Update admin_utils.py

admin_utils.py

@@ -50,3 +50,30 @@ def push_to_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,em
     index_name = pinecone_index_name
     index = Pinecone.from_documents(docs, embeddings, index_name=index_name)
     return index
+
+def read_data(data):
+    df = pd.read_csv(data,delimiter=',', header=None)  
+    return df
+
+#Create embeddings instance
+def get_embeddings():
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    return embeddings
+
+#Generating embeddings for our input dataset
+def create_embeddings(df,embeddings):
+    df[2] = df[0].apply(lambda x: embeddings.embed_query(x))
+    return df
+
+#Splitting the data into train & test
+def split_train_test__data(df_sample):
+    # Split into training and testing sets
+    sentences_train, sentences_test, labels_train, labels_test = train_test_split(
+    list(df_sample[2]), list(df_sample[1]), test_size=0.25, random_state=0)
+    print(len(sentences_train))
+    return sentences_train, sentences_test, labels_train, labels_test
+
+#Get the accuracy score on test data
+def get_score(svm_classifier,sentences_test,labels_test):
+    score = svm_classifier.score(sentences_test, labels_test)
+    return score