41 lines
1.2 KiB
Python
41 lines
1.2 KiB
Python
import pandas as pd
|
|
from dagster import op
|
|
|
|
|
|
@op
|
|
def fetch_data() -> list:
|
|
"""Fetches raw data from a source."""
|
|
return [{"id": 1, "value": "A"}, {"id": 2, "value": "B"}]
|
|
|
|
|
|
@op
|
|
def process_data(data: list) -> dict:
|
|
"""Processes raw data and returns a summary."""
|
|
return {"count": len(data), "status": "success"}
|
|
|
|
|
|
@op
|
|
def generate_example_dataset() -> pd.DataFrame:
|
|
"""Generates a small example dataset as a pandas DataFrame."""
|
|
return pd.DataFrame(
|
|
[
|
|
{"order_id": 1001, "customer": "Alice", "quantity": 2, "unit_price": 9.50},
|
|
{"order_id": 1002, "customer": "Bob", "quantity": 1, "unit_price": 15.00},
|
|
{"order_id": 1003, "customer": "Charlie", "quantity": 4, "unit_price": 7.25},
|
|
{"order_id": 1004, "customer": "Dora", "quantity": 3, "unit_price": 11.00},
|
|
]
|
|
)
|
|
|
|
|
|
@op
|
|
def transform_example_dataset(df: pd.DataFrame) -> pd.DataFrame:
|
|
"""Applies a simple transformation to the example dataset."""
|
|
|
|
df["price_band"] = df["total_price"].apply(
|
|
lambda value: "high" if value >= 25 else "standard"
|
|
)
|
|
|
|
df["total_price"] = df["quantity"] * df["unit_price"]
|
|
|
|
return df
|