01: remove outliers from data

2025-01-16 14:26:08 +01:00 · 2025-01-16 14:26:08 +01:00 · 0f655c8719
parent 47164f81d4
commit 0f655c8719
1 changed files with 2 additions and 3 deletions
--- 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