updates to vector

Watts-Lab · Dec 18, 2024 · 9c4663c · 9c4663c
1 parent 26befed
commit 9c4663c
Show file tree

Hide file tree

Showing 3 changed files with 96 additions and 273 deletions.
diff --git a/examples/featurize.py b/examples/featurize.py
@@ -58,6 +58,8 @@
 	vect_diff_length_df = pd.read_csv("../tests/vector_data/sentence/chats/test_vector_valid.csv", encoding='utf-8')
 	vect_null = pd.read_csv("../tests/vector_data/sentence/chats/test_vector_valid.csv", encoding='utf-8')
 	vect_nan = pd.read_csv("../tests/vector_data/sentence/chats/test_vector_valid.csv", encoding='utf-8')
+	vect_no_one_to_one = pd.read_csv("../tests/vector_data/sentence/chats/test_vector_valid.csv", encoding='utf-8')
+	test_convo_num_issue = pd.read_csv("../tests/vector_data/sentence/chats/test_turns_convo_num_issue.csv", encoding='utf-8')
 
 	# test number of rows mismatch
 	vector_row_mismatch_df = vector_row_mismatch_df.iloc[:-1]
@@ -77,6 +79,9 @@
 	# test nan vectors
 	vect_nan.loc[0, 'message_embedding'] = '[np.nan, np.nan]'
 
+	# test no 1-1 mapping
+	vect_no_one_to_one.loc[0, 'message_embedding'] = '[0.1, 0.2]'
+
 	test_cases = {
 		"Valid DataFrame": valid_df,
   		"Vector Row Mismatch": vector_row_mismatch_df,
@@ -87,10 +92,9 @@
 		"Vectors Null": vect_null,
 		"Vectors Nan": vect_nan,
   		"Custom File Equals Default Dir": valid_df,
+		"No 1-1 Mapping": vect_no_one_to_one,
 	}
 
-	# custom_vect_path = "../tests/vector_data/sentence/chats/test_vector.csv"
-
 	for name, df in test_cases.items():
 		custom_vect_path = "../tests/vector_data/sentence/chats/test_vector.csv"
 		print(name)