getting part

rowers/interactiveplots.py

@@ -192,11 +192,11 @@ def tailwind(bearing, vwind, winddir):
 
 
 def interactive_hr_piechart(df, rower, title, totalseconds=0):
-    if df.empty:
+    if df.is_empty():
         return "", "Not enough data to make a chart"
 
-    df.sort_values(by='hr', inplace=True)
-    df['timehr'] = df['deltat']*df['hr']
+    df = df.sort("hr")
+    df = df.with_columns((pl.col("deltat")*pl.col("hr")).alias("deltat"))
 
     sumtimehr = df['deltat'].sum()
 
@@ -205,24 +205,23 @@ def interactive_hr_piechart(df, rower, title, totalseconds=0):
 
     hrzones = rower.hrzones
 
-    qry = 'hr < {ut2}'.format(ut2=rower.ut2)
-    qrydata = df.query(qry)
+    qrydata = df.filter(pl.col("hr") < rower.ut2)
     frac_lut2 = totalseconds*qrydata['deltat'].sum()/sumtimehr
 
-    qry = '{ut2} <= hr < {ut1}'.format(ut1=rower.ut1, ut2=rower.ut2)
-    frac_ut2 = totalseconds*df.query(qry)['deltat'].sum()/sumtimehr
+    qrydata = df.lazy().filter(pl.col("hr") >= rower.ut2).filter(pl.col("hr") < rower.ut1)
+    frac_ut2 = totalseconds*qrydata.collect()['deltat'].sum()/sumtimehr
 
-    qry = '{ut1} <= hr < {at}'.format(ut1=rower.ut1, at=rower.at)
-    frac_ut1 = totalseconds*df.query(qry)['deltat'].sum()/sumtimehr
+    qrydata = df.lazy().filter(pl.col("hr") >= rower.ut1).filter(pl.col("hr") < rower.at)
+    frac_ut1 = totalseconds*qrydata.collect()['deltat'].sum()/sumtimehr
 
-    qry = '{at} <= hr < {tr}'.format(at=rower.at, tr=rower.tr)
-    frac_at = totalseconds*df.query(qry)['deltat'].sum()/sumtimehr
+    qrydata = df.lazy().filter(pl.col("hr") >= rower.at).filter(pl.col("hr") < rower.tr)
+    frac_at = totalseconds*qrydata.collect()['deltat'].sum()/sumtimehr
 
-    qry = '{tr} <= hr < {an}'.format(tr=rower.tr, an=rower.an)
-    frac_tr = totalseconds*df.query(qry)['deltat'].sum()/sumtimehr
+    qrydata = df.lazy().filter(pl.col("hr") >= rower.tr).filter(pl.col("hr") < rower.an)
+    frac_tr = totalseconds*qrydata.collect()['deltat'].sum()/sumtimehr
 
-    qry = 'hr >= {an}'.format(an=rower.an)
-    frac_an = totalseconds*df.query(qry)['deltat'].sum()/sumtimehr
+    qrydata = df.filter(pl.col("hr") >= rower.an)
+    frac_an = totalseconds*qrydata['deltat'].sum()/sumtimehr
 
     datadict = {
         '<{ut2}'.format(ut2=hrzones[1]): frac_lut2,
@@ -1931,7 +1930,6 @@ def interactive_streamchart(id=0, promember=0):
     return [script, div]
 
 def forcecurve_multi_interactive_chart(selected): # pragma: no cover
-    df_plot = pd.DataFrame()
     ids = [analysis.id for analysis in selected]
     workoutids = [analysis.workout.id for analysis in selected]
 
@@ -1940,18 +1938,17 @@ def forcecurve_multi_interactive_chart(selected): # pragma: no cover
     columns = ['catch', 'slip', 'wash', 'finish', 'averageforce',
                'peakforceangle', 'peakforce', 'spm', 'distance',
                'workoutstate', 'workoutid', 'driveenergy', 'cumdist']
+    columns = columns + [name for name, d in metrics.rowingmetrics]
 
-    rowdata = dataprep.getsmallrowdata_db(columns, ids=workoutids,
+    rowdata = dataprep.getsmallrowdata_pl(columns, ids=workoutids,
                                               workstrokesonly=False)
 
+    rowdata = rowdata.fill_nan(None).drop_nulls()
 
-    rowdata.dropna(axis=1, how='all', inplace=True)
-    rowdata.dropna(axis=0, how='any', inplace=True)
-
-    if rowdata.empty:
+    if rowdata.is_empty():
         return "", "No Valid Data Available", "", ""
 
-    data_dict = rowdata.to_dict("records")
+    data_dict = rowdata.to_dicts()
 
     thresholdforces = []
     for analysis in selected:

rowers/views/analysisviews.py

@@ -2381,14 +2381,16 @@ def history_view_data(request, userid=0):
 
     ids = [w.id for w in g_workouts]
 
