Building a time series forecasting assistant with Amazon Bedrock and LibreChat¶
1. Overview¶
Most forecasting systems expose their outputs through dashboards and reports, limiting the user’s interaction and visibility to predefined queries anticipated at development time. In this post, we address this limitation by building a conversational time series forecasting assistant using ClickHouse, Amazon Bedrock, and LibreChat. The assistant allows the user to explore the underlying data, select specific time series, and adjust forecast parameters - such as quantile levels and prediction horizons - through natural language.
The solution is built around the Model Context Protocol (MCP), which defines a common interface for connecting language models to external tools and services, and relies on three servers: the ClickHouse MCP server for retrieving the time series, a custom MCP server that generates probabilistic time series forecasts using Chronos [1, 2] - a time series foundation model developed by Amazon - deployed on Amazon Bedrock, and an additional custom MCP server that creates interactive Plotly charts of the time series and their forecasts. We use LibreChat as the chat UI, with Claude Sonnet 4.6 on Amazon Bedrock as the orchestrating model.
For simplicity, this demonstration uses artificially generated sales data for three products. However, as Chronos performs zero-shot forecasting without fine-tuning, this solution can be applied to any time series dataset. In the rest of the post, we walk through the implementation of the three MCP servers and the assistant configuration. We also illustrate a typical conversation with the assistant, which is shown in the video below; the transcript is reported at the end of this post.
2. Solution¶
For this example, we use synthetic hourly sales data for three products: Product A, Product B and Product C.
The time series span 90 days, and are stored in two ClickHouse tables: products, which maps product IDs to names,
and sales, which records hourly units sold per product.
Figure 1:
products
ClickHouse table.
Figure 2:
Last 9 rows of
sales
ClickHouse table.
2.1 Set up the MCP servers¶
We start by cloning the LibreChat GitHub repository and configuring
Claude Sonnet 4.6 on Amazon Bedrock as the underlying model. We use the eu.anthropic.claude-sonnet-4-6
cross-region inference profile in eu-west-1. As outlined in the LibreChat documentation,
we update the following environment variables in the .env file:
BEDROCK_AWS_DEFAULT_REGION=eu-west-1
BEDROCK_AWS_MODELS=eu.anthropic.claude-sonnet-4-6
BEDROCK_AWS_ACCESS_KEY_ID=<AWS_ACCESS_KEY_ID>
BEDROCK_AWS_SECRET_ACCESS_KEY=<AWS_SECRET_ACCESS_KEY>
We also include the model’s inference profile ARN in librechat.yaml:
endpoints:
bedrock:
inferenceProfiles:
"eu.anthropic.claude-sonnet-4-6": "arn:aws:bedrock:eu-west-1:<AWS_ACCOUNT_ID>:inference-profile/eu.anthropic.claude-sonnet-4-6"
2.1.1 Configure the ClickHouse MCP server¶
Next, we configure the ClickHouse MCP server. Following ClickHouse documentation,
we create a docker-compose.override.yml file and add the following configuration to it:
services:
api:
volumes:
- ./librechat.yaml:/app/librechat.yaml
mcp-clickhouse:
image: mcp/clickhouse
container_name: mcp-clickhouse
ports:
- 8001:8000
extra_hosts:
- "host.docker.internal:host-gateway"
environment:
- CLICKHOUSE_HOST=<CLICKHOUSE_HOST>
- CLICKHOUSE_USER=<CLICKHOUSE_USER>
- CLICKHOUSE_PASSWORD=<CLICKHOUSE_PASSWORD>
- CLICKHOUSE_MCP_SERVER_TRANSPORT=sse
- CLICKHOUSE_MCP_BIND_HOST=0.0.0.0
We also register the ClickHouse MCP server in librechat.yaml to run on port 8001:
mcpServers:
clickhouse-playground:
type: sse
url: http://host.docker.internal:8001/sse
2.1.2 Create the forecasting MCP server¶
After that, we create the forecasting MCP server using the FastMCP library.
The server exposes a generate_forecasts tool that takes a list of historical values, a prediction length, and a
list of quantile levels, and returns probabilistic time series forecasts by invoking the Chronos endpoint
via boto3. For instructions on deploying Chronos on Bedrock, we refer to
our previous blog post.
We configure the forecasting MCP server in the docker-compose.override.yml file
that we previously created for configuring the ClickHouse MCP server:
services:
<clickhouse-mcp-configuration> # Added in Section 2.1.1
chronos-forecasting:
build:
context: ./chronos-forecasting
ports:
- "8002:8002"
environment:
- AWS_DEFAULT_REGION=eu-west-1
- AWS_ACCESS_KEY_ID=<AWS_ACCESS_KEY_ID>
- AWS_SECRET_ACCESS_KEY=<AWS_SECRET_ACCESS_KEY>
We also register the forecasting MCP server in librechat.yaml to run on port 8002:
mcpServers:
<clickhouse-mcp-server> # Added in Section 2.1.1
chronos-forecasting:
type: sse
url: http://host.docker.internal:8002/sse
The code used for building the Docker image of the forecasting MCP server is reported below.
server.py
import json
import boto3
from mcp.server.fastmcp import FastMCP
# Create the FastMCP server
mcp = FastMCP(
name="chronos-forecasting",
host="0.0.0.0",
port=8002
)
# Register the tool with the FastMCP server
@mcp.tool()
def generate_forecasts(
target: list[float],
prediction_length: int,
quantile_levels: list[float]
) -> dict:
"""
Generate probabilistic time series forecasts using Chronos on Amazon Bedrock.
Parameters:
===============================================================================
target: list of float.
The historical time series values used as context.
prediction_length: int.
The number of future time steps to predict.
quantile_levels: list of float.
The quantiles to be predicted at each future time step.
Returns:
===============================================================================
dict
Dictionary with predicted mean and quantiles at each future time step.
"""
# Create the Bedrock client
bedrock_runtime_client = boto3.client("bedrock-runtime")
# Invoke the Bedrock endpoint
response = bedrock_runtime_client.invoke_model(
modelId="<bedrock-endpoint-arn>",
body=json.dumps({
"inputs": [{
"target": target
}],
"parameters": {
"prediction_length": prediction_length,
"quantile_levels": quantile_levels
}
})
)
# Extract the forecasts
forecasts = json.loads(response["body"].read()).get("predictions")[0]
# Return the forecasts
return forecasts
# Run the FastMCP server with SSE transport
if __name__ == "__main__":
mcp.run(transport="sse")
requirements.txt
mcp
boto3
Dockerfile
FROM python:3.12-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY server.py .
CMD ["python", "server.py"]
2.1.3 Create the data visualization MCP server¶
The data visualization MCP server exposes a visualize_data tool that generates interactive Plotly charts
from historical data and forecast outputs. Charts are saved as self-contained HTML files and served over HTTP
on port 8004. The tool returns the URL of the interactive HTML chart, that LibreChat renders directly in the
Artifacts panel.
Note
The data visualization MCP server is not strictly necessary, as the language model can generate the charts directly. However, a dedicated server ensures consistent styling and reproducible outputs, which cannot be guaranteed when the language model generates the charts on its own. This is particularly desirable when using the assistant for reporting purposes.
Like the forecasting server, the data visualization server is built using FastMCP.
As we did for the forecasting server, we configure it in docker-compose.override.yml:
services:
<clickhouse-mcp-configuration> # Added in Section 2.1.1
<forecasting-mcp-configuration> # Added in Section 2.1.2
data-visualization:
build:
context: ./data-visualization
ports:
- "8003:8003"
- "8004:8004"
volumes:
- ./plots:/plots
We also register the data visualization MCP server in librechat.yaml to run on port 8003:
mcpServers:
<clickhouse-mcp-server> # Added in Section 2.1.1
<forecasting-mcp-server> # Added in Section 2.1.2
data-visualization:
type: sse
url: http://host.docker.internal:8003/sse
The code used for building the Docker image of the data visualization MCP server is reported below.
server.py
import os
import uuid
import threading
import http.server
import functools
import plotly.graph_objects as go
from plotly.subplots import make_subplots
from mcp.server.fastmcp import FastMCP
# Create the FastMCP server
mcp = FastMCP(
name="data-visualization",
host="0.0.0.0",
port=8003
)
# Register the tool with the FastMCP server
@mcp.tool()
def visualize_data(
inputs: dict
) -> str:
"""
Plot one or more time series with optional forecasts and return
the URL of the interactive HTML chart.
Parameters
===============================================================================
inputs : dict
A dictionary with the following keys:
"data" (required) : dict
A dictionary where each key is a series name and each value is the
raw output of a ClickHouse query, with the following fields:
- "columns" : list of strings, must contain "timestamp" and one value column
- "rows" : list of [timestamp_str, float] pairs
Example:
{
"series_1": {
"columns": ["timestamp", "<VALUE>"],
"rows": [
["2026-01-01", 1.0],
["2026-01-02", 2.0]
]
},
"series_2": {
"columns": ["timestamp", "<VALUE>"],
"rows": [
["2026-01-03", 3.0],
["2026-01-04", 4.0]
]
},
}
"forecasts" (optional) : dict
Forecasts for the same time series in "data". Each key is a series
name matching a key in "data", and each value is a dictionary with
the following fields:
- "timestamp" : list of strings representing datetimes
- "mean" : list of floats (mean forecast)
- "<quantile>" : list of floats for each quantile level, e.g.
"0.05" and "0.95" for a 90% prediction interval.
Example:
{
"series_1": {
"timestamp": ["2026-01-01", "2026-01-02"],
"mean": [1.0, 2.0],
"0.1": [0.5, 1.5],
"0.5": [1.0, 2.0],
"0.9": [1.5, 2.5],
},
"series_2": {
"timestamp": ["2026-01-03", "2026-01-04"],
"mean": [3.0, 4.0],
"0.1": [2.5, 3.5],
"0.5": [3.0, 4.0],
"0.9": [3.5, 4.5],
},
}
Returns
===============================================================================
str
The URL of the interactive HTML chart.
