diff --git a/Dockerfile b/Dockerfile
index a9b0d28..7bdc7f7 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -10,7 +10,7 @@ RUN pip3 install --upgrade pip
 RUN pip3 install pandas
 RUN pip3 install numpy
 RUN pip3 install kaggle
-
+RUN apt-get install zip unzip
 ARG CUTOFF
 ARG KAGGLE_USERNAME
 ARG KAGGLE_KEY
@@ -27,4 +27,4 @@ COPY ./process_data.sh .
 COPY ./download_data_and_process.py .
 COPY ./stats.py .
 
-# RUN ./process_data.sh
+RUN ./process_data.sh
diff --git a/download_data_and_process.py b/download_data_and_process.py
index a225f2d..b4dd4f2 100644
--- a/download_data_and_process.py
+++ b/download_data_and_process.py
@@ -1,17 +1,17 @@
 import subprocess
 import pandas as pd
 import numpy as np
-import kaggle
+# import kaggle
 
-kaggle.api.authenticate()
-kaggle.api.dataset_download_files('shivamb/real-or-fake-fake-jobposting-prediction', path='fake_job_postings.csv', unzip=True)
+# kaggle.api.authenticate()
+# kaggle.api.dataset_download_files('shivamb/real-or-fake-fake-jobposting-prediction', path='fake_job_postings.csv', unzip=True)
 
 
 
 
 
 
-data=pd.read_csv('fake_job_postings.csv/fake_job_postings.csv')
+data=pd.read_csv('fake_job_postings.csv')
 data = data.replace(np.nan, '', regex=True)
 
 print("="*20)