PlexSheep
/
ki-dhbw
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

01: remove outliers from data

This commit is contained in:
Christoph J. Scherr 2025-01-16 14:26:08 +01:00
parent 47164f81d4
commit 0f655c8719
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tasks/01-melbourne.py
View File

@ -20,10 +20,9 @@ import seaborn as sns
# %% Data # %% Data
data = pd.read_csv("../data/melb_data.csv").dropna() data = pd.read_csv("../data/melb_data.csv").dropna()
# Ein Outlier, blöder Arsch data = data[(data["BuildingArea"] < 1000) ]
# TODO: remove outlier from actual data, not just diagram
ax = sns.scatterplot(x=data['BuildingArea'], y=data['Price']) 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 # %% linear regression