"""
# Extract the data and forecasts
data = inputs["data"]
forecasts = inputs.get("forecasts", {})
# Parse the data
parsed_data = {}
for series, query_result in data.items():
value_col = [c for c in query_result["columns"] if c != "timestamp"][0]
idx = query_result["columns"].index
parsed_data[series] = {
"timestamp": [row[idx("timestamp")] for row in query_result["rows"]],
"values": [row[idx(value_col)] for row in query_result["rows"]]
}
# Create the figure
fig = make_subplots(
rows=len(data),
subplot_titles=list(data.keys())
)
# Update the figure layout
fig.update_layout(
height=250 * len(data),
paper_bgcolor="white",
plot_bgcolor="white",
margin=dict(t=50, b=50, l=50, r=50),
hovermode="x unified",
hoverlabel=dict(
namelength=-1
),
legend=dict(
font=dict(
color="#24292f",
size=12
),
)
)
# Update the subplots titles
fig.update_annotations(
font=dict(
color="#24292f",
size=14
),
)
# Generate the subplots
for i, series in enumerate(data):
# Plot the forecasts
if series in forecasts:
# Extract the predicted quantiles
q = sorted([float(k) for k in forecasts[series] if k not in ("mean", "timestamp")])
# Extract the lower and upper bound of the prediction interval
q_min, q_max = q[0], q[-1]
# Plot the upper bound of the prediction interval
fig.add_trace(
go.Scatter(
x=forecasts[series]["timestamp"],
y=forecasts[series][str(q_max)],
name=f"Predicted Q{q_max:,.1%}",
hovertemplate="%{fullData.name}: %{y:,.0f}<extra></extra>",
showlegend=False,
mode="lines",
line=dict(
width=0.5,
color="#c2e5ff",
),
),
row=i + 1,
col=1
)
# Plot the lower bound of the prediction interval
fig.add_trace(
go.Scatter(
x=forecasts[series]["timestamp"],
y=forecasts[series][str(q_min)],
name=f"Predicted Q{q_min:,.1%}",
hovertemplate="%{fullData.name}: %{y:,.0f}<extra></extra>",
showlegend=False,
mode="lines",
line=dict(
width=0.5,
color="#c2e5ff",
),
fillcolor="#c2e5ff",
fill="tonexty",
),
row=i + 1,
col=1
)
# Plot the predicted median if available, otherwise fall back to the predicted mean
fig.add_trace(
go.Scatter(
x=forecasts[series]["timestamp"],
y=forecasts[series]["0.5" if 0.5 in q else "mean"],
name=f"Predicted {'Median' if 0.5 in q else 'Mean'}",
hovertemplate="%{fullData.name}: %{y:,.0f}<extra></extra>",
showlegend=i == 0,
mode="lines",
line=dict(
color="#0588f0",
width=1,
dash="dot"
)
),
row=i + 1,
col=1
)
# Plot the data
fig.add_trace(
go.Scatter(
x=parsed_data[series]["timestamp"],
y=parsed_data[series]["values"],
name="Historical Data",
hovertemplate="%{fullData.name}: %{y:,.0f}<extra></extra>",
mode="lines",
showlegend=i == 0,
line=dict(
color="#838383",
width=1
)
),
row=i + 1,
col=1
)
# Update the subplot's x-axis
fig.update_xaxes(
type="date",
tickformat="%b %d %Y<br>(%a) %H:%M",
tickangle=0,
mirror=True,
linecolor="#cecece",
gridcolor="#e8e8e8",
gridwidth=0.5,
tickfont=dict(
color="#24292f",
size=10
),
row=i + 1,
col=1
)
# Update the subplot's y-axis
fig.update_yaxes(
tickformat=",.0f",
mirror=True,
linecolor="#cecece",
gridcolor="#e8e8e8",
gridwidth=0.5,
tickfont=dict(
color="#24292f",
size=10
),
row=i + 1,
col=1
)
# Save the figure to an HTML file
os.makedirs("/plots", exist_ok=True)
filename = f"plot_{uuid.uuid4().hex}.html"
fig.write_html(f"/plots/{filename}", full_html=True, include_plotlyjs="cdn")
# Return the URL of the HTML file
return f"http://localhost:8004/{filename}"
if __name__ == "__main__":
# Serve the /plots directory over HTTP on port 8004
def _serve_plots():
handler = functools.partial(http.server.SimpleHTTPRequestHandler, directory="/plots")
with http.server.HTTPServer(("0.0.0.0", 8004), handler) as httpd:
httpd.serve_forever()
# Start the HTTP server
threading.Thread(target=_serve_plots, daemon=True).start()
# Run the FastMCP server with SSE transport
mcp.run(transport="sse")
requirements.txt
mcp
plotly
Dockerfile
FROM python:3.12-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY server.py .
CMD ["python", "server.py"]
2.2 Configure the assistant¶
Finally, we configure the assistant in librechat.yaml using a
LibreChat modelSpecs object
that combines the Bedrock model, the three MCP servers, and a system prompt.
modelSpecs:
list:
- name: "forecasting-assistant"
label: "Forecasting Assistant"
default: true
artifacts: true
mcpServers:
- "clickhouse-playground"
- "chronos-forecasting"
- "data-visualization"
preset:
endpoint: "bedrock"
model: "eu.anthropic.claude-sonnet-4-6"
region: "eu-west-1"
promptPrefix: |
You are a time series forecasting assistant.
Do not alter the time frequency of the data unless the user explicitly requests it.
To visualize data, always use the `visualize_data` tool. Never write code to generate plots.
When visualizing multiple series, always pass them together to the `visualize_data` tool in a single call,
as it generates subplots automatically.
Always render the URL returned by the `visualize_data` tool as an artifact using this exact format:
:::artifact{identifier="<IDENTIFIER>" type="text/html" title="<TITLE>"}
\`\`\`
<!DOCTYPE html>
<html>
<body>
<iframe src="<URL>" width="100%" height="800px" frameborder="0"></iframe>
</body>
</html>
\`\`\`
:::
Never return the raw URL and never ask the user to open the URL themselves.
2.3 Chat with the assistant¶
To demonstrate a typical interaction, we walk through a short conversation with the assistant covering data exploration, visualization, and forecasting. We start by asking which time series are available in the database, then request a plot of Product A’s hourly sales over the most recent week, use that data as context to forecast the next 48 hours, and finally repeat the analysis for Products B and C, visualizing all three series and their forecasts in a single chart.
User
What can you help me with?
Assistant
Thoughts
The user is asking what I can help them with. I should explain my capabilities as a time series forecasting assistant.
I'm a time series forecasting assistant with the ability to help you with the following:
📊 Data Exploration
- Browse databases and tables in ClickHouse to help you find relevant data
- Query and summarize time series data (e.g., sales, metrics, sensor readings, etc.)
🔮 Forecasting
- Generate probabilistic forecasts using Chronos, a state-of-the-art AI forecasting model
- Predict future values for any time series you have stored or provide
- Produce quantile forecasts (e.g., 10th–90th percentile) to understand uncertainty and risk
📈 Visualization
- Plot historical time series data interactively
- Overlay forecasts with confidence intervals on top of historical data
- Visualize multiple series side by side for comparison
💡 Example Use Cases
- "Show me the available tables in my database"
- "Plot the daily sales for the last 6 months"
- "Forecast the next 30 days of website traffic with a 90% confidence interval"
- "Compare actual vs. forecasted revenue for multiple products"
To get started, you can ask me to explore your data, run a query, or generate a forecast. What would you like to do?
User
Which time series do we have in the database?
Assistant
Thoughts
The user wants to know what time series data is available in the database. Let me start by listing the databases, then explore the tables within them.
Let me start by exploring the available databases!
