# import testing data
df_resume = pd.read_csv('resumes/resumes_test.csv')

# generate embeddings
text_embedding_list = generate_embeddings(df_resume['resume'], my_sk)
text_embedding_list = 
  [text_embedding_list[i].embedding for i in range(len(text_embedding_list))]

# store text embeddings in dataframe
df_test = pd.DataFrame(text_embedding_list, columns=column_names)

# create target variable
df_test['is_data_scientist'] = df_resume['role']=="Data Scientist"

# define predictors and target
X_test = df_test.iloc[:,:-1]
y_test = df_test.iloc[:,-1]