diff --git a/Dockerfile b/Dockerfile index 948ba60..73c4dc7 100644 --- a/Dockerfile +++ b/Dockerfile @@ -18,6 +18,4 @@ ARG KAGGLE_USERNAME ARG KAGGLE_KEY ENV CUTOFF=${CUTOFF} ENV KAGGLE_USERNAME=${KAGGLE_USERNAME} -ENV KAGGLE_KEY=${KAGGLE_KEY} -# Domyślne polecenie, które zostanie uruchomione w kontenerze po jego starcie -RUN ./process_data.sh \ No newline at end of file +ENV KAGGLE_KEY=${KAGGLE_KEY} \ No newline at end of file diff --git a/download_data_and_process.py b/download_data_and_process.py index eb23b6a..932c995 100644 --- a/download_data_and_process.py +++ b/download_data_and_process.py @@ -1,6 +1,7 @@ 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)