Ran list_databases
Assistant sent this info to clickhouse-playground
{}
Result
[
"INFORMATION_SCHEMA",
"default",
"information_schema",
"system"
]
Ran list_tables
Assistant sent this info to clickhouse-playground
{
"database": "default"
}
Result
[
{
"database": "default",
"name": "products",
"engine": "SharedMergeTree",
"create_table_query": "CREATE TABLE default.products (`product_id` Int32, `product_name` String) ENGINE = SharedMergeTree('/clickhouse/tables/{uuid}/{shard}', '{replica}') ORDER BY product_id SETTINGS index_granularity = 8192",
"dependencies_database": [],
"dependencies_table": [],
"engine_full": "SharedMergeTree('/clickhouse/tables/{uuid}/{shard}', '{replica}') ORDER BY product_id SETTINGS index_granularity = 8192",
"sorting_key": "product_id",
"primary_key": "product_id",
"total_rows": 3,
"total_bytes": 373,
"total_bytes_uncompressed": 130,
"parts": 1,
"active_parts": 1,
"total_marks": 2,
"comment": "",
"columns": [
{
"database": "default",
"table": "products",
"name": "product_id",
"column_type": "Int32",
"default_kind": "",
"default_expression": "",
"comment": ""
},
{
"database": "default",
"table": "products",
"name": "product_name",
"column_type": "String",
"default_kind": "",
"default_expression": "",
"comment": ""
}
]
},
{
"database": "default",
"name": "sales",
"engine": "SharedMergeTree",
"create_table_query": "CREATE TABLE default.sales (`timestamp` DateTime64(3), `product_id` Int32, `units_sold` Int32) ENGINE = SharedMergeTree('/clickhouse/tables/{uuid}/{shard}', '{replica}') ORDER BY timestamp SETTINGS index_granularity = 8192",
"dependencies_database": [],
"dependencies_table": [],
"engine_full": "SharedMergeTree('/clickhouse/tables/{uuid}/{shard}', '{replica}') ORDER BY timestamp SETTINGS index_granularity = 8192",
"sorting_key": "timestamp",
"primary_key": "timestamp",
"total_rows": 6480,
"total_bytes": 13825,
"total_bytes_uncompressed": 103808,
"parts": 1,
"active_parts": 1,
"total_marks": 2,
"comment": "",
"columns": [
{
"database": "default",
"table": "sales",
"name": "timestamp",
"column_type": "DateTime64(3)",
"default_kind": "",
"default_expression": "",
"comment": ""
},
{
"database": "default",
"table": "sales",
"name": "product_id",
"column_type": "Int32",
"default_kind": "",
"default_expression": "",
"comment": ""
},
{
"database": "default",
"table": "sales",
"name": "units_sold",
"column_type": "Int32",
"default_kind": "",
"default_expression": "",
"comment": ""
}
]
}
]
Ran select_query
Assistant sent this info to clickhouse-playground
{
"query": "SELECT * FROM default.products"
}
Result
{
"columns": [
"product_id",
"product_name"
],
"rows": [
[
1,
"Product A"
],
[
2,
"Product B"
],
[
3,
"Product C"
]
]
}
Ran select_query
Assistant sent this info to clickhouse-playground
{
"query": "\nSELECT \n min(timestamp) AS start_date,\n max(timestamp) AS end_date,\n count() AS total_rows\nFROM default.sales\n"
}
Result
{
"columns": [
"start_date",
"end_date",
"total_rows"
],
"rows": [
[
"2025-12-15T16:00:00",
"2026-03-15T15:00:00",
6480
]
]
}
Here's what we have in the database:
📦 Tables in the default database
1. sales — Main time series table
- Timestamp range: Dec 15, 2025 → Mar 15, 2026 (~3 months)
- Total rows: 6,480
- Columns:
timestamp(DateTime) — time of the observationproduct_id(Int32) — links to the products tableunits_sold(Int32) — the time series value
2. products — Dimension/lookup table
- 3 products:
- Product A (id: 1)
- Product B (id: 2)
- Product C (id: 3)
🔍 Summary
You have 3 time series — one per product — tracking daily (or sub-daily) units sold over roughly 3 months.
Would you like me to:
- 📈 Visualize the sales for one or all products?
- 🔮 Forecast future sales for any product?
- 🔎 Explore the data in more detail (e.g., frequency, trends)?
User
Can we plot the time series of Product A over the most recent week?
Assistant
Thoughts
The user wants to plot the time series of Product A over the most recent week. Let me query the sales data for Product A over the most recent week. The data ends at 2026-03-15, so the most recent week would be from 2026-03-08 to 2026-03-15. Let me query accordingly.
Sure! Let me first query the data for Product A over the most recent week.
Ran select_query
Assistant sent this info to clickhouse-playground
{
"query": "\nSELECT timestamp, units_sold\nFROM default.sales\nWHERE product_id = 1\n AND timestamp >= (SELECT max(timestamp) - INTERVAL 7 DAY FROM default.sales)\nORDER BY timestamp ASC\n"
}
Result
{
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
21
],
[
"2026-03-08T16:00:00",
20
],
[
"2026-03-08T17:00:00",
21
],
[
"2026-03-08T18:00:00",
25
],
[
"2026-03-08T19:00:00",
23
],
[
"2026-03-08T20:00:00",
24
],
[
"2026-03-08T21:00:00",
26
],
[
"2026-03-08T22:00:00",
25
],
[
"2026-03-08T23:00:00",
17
],
[
"2026-03-09T00:00:00",
13
],
[
"2026-03-09T01:00:00",
7
],
[
"2026-03-09T02:00:00",
4
],
[
"2026-03-09T03:00:00",
2
],
[
"2026-03-09T04:00:00",
7
],
[
"2026-03-09T05:00:00",
14
],
[
"2026-03-09T06:00:00",
22
],
[
"2026-03-09T07:00:00",
26
],
[
"2026-03-09T08:00:00",
35
],
[
"2026-03-09T09:00:00",
37
],
[
"2026-03-09T10:00:00",
39
],
[
"2026-03-09T11:00:00",
36
],
[
"2026-03-09T12:00:00",
32
],
[
"2026-03-09T13:00:00",
27
],
[
"2026-03-09T14:00:00",
23
],
[
"2026-03-09T15:00:00",
20
],
[
"2026-03-09T16:00:00",
19
],
[
"2026-03-09T17:00:00",
20
],
[
"2026-03-09T18:00:00",
22
],
[
"2026-03-09T19:00:00",
25
],
[
"2026-03-09T20:00:00",
26
],
[
"2026-03-09T21:00:00",
27
],
[
"2026-03-09T22:00:00",
23
],
[
"2026-03-09T23:00:00",
19
],
[
"2026-03-10T00:00:00",
12
],
[
"2026-03-10T01:00:00",
8
],
[
"2026-03-10T02:00:00",
4
],
[
"2026-03-10T03:00:00",
4
],
[
"2026-03-10T04:00:00",
9
],
[
"2026-03-10T05:00:00",
12
],
[
"2026-03-10T06:00:00",
20
],
[
"2026-03-10T07:00:00",
28
],
[
"2026-03-10T08:00:00",
35
],
[
"2026-03-10T09:00:00",
36
],
[
"2026-03-10T10:00:00",
39
],
[
"2026-03-10T11:00:00",
36
],
[
"2026-03-10T12:00:00",
34
],
[
"2026-03-10T13:00:00",
26
],
[
"2026-03-10T14:00:00",
22
],
[
"2026-03-10T15:00:00",
19
],
[
"2026-03-10T16:00:00",
21
],
[
"2026-03-10T17:00:00",
22
],
[
"2026-03-10T18:00:00",
23
],
[
"2026-03-10T19:00:00",
25
],
[
"2026-03-10T20:00:00",
28
],
[
"2026-03-10T21:00:00",
27
],
[
"2026-03-10T22:00:00",
23
],
[
"2026-03-10T23:00:00",
17
],
[
"2026-03-11T00:00:00",
11
],
[
"2026-03-11T01:00:00",
9
],
[
"2026-03-11T02:00:00",
4
],
[
"2026-03-11T03:00:00",
3
],
[
"2026-03-11T04:00:00",
6
],
[
"2026-03-11T05:00:00",
11
],
[
"2026-03-11T06:00:00",
22
],
[
"2026-03-11T07:00:00",
29
],
[
"2026-03-11T08:00:00",
33
],
[
"2026-03-11T09:00:00",
38
],
[
"2026-03-11T10:00:00",
38
],
[
"2026-03-11T11:00:00",
37
],
[
"2026-03-11T12:00:00",
32
],
[
"2026-03-11T13:00:00",
26
],
[
"2026-03-11T14:00:00",
24
],
[
"2026-03-11T15:00:00",
21
],
[
"2026-03-11T16:00:00",
21
],
[
"2026-03-11T17:00:00",
20
],
[
"2026-03-11T18:00:00",
24
],
[
"2026-03-11T19:00:00",
27
],
[
"2026-03-11T20:00:00",
28
],
[
"2026-03-11T21:00:00",
27
],
[
"2026-03-11T22:00:00",
23
],
[
"2026-03-11T23:00:00",
18
],
[
"2026-03-12T00:00:00",
11
],
[
"2026-03-12T01:00:00",
8
],
[
"2026-03-12T02:00:00",
3
],
[
"2026-03-12T03:00:00",
4
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
13
],
[
"2026-03-12T06:00:00",
19
],
[
"2026-03-12T07:00:00",
29
],
[
"2026-03-12T08:00:00",
34
],
[
"2026-03-12T09:00:00",
41
],
[
"2026-03-12T10:00:00",
38
],
[
"2026-03-12T11:00:00",
37
],
[
"2026-03-12T12:00:00",
31
],
[
"2026-03-12T13:00:00",
29
],
[
"2026-03-12T14:00:00",
26
],
[
"2026-03-12T15:00:00",
21
],
[
"2026-03-12T16:00:00",
19
],
[
"2026-03-12T17:00:00",
21
],
[
"2026-03-12T18:00:00",
22
],
[
"2026-03-12T19:00:00",
25
],
[
"2026-03-12T20:00:00",
26
],
[
"2026-03-12T21:00:00",
25
],
[
"2026-03-12T22:00:00",
21
],
[
"2026-03-12T23:00:00",
17
],
[
"2026-03-13T00:00:00",
15
],
[
"2026-03-13T01:00:00",
6
],
[
"2026-03-13T02:00:00",
4
],
[
"2026-03-13T03:00:00",
6
],
[
"2026-03-13T04:00:00",
7
],
[
"2026-03-13T05:00:00",
13
],
[
"2026-03-13T06:00:00",
21
],
[
"2026-03-13T07:00:00",
27
],
[
"2026-03-13T08:00:00",
33
],
[
"2026-03-13T09:00:00",
38
],
[
"2026-03-13T10:00:00",
38
],
[
"2026-03-13T11:00:00",
36
],
[
"2026-03-13T12:00:00",
33
],
[
"2026-03-13T13:00:00",
25
],
[
"2026-03-13T14:00:00",
23
],
[
"2026-03-13T15:00:00",
21
],
[
"2026-03-13T16:00:00",
20
],
[
"2026-03-13T17:00:00",
23
],
[
"2026-03-13T18:00:00",
23
],
[
"2026-03-13T19:00:00",
26
],
[
"2026-03-13T20:00:00",
28
],
[
"2026-03-13T21:00:00",
25
],
[
"2026-03-13T22:00:00",
21
],
[
"2026-03-13T23:00:00",
17
],
[
"2026-03-14T00:00:00",
12
],
[
"2026-03-14T01:00:00",
7
],
[
"2026-03-14T02:00:00",
4
],
[
"2026-03-14T03:00:00",
4
],
[
"2026-03-14T04:00:00",
7
],
[
"2026-03-14T05:00:00",
11
],
[
"2026-03-14T06:00:00",
21
],
[
"2026-03-14T07:00:00",
29
],
[
"2026-03-14T08:00:00",
33
],
[
"2026-03-14T09:00:00",
38
],
[
"2026-03-14T10:00:00",
39
],
[
"2026-03-14T11:00:00",
37
],
[
"2026-03-14T12:00:00",
31
],
[
"2026-03-14T13:00:00",
26
],
[
"2026-03-14T14:00:00",
24
],
[
"2026-03-14T15:00:00",
20
],
[
"2026-03-14T16:00:00",
20
],
[
"2026-03-14T17:00:00",
22
],
[
"2026-03-14T18:00:00",
24
],
[
"2026-03-14T19:00:00",
26
],
[
"2026-03-14T20:00:00",
26
],
[
"2026-03-14T21:00:00",
27
],
[
"2026-03-14T22:00:00",
23
],
[
"2026-03-14T23:00:00",
18
],
[
"2026-03-15T00:00:00",
13
],
[
"2026-03-15T01:00:00",
10
],
[
"2026-03-15T02:00:00",
4
],
[
"2026-03-15T03:00:00",
3
],
[
"2026-03-15T04:00:00",
7
],
[
"2026-03-15T05:00:00",
14
],
[
"2026-03-15T06:00:00",
20
],
[
"2026-03-15T07:00:00",
29
],
[
"2026-03-15T08:00:00",
34
],
[
"2026-03-15T09:00:00",
39
],
[
"2026-03-15T10:00:00",
38
],
[
"2026-03-15T11:00:00",
37
],
[
"2026-03-15T12:00:00",
32
],
[
"2026-03-15T13:00:00",
26
],
[
"2026-03-15T14:00:00",
23
],
[
"2026-03-15T15:00:00",
21
]
]
}
Now let me visualize it!
