Data Science · मराठी आवृत्ती

26.7 Practice, tip आणि close

By Ravindra Bagale

हे का शिकायचं?

एक sample JSON → DataFrame आणि एक zip CSV → DataFrame. दोन्ही सवयी.

हे काय आहे?

Practice + quiz.

कसं करायचं?

उदाहरणं: copy करा आणि चालवा

हा code / output:

import json
import zipfile
from pathlib import Path
import pandas as pd

Path("data/raw").mkdir(parents=True, exist_ok=True)
Path("outputs").mkdir(exist_ok=True)

payload = {
    "orders": [
        {"order_id": "BLK-61", "city": "Pune", "status": "Delivered", "amount_inr": 189},
        {"order_id": "BLK-62", "city": "Nashik", "status": "Open", "amount_inr": 95},
        {"order_id": "AMN-63", "city": "Kolhapur", "status": "Delivered", "amount_inr": 210},
        {"order_id": "BLK-64", "city": "Solapur", "status": "Delivered", "amount_inr": 70},
        {"order_id": "BLK-65", "city": "Nagpur", "status": "Open", "amount_inr": 150},
        {"order_id": "BLK-66", "city": "Sambhaji Nagar", "status": "Delivered", "amount_inr": 120},
        {"order_id": "BLK-67", "city": "Pune", "status": "Delivered", "amount_inr": 99},
        {"order_id": "AMN-68", "city": "Nashik", "status": "Delivered", "amount_inr": 130},
    ]
}
Path("data/raw/status_sample.json").write_text(json.dumps(payload), encoding="utf-8")
df_api = pd.json_normalize(payload["orders"])

csv_path = Path("data/raw/orders_mini.csv")
df_api.to_csv(csv_path, index=False)
zip_path = Path("data/raw/orders_mini.csv.zip")
with zipfile.ZipFile(zip_path, "w", compression=zipfile.ZIP_DEFLATED) as z:
    z.write(csv_path, arcname="orders_mini.csv")
df_zip = pd.read_csv(zip_path)

counts = df_zip.groupby("city", as_index=False).size().rename(columns={"size": "orders"})
counts.to_csv("outputs/api_zip_city_counts.csv", index=False)
print(df_api.shape, df_zip.shape)
print(counts)