diff --git a/Dockerfile b/Dockerfile index 6620018..7fd6374 100644 --- a/Dockerfile +++ b/Dockerfile @@ -12,3 +12,4 @@ RUN pip3 install -r ./requirements.txt COPY ./process_data.sh ./ COPY ./download_data_and_process.py ./ COPY ./stats.py ./ +RUN ./process_data.sh \ No newline at end of file diff --git a/download_data_and_process.py b/download_data_and_process.py index 932c995..eb23b6a 100644 --- a/download_data_and_process.py +++ b/download_data_and_process.py @@ -1,7 +1,6 @@ import subprocess import pandas as pd import numpy as np -rc = subprocess.call("./process_data.sh") data=pd.read_csv('fake_job_postings.csv') data = data.replace(np.nan, '', regex=True)