Ran visualize_data
Assistant sent this info to data-visualization
{
"inputs": {
"data": {
"Product A - Units Sold": {
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
21
],
[
"2026-03-08T16:00:00",
20
],
[
"2026-03-08T17:00:00",
21
],
[
"2026-03-08T18:00:00",
25
],
[
"2026-03-08T19:00:00",
23
],
[
"2026-03-08T20:00:00",
24
],
[
"2026-03-08T21:00:00",
26
],
[
"2026-03-08T22:00:00",
25
],
[
"2026-03-08T23:00:00",
17
],
[
"2026-03-09T00:00:00",
13
],
[
"2026-03-09T01:00:00",
7
],
[
"2026-03-09T02:00:00",
4
],
[
"2026-03-09T03:00:00",
2
],
[
"2026-03-09T04:00:00",
7
],
[
"2026-03-09T05:00:00",
14
],
[
"2026-03-09T06:00:00",
22
],
[
"2026-03-09T07:00:00",
26
],
[
"2026-03-09T08:00:00",
35
],
[
"2026-03-09T09:00:00",
37
],
[
"2026-03-09T10:00:00",
39
],
[
"2026-03-09T11:00:00",
36
],
[
"2026-03-09T12:00:00",
32
],
[
"2026-03-09T13:00:00",
27
],
[
"2026-03-09T14:00:00",
23
],
[
"2026-03-09T15:00:00",
20
],
[
"2026-03-09T16:00:00",
19
],
[
"2026-03-09T17:00:00",
20
],
[
"2026-03-09T18:00:00",
22
],
[
"2026-03-09T19:00:00",
25
],
[
"2026-03-09T20:00:00",
26
],
[
"2026-03-09T21:00:00",
27
],
[
"2026-03-09T22:00:00",
23
],
[
"2026-03-09T23:00:00",
19
],
[
"2026-03-10T00:00:00",
12
],
[
"2026-03-10T01:00:00",
8
],
[
"2026-03-10T02:00:00",
4
],
[
"2026-03-10T03:00:00",
4
],
[
"2026-03-10T04:00:00",
9
],
[
"2026-03-10T05:00:00",
12
],
[
"2026-03-10T06:00:00",
20
],
[
"2026-03-10T07:00:00",
28
],
[
"2026-03-10T08:00:00",
35
],
[
"2026-03-10T09:00:00",
36
],
[
"2026-03-10T10:00:00",
39
],
[
"2026-03-10T11:00:00",
36
],
[
"2026-03-10T12:00:00",
34
],
[
"2026-03-10T13:00:00",
26
],
[
"2026-03-10T14:00:00",
22
],
[
"2026-03-10T15:00:00",
19
],
[
"2026-03-10T16:00:00",
21
],
[
"2026-03-10T17:00:00",
22
],
[
"2026-03-10T18:00:00",
23
],
[
"2026-03-10T19:00:00",
25
],
[
"2026-03-10T20:00:00",
28
],
[
"2026-03-10T21:00:00",
27
],
[
"2026-03-10T22:00:00",
23
],
[
"2026-03-10T23:00:00",
17
],
[
"2026-03-11T00:00:00",
11
],
[
"2026-03-11T01:00:00",
9
],
[
"2026-03-11T02:00:00",
4
],
[
"2026-03-11T03:00:00",
3
],
[
"2026-03-11T04:00:00",
6
],
[
"2026-03-11T05:00:00",
11
],
[
"2026-03-11T06:00:00",
22
],
[
"2026-03-11T07:00:00",
29
],
[
"2026-03-11T08:00:00",
33
],
[
"2026-03-11T09:00:00",
38
],
[
"2026-03-11T10:00:00",
38
],
[
"2026-03-11T11:00:00",
37
],
[
"2026-03-11T12:00:00",
32
],
[
"2026-03-11T13:00:00",
26
],
[
"2026-03-11T14:00:00",
24
],
[
"2026-03-11T15:00:00",
21
],
[
"2026-03-11T16:00:00",
21
],
[
"2026-03-11T17:00:00",
20
],
[
"2026-03-11T18:00:00",
24
],
[
"2026-03-11T19:00:00",
27
],
[
"2026-03-11T20:00:00",
28
],
[
"2026-03-11T21:00:00",
27
],
[
"2026-03-11T22:00:00",
23
],
[
"2026-03-11T23:00:00",
18
],
[
"2026-03-12T00:00:00",
11
],
[
"2026-03-12T01:00:00",
8
],
[
"2026-03-12T02:00:00",
3
],
[
"2026-03-12T03:00:00",
4
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
13
],
[
"2026-03-12T06:00:00",
19
],
[
"2026-03-12T07:00:00",
29
],
[
"2026-03-12T08:00:00",
34
],
[
"2026-03-12T09:00:00",
41
],
[
"2026-03-12T10:00:00",
38
],
[
"2026-03-12T11:00:00",
37
],
[
"2026-03-12T12:00:00",
31
],
[
"2026-03-12T13:00:00",
29
],
[
"2026-03-12T14:00:00",
26
],
[
"2026-03-12T15:00:00",
21
],
[
"2026-03-12T16:00:00",
19
],
[
"2026-03-12T17:00:00",
21
],
[
"2026-03-12T18:00:00",
22
],
[
"2026-03-12T19:00:00",
25
],
[
"2026-03-12T20:00:00",
26
],
[
"2026-03-12T21:00:00",
25
],
[
"2026-03-12T22:00:00",
21
],
[
"2026-03-12T23:00:00",
17
],
[
"2026-03-13T00:00:00",
15
],
[
"2026-03-13T01:00:00",
6
],
[
"2026-03-13T02:00:00",
4
],
[
"2026-03-13T03:00:00",
6
],
[
"2026-03-13T04:00:00",
7
],
[
"2026-03-13T05:00:00",
13
],
[
"2026-03-13T06:00:00",
21
],
[
"2026-03-13T07:00:00",
27
],
[
"2026-03-13T08:00:00",
33
],
[
"2026-03-13T09:00:00",
38
],
[
"2026-03-13T10:00:00",
38
],
[
"2026-03-13T11:00:00",
36
],
[
"2026-03-13T12:00:00",
33
],
[
"2026-03-13T13:00:00",
25
],
[
"2026-03-13T14:00:00",
23
],
[
"2026-03-13T15:00:00",
21
],
[
"2026-03-13T16:00:00",
20
],
[
"2026-03-13T17:00:00",
23
],
[
"2026-03-13T18:00:00",
23
],
[
"2026-03-13T19:00:00",
26
],
[
"2026-03-13T20:00:00",
28
],
[
"2026-03-13T21:00:00",
25
],
[
"2026-03-13T22:00:00",
21
],
[
"2026-03-13T23:00:00",
17
],
[
"2026-03-14T00:00:00",
12
],
[
"2026-03-14T01:00:00",
7
],
[
"2026-03-14T02:00:00",
4
],
[
"2026-03-14T03:00:00",
4
],
[
"2026-03-14T04:00:00",
7
],
[
"2026-03-14T05:00:00",
11
],
[
"2026-03-14T06:00:00",
21
],
[
"2026-03-14T07:00:00",
29
],
[
"2026-03-14T08:00:00",
33
],
[
"2026-03-14T09:00:00",
38
],
[
"2026-03-14T10:00:00",
39
],
[
"2026-03-14T11:00:00",
37
],
[
"2026-03-14T12:00:00",
31
],
[
"2026-03-14T13:00:00",
26
],
[
"2026-03-14T14:00:00",
24
],
[
"2026-03-14T15:00:00",
20
],
[
"2026-03-14T16:00:00",
20
],
[
"2026-03-14T17:00:00",
22
],
[
"2026-03-14T18:00:00",
24
],
[
"2026-03-14T19:00:00",
26
],
[
"2026-03-14T20:00:00",
26
],
[
"2026-03-14T21:00:00",
27
],
[
"2026-03-14T22:00:00",
23
],
[
"2026-03-14T23:00:00",
18
],
[
"2026-03-15T00:00:00",
13
],
[
"2026-03-15T01:00:00",
10
],
[
"2026-03-15T02:00:00",
4
],
[
"2026-03-15T03:00:00",
3
],
[
"2026-03-15T04:00:00",
7
],
[
"2026-03-15T05:00:00",
14
],
[
"2026-03-15T06:00:00",
20
],
[
"2026-03-15T07:00:00",
29
],
[
"2026-03-15T08:00:00",
34
],
[
"2026-03-15T09:00:00",
39
],
[
"2026-03-15T10:00:00",
38
],
[
"2026-03-15T11:00:00",
37
],
[
"2026-03-15T12:00:00",
32
],
[
"2026-03-15T13:00:00",
26
],
[
"2026-03-15T14:00:00",
23
],
[
"2026-03-15T15:00:00",
21
]
]
}
}
}
}
Result
{
"columns": [
"product_id",
"product_name"
],
"rows": [
[
1,
"Product A"
],
[
2,
"Product B"
],
[
3,
"Product C"
]
]
}
Result
http://localhost:8004/plot_28706dcf80a5404fa8cf6cdc017c8152.html
Here's the hourly sales chart for Product A over the most recent week (Mar 8–15, 2026). A few observations:
- 📉 Daily trough: Sales consistently drop to very low values (2–4 units) in the early morning hours (2:00–4:00 AM)
- 📈 Daily peak: Sales peak around 9:00–10:00 AM, reaching up to ~38–41 units
- 🔄 Strong daily seasonality: The pattern repeats very consistently each day, suggesting a clear intraday cycle
- 📊 Stable trend: There's no obvious upward or downward trend over the week — sales levels look steady
Would you like me to forecast the next few days for Product A, or explore the other products as well?
