From ce2e0cdbf50c2de0e0e5608883eb22b3802e0736 Mon Sep 17 00:00:00 2001
From: Your Name <nikhilkarnati@Nikhils-MacBook-Air.local>
Date: Mon, 3 Aug 2026 10:01:44 -0400
Subject: [PATCH] Add Docker Compose configuration and upload script

---
 .../docker-sql/docker-compose.yaml            | 26 ++++++++++++
 01-docker-terraform/docker-sql/upload_data.py | 42 +++++++++++++++++++
 2 files changed, 68 insertions(+)
 create mode 100644 01-docker-terraform/docker-sql/docker-compose.yaml
 create mode 100644 01-docker-terraform/docker-sql/upload_data.py

diff --git a/01-docker-terraform/docker-sql/docker-compose.yaml b/01-docker-terraform/docker-sql/docker-compose.yaml
new file mode 100644
index 0000000000..b92597766d
--- /dev/null
+++ b/01-docker-terraform/docker-sql/docker-compose.yaml
@@ -0,0 +1,26 @@
+version: '3.8'
+
+services:
+  pgdatabase:
+    image: postgres:13
+    container_name: postgres
+    environment:
+      - POSTGRES_USER=root
+      - POSTGRES_PASSWORD=rootpassword
+      - POSTGRES_DB=ny_taxi
+    volumes:
+      - ny_taxi_postgres_data:/var/lib/postgresql/data
+    ports:
+      - "5432:5432"
+
+  pgadmin:
+    image: dpage/pgadmin4
+    container_name: pgadmin
+    environment:
+      - PGADMIN_DEFAULT_EMAIL=admin@admin.com
+      - PGADMIN_DEFAULT_PASSWORD=root
+    ports:
+      - "8080:80"
+
+volumes:
+  ny_taxi_postgres_data:
diff --git a/01-docker-terraform/docker-sql/upload_data.py b/01-docker-terraform/docker-sql/upload_data.py
new file mode 100644
index 0000000000..7db1c61e36
--- /dev/null
+++ b/01-docker-terraform/docker-sql/upload_data.py
@@ -0,0 +1,42 @@
+import os
+import pandas as pd
+from sqlalchemy import create_engine
+
+# 1. Download setup
+url = "https://github.com/DataTalksClub/nyc-tlc-data/releases/download/green/green_tripdata_2019-09.csv.gz"
+csv_name = "green_tripdata_2019-09.csv.gz"
+
+print("Cleaning old files and downloading dataset...")
+os.system(f"rm -f {csv_name}")
+os.system(f"curl -L -o {csv_name} {url}")
+
+# 2. Database connection
+engine = create_engine('postgresql://root:rootpassword@localhost:5432/ny_taxi')
+
+# 3. Read iterator
+df_iter = pd.read_csv(csv_name, iterator=True, chunksize=100000, compression='gzip')
+
+# --- THIS IS THE MISSING PART ---
+# Get first chunk to create header/table schema
+df = next(df_iter)
+
+# Parse datetime columns if needed
+df.lpep_pickup_datetime = pd.to_datetime(df.lpep_pickup_datetime)
+df.lpep_dropoff_datetime = pd.to_datetime(df.lpep_dropoff_datetime)
+
+# Create the table schema (replace existing if any)
+df.head(n=0).to_sql(name='green_taxi_data', con=engine, if_exists='replace')
+
+# Insert the first chunk
+df.to_sql(name='green_taxi_data', con=engine, if_exists='append')
+print("Inserted first chunk...")
+
+# Loop through remaining chunks
+for chunk in df_iter:
+    chunk.lpep_pickup_datetime = pd.to_datetime(chunk.lpep_pickup_datetime)
+    chunk.lpep_dropoff_datetime = pd.to_datetime(chunk.lpep_dropoff_datetime)
+    
+    chunk.to_sql(name='green_taxi_data', con=engine, if_exists='append')
+    print("Inserted another chunk...")
+
+print("Finished inserting all data!")
\ No newline at end of file