Ryan Chen
e28d71fa5a
- Flask dashboard with Plotly charts (stores, monthly, hourly, weekday, heatmap) - Spotify Wrapped-style summary with year dropdown and inflation toggle - CSV upload flow (ephemeral, no storage) - Homepage with upload and saved data options - Import script for loading CSVs into SQLite - Dockerized with gunicorn for production Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
85 lines
2.5 KiB
Python
85 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Import a DoorDash CSV export into doordash.db."""
|
|
|
|
import csv
|
|
import sqlite3
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
DB_PATH = Path(__file__).parent / "doordash.db"
|
|
|
|
CREATE_TABLE = """CREATE TABLE IF NOT EXISTS "doordash"(
|
|
"ITEM" TEXT, "CATEGORY" TEXT, "STORE_NAME" TEXT, "UNIT_PRICE" TEXT,
|
|
"QUANTITY" TEXT, "SUBTOTAL" TEXT, "CREATED_AT" TEXT, "DELIVERY_TIME" TEXT,
|
|
"DELIVERY_ADDRESS" TEXT
|
|
);"""
|
|
|
|
EXPECTED_HEADER = [
|
|
"ITEM", "CATEGORY", "STORE_NAME", "UNIT_PRICE", "QUANTITY",
|
|
"SUBTOTAL", "CREATED_AT", "DELIVERY_TIME", "DELIVERY_ADDRESS",
|
|
]
|
|
|
|
|
|
def import_csv(csv_path: str):
|
|
path = Path(csv_path)
|
|
if not path.exists():
|
|
print(f"Error: {csv_path} not found")
|
|
sys.exit(1)
|
|
|
|
conn = sqlite3.connect(DB_PATH)
|
|
c = conn.cursor()
|
|
c.execute(CREATE_TABLE)
|
|
|
|
# Get existing row count for reporting
|
|
before_count = c.execute("SELECT COUNT(*) FROM doordash").fetchone()[0]
|
|
|
|
# Check for duplicates using CREATED_AT + ITEM + STORE_NAME
|
|
existing = set()
|
|
for row in c.execute("SELECT ITEM, STORE_NAME, CREATED_AT FROM doordash"):
|
|
existing.add((row[0], row[1], row[2]))
|
|
|
|
imported = 0
|
|
skipped = 0
|
|
|
|
with open(path, newline="") as f:
|
|
reader = csv.reader(f)
|
|
header = next(reader)
|
|
|
|
# Validate header
|
|
header_upper = [h.strip().upper() for h in header]
|
|
if header_upper != EXPECTED_HEADER:
|
|
print(f"Error: unexpected CSV header.\nExpected: {EXPECTED_HEADER}\nGot: {header_upper}")
|
|
sys.exit(1)
|
|
|
|
for row in reader:
|
|
if len(row) != 9:
|
|
print(f"Warning: skipping row with {len(row)} columns: {row[:3]}...")
|
|
skipped += 1
|
|
continue
|
|
|
|
key = (row[0], row[2], row[6]) # ITEM, STORE_NAME, CREATED_AT
|
|
if key in existing:
|
|
skipped += 1
|
|
continue
|
|
|
|
c.execute("INSERT INTO doordash VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)", row)
|
|
existing.add(key)
|
|
imported += 1
|
|
|
|
conn.commit()
|
|
after_count = c.execute("SELECT COUNT(*) FROM doordash").fetchone()[0]
|
|
conn.close()
|
|
|
|
print(f"Done! Imported {imported} rows, skipped {skipped} duplicates.")
|
|
print(f"Total rows: {before_count} -> {after_count}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print(f"Usage: {sys.argv[0]} <csv_file> [csv_file2 ...]")
|
|
sys.exit(1)
|
|
|
|
for csv_file in sys.argv[1:]:
|
|
print(f"\nImporting {csv_file}...")
|
|
import_csv(csv_file)
|