Finalize behavior of averaging wind properties in summary file

aosstower/level_b1/nc.py

@@ -207,7 +207,7 @@ def calculate_wind_gust(wind_speed_5s, wind_speed_2m):
 
     """
     # 1 minute rolling peaks
-    wind_peak_1m = wind_speed_5s.rolling(window=12, center=False).max()
+    wind_peak_1m = wind_speed_5s.rolling(window='1T', center=False).max()
     # criteria for a fast wind to be considered a wind gust
     gust_mask = (wind_speed_2m >= KNOTS_9) & \
                 (wind_peak_1m >= wind_speed_2m + KNOTS_5)
@@ -215,9 +215,9 @@ def calculate_wind_gust(wind_speed_5s, wind_speed_2m):
 
     # determine highest gust in the last 10 minutes
     # 5 seconds * 120 = 10 minutes
-    max_10m_gusts = gusts.rolling(window=120, center=False).max()
+    max_10m_gusts = gusts.rolling(window='10T', center=False).max()
     # Minimum 5-second average in the past 10 minutes
-    min_10m_5avg = wind_speed_5s.rolling(window=120, center=False).min()
+    min_10m_5avg = wind_speed_5s.rolling(window='10T', center=False).min()
     # criteria for a wind gust to be reportable
     reportable_mask = (max_10m_gusts >= wind_speed_2m + KNOTS_3) & \
                       (wind_speed_2m > KNOTS_2) & \
@@ -264,7 +264,7 @@ def summary_over_interval(frame, interval_width):
     # the value at time X is for the data X - interval_width minutes
     exclude = ['gust', 'wind_east', 'wind_north']
     include = [c for c in frame.columns if c not in exclude]
-    gb = frame[include].resample(interval_width, closed='right', loffset=interval_width)
+    gb = frame[include].resample(interval_width, closed='left')
 
     low = gb.min()
     low.rename(columns=lambda x: x + "_min", inplace=True)
@@ -276,8 +276,8 @@ def summary_over_interval(frame, interval_width):
     out_frames = pd.concat((low, high, mean), axis=1)
 
     # wind fields need to be handled specially
-    ws_min_idx = frame['wind_speed'].resample(interval_width, closed='right', loffset=interval_width).apply(lambda arr_like: arr_like.argmin())
-    ws_max_idx = frame['wind_speed'].resample(interval_width, closed='right', loffset=interval_width).apply(lambda arr_like: arr_like.argmax())
+    ws_min_idx = frame['wind_speed'].resample(interval_width, closed='left').apply(lambda arr_like: arr_like.argmin())
+    ws_max_idx = frame['wind_speed'].resample(interval_width, closed='left').apply(lambda arr_like: arr_like.argmax())
     # probably redundant but need to make sure the direction indexes are
     # the same as those used in the wind speed values
     # must use .values so we don't take data at out_frames index, but rather
@@ -286,11 +286,11 @@ def summary_over_interval(frame, interval_width):
     out_frames['wind_speed_max'] = frame['wind_speed'][ws_max_idx].values
     out_frames['wind_speed_min_dir'] = calc.wind_vector_degrees(frame['wind_east'][ws_min_idx], frame['wind_north'][ws_min_idx]).values
     out_frames['wind_speed_max_dir'] = calc.wind_vector_degrees(frame['wind_east'][ws_max_idx], frame['wind_north'][ws_max_idx]).values
-    we = frame['wind_east'].resample(interval_width, closed='right', loffset=interval_width).mean()
-    wn = frame['wind_north'].resample(interval_width, closed='right', loffset=interval_width).mean()
+    we = frame['wind_east'].resample(interval_width, closed='left').mean()
+    wn = frame['wind_north'].resample(interval_width, closed='left').mean()
     out_frames['wind_speed_mean_dir'] = calc.wind_vector_degrees(we, wn).values
 
-    gust_idx = frame['gust'].resample(interval_width, closed='right', loffset=interval_width).apply(lambda arr_like: arr_like.argmax())
+    gust_idx = frame['gust'].resample(interval_width, closed='left').apply(lambda arr_like: arr_like.argmax())
     # gusts may be NaN so this argmax will be NaN indexes which don't work great
     gust_idx = gust_idx.astype('datetime64[ns]', copy=False)
     peak_gust = frame['gust'][gust_idx]
@@ -397,13 +397,11 @@ def create_giant_netcdf(input_files, output_fn, zlib, chunk_size,
     frame['wind_east'], frame['wind_north'], _ = calc.wind_vector_components(frame['wind_speed'], frame['wind_dir'])
     # round up each 1 minute group so data at time T is the average of data
     # from T - 1 (exclusive) to T (inclusive).
-    # new_frame = frame.resample('1T', closed='right', loffset='1T').mean()
     new_frame = frame.resample('5S', closed='right', loffset='5S').mean()
 
     # 2 minute rolling average of 5 second data (5 seconds * 24 = 120 seconds = 2 minutes)
     winds_frame_5s = new_frame[['wind_speed', 'wind_east', 'wind_north']]
-    # winds_frame_5s = winds_frame_5s.resample('5S', closed='right', loffset='5S').mean()
-    winds_frame_2m = winds_frame_5s.rolling(24, win_type='boxcar').mean()
+    winds_frame_2m = winds_frame_5s.rolling('2T').mean()
     winds_frame_2m['gust'] = calculate_wind_gust(winds_frame_5s['wind_speed'], winds_frame_2m['wind_speed'])
 
     # rolling average is used for mean output
@@ -415,9 +413,6 @@ def create_giant_netcdf(input_files, output_fn, zlib, chunk_size,
         frame = summary_over_interval(new_frame, interval_width)
     else:
         frame = new_frame.resample(interval_width, closed='right', loffset=interval_width).mean()
-        # gust_idx = new_frame['gust'].resample(interval_width, closed='right', loffset=interval_width).apply(lambda arr_like: arr_like.argmax())
-        # frame['gust'][:] = new_frame['gust'][gust_idx.values]
-        # frame['wind_dir'] = calc.wind_vector_degrees(frame['wind_east'][gust_idx.values], frame['wind_north'][gust_idx.values])
         frame['wind_dir'] = calc.wind_vector_degrees(frame['wind_east'], frame['wind_north'])
         frame['gust'] = new_frame['gust'].resample(interval_width, closed='right', loffset=interval_width).max()
     frame.fillna(np.nan, inplace=True)