diff --git a/avocado-preprocessing.py b/avocado-preprocessing.py
index c47aa75..ba7656f 100644
--- a/avocado-preprocessing.py
+++ b/avocado-preprocessing.py
@@ -1,10 +1,14 @@
+import kaggle
 import pandas as pd
 import numpy as np
 from sklearn import preprocessing
 
 
+# kaggle
+kaggle.api.authenticate()
+kaggle.api.dataset_download_files('timmate/avocado-prices-2020', path='.', unzip=True)
+
 avocado_with_year = pd.read_csv('avocado-updated-2020.csv')
-avocado_with_year
 
 new = ['date', 'average_price', 'total_volume', '4046', '4225', '4770', 'total_bags', 'small_bags', 'large_bags', 'xlarge_bags', 'type', 'geography']
 avocado = avocado_with_year[new]