Python Example — Forecasting Multiple SKUs

The following script shows how to loop through a list of SKU codes, call the Graphite Note Time Series Forecasting API for each, and save all daily predictions into a single CSV file. This example requests forecasts for October 2025 and assumes the model does not use regressors.

import requests
import pandas as pd

# --- CONFIGURATION ---
API_URL = "https://app.graphite-note.com/api/v1/prediction/model/[model-code]"
API_TOKEN = "Bearer YOUR_TOKEN_HERE"

# Example SKUs
sku_list = [f"SKU{i:03d}" for i in range(1, 11)]

# Prediction window
START_DATE = "2025-10-01"
END_DATE   = "2025-10-31"

# --- STORAGE ---
all_results = []

# --- LOOP THROUGH SKUs ---
for sku in sku_list:
    payload = {
        "data": {
            "predict_values": {
                "startDate": START_DATE,
                "endDate": END_DATE,
                "sequenceID": sku
            }
        }
    }

    headers = {
        "Authorization": API_TOKEN,
        "Content-Type": "application/json"
    }

    response = requests.post(API_URL, json=payload, headers=headers)
    response.raise_for_status()

    data = response.json().get("data", [])

    for row in data:
        if "date" in row:  # skip the trailing { "sequenceID": ... }
            all_results.append({
                "SKU": sku,
                "Date": row["date"].split("T")[0],
                "Predicted": row["predicted"],
                "Predicted_Lower": row["predicted_lower"],
                "Predicted_Upper": row["predicted_upper"]
            })

# --- EXPORT TO CSV ---
df = pd.DataFrame(all_results)
df.to_csv("october_2025_forecasts.csv", index=False)

print("Saved results to october_2025_forecasts.csv")

This script:

1. Iterates through ten SKUs.

2. Sends a POST request for each SKU with the requested date range.

3. Collects all daily predictions, including lower and upper bounds.

4. Saves the results into a CSV file for further analysis.