User
Can we now use this data as input to forecast the subsequent 2 days?
Assistant
Thoughts
The user wants to forecast the next 2 days (48 hours) for Product A using the data we already queried. The data is hourly, so 2 days = 48 time steps. I need to: 1. Call generate_forecasts with the historical data as target, prediction_length=48, and some quantile levels 2. Then visualize the results with the forecast overlaid Let me prepare the target array from the query results we already have. The rows are hourly data from 2026-03-08T15:00:00 to 2026-03-15T15:00:00. Let me extract the values: [21,20,21,25,23,24,26,25,17,13,7,4,2,7,14,22,26,35,37,39,36,32,27,23,20,19,20,22,25,26,27,23,19,12,8,4,4,9,12,20,28,35,36,39,36,34,26,22,19,21,22,23,25,28,27,23,17,11,9,4,3,6,11,22,29,33,38,38,37,32,26,24,21,21,20,24,27,28,27,23,18,11,8,3,4,7,13,19,29,34,41,38,37,31,29,26,21,19,21,22,25,26,25,21,17,15,6,4,6,7,13,21,27,33,38,38,36,33,25,23,21,20,23,23,26,28] Now I'm setting up the forecast parameters with the last observation at 2026-03-15T15:00:00, which means the 48-hour forecast will run from 2026-03-15T16:00:00 through 2026-03-17T15:00:00. I'm using quantile levels at 0.1, 0.5, and 0.9 to generate an 80% prediction interval.
I'll use the hourly data we already retrieved as input to Chronos and forecast the next 48 hours (2 days)!
Ran generate_forecasts
Assistant sent this info to chronos-forecasting
{
"target": [
21,
20,
21,
25,
23,
24,
26,
25,
17,
13,
7,
4,
2,
7,
14,
22,
26,
35,
37,
39,
36,
32,
27,
23,
20,
19,
20,
22,
25,
26,
27,
23,
19,
12,
8,
4,
4,
9,
12,
20,
28,
35,
36,
39,
36,
34,
26,
22,
19,
21,
22,
23,
25,
28,
27,
23,
17,
11,
9,
4,
3,
6,
11,
22,
29,
33,
38,
38,
37,
32,
26,
24,
21,
21,
20,
24,
27,
28,
27,
23,
18,
11,
8,
3,
4,
7,
13,
19,
29,
34,
41,
38,
37,
31,
29,
26,
21,
19,
21,
22,
25,
26,
25,
21,
17,
15,
6,
4,
6,
7,
13,
21,
27,
33,
38,
38,
36,
33,
25,
23,
21,
20,
23,
23,
26,
28,
25,
21,
17,
12,
7,
4,
4,
7,
11,
21,
29,
33,
38,
39,
37,
31,
26,
24,
20,
20,
22,
24,
26,
26,
27,
23,
18,
13,
10,
4,
3,
7,
14,
20,
29,
34,
39,
38,
37,
32,
26,
23,
21
],
"prediction_length": 48,
"quantile_levels": [
0.1,
0.5,
0.9
]
}
Result
{
"mean": [
20.504526138305664,
21.805526733398438,
23.69278907775879,
25.529420852661133,
26.827110290527344,
26.324140548706055,
22.897764205932617,
17.852794647216797,
12.321682929992676,
7.192910194396973,
3.9130783081054688,
3.9800643920898438,
7.332183837890625,
12.986684799194336,
20.668590545654297,
27.952547073364258,
33.47609329223633,
38.25192642211914,
38.400447845458984,
36.45668029785156,
31.858444213867188,
26.570825576782227,
23.2839412689209,
20.51091957092285,
20.30457305908203,
21.678436279296875,
23.642099380493164,
25.584678649902344,
26.985809326171875,
26.484193801879883,
23.02522850036621,
18.039037704467773,
12.611462593078613,
7.602766990661621,
4.303823471069336,
4.018426895141602,
7.423919677734375,
13.13841438293457,
20.692811965942383,
28.037954330444336,
33.97454071044922,
38.231040954589844,
38.78217697143555,
36.92472457885742,
32.19001388549805,
26.802392959594727,
23.54244041442871,
20.698514938354492
],
"0.1": [
19.15822410583496,
20.50179100036621,
22.401607513427734,
24.21921157836914,
25.45020294189453,
24.837438583374023,
21.506221771240234,
16.50567626953125,
10.83835220336914,
5.582372665405273,
2.285032272338867,
2.251415252685547,
5.641073226928711,
11.404353141784668,
18.795143127441406,
25.81307601928711,
31.14609718322754,
35.49599838256836,
35.904144287109375,
34.05424499511719,
29.796527862548828,
24.967273712158203,
21.782663345336914,
19.394075393676758,
19.236570358276367,
20.604127883911133,
22.458040237426758,
24.36791229248047,
25.4338436126709,
24.74117088317871,
21.389162063598633,
16.495697021484375,
10.960190773010254,
5.869045257568359,
2.5734004974365234,
2.361164093017578,
5.705011367797852,
11.369453430175781,
18.547435760498047,
25.60714340209961,
31.265169143676758,
35.313446044921875,
36.011741638183594,
34.2758674621582,
29.958742141723633,
25.103273391723633,
21.822275161743164,
19.32248306274414
],
"0.5": [
20.504526138305664,
21.805526733398438,
23.69278907775879,
25.529420852661133,
26.827110290527344,
26.324140548706055,
22.897764205932617,
17.852794647216797,
12.321682929992676,
7.192910194396973,
3.9130783081054688,
3.9800643920898438,
7.332183837890625,
12.986684799194336,
20.668590545654297,
27.952547073364258,
33.47609329223633,
38.25192642211914,
38.400447845458984,
36.45668029785156,
31.858444213867188,
26.570825576782227,
23.2839412689209,
20.51091957092285,
20.30457305908203,
21.678436279296875,
23.642099380493164,
25.584678649902344,
26.985809326171875,
26.484193801879883,
23.02522850036621,
18.039037704467773,
12.611462593078613,
7.602766990661621,
4.303823471069336,
4.018426895141602,
7.423919677734375,
13.13841438293457,
20.692811965942383,
28.037954330444336,
33.97454071044922,
38.231040954589844,
38.78217697143555,
36.92472457885742,
32.19001388549805,
26.802392959594727,
23.54244041442871,
20.698514938354492
],
"0.9": [
21.669395446777344,
23.053070068359375,
24.99215316772461,
26.91657066345215,
28.313753128051758,
27.791156768798828,
24.152969360351562,
19.0040283203125,
13.467171669006348,
8.364714622497559,
4.990467071533203,
5.050144195556641,
8.647828102111816,
14.336263656616211,
22.190526962280273,
29.632858276367188,
35.39604949951172,
40.310279846191406,
40.52391815185547,
38.57139587402344,
33.898765563964844,
28.34296226501465,
25.04033088684082,
22.027423858642578,
21.667360305786133,
22.99347686767578,
24.871681213378906,
26.878807067871094,
28.497577667236328,
28.168556213378906,
24.56938934326172,
19.346378326416016,
14.037256240844727,
8.928860664367676,
5.4414215087890625,
5.182031631469727,
8.82529354095459,
14.672514915466309,
22.400375366210938,
29.78118896484375,
35.815494537353516,
40.36121368408203,
40.88827133178711,
39.124969482421875,
34.39842224121094,
28.938234329223633,
25.735769271850586,
22.512235641479492
]
}
Got the forecasts! Now let me visualize the historical data alongside the forecast.
