How to use the tsfresh.feature_extraction.extract_features function in tsfresh

To help you get started, we’ve selected a few tsfresh examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github earthgecko / skyline / utils / test_ionosphere_echo.py View on Github external
del converted
        else:
            print('file found %s, using for data' % minmax_fp_ts_csv)

        if not os.path.isfile(minmax_fp_ts_csv):
            print('error :: file not found %s' % minmax_fp_ts_csv)
        else:
            print('file exists to create the minmax_fp_ts data frame from - %s' % minmax_fp_ts_csv)

        try:
            df = pd.read_csv(minmax_fp_ts_csv, delimiter=',', header=None, names=['metric', 'timestamp', 'value'])
            df.columns = ['metric', 'timestamp', 'value']
        except:
            print('error :: failed to created data frame from %s' % (str(minmax_fp_ts_csv)))
        try:
            df_features = extract_features(
                df, column_id='metric', column_sort='timestamp', column_kind=None,
                column_value=None, feature_extraction_settings=tsf_settings)
        except:
            print('error :: failed to created df_features from %s' % (str(minmax_fp_ts_csv)))
        # Create transposed features csv
        if not os.path.isfile(minmax_fp_fname_out):
            # Transpose
            df_t = df_features.transpose()
            df_t.to_csv(minmax_fp_fname_out)

        try:
            # Calculate the count and sum of the features values
            df_sum = pd.read_csv(
                minmax_fp_fname_out, delimiter=',', header=0,
                names=['feature_name', 'value'])
            df_sum.columns = ['feature_name', 'value']
github earthgecko / skyline / utils / test_ionosphere_echo.py View on Github external
converted = []
            for datapoint in datapoints:
                try:
                    new_datapoint = [float(datapoint[0]), float(datapoint[1])]
                    converted.append(new_datapoint)
                except:  # nosec
                    continue
            for ts, value in converted:
                utc_ts_line = '%s,%s,%s\n' % (base_name, str(int(ts)), str(value))
                with open(anomalous_ts_csv, 'a') as fh:
                    fh.write(utc_ts_line)
            del converted

        df = pd.read_csv(anomalous_ts_csv, delimiter=',', header=None, names=['metric', 'timestamp', 'value'])
        df.columns = ['metric', 'timestamp', 'value']
        df_features_current = extract_features(
            df, column_id='metric', column_sort='timestamp', column_kind=None,
            column_value=None, feature_extraction_settings=tsf_settings)
        del df

        # Create transposed features csv
        if not os.path.isfile(anomalous_fp_fname_out):
            # Transpose
            df_t = df_features_current.transpose()
            df_t.to_csv(anomalous_fp_fname_out)
            del df_t
            del df_features_current
        # Calculate the count and sum of the features values
        df_sum_2 = pd.read_csv(
            anomalous_fp_fname_out, delimiter=',', header=0,
            names=['feature_name', 'value'])
        df_sum_2.columns = ['feature_name', 'value']
github earthgecko / skyline / utils / test_ionosphere_echo.py View on Github external
os.remove(ts_csv)

    for ts, value in converted:
        # print('%s,%s' % (str(int(ts)), str(value)))
        utc_ts_line = '%s,%s,%s\n' % (metric, str(int(ts)), str(value))
        with open(ts_csv, 'a') as fh:
            fh.write(utc_ts_line)
    del converted

    df = pd.read_csv(ts_csv, delimiter=',', header=None, names=['metric', 'timestamp', 'value'])
#    print('DataFrame created with %s' % ts_csv)
    df.columns = ['metric', 'timestamp', 'value']
    tsf_settings = ReasonableFeatureExtractionSettings()
    # Disable tqdm progress bar
    tsf_settings.disable_progressbar = True
    df_features = extract_features(
        df, column_id='metric', column_sort='timestamp', column_kind=None,
        column_value=None, feature_extraction_settings=tsf_settings)
    del df
#    print('features extracted from %s data' % ts_csv)
    # write to disk
    fname_out = fname_in + '.features.csv'
    # Transpose
    df_t = df_features.transpose()
#    print('features transposed')
    # Create transposed features csv
    t_fname_out = fname_in + '.features.transposed.csv'
    df_t.to_csv(t_fname_out)
    del df_t
    # Calculate the count and sum of the features values
    df_sum = pd.read_csv(
        t_fname_out, delimiter=',', header=0,
github mindsdb / lightwood / lightwood / encoders / time_series / ts_fresh_ts.py View on Github external
all_values = []


        for i, values in enumerate(column_data):
            if values is None:
                values = [0] * self.max_series_len
            elif type(values) == type([]):
                values = list(map(float,values))
            else:
                values = list(map(lambda x: float(x), values.split(' ')))

            all_values.append(values)
            df = pd.DataFrame({'main_feature': values, 'id': [1] * len(values)})

            try:
                features = extract_features(df, column_id='id',disable_progressbar=True, default_fc_parameters=default_fc_parameters,n_jobs=self.n_jobs)
            except:
                self.n_jobs = 1
                features = extract_features(df, column_id='id',disable_progressbar=True, default_fc_parameters=default_fc_parameters,n_jobs=self.n_jobs)

