fixed dataplep

rowers/dataroutines.py

@@ -569,6 +569,7 @@ def clean_df_stats(datadf, workstrokesonly=True, ignorehr=True,
             except KeyError:
                 pass
 
+
     if not ignoreadvanced:
         try:
             mask = datadf['rhythm'] < 0
@@ -1418,7 +1419,7 @@ def getrowdata_pl(id=0, doclean=False, convertnewtons=True,
                   checkefficiency=True, for_chart=False):
     data = read_df_sql(id,polars=True)
     try:
-        data = data.with_columns(pl.col(data['time'].diff()).alias("deltat")) # data['time'].diff()
+        data = data.with_columns((pl.col('time').diff()).alias("deltat")) # data['time'].diff()
     except KeyError:  # pragma: no cover
         data = pl.DataFrame()
 
@@ -1781,7 +1782,7 @@ def read_df_sql(id, polars=False):
     if polars:
         try:
             f = 'media/strokedata_{id}.parquet.gz'.format(id=id)
-            df = pd.read_parquet(f)
+            df = pl.read_parquet(f)
         except (IsADirectoryError, FileNotFoundError, OSError, ArrowInvalid, IndexError):  # pragma: no cover
             rowdata, row = getrowdata(id=id)
             try:
@@ -2018,11 +2019,15 @@ def dataplep(rowdatadf, id=0, inboard=0.88, forceunit='lbs', bands=True, barchar
     if 'driveenergy' not in df.columns:
         if forceunit == 'lbs':
             df = df.with_columns((pl.col(" DriveLength (meters)") * pl.col(" AverageDriveForce (lbs)") * lbstoN).alias("driveenergy"))
-            df = df.with_columns((pl.col(" AverageDriveForce (lbs)") * lbstoN).alias(" AverageDriveForce (lbs)"))
-            df = df.with_columns((pl.col(" PeakDriveForce (lbs)") * lbstoN).alias(" PeakDriveForce (lbs)"))
         else:
             df = df.with_columns((pl.col(" DriveLength (meters)") * pl.col(" AverageDriveForce (lbs)")).alias("driveenergy"))
 
+
+    if forceunit == 'lbs':
+        df = df.with_columns((pl.col(" AverageDriveForce (lbs)") * lbstoN).alias(" AverageDriveForce (lbs)"))
+        df = df.with_columns((pl.col(" PeakDriveForce (lbs)") * lbstoN).alias(" PeakDriveForce (lbs)"))
+
+            
     if df["driveenergy"].mean() == 0 and df["driveenergy"].std() == 0:
         df = df.with_columns((0.0*pl.col("driveenergy")+100).alias("driveenergy"))
 
@@ -2067,14 +2072,14 @@ def dataplep(rowdatadf, id=0, inboard=0.88, forceunit='lbs', bands=True, barchar
 
     if 'wash' not in df.columns:
         data = data.with_columns(
-            wash = pl.lit("0"),
+            wash = pl.lit(0.0),
-            catch = pl.lit("0"),
+            catch = pl.lit(0.0),
-            peakforceangle = pl.lit("0"),
+            peakforceangle = pl.lit(0.0),
-            finish = pl.lit("0"),
+            finish = pl.lit(0.0),
-            slip = pl.lit("0"),
+            slip = pl.lit(0.0),
-            totalangle = pl.lit("0"),
+            totalangle = pl.lit(0.0),
-            effectiveangle = pl.lit("0"),
+            effectiveangle = pl.lit(0.0),
-            efficiency = pl.lit("0"),
+            efficiency = pl.lit(0.0),
         )
     else:
         wash = df['wash']
@@ -2145,6 +2150,10 @@ def dataplep(rowdatadf, id=0, inboard=0.88, forceunit='lbs', bands=True, barchar
         data = data.with_columns(
             workoutid = pl.lit(id)
         )
+        # cast data
+        for k, v in dtypes.items():
+            if v == 'int':
+                data = data.cast({k: pl.Int64})
         filename = 'media/strokedata_{id}.parquet.gz'.format(id=id)
         try:
             data.write_parquet(filename, compression='gzip')