Update README for Chronos-2

[abdulfatir]

Issue #, if available:

Description of changes:

TODOs:

• Shorten introduction.
• Change example to Chronos-2.
• Move pretraining related stuff to Chronos notebook.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[shchur]

This could be more concise:

import matplotlib.pyplot as plt

ts_context = context_df.set_index(timestamp_column)[target].tail(256)
ts_pred = pred_df.set_index(timestamp_column)
ts_ground_truth = test_df.set_index(timestamp_column)[target]

ts_context.plot(label=f"historical data", color="xkcd:azure", figsize=(12, 3))
ts_ground_truth.plot(label=f"future data (ground truth)", color="xkcd:grass green")
ts_pred["predictions"].plot(label="forecast", color="xkcd:violet")
plt.fill_between(
    ts_pred.index,
    ts_pred["0.1"],
    ts_pred["0.9"],
    alpha=0.7,
    label="prediction interval",
    color="xkcd:light lavender",
)
plt.legend()

[abdulfatir]

You're right. I was going for "more general" but I guess for README example this is good enough.

[shchur]

How about we remove these variables completely and make the example for Chronos-2 usage shorter?

import pandas as pd  # requires: pip install pandas
from chronos import Chronos2Pipeline

pipeline = Chronos2Pipeline.from_pretrained("s3://autogluon/chronos-2", device_map="cuda")

# Load historical energy prices and past values of covariates
context_df = pd.read_parquet("https://autogluon.s3.amazonaws.com/datasets/timeseries/electricity_price/train.parquet")

# (Optional) Load future values of covariates
test_df = pd.read_parquet("https://autogluon.s3.amazonaws.com/datasets/timeseries/electricity_price/test.parquet")
future_df = test_df.drop(columns="target")

# Generate predictions with covariates
pred_df = pipeline.predict_df(
    context_df, 
    future_df=future_df,
    prediction_length = 24  # Number of steps to forecast
    quantile_levels=[0.1, 0.5, 0.9],  # Quantiles for probabilistic forecast
    id_column = "id"  # Column identifying different time series
    timestamp_column = "timestamp"  # Column with datetime information
    target = "target"  # Column(s) with time series values to predict
)

[shchur]

LGTM!