Correct add_season to avoid duplicates

stella-bourdin · Mar 28, 2022 · 9d02eb4 · 9d02eb4
1 parent bd1e821
commit 9d02eb4
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/dynamicopy/tc/metrics.py b/dynamicopy/tc/metrics.py
@@ -159,7 +159,7 @@ def storm_stats(tracks):
     tracks.loc[tracks.ET.isna(), "ET"] = False
     storms = (
         tracks.groupby(["track_id"])[["hemisphere", "basin", "season", "month"]]
-        .agg(lambda x: x.value_counts().index[0])  #TODO : line responsible for the slow behavior
+        .agg(lambda x: x.value_counts().index[0])  #TODO : line responsible for the slow behavior / remplacer par pd.Series.mode : https://stackoverflow.com/questions/15222754/groupby-pandas-dataframe-and-select-most-common-value
         .reset_index()
     )
     storms = storms.merge(

diff --git a/dynamicopy/tc/utils.py b/dynamicopy/tc/utils.py
@@ -1,7 +1,7 @@
 import numpy as np
 from ._basins import *
 from shapely.geometry import Point
-
+import pandas as pd
 
 def add_season(tracks):
     """
@@ -23,7 +23,7 @@ def add_season(tracks):
         .mean()
         .astype(int)
         .join(
-            tracks[["track_id", "hemisphere"]].drop_duplicates().set_index("track_id"),
+            tracks.groupby("track_id")[["hemisphere"]].agg(pd.Series.mode),
             on="track_id",
         )
     )