From 988a9361d2cffbe19d5c8e96b94d2b4cf1f10537 Mon Sep 17 00:00:00 2001
From: Sander Roosendaal <roosendaalsander@gmail.com>
Date: Mon, 12 Jun 2017 20:51:09 +0200
Subject: [PATCH] Algo to reduce too high resolution data files

---
 rowers/dataprep.py | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/rowers/dataprep.py b/rowers/dataprep.py
index 08d3a202..87073d1a 100644
--- a/rowers/dataprep.py
+++ b/rowers/dataprep.py
@@ -204,6 +204,15 @@ def getcp(dfgrouped,logarr):
     cpvalue = pd.Series(cpvalue,name='CP')
     return delta,cpvalue,avgpower
 
+
+def df_resample(datadf):
+    # time stamps must be in seconds
+    timestamps = datadf['TimeStamp (sec)'].astype('int')
+    datadf['timestamps'] = timestamps
+    newdf = datadf.groupby(['timestamps']).mean()
+    return newdf
+    
+
 def clean_df_stats(datadf,workstrokesonly=True,ignorehr=True,
                    ignoreadvanced=False):
     # clean data remove zeros and negative values
@@ -479,6 +488,13 @@ def save_workout_database(f2,r,dosmooth=True,workouttype='rower',
                 powerperc=powerperc,powerzones=r.powerzones)
     row = rdata(f2,rower=rr)
 
+    dtavg = row.df['TimeStamp (sec)'].diff().mean()
+
+    if dtavg < 1:
+        newdf = df_resample(row.df)
+        return new_workout_from_df(r,newdf,
+                                   title=title)
+    
     checks = row.check_consistency()
     allchecks = 1
     for key,value in checks.iteritems():