"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Compare: forecast without covariates\n",
"sales_pred_no_cov_df = pipeline.predict_df(\n",
" sales_context_df[[id_column, timestamp_column, target]],\n",
" future_df=None,\n",
" prediction_length=prediction_length,\n",
" quantile_levels=[0.1, 0.5, 0.9],\n",
" id_column=id_column,\n",
" timestamp_column=timestamp_column,\n",
" target=target,\n",
")\n",
"\n",
"plot_forecast(\n",
" sales_context_df,\n",
" sales_pred_no_cov_df,\n",
" sales_test_df,\n",
" target_column=target,\n",
" timeseries_id=timeseries_id,\n",
" title_suffix=\"(without covariates)\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "7cf9f929",
"metadata": {},
"source": [
"Chronos-2's univariate forecast is nearly flat with high uncertainty. In contrast, the forecast with covariates leverages promotion and holiday information to capture the true sales dynamics over the forecast horizon."
]
},
{
"cell_type": "markdown",
"id": "f0e64196",
"metadata": {},
"source": [
"## Cross-Learning with Joint Prediction\n",
"\n",
"Chronos-2 supports **cross-learning** through the `predict_batches_jointly=True` parameter, which enables the model to share information across all time series in a batch during prediction. This can be particularly beneficial when forecasting multiple related time series with short historical context."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "60585f64",
"metadata": {},
"outputs": [],
"source": [
"# Example: Enable cross-learning for joint prediction\n",
"# This assigns the same group ID to all time series, allowing information sharing\n",
"joint_pred_df = pipeline.predict_df(\n",
" context_df,\n",
" prediction_length=24,\n",
" quantile_levels=[0.1, 0.5, 0.9],\n",
" predict_batches_jointly=True, # Enable cross-learning\n",
" batch_size=100,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "b427ca20",
"metadata": {},
"source": [
"### Important Considerations for Cross-Learning\n",
"\n",
"When using `predict_batches_jointly=True`, keep these caveats in mind:\n",
"\n",
"- **Task-dependent results**: Cross-learning may not always improve forecasts and could worsen performance for some tasks. Evaluate this feature for your specific use case.\n",
"\n",
"- **Batch size dependency**: Results become dependent on batch size. Very large batch sizes may not provide benefits as they deviate from the maximum group size used during pretraining. For optimal results, consider using a batch size around 100 (as used in the paper).\n",
"\n",
"- **Input homogeneity**: This feature works best with homogeneous inputs (e.g., multiple univariate time series of the same type). Mixing different task types may lead to unexpected behavior.\n",
"\n",
"- **Short context benefit**: Cross-learning is most helpful when individual time series have limited historical context, as the model can leverage patterns from related series in the batch."
]
},
{
"cell_type": "markdown",
"id": "6c16f90c",
"metadata": {},
"source": [
"## (Advanced) Numpy/torch API\n",
"\n",
"For advanced use cases, Chronos-2 provides a lower-level numpy/torch API via the `predict_quantiles` method.\n",
"\n",
"The `predict_quantiles` method accepts:\n",
"- `inputs`: Time series to forecast (see formats below)\n",
"- `prediction_length`: Number of timesteps to forecast\n",
"- `quantile_levels`: List of quantiles to compute\n",
"\n",
"Two input formats are supported:\n",
"1. **3D array**: `(batch_size, num_variates, history_length)` for forecasting without covariates\n",
"2. **List of dicts**: Each dict contains:\n",
" - `target`: 1D or 2D array of shape `(history_length,)` or `(num_variates, history_length)`\n",
" - `past_covariates` (optional): Dict mapping covariate names to 1D arrays of length `history_length`\n",
" - `future_covariates` (optional): Dict mapping covariate names to 1D arrays of length `prediction_length`"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "49e9d93a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Univariate output shapes: torch.Size([1, 24, 3]) torch.Size([1, 24])\n"
]
}
],
"source": [
"# Univariate forecasting\n",
"inputs = np.random.randn(32, 1, 100)\n",
"quantiles, mean = pipeline.predict_quantiles(\n",
" inputs, prediction_length=24, quantile_levels=[0.1, 0.5, 0.9]\n",
")\n",
"print(\"Univariate output shapes:\", quantiles[0].shape, mean[0].shape)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "41d95e35",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Multivariate output shapes: torch.Size([3, 48, 3]) torch.Size([3, 48])\n"
]
}
],
"source": [
"# Multivariate forecasting\n",
"inputs = np.random.randn(32, 3, 512)\n",
"quantiles, mean = pipeline.predict_quantiles(\n",
" inputs, prediction_length=48, quantile_levels=[0.1, 0.5, 0.9]\n",
")\n",
"print(\"Multivariate output shapes:\", quantiles[0].shape, mean[0].shape)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "879cf65b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Univariate with covariates output shapes: torch.Size([1, 64, 3]) torch.Size([1, 64])\n"
]
}
],
"source": [
"# Univariate forecasting with covariates\n",
"prediction_length = 64\n",
"inputs = [\n",
" {\n",
" \"target\": np.random.randn(200),\n",
