junos
/
stress_at_work_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Better handling of "medium" category.

master
junos 2023-05-19 01:10:30 +02:00
parent 8a9595c615
commit 70232949c3
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
exploration/ml_pipeline_classification.py
View File

@ -82,11 +82,15 @@ print(model_input["target"].value_counts())
REMOVE_MEDIUM = True REMOVE_MEDIUM = True
if ("medium" in model_input["target"]) and REMOVE_MEDIUM: if ("medium" in model_input["target"]) and REMOVE_MEDIUM:
model_input = model_input[model_input["target"] != "medium"] model_input = model_input[model_input["target"] != "medium"]
print(model_input["target"].value_counts())
model_input["target"] = ( model_input["target"] = (
model_input["target"].astype(str).apply(lambda x: 0 if x == "low" else 1) model_input["target"].astype(str).apply(lambda x: 0 if x == "low" else 1)
) )
else:
model_input["target"] = model_input["target"].map(
{"low": 0, "medium": 1, "high": 2}
)
print(model_input["target"].value_counts())
# %% jupyter={"outputs_hidden": false, "source_hidden": false} # %% jupyter={"outputs_hidden": false, "source_hidden": false}
# UnderSampling # UnderSampling