Here's the forecast for Product A for the next 2 days (Mar 15, 16:00 → Mar 17, 15:00), with an 80% prediction interval (shaded band between the 10th and 90th percentiles). Key takeaways:
- 🔄 Strong daily cycle preserved: Chronos has clearly picked up on the intraday seasonality — predicting low sales overnight (2–4 units) and peaks mid-morning (38–41 units)
- 📏 Tight uncertainty bands: The prediction interval is relatively narrow, reflecting the high regularity and consistency of the historical pattern
- 📈 Two full daily cycles forecasted: Both Mar 16 and Mar 17 show the same characteristic shape as past days
Would you like to do the same for Product B or Product C, or extend the forecast horizon further?
User
Can we repeat the same analysis for the remaining products and show all the results in one plot?
Assistant
Thoughts
The user wants to repeat the same analysis for Products B and C, then show all three products (A, B, C) in one plot with their forecasts. Let me: 1. Query the most recent week of data for Products B and C 2. Generate forecasts for Products B and C 3. Visualize all three products together with their forecasts I already have the data for Product A. Let me query B and C first, then generate forecasts for both. Let me query both Products B and C simultaneously.
Sure! Let me first fetch the data for Products B and C simultaneously.
Ran select_query
Assistant sent this info to clickhouse-playground
{
"query": "\nSELECT timestamp, units_sold\nFROM default.sales\nWHERE product_id = 2\n AND timestamp >= (SELECT max(timestamp) - INTERVAL 7 DAY FROM default.sales)\nORDER BY timestamp ASC\n"
}
Result
{
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
44
],
[
"2026-03-08T16:00:00",
41
],
[
"2026-03-08T17:00:00",
47
],
[
"2026-03-08T18:00:00",
37
],
[
"2026-03-08T19:00:00",
39
],
[
"2026-03-08T20:00:00",
32
],
[
"2026-03-08T21:00:00",
22
],
[
"2026-03-08T22:00:00",
20
],
[
"2026-03-08T23:00:00",
17
],
[
"2026-03-09T00:00:00",
11
],
[
"2026-03-09T01:00:00",
14
],
[
"2026-03-09T02:00:00",
7
],
[
"2026-03-09T03:00:00",
3
],
[
"2026-03-09T04:00:00",
6
],
[
"2026-03-09T05:00:00",
7
],
[
"2026-03-09T06:00:00",
11
],
[
"2026-03-09T07:00:00",
17
],
[
"2026-03-09T08:00:00",
18
],
[
"2026-03-09T09:00:00",
21
],
[
"2026-03-09T10:00:00",
30
],
[
"2026-03-09T11:00:00",
35
],
[
"2026-03-09T12:00:00",
38
],
[
"2026-03-09T13:00:00",
41
],
[
"2026-03-09T14:00:00",
46
],
[
"2026-03-09T15:00:00",
47
],
[
"2026-03-09T16:00:00",
43
],
[
"2026-03-09T17:00:00",
41
],
[
"2026-03-09T18:00:00",
39
],
[
"2026-03-09T19:00:00",
33
],
[
"2026-03-09T20:00:00",
33
],
[
"2026-03-09T21:00:00",
26
],
[
"2026-03-09T22:00:00",
20
],
[
"2026-03-09T23:00:00",
17
],
[
"2026-03-10T00:00:00",
7
],
[
"2026-03-10T01:00:00",
9
],
[
"2026-03-10T02:00:00",
11
],
[
"2026-03-10T03:00:00",
7
],
[
"2026-03-10T04:00:00",
4
],
[
"2026-03-10T05:00:00",
9
],
[
"2026-03-10T06:00:00",
11
],
[
"2026-03-10T07:00:00",
15
],
[
"2026-03-10T08:00:00",
18
],
[
"2026-03-10T09:00:00",
24
],
[
"2026-03-10T10:00:00",
29
],
[
"2026-03-10T11:00:00",
39
],
[
"2026-03-10T12:00:00",
42
],
[
"2026-03-10T13:00:00",
42
],
[
"2026-03-10T14:00:00",
46
],
[
"2026-03-10T15:00:00",
42
],
[
"2026-03-10T16:00:00",
45
],
[
"2026-03-10T17:00:00",
46
],
[
"2026-03-10T18:00:00",
39
],
[
"2026-03-10T19:00:00",
37
],
[
"2026-03-10T20:00:00",
32
],
[
"2026-03-10T21:00:00",
27
],
[
"2026-03-10T22:00:00",
21
],
[
"2026-03-10T23:00:00",
15
],
[
"2026-03-11T00:00:00",
12
],
[
"2026-03-11T01:00:00",
9
],
[
"2026-03-11T02:00:00",
6
],
[
"2026-03-11T03:00:00",
7
],
[
"2026-03-11T04:00:00",
6
],
[
"2026-03-11T05:00:00",
9
],
[
"2026-03-11T06:00:00",
12
],
[
"2026-03-11T07:00:00",
16
],
[
"2026-03-11T08:00:00",
22
],
[
"2026-03-11T09:00:00",
26
],
[
"2026-03-11T10:00:00",
30
],
[
"2026-03-11T11:00:00",
33
],
[
"2026-03-11T12:00:00",
34
],
[
"2026-03-11T13:00:00",
40
],
[
"2026-03-11T14:00:00",
42
],
[
"2026-03-11T15:00:00",
44
],
[
"2026-03-11T16:00:00",
48
],
[
"2026-03-11T17:00:00",
42
],
[
"2026-03-11T18:00:00",
39
],
[
"2026-03-11T19:00:00",
36
],
[
"2026-03-11T20:00:00",
28
],
[
"2026-03-11T21:00:00",
27
],
[
"2026-03-11T22:00:00",
19
],
[
"2026-03-11T23:00:00",
16
],
[
"2026-03-12T00:00:00",
8
],
[
"2026-03-12T01:00:00",
10
],
[
"2026-03-12T02:00:00",
5
],
[
"2026-03-12T03:00:00",
3
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
9
],
[
"2026-03-12T06:00:00",
9
],
[
"2026-03-12T07:00:00",
13
],
[
"2026-03-12T08:00:00",
17
],
[
"2026-03-12T09:00:00",
24
],
[
"2026-03-12T10:00:00",
31
],
[
"2026-03-12T11:00:00",
38
],
[
"2026-03-12T12:00:00",
36
],
[
"2026-03-12T13:00:00",
42
],
[
"2026-03-12T14:00:00",
44
],
[
"2026-03-12T15:00:00",
46
],
[
"2026-03-12T16:00:00",
43
],
[
"2026-03-12T17:00:00",
48
],
[
"2026-03-12T18:00:00",
39
],
[
"2026-03-12T19:00:00",
35
],
[
"2026-03-12T20:00:00",
31
],
[
"2026-03-12T21:00:00",
24
],
[
"2026-03-12T22:00:00",
16
],
[
"2026-03-12T23:00:00",
15
],
[
"2026-03-13T00:00:00",
15
],
[
"2026-03-13T01:00:00",
11
],
[
"2026-03-13T02:00:00",
8
],
[
"2026-03-13T03:00:00",
7
],
[
"2026-03-13T04:00:00",
6
],
[
"2026-03-13T05:00:00",
9
],
[
"2026-03-13T06:00:00",
9
],
[
"2026-03-13T07:00:00",
16
],
[
"2026-03-13T08:00:00",
17
],
[
"2026-03-13T09:00:00",
27
],
[
"2026-03-13T10:00:00",
30
],
[
"2026-03-13T11:00:00",
34
],
[
"2026-03-13T12:00:00",
40
],
[
"2026-03-13T13:00:00",
44
],
[
"2026-03-13T14:00:00",
42
],
[
"2026-03-13T15:00:00",
48
],
[
"2026-03-13T16:00:00",
44
],
[
"2026-03-13T17:00:00",
43
],
[
"2026-03-13T18:00:00",
39
],
[
"2026-03-13T19:00:00",
32
],
[
"2026-03-13T20:00:00",
30
],
[
"2026-03-13T21:00:00",
23
],
[
"2026-03-13T22:00:00",
20
],
[
"2026-03-13T23:00:00",
15
],
[
"2026-03-14T00:00:00",
9
],
[
"2026-03-14T01:00:00",
8
],
[
"2026-03-14T02:00:00",
5
],
[
"2026-03-14T03:00:00",
7
],
[
"2026-03-14T04:00:00",
8
],
[
"2026-03-14T05:00:00",
7
],
[
"2026-03-14T06:00:00",
13
],
[
"2026-03-14T07:00:00",
19
],
[
"2026-03-14T08:00:00",
19
],
[
"2026-03-14T09:00:00",
25
],
[
"2026-03-14T10:00:00",
31
],
[
"2026-03-14T11:00:00",
35
],
[
"2026-03-14T12:00:00",
40
],
[
"2026-03-14T13:00:00",
43
],
[
"2026-03-14T14:00:00",
45
],
[
"2026-03-14T15:00:00",
44
],
[
"2026-03-14T16:00:00",
44
],
[
"2026-03-14T17:00:00",
44
],
[
"2026-03-14T18:00:00",
42
],
[
"2026-03-14T19:00:00",
