_stat_100'] = feature_calculators.time_reversal_asymmetry_statistic(
x, 100)
return output
