From f39696de4a68ada9ad6040f173f5b6b19a24eebc Mon Sep 17 00:00:00 2001
From: fzayguler <65349101+fzayguler@users.noreply.github.com>
Date: Fri, 10 May 2024 16:39:09 +0000
Subject: [PATCH] investigate datasets

---
 authorship-verification-submission/run.py   | 2 +-
 authorship-verification-submission/train.py | 5 ++++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/authorship-verification-submission/run.py b/authorship-verification-submission/run.py
index 268f45e..4e664ff 100644
--- a/authorship-verification-submission/run.py
+++ b/authorship-verification-submission/run.py
@@ -20,7 +20,7 @@
     predictions = model.predict(df["text"])
     df["generated"] = predictions
     df = df[["id", "generated"]]
-
+    print(len(df.index))
 
     # Save the predictions
     output_directory = get_output_directory(str(Path(__file__).parent))
diff --git a/authorship-verification-submission/train.py b/authorship-verification-submission/train.py
index afd9363..ba520fc 100644
--- a/authorship-verification-submission/train.py
+++ b/authorship-verification-submission/train.py
@@ -25,7 +25,10 @@
     df = text.join(labels.set_index("id"))
 
     # print the first 5 rows
-    #print(df.head())
+    print(df.head())
+    #print the number of rows
+    print(len(df.index))
+    
 
     # export the data to a json file with indent=4
     #df.to_json(Path(__file__).parent / "data.json", indent=4)