            features.fillna(value=0, inplace=True)

            features = list(features.iloc[0])
            ret.append(features)

        for i, values in  enumerate(all_values):
            while len(values) < self.max_series_len:
                values.append(0)

            encoded_values = self.numerical_encoder.encode(values)

            encoded_numbers_list = []
github earthgecko / skyline / skyline / ionosphere / common_functions.py View on Github external
datapoints = minmax_anomalous_ts
            converted = []
            for datapoint in datapoints:
                try:
                    new_datapoint = [float(datapoint[0]), float(datapoint[1])]
                    converted.append(new_datapoint)
                except:  # nosec
                    continue
            for ts, value in converted:
                utc_ts_line = '%s,%s,%s\n' % (base_name, str(int(ts)), str(value))
                with open(anomalous_ts_csv, 'a') as fh:
                    fh.write(utc_ts_line)

        df = pd.read_csv(anomalous_ts_csv, delimiter=',', header=None, names=['metric', 'timestamp', 'value'])
        df.columns = ['metric', 'timestamp', 'value']
        df_features_current = extract_features(
            df, column_id='metric', column_sort='timestamp', column_kind=None,
            column_value=None, feature_extraction_settings=tsf_settings)

        # Create transposed features csv
        if not os.path.isfile(anomalous_fp_fname_out):
            # Transpose
            df_t = df_features_current.transpose()
            df_t.to_csv(anomalous_fp_fname_out)
        # Calculate the count and sum of the features values
        df_sum_2 = pd.read_csv(
            anomalous_fp_fname_out, delimiter=',', header=0,
            names=['feature_name', 'value'])
        df_sum_2.columns = ['feature_name', 'value']
        df_sum_2['feature_name'] = df_sum_2['feature_name'].astype(str)
        df_sum_2['value'] = df_sum_2['value'].astype(float)
        minmax_anomalous_features_count = len(df_sum_2['value'])
github earthgecko / skyline / skyline / ionosphere / common_functions.py View on Github external
else:
            logger.info('file found %s, using for data' % minmax_fp_ts_csv)

        if not os.path.isfile(minmax_fp_ts_csv):
            logger.error('error :: file not found %s' % minmax_fp_ts_csv)
        else:
            logger.info('file exists to create the minmax_fp_ts data frame from - %s' % minmax_fp_ts_csv)

        try:
            df = pd.read_csv(minmax_fp_ts_csv, delimiter=',', header=None, names=['metric', 'timestamp', 'value'])
            df.columns = ['metric', 'timestamp', 'value']
        except:
            logger.error(traceback.format_exc())
            logger.error('error :: failed to created data frame from %s' % (str(minmax_fp_ts_csv)))
        try:
            df_features = extract_features(
                df, column_id='metric', column_sort='timestamp', column_kind=None,
                column_value=None, feature_extraction_settings=tsf_settings)
        except:
            logger.error(traceback.format_exc())
            logger.error('error :: failed to created df_features from %s' % (str(minmax_fp_ts_csv)))
        # Create transposed features csv
        if not os.path.isfile(minmax_fp_fname_out):
            # Transpose
            df_t = df_features.transpose()
            df_t.to_csv(minmax_fp_fname_out)
        else:
            if LOCAL_DEBUG:
                logger.debug('debug :: file exists - %s' % minmax_fp_fname_out)
        try:
            # Calculate the count and sum of the features values
            df_sum = pd.read_csv(
github earthgecko / skyline / skyline / features_profile.py View on Github external
df_features = False
    try:
        # @modified 20161226 - Bug #1822: tsfresh extract_features process stalling
        # Changed to use the new ReasonableFeatureExtractionSettings that was
        # introduced in tsfresh-0.4.0 to exclude the computationally high cost
        # of extracting features from very static timeseries that has little to
        # no variation is the values, which results in features taking up to
        # almost 600 seconds to calculate on a timeseries of length 10075
        # (168h - 1 datapoint per 60s)
        # In terms of inline feature calculatation, always exclude
        # high_comp_cost features.
        # df_features = extract_features(df, column_id='metric', column_sort='timestamp', column_kind=None, column_value=None)
        tsf_settings = ReasonableFeatureExtractionSettings()
        # Disable tqdm progress bar
        tsf_settings.disable_progressbar = True
        df_features = extract_features(
            df, column_id='metric', column_sort='timestamp', column_kind=None,
            column_value=None, feature_extraction_settings=tsf_settings)
        # @modified 20190413 - Bug #2934: Ionosphere - no mirage.redis.24h.json file
        # Added log_context to report the context
        current_logger.info('%s :: features extracted from %s data' % (
            log_context, ts_csv))
    except:
        trace = traceback.print_exc()
        current_logger.debug(trace)
        # @modified 20190413 - Bug #2934: Ionosphere - no mirage.redis.24h.json file
        # Added log_context to report the context
        fail_msg = 'error: %s :: extracting features with tsfresh from - %s' % (log_context, ts_csv)
        current_logger.error('%s' % fail_msg)
        end_feature_extraction = timer()
        # @modified 20190413 - Bug #2934: Ionosphere - no mirage.redis.24h.json file
        # Added log_context to report the context