-    columns = ['hr', 'power', 'time']
-
-    df = getsmallrowdata_db(columns, ids=ids)
+    # columns = ['hr', 'power', 'time']
+    columns = [name for name, d in metrics.rowingmetrics]+['workoutstate', 'workoutid']
+    
+    df = getsmallrowdata_pl(columns, ids=ids)
     try:
-        df['deltat'] = df['time'].diff().clip(lower=0)
+         df = df.with_columns(pl.col('time').diff().clip(lower_bound=0).alias("deltat")) 
     except KeyError: # pragma: no cover
         pass
-    df = dataprep.clean_df_stats(df, workstrokesonly=True,
+
+    df = dataprep.clean_df_stats_pl(df, workstrokesonly=True,
                                  ignoreadvanced=True, ignorehr=False)
 
     totalmeters, totalhours, totalminutes, totalseconds = get_totals(
@@ -2418,13 +2420,13 @@ def history_view_data(request, userid=0):
             whours=whours,
             wminutes=wminutes, wseconds=wseconds,
         )
-        ddf = getsmallrowdata_db(columns, ids=[w.id for w in a_workouts])
+        ddf = getsmallrowdata_pl(columns, ids=[w.id for w in a_workouts])
         try:
-            ddf['deltat'] = ddf['time'].diff().clip(lower=0)
+            ddf = ddf.with_columns(pl.col("time").diff().clip(lower_bound=0).alias("deltat"))
         except KeyError:  # pragma: no cover
             pass
 
-        ddf = dataprep.clean_df_stats(ddf, workstrokesonly=False,
+        ddf = dataprep.clean_df_stats_pl(ddf, workstrokesonly=False,
                                       ignoreadvanced=True)
 
         try:
@@ -2432,13 +2434,13 @@ def history_view_data(request, userid=0):
         except (KeyError, ValueError, AttributeError):  # pragma: no cover
             ddict['hrmean'] = 0
         try:
-            ddict['hrmax'] = ddf['hr'].max().astype(int)
+            ddict['hrmax'] = int(ddf['hr'].max())
         except (KeyError, ValueError, AttributeError):  # pragma: no cover
             ddict['hrmax'] = 0
 
         ddict['powermean'] = int(wavg(ddf, 'power', 'deltat'))
         try:
-            ddict['powermax'] = ddf['power'].max().astype(int)
+            ddict['powermax'] = int(ddf['power'].max())
         except KeyError: # pragma: no cover
             ddict['powermax'] = 0
         ddict['nrworkouts'] = a_workouts.count()
@@ -2453,13 +2455,13 @@ def history_view_data(request, userid=0):
     totalsdict['distance'] = totalmeters
     try:
         totalsdict['powermean'] = int(wavg(df, 'power', 'deltat'))
-        totalsdict['powermax'] = df['power'].max().astype(int)
+        totalsdict['powermax'] = int(df['power'].max())
     except KeyError: # pragma: no cover
         totalsdict['powermean'] = 0
         totalsdict['powermax'] = 0
     try:
         totalsdict['hrmean'] = int(wavg(df, 'hr', 'deltat'))
-        totalsdict['hrmax'] = df['hr'].max().astype(int)
+        totalsdict['hrmax'] = int(df['hr'].max())
     except KeyError:  # pragma: no cover
         totalsdict['hrmean'] = 0
         totalsdict['hrmax'] = 0
@@ -2479,14 +2481,14 @@ def history_view_data(request, userid=0):
         a_workouts = g_workouts.filter(workouttype=typeselect)
         meters, hours, minutes, seconds = get_totals(a_workouts)
         totalseconds = 3600 * hours + 60 * minutes + seconds
-        ddf = getsmallrowdata_db(columns, ids=[w.id for w in a_workouts])
+        ddf = getsmallrowdata_pl(columns, ids=[w.id for w in a_workouts])
 
         try:
-            ddf['deltat'] = ddf['time'].diff().clip(lower=0)
+            ddf = ddf.with_columns(pl.col("time").diff().clip(lower_bound=0).alias("deltat"))
         except KeyError:
             pass
 
-        ddf = dataprep.clean_df_stats(ddf, workstrokesonly=True,
+        ddf = dataprep.clean_df_stats_pl(ddf, workstrokesonly=True,
                                       ignoreadvanced=True)
 
         totalscript, totaldiv = interactive_hr_piechart(

rowers/views/statements.py

@@ -16,7 +16,7 @@ from rowers.utils import (
 from rowers.celery import result as celery_result
 from rowers.interactiveplots import *
 from scipy.interpolate import griddata
-from rowers.dataprep import getsmallrowdata_db
+from rowers.dataprep import getsmallrowdata_db, getsmallrowdata_pl
 from rowers.dataprep import timedeltaconv
 from scipy.special import lambertw
 from io import BytesIO