diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..4745b5a
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,10 @@
+FROM python:latest
+
+WORKDIR /app
+
+RUN pip install pandas
+
+COPY pipeline.py pipeline_c.py
+RUN python pipeline_c.py https://www.stats.govt.nz/assets/Uploads/Annual-enterprise-survey/Annual-enterprise-survey-2021-financial-year-provisional/Download-data/annual-enterprise-survey-2021-financial-year-provisional-csv.csv target.csv
+
+ENTRYPOINT [ "bash" ]
\ No newline at end of file
diff --git a/Untitled-1.ipynb b/Untitled-1.ipynb
deleted file mode 100644
index 746d752..0000000
--- a/Untitled-1.ipynb
+++ /dev/null
@@ -1,43 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Hello world\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(\"Hello world\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/pipeline.py b/pipeline.py
new file mode 100644
index 0000000..280d518
--- /dev/null
+++ b/pipeline.py
@@ -0,0 +1,24 @@
+import pandas as pd
+import argparse
+
+def main(source, target):
+    print("Starting")
+
+    # Extract data
+    data = pd.read_csv(source)
+
+    # Transform data
+    data.drop(["Industry_code_ANZSIC06"], axis=1, inplace=True)
+
+    # Load data
+    data.to_csv(target, index=False)
+
+    print("Complete")
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('source', help='source.csv')
+    parser.add_argument('target', help='target.csv')
+    args = parser.parse_args()
+
+    main(args.source, args.target)