workaround issue #228

aurora/pipelines/time_series_helpers.py

@@ -52,10 +52,14 @@ def apply_prewhitening(decimation_obj, run_xrts_input):
         prewhitened time series
 
     """
+    if not decimation_obj.prewhitening_type:
+        return run_xrts_input
+
     if decimation_obj.prewhitening_type == "first difference":
         run_xrts = run_xrts_input.differentiate("time")
+
     else:
-        print(f"{decimation_obj.prewhitening_type} prehitening not yet implemented")
+        print(f"{decimation_obj.prewhitening_type} pre-whitening not implemented")
         raise NotImplementedError
     return run_xrts
 
@@ -75,6 +79,9 @@ def apply_recoloring(decimation_obj, stft_obj):
     stft_obj : xarray.core.dataset.Dataset
         Recolored time series of Fourier coefficients
     """
+    if not decimation_obj.prewhitening_type:
+        return stft_obj
+
     if decimation_obj.prewhitening_type == "first difference":
         # replace below with decimation_obj.get_fft_harmonics() ?
         freqs = get_fft_harmonics(

aurora/time_series/xarray_helpers.py

@@ -54,7 +54,22 @@ def handle_nan(X, Y, RR, drop_dim=""):
     RR = RR.rename(data_var_add_label_mapper)
 
     merged_xr = X.merge(Y, join="exact")
-    merged_xr = merged_xr.merge(RR, join="exact")
+    # Workaround for issue #228
+    # merged_xr = merged_xr.merge(RR, join="exact")
+    try:
+        merged_xr = merged_xr.merge(RR, join="exact")
+    except ValueError:
+        print("Coordinate alignment mismatch -- see aurora issue #228 ")
+        matches = X.time.values == RR.time.values
+        print(f"{matches.sum()}/{len(matches)} timestamps match exactly")
+        deltas = X.time.values - RR.time.values
+        print(f"Maximum offset is {deltas.__abs__().max()}ns")
+        #        print(f"X.time.[0]: {X.time[0].values}")
+        #        print(f"RR.time.[0]: {RR.time[0].values}")
+        merged_xr = merged_xr.merge(RR, join="left")
+        for ch in list(RR.keys()):
+            merged_xr[ch].values = RR[ch].values
+
     merged_xr = merged_xr.dropna(dim=drop_dim)
     merged_xr = merged_xr.to_array(dim="channel")
     X = merged_xr.sel(channel=input_channels)

aurora/transfer_function/kernel_dataset.py

@@ -101,7 +101,14 @@ def __init__(self, **kwargs):
         self.df = kwargs.get("df")
         self.local_station_id = kwargs.get("local_station_id")
         self.remote_station_id = kwargs.get("remote_station_id")
-        self._mini_summary_columns = ["survey", "station_id", "run_id", "start", "end"]
+        self._mini_summary_columns = [
+            "survey",
+            "station_id",
+            "run_id",
+            "start",
+            "end",
+            "duration",
+        ]
 
     def clone(self):
         return copy.deepcopy(self)

aurora/transfer_function/regression/base.py

@@ -18,11 +18,11 @@ class RegressionEstimator(object):
 
     Many of the robust transfer estimation methods we will use repeat the
     model of solving Y = X*b +epsilon for b.  X is variously called the "input",
-    "predictor", "explanatory", "confounding", "independent" variable(s) or the
-    "design matrix", "model matrix" or "regressor matrix".
+    "predictor", "explanatory", "confounding", "independent" "exogenous", variable(s)
+    or the "design matrix", "model matrix" or "regressor matrix".
     Y are variously called the the "output", "predicted", "outcome",
-    "response",  or "dependent" variable.  I will try to use input and
-    output.
+    "response", "endogenous", "regressand", or "dependent" variable.  I will try to
+    use input and output.
 
     When we "regress Y on X", we use the values of variable X to predict
     those of Y.

tutorials/processing_configuration.ipynb

@@ -21,7 +21,7 @@
     "In this tutorial, we will use the synthetic dataset example to show some of the features of the config object.\n",
     "\n",
     "Hopefully, it will be fairly easy to add other parameters to the config, such as:\n",
-    "- coherncey sorting \n",
+    "- coherencey sorting \n",
     "- polarization sorting\n",
     "- ARMA prewhitening \n",
     "- Other tools from the community\n",
@@ -1148,6 +1148,7 @@
     "- Channel Nomenclature\n",
     "    - for example ex,ey maybe called e1, e2 in the mth5\n",
     "        - This is handled by passing a channel_nomenclature keyword argument.\n",
+    "        - Examples of systems that might need this are LEMI and Phoenix\n",
     "- Windowing Parameters\n",
     "    - Window shape (family)\n",
     "    - Window length\n",
@@ -1260,7 +1261,7 @@
     "These legacy files have the following significance;\n",
     "The first line, 25 indicates the number of bands, and there are 25 lines following, one line per frequency band.\n",
     "\n",
-    "Each line is three numbers:\n",
+    "Each line comprises three numbers:\n",
     "\n",
     "`decimation_level, first_FC_index, last_FC_index`\n",
     "\n",