From 92d3ee2ff004ea32e0b07dfc101a77d76f3b694d Mon Sep 17 00:00:00 2001
From: Shishir Patil <30296397+ShishirPatil@users.noreply.github.com>
Date: Sat, 13 Apr 2024 20:43:22 -0700
Subject: [PATCH] Update raft.py with default `p` to match paper

Change `p` which dictates the fraction of dataset with golden documents in them (vs) no golden documents.

So, p = 0.8 means, for 80% of the train data set, `A* = Q + D* + D1 .. Dn` and for 20% of the train data set `A* = Q + D1 .. Dn` where `D*` are/is the golden document with the answer `A*`.
---
 raft/raft.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/raft/raft.py b/raft/raft.py
index 4280579d5..9b07e0c23 100644
--- a/raft/raft.py
+++ b/raft/raft.py
@@ -185,7 +185,7 @@ def add_chunk_to_dataset(
     doctype: DocType = "api", 
     x: int = 5, 
     num_distract: int = 3, 
-    p: float = 1.0
+    p: float = 0.8
 ) -> None:
     """
     Given a chunk, create {Q, A, D} triplets and add them to the dataset.