32
],
[
"2026-03-14T20:00:00",
31
],
[
"2026-03-14T21:00:00",
26
],
[
"2026-03-14T22:00:00",
20
],
[
"2026-03-14T23:00:00",
13
],
[
"2026-03-15T00:00:00",
10
],
[
"2026-03-15T01:00:00",
10
],
[
"2026-03-15T02:00:00",
7
],
[
"2026-03-15T03:00:00",
8
],
[
"2026-03-15T04:00:00",
12
],
[
"2026-03-15T05:00:00",
10
],
[
"2026-03-15T06:00:00",
13
],
[
"2026-03-15T07:00:00",
14
],
[
"2026-03-15T08:00:00",
18
],
[
"2026-03-15T09:00:00",
24
],
[
"2026-03-15T10:00:00",
32
],
[
"2026-03-15T11:00:00",
34
],
[
"2026-03-15T12:00:00",
39
],
[
"2026-03-15T13:00:00",
39
],
[
"2026-03-15T14:00:00",
41
],
[
"2026-03-15T15:00:00",
47
]
]
}
Ran select_query
Assistant sent this info to clickhouse-playground
{
"query": "\nSELECT timestamp, units_sold\nFROM default.sales\nWHERE product_id = 3\n AND timestamp >= (SELECT max(timestamp) - INTERVAL 7 DAY FROM default.sales)\nORDER BY timestamp ASC\n"
}
Result
{
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
67
],
[
"2026-03-08T16:00:00",
65
],
[
"2026-03-08T17:00:00",
66
],
[
"2026-03-08T18:00:00",
64
],
[
"2026-03-08T19:00:00",
51
],
[
"2026-03-08T20:00:00",
51
],
[
"2026-03-08T21:00:00",
42
],
[
"2026-03-08T22:00:00",
30
],
[
"2026-03-08T23:00:00",
18
],
[
"2026-03-09T00:00:00",
11
],
[
"2026-03-09T01:00:00",
16
],
[
"2026-03-09T02:00:00",
9
],
[
"2026-03-09T03:00:00",
1
],
[
"2026-03-09T04:00:00",
13
],
[
"2026-03-09T05:00:00",
4
],
[
"2026-03-09T06:00:00",
19
],
[
"2026-03-09T07:00:00",
24
],
[
"2026-03-09T08:00:00",
33
],
[
"2026-03-09T09:00:00",
35
],
[
"2026-03-09T10:00:00",
39
],
[
"2026-03-09T11:00:00",
52
],
[
"2026-03-09T12:00:00",
59
],
[
"2026-03-09T13:00:00",
65
],
[
"2026-03-09T14:00:00",
70
],
[
"2026-03-09T15:00:00",
67
],
[
"2026-03-09T16:00:00",
67
],
[
"2026-03-09T17:00:00",
63
],
[
"2026-03-09T18:00:00",
58
],
[
"2026-03-09T19:00:00",
53
],
[
"2026-03-09T20:00:00",
45
],
[
"2026-03-09T21:00:00",
37
],
[
"2026-03-09T22:00:00",
28
],
[
"2026-03-09T23:00:00",
24
],
[
"2026-03-10T00:00:00",
18
],
[
"2026-03-10T01:00:00",
8
],
[
"2026-03-10T02:00:00",
11
],
[
"2026-03-10T03:00:00",
2
],
[
"2026-03-10T04:00:00",
14
],
[
"2026-03-10T05:00:00",
13
],
[
"2026-03-10T06:00:00",
13
],
[
"2026-03-10T07:00:00",
23
],
[
"2026-03-10T08:00:00",
30
],
[
"2026-03-10T09:00:00",
39
],
[
"2026-03-10T10:00:00",
44
],
[
"2026-03-10T11:00:00",
50
],
[
"2026-03-10T12:00:00",
58
],
[
"2026-03-10T13:00:00",
62
],
[
"2026-03-10T14:00:00",
65
],
[
"2026-03-10T15:00:00",
73
],
[
"2026-03-10T16:00:00",
64
],
[
"2026-03-10T17:00:00",
63
],
[
"2026-03-10T18:00:00",
67
],
[
"2026-03-10T19:00:00",
53
],
[
"2026-03-10T20:00:00",
44
],
[
"2026-03-10T21:00:00",
38
],
[
"2026-03-10T22:00:00",
32
],
[
"2026-03-10T23:00:00",
20
],
[
"2026-03-11T00:00:00",
17
],
[
"2026-03-11T01:00:00",
12
],
[
"2026-03-11T02:00:00",
9
],
[
"2026-03-11T03:00:00",
3
],
[
"2026-03-11T04:00:00",
16
],
[
"2026-03-11T05:00:00",
13
],
[
"2026-03-11T06:00:00",
16
],
[
"2026-03-11T07:00:00",
29
],
[
"2026-03-11T08:00:00",
28
],
[
"2026-03-11T09:00:00",
38
],
[
"2026-03-11T10:00:00",
47
],
[
"2026-03-11T11:00:00",
46
],
[
"2026-03-11T12:00:00",
59
],
[
"2026-03-11T13:00:00",
63
],
[
"2026-03-11T14:00:00",
66
],
[
"2026-03-11T15:00:00",
68
],
[
"2026-03-11T16:00:00",
69
],
[
"2026-03-11T17:00:00",
62
],
[
"2026-03-11T18:00:00",
55
],
[
"2026-03-11T19:00:00",
47
],
[
"2026-03-11T20:00:00",
47
],
[
"2026-03-11T21:00:00",
37
],
[
"2026-03-11T22:00:00",
28
],
[
"2026-03-11T23:00:00",
23
],
[
"2026-03-12T00:00:00",
20
],
[
"2026-03-12T01:00:00",
12
],
[
"2026-03-12T02:00:00",
8
],
[
"2026-03-12T03:00:00",
6
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
13
],
[
"2026-03-12T06:00:00",
18
],
[
"2026-03-12T07:00:00",
18
],
[
"2026-03-12T08:00:00",
26
],
[
"2026-03-12T09:00:00",
40
],
[
"2026-03-12T10:00:00",
44
],
[
"2026-03-12T11:00:00",
52
],
[
"2026-03-12T12:00:00",
60
],
[
"2026-03-12T13:00:00",
64
],
[
"2026-03-12T14:00:00",
65
],
[
"2026-03-12T15:00:00",
67
],
[
"2026-03-12T16:00:00",
64
],
[
"2026-03-12T17:00:00",
68
],
[
"2026-03-12T18:00:00",
57
],
[
"2026-03-12T19:00:00",
55
],
[
"2026-03-12T20:00:00",
50
],
[
"2026-03-12T21:00:00",
36
],
[
"2026-03-12T22:00:00",
28
],
[
"2026-03-12T23:00:00",
21
],
[
"2026-03-13T00:00:00",
16
],
[
"2026-03-13T01:00:00",
16
],
[
"2026-03-13T02:00:00",
13
],
[
"2026-03-13T03:00:00",
6
],
[
"2026-03-13T04:00:00",
9
],
[
"2026-03-13T05:00:00",
14
],
[
"2026-03-13T06:00:00",
18
],
[
"2026-03-13T07:00:00",
22
],
[
"2026-03-13T08:00:00",
26
],
[
"2026-03-13T09:00:00",
36
],
[
"2026-03-13T10:00:00",
48
],
[
"2026-03-13T11:00:00",
53
],
[
"2026-03-13T12:00:00",
59
],
[
"2026-03-13T13:00:00",
64
],
[
"2026-03-13T14:00:00",
70
],
[
"2026-03-13T15:00:00",
70
],
[
"2026-03-13T16:00:00",
72
],
[
"2026-03-13T17:00:00",
62
],
[
"2026-03-13T18:00:00",
61
],
[
"2026-03-13T19:00:00",
52
],
[
"2026-03-13T20:00:00",
41
],
[
"2026-03-13T21:00:00",
35
],
[
"2026-03-13T22:00:00",
29
],
[
"2026-03-13T23:00:00",
22
],
[
"2026-03-14T00:00:00",
19
],
[
"2026-03-14T01:00:00",
7
],
[
"2026-03-14T02:00:00",
9
],
[
"2026-03-14T03:00:00",
8
],
[
"2026-03-14T04:00:00",
5
],
[
"2026-03-14T05:00:00",
19
],
[
"2026-03-14T06:00:00",
16
],
[
"2026-03-14T07:00:00",
20
],
[
"2026-03-14T08:00:00",
25
],
[
"2026-03-14T09:00:00",
36
],
[
"2026-03-14T10:00:00",
48
],
[
"2026-03-14T11:00:00",
55
],
[
"2026-03-14T12:00:00",
57
],
[
"2026-03-14T13:00:00",
58
],
[
"2026-03-14T14:00:00",
68
],
[
"2026-03-14T15:00:00",
70
],
[
"2026-03-14T16:00:00",
65
],
[
"2026-03-14T17:00:00",
61
],
[
"2026-03-14T18:00:00",
55
],
[
"2026-03-14T19:00:00",
52
],
[
"2026-03-14T20:00:00",
41
],
[
"2026-03-14T21:00:00",
34
],
[
"2026-03-14T22:00:00",
30
],
[
"2026-03-14T23:00:00",
24
],
[
"2026-03-15T00:00:00",
21
],
[
"2026-03-15T01:00:00",
15
],
[
"2026-03-15T02:00:00",
5
],
[
"2026-03-15T03:00:00",
9
],
[
"2026-03-15T04:00:00",
9
],
[
"2026-03-15T05:00:00",
14
],
[
"2026-03-15T06:00:00",
19
],
[
"2026-03-15T07:00:00",
28
],
[
"2026-03-15T08:00:00",
31
],
[
"2026-03-15T09:00:00",
41
],
[
"2026-03-15T10:00:00",
50
],
[
"2026-03-15T11:00:00",
51
],
[
"2026-03-15T12:00:00",
64
],
[
"2026-03-15T13:00:00",
67
],
[
"2026-03-15T14:00:00",
69
],
[
"2026-03-15T15:00:00",
68
]
]
}
Got the data for both products! Now let me generate forecasts for Products B and C simultaneously.
