investigate datasets

tira-io · May 10, 2024 · f39696d · f39696d
1 parent fdc437c
commit f39696d
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git 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
@@ -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)