From 0f655c8719fc4fdd748c40bb23f9bebb89e02e46 Mon Sep 17 00:00:00 2001 From: PlexSheep Date: Thu, 16 Jan 2025 14:26:08 +0100 Subject: [PATCH] 01: remove outliers from data --- tasks/01-melbourne.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tasks/01-melbourne.py b/tasks/01-melbourne.py index 40c4e51..e27c6f9 100644 --- a/tasks/01-melbourne.py +++ b/tasks/01-melbourne.py @@ -20,10 +20,9 @@ import seaborn as sns # %% Data data = pd.read_csv("../data/melb_data.csv").dropna() -# Ein Outlier, blöder Arsch -# TODO: remove outlier from actual data, not just diagram +data = data[(data["BuildingArea"] < 1000) ] ax = sns.scatterplot(x=data['BuildingArea'], y=data['Price']) -ax.set(xlim=(0, 1000)) +# ax.set(xlim=(0, 1000)) # brauch ich nicht mehr wenn ich die outlier aus den daten rausschmeiße # %% linear regression