" \"past_covariates\": {\"temperature\": np.random.randn(200), \"precipitation\": np.random.randn(200)},\n",
" \"future_covariates\": {\"temperature\": np.random.randn(prediction_length)},\n",
" }\n",
" for _ in range(16)\n",
"]\n",
"quantiles, mean = pipeline.predict_quantiles(\n",
" inputs, prediction_length=prediction_length, quantile_levels=[0.1, 0.5, 0.9]\n",
")\n",
"print(\"Univariate with covariates output shapes:\", quantiles[0].shape, mean[0].shape)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "08c7556e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Multivariate with categorical covariates output shapes: torch.Size([2, 96, 3]) torch.Size([2, 96])\n"
]
}
],
"source": [
"# Multivariate forecasting with categorical covariates\n",
"prediction_length = 96\n",
"inputs = [\n",
" {\n",
" \"target\": np.random.randn(2, 1000),\n",
" \"past_covariates\": {\n",
" \"temperature\": np.random.randn(1000),\n",
" \"weather_type\": np.random.choice([\"sunny\", \"cloudy\", \"rainy\"], size=1000),\n",
" },\n",
" \"future_covariates\": {\n",
" \"temperature\": np.random.randn(prediction_length),\n",
" \"weather_type\": np.random.choice([\"sunny\", \"cloudy\", \"rainy\"], size=prediction_length),\n",
" },\n",
" }\n",
" for _ in range(10)\n",
"]\n",
"quantiles, mean = pipeline.predict_quantiles(\n",
" inputs, prediction_length=prediction_length, quantile_levels=[0.1, 0.5, 0.9]\n",
")\n",
"print(\"Multivariate with categorical covariates output shapes:\", quantiles[0].shape, mean[0].shape)"
]
},
{
"cell_type": "markdown",
"id": "c99a5ae1",
"metadata": {},
"source": [
"## Fine-Tuning\n",
"\n",
"Chronos-2 supports fine-tuning on your own data."
]
},
{
"cell_type": "markdown",
"id": "ae26a137",
"metadata": {},
"source": [
"### Fine-Tuning API\n",
"\n",
"The `fit` method accepts:\n",
"- `inputs`: Time series for fine-tuning (same format as predict_quantiles)\n",
"- `prediction_length`: Forecast horizon for fine-tuning\n",
"- `validation_inputs`: Optional validation data (same format as inputs)\n",
"- `learning_rate`: Optimizer learning rate (default: 1e-5)\n",
"- `num_steps`: Number of training steps (default: 1000)\n",
"- `batch_size`: Batch size for training (default: 256)\n",
"\n",
"Returns a new pipeline with the fine-tuned model."
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "75915194",
"metadata": {},
"outputs": [],
"source": [
"# Prepare data for fine-tuning using the retail sales dataset\n",
"known_covariates = [\"Open\", \"Promo\", \"SchoolHoliday\", \"StateHoliday\"]\n",
"past_covariates = [\"Customers\"]\n",
"\n",
"train_inputs = []\n",
"for item_id, group in sales_context_df.groupby(\"id\"):\n",
" train_inputs.append({\n",
" \"target\": group[target].values,\n",
" \"past_covariates\": {col: group[col].values for col in past_covariates + known_covariates},\n",
" # Future values of covariates are not used during training.\n",
" # However, we need to include their names to indicate that these columns will be available at prediction time\n",
" \"future_covariates\": {col: None for col in known_covariates},\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "ea999650",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Could not estimate the number of tokens of the input, floating-point operations will not be computed\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
"
\n",
" [50/50 00:03, Epoch 1/9223372036854775807]\n",
"
\n",
" \n",
" \n",
" \n",
" Step \n",
" Training Loss \n",
" \n",
" \n",
" \n",
" \n",
" 10 \n",
" 0.695100 \n",
" \n",
" \n",
" 20 \n",
" 0.718000 \n",
" \n",
" \n",
" 30 \n",
" 0.734500 \n",
" \n",
" \n",
" 40 \n",
" 0.640800 \n",
" \n",
" \n",
" 50 \n",
" 0.667400 \n",
" \n",
" \n",
"
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Fine-tune the model\n",
"finetuned_pipeline = pipeline.fit(\n",
" inputs=train_inputs,\n",
" prediction_length=13,\n",
" num_steps=50, # few fine-tuning steps for a quick demo\n",
" learning_rate=1e-5,\n",
" batch_size=32,\n",
" logging_steps=10,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "d77f7a9f",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Use the fine-tuned model for predictions\n",
"finetuned_pred_df = finetuned_pipeline.predict_df(\n",
" sales_context_df,\n",
" future_df=sales_future_df,\n",
" prediction_length=13,\n",
" quantile_levels=[0.1, 0.5, 0.9],\n",
" id_column=\"id\",\n",
" timestamp_column=\"timestamp\",\n",
" target=\"Sales\",\n",
")\n",
"\n",
"plot_forecast(\n",
" sales_context_df,\n",
" finetuned_pred_df,\n",
" sales_test_df,\n",
" target_column=\"Sales\",\n",
" timeseries_id=\"1\",\n",
" title_suffix=\"(fine-tuned)\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "91083481",
"metadata": {},
"source": [
"**Note:** Fine-tuning functionality is intended for advanced users. The default fine-tuning hyperparameters may not always improve accuracy for your specific use case. We recommend experimenting with different hyperparameters. "
]
},
{
"cell_type": "markdown",
"id": "771d7f6a",
"metadata": {},
"source": []
}
],
"metadata": {
"jupytext": {
"cell_metadata_filter": "-all",
"main_language": "python",
"notebook_metadata_filter": "-all"
},
"kernelspec": {
"display_name": "chronos-forecasting",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}