From cfa87567c26683a9c59682fc1bf787cf5bebff86 Mon Sep 17 00:00:00 2001
From: Nikolai <osterei33@gmx.de>
Date: Fri, 10 Aug 2018 10:11:22 +0200
Subject: [PATCH] include identifiers in to_DataFrame
---
toolkit.py | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/toolkit.py b/toolkit.py
index 0cea431..fabfebe 100755
--- a/toolkit.py
+++ b/toolkit.py
@@ -1140,6 +1140,12 @@ class ClassificationProject(object):
np.concatenate([self.y_train, self.y_test]),
categories=["background", "signal"]
)
+ for identifier in self.identifiers:
+ df[identifier] = np.concatenate([self.s_eventlist_train[identifier],
+ self.b_eventlist_train[identifier],
+ -1*np.ones(len(self.x_test), dtype="i8")])
+ df["is_train"] = np.concatenate([np.ones(len(self.x_train), dtype=np.bool),
+ np.zeros(len(self.x_test), dtype=np.bool)])
return df
@@ -1161,6 +1167,17 @@ for dataset_name in ClassificationProject.dataset_names:
create_setter(dataset_name)))
+# class ClassificationProjectDataFrame(ClassificationProject):
+
+# """
+# A little hack to initialize a ClassificationProject from a pandas DataFrame instead of ROOT TTrees
+# """
+
+# def __init__(self,
+# **kwargs):
+# pass
+
+
if __name__ == "__main__":
logging.basicConfig()
--
GitLab