From b756ed5febbb920784a43f0367fcfab47355bb16 Mon Sep 17 00:00:00 2001 From: junos Date: Thu, 18 May 2023 18:06:32 +0200 Subject: [PATCH] Set more parameters as user-specified constants. --- exploration/ml_pipeline_classification.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/exploration/ml_pipeline_classification.py b/exploration/ml_pipeline_classification.py index 33fbfcb..3bdcce2 100644 --- a/exploration/ml_pipeline_classification.py +++ b/exploration/ml_pipeline_classification.py @@ -73,18 +73,21 @@ model_input["target"].value_counts() # %% jupyter={"outputs_hidden": false, "source_hidden": false} # bins = [-10, 0, 10] # bins for z-scored targets -bins = [-1, 0, 4] # bins for stressfulness (0-4) target +BINS = [-1, 0, 4] # bins for stressfulness (0-4) target +print("BINS: ", BINS) model_input["target"], edges = pd.cut( - model_input.target, bins=bins, labels=["low", "high"], retbins=True, right=True + model_input.target, bins=BINS, labels=["low", "high"], retbins=True, right=True ) # ['low', 'medium', 'high'] -model_input["target"].value_counts(), edges -model_input = model_input[model_input["target"] != "medium"] +print(model_input["target"].value_counts()) +REMOVE_MEDIUM = True +if ("medium" in model_input["target"]) and REMOVE_MEDIUM: + model_input = model_input[model_input["target"] != "medium"] + print(model_input["target"].value_counts()) + model_input["target"] = ( model_input["target"].astype(str).apply(lambda x: 0 if x == "low" else 1) ) -model_input["target"].value_counts() - # %% jupyter={"outputs_hidden": false, "source_hidden": false} # UnderSampling if UNDERSAMPLING: