From 33742a72ee503c1cae363818072d684deac5ef0d Mon Sep 17 00:00:00 2001 From: LinlyBoi Date: Thu, 30 Mar 2023 09:10:23 +0200 Subject: [PATCH] can say this is a slam dunk --- py_scripts/digger.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/py_scripts/digger.py b/py_scripts/digger.py index dd68b61..f0e9f99 100644 --- a/py_scripts/digger.py +++ b/py_scripts/digger.py @@ -21,6 +21,13 @@ def write_joined_df(left, right, lsuf="new_key"): return merged -def slam_dunk(dataset, column, size): - dataset["dunked"] = pd.qcut(dataset[column], q=3) - return dataset["dunked"] +def slam_dunk(dataset, column, size, labels): + min_value = dataset[column].min() + max_value = dataset[column].max() + bins = np.linspace(min_value, max_value, size) + + dunked_column = "bin_" + column + dataset[dunked_column] = pd.cut( + dataset[column], bins=bins, labels=labels, include_lowest=True + ) + return dataset[dunked_column]