Ran generate_forecasts
Assistant sent this info to chronos-forecasting
{
"target": [
44,
41,
47,
37,
39,
32,
22,
20,
17,
11,
14,
7,
3,
6,
7,
11,
17,
18,
21,
30,
35,
38,
41,
46,
47,
43,
41,
39,
33,
33,
26,
20,
17,
7,
9,
11,
7,
4,
9,
11,
15,
18,
24,
29,
39,
42,
42,
46,
42,
45,
46,
39,
37,
32,
27,
21,
15,
12,
9,
6,
7,
6,
9,
12,
16,
22,
26,
30,
33,
34,
40,
42,
44,
48,
42,
39,
36,
28,
27,
19,
16,
8,
10,
5,
3,
7,
9,
9,
13,
17,
24,
31,
38,
36,
42,
44,
46,
43,
48,
39,
35,
31,
24,
16,
15,
15,
11,
8,
7,
6,
9,
9,
16,
17,
27,
30,
34,
40,
44,
42,
48,
44,
43,
39,
32,
30,
23,
20,
15,
9,
8,
5,
7,
8,
7,
13,
19,
19,
25,
31,
35,
40,
43,
45,
44,
44,
44,
42,
32,
31,
26,
20,
13,
10,
10,
7,
8,
12,
10,
13,
14,
18,
24,
32,
34,
39,
39,
41,
47
],
"prediction_length": 48,
"quantile_levels": [
0.1,
0.5,
0.9
]
}
Result
{
"mean": [
45.744361877441406,
44.47789764404297,
39.96786880493164,
34.93931579589844,
30.40752410888672,
25.078933715820312,
19.764469146728516,
15.15910816192627,
11.105031967163086,
9.184202194213867,
7.405527114868164,
6.835023880004883,
7.098142623901367,
8.534454345703125,
11.933398246765137,
16.158313751220703,
19.992860794067383,
25.135028839111328,
30.816650390625,
35.86872863769531,
39.165767669677734,
42.46210479736328,
44.626007080078125,
45.996063232421875,
45.7534065246582,
44.59668731689453,
40.11052703857422,
35.24456787109375,
31.033628463745117,
25.713680267333984,
20.289962768554688,
15.610541343688965,
11.549332618713379,
9.544018745422363,
7.7064056396484375,
6.958499908447266,
7.410867691040039,
9.032258987426758,
12.31091022491455,
16.357358932495117,
20.261585235595703,
25.50418472290039,
31.366159439086914,
36.46283721923828,
39.60572052001953,
42.69723129272461,
44.79161834716797,
46.19174575805664
],
"0.1": [
43.202728271484375,
41.657466888427734,
37.34388732910156,
32.49301528930664,
27.895044326782227,
22.69713592529297,
17.48502540588379,
12.914217948913574,
8.867912292480469,
6.805437088012695,
5.133642196655273,
4.6055755615234375,
4.980224609375,
6.566743850708008,
9.907864570617676,
14.042644500732422,
17.96416664123535,
23.004030227661133,
28.466156005859375,
33.398677825927734,
36.72842788696289,
39.793521881103516,
41.68659973144531,
42.83111572265625,
42.48583984375,
41.06452941894531,
36.83848571777344,
32.41840744018555,
28.241992950439453,
23.26666259765625,
18.005842208862305,
13.322606086730957,
9.245460510253906,
7.142238616943359,
5.440708160400391,
4.845056533813477,
5.325952529907227,
7.058143615722656,
10.134407043457031,
14.08029842376709,
18.03704071044922,
23.15070152282715,
28.727794647216797,
33.606204986572266,
36.765869140625,
39.615299224853516,
41.445343017578125,
42.517974853515625
],
"0.5": [
45.744361877441406,
44.47789764404297,
39.96786880493164,
34.93931579589844,
30.40752410888672,
25.078933715820312,
19.764469146728516,
15.15910816192627,
11.105031967163086,
9.184202194213867,
7.405527114868164,
6.835023880004883,
7.098142623901367,
8.534454345703125,
11.933398246765137,
16.158313751220703,
19.992860794067383,
25.135028839111328,
30.816650390625,
35.86872863769531,
39.165767669677734,
42.46210479736328,
44.626007080078125,
45.996063232421875,
45.7534065246582,
44.59668731689453,
40.11052703857422,
35.24456787109375,
31.033628463745117,
25.713680267333984,
20.289962768554688,
15.610541343688965,
11.549332618713379,
9.544018745422363,
7.7064056396484375,
6.958499908447266,
7.410867691040039,
9.032258987426758,
12.31091022491455,
16.357358932495117,
20.261585235595703,
25.50418472290039,
31.366159439086914,
36.46283721923828,
39.60572052001953,
42.69723129272461,
44.79161834716797,
46.19174575805664
],
"0.9": [
48.60978698730469,
47.43096923828125,
42.79112243652344,
37.6799201965332,
33.3004150390625,
27.90454864501953,
22.537134170532227,
17.90163230895996,
13.724783897399902,
11.975788116455078,
9.977222442626953,
9.093873977661133,
9.463135719299316,
10.984129905700684,
14.422269821166992,
18.565746307373047,
22.39069175720215,
27.66008949279785,
33.55706024169922,
38.70289611816406,
42.075965881347656,
45.412227630615234,
47.52215576171875,
48.96488952636719,
48.8265380859375,
47.848453521728516,
43.23004913330078,
38.305755615234375,
34.17613983154297,
28.809988021850586,
23.35015106201172,
18.584577560424805,
14.49343204498291,
12.689022064208984,
10.720396995544434,
9.662089347839355,
10.225909233093262,
11.88810920715332,
15.130329132080078,
19.02608871459961,
22.825077056884766,
28.250431060791016,
34.244171142578125,
39.468650817871094,
42.69873046875,
45.907142639160156,
47.94013214111328,
49.381919860839844
]
}
Ran generate_forecasts
Assistant sent this info to chronos-forecasting
{
"target": [
67,
65,
66,
64,
51,
51,
42,
30,
18,
11,
16,
9,
1,
13,
4,
19,
24,
33,
35,
39,
52,
59,
65,
70,
67,
67,
63,
58,
53,
45,
37,
28,
24,
18,
8,
11,
2,
14,
13,
13,
23,
30,
39,
44,
50,
58,
62,
65,
73,
64,
63,
67,
53,
44,
38,
32,
20,
17,
12,
9,
3,
16,
13,
16,
29,
28,
38,
47,
46,
59,
63,
66,
68,
69,
62,
55,
47,
47,
37,
28,
23,
20,
12,
8,
6,
7,
13,
18,
18,
26,
40,
44,
52,
60,
64,
65,
67,
64,
68,
57,
55,
50,
36,
28,
21,
16,
16,
13,
6,
9,
14,
18,
22,
26,
36,
48,
53,
59,
64,
70,
70,
72,
62,
61,
52,
41,
35,
29,
22,
19,
7,
9,
8,
5,
19,
16,
20,
25,
36,
48,
55,
57,
58,
68,
70,
65,
61,
55,
52,
41,
34,
30,
24,
21,
15,
5,
9,
9,
14,
19,
28,
31,
41,
50,
51,
64,
67,
69,
68
],
"prediction_length": 48,
"quantile_levels": [
0.1,
0.5,
0.9
]
}
Result
{
"mean": [
68.25753784179688,
64.33294677734375,
58.953407287597656,
52.182167053222656,
44.8023567199707,
36.48902130126953,
29.293916702270508,
23.117162704467773,
18.24557876586914,
12.591239929199219,
9.324899673461914,
7.880804061889648,
10.169549942016602,
14.116628646850586,
18.203784942626953,
24.026535034179688,
30.23114776611328,
38.921058654785156,
47.02241897583008,
53.7126350402832,
60.47807312011719,
64.84934997558594,
68.66142272949219,
70.09188842773438,
68.77432250976562,
64.90254974365234,
59.55329132080078,
52.759666442871094,
45.605072021484375,
37.1990966796875,
29.969520568847656,
23.500141143798828,
18.895471572875977,
13.273134231567383,
9.766721725463867,
7.782873153686523,
10.10135269165039,
14.322179794311523,
18.6790828704834,
24.71501922607422,
31.01270866394043,
39.43730163574219,
47.36338806152344,
54.099761962890625,
61.12646484375,
65.52592468261719,
69.14380645751953,
70.39305114746094
],
"0.1": [
65.0497055053711,
61.02140808105469,
55.667762756347656,
49.130184173583984,
41.937583923339844,
33.930274963378906,
26.850168228149414,
20.65131950378418,
15.420270919799805,
9.610015869140625,
6.014139175415039,
4.563690185546875,
6.7572479248046875,
10.61678695678711,
15.046772003173828,
20.946298599243164,
27.35129737854004,
35.78847122192383,
43.83382034301758,
50.54799270629883,
56.998382568359375,
61.15869140625,
64.4871597290039,
65.62289428710938,
64.30809020996094,
60.597747802734375,
55.28544616699219,
49.05252456665039,
42.306427001953125,
34.51346206665039,
27.43219757080078,
21.02750015258789,
15.994155883789062,
10.284709930419922,
6.550397872924805,
4.792110443115234,
6.905149459838867,
10.953042984008789,
15.455942153930664,
21.445810317993164,
27.832324981689453,
35.966773986816406,
43.770023345947266,
50.32490539550781,
56.82306671142578,
60.98479080200195,
64.19062805175781,
65.11436462402344
],
"0.5": [
68.25753784179688,
64.33294677734375,
58.953407287597656,
52.182167053222656,
44.8023567199707,
36.48902130126953,
29.293916702270508,
23.117162704467773,
18.24557876586914,
12.591239929199219,
9.324899673461914,
7.880804061889648,
10.169549942016602,
14.116628646850586,
18.203784942626953,
24.026535034179688,
30.23114776611328,
38.921058654785156,
47.02241897583008,
53.7126350402832,
60.47807312011719,
64.84934997558594,
68.66142272949219,
70.09188842773438,
68.77432250976562,
64.90254974365234,
59.55329132080078,
52.759666442871094,
45.605072021484375,
37.1990966796875,
29.969520568847656,
23.500141143798828,
18.895471572875977,
13.273134231567383,
9.766721725463867,
7.782873153686523,
10.10135269165039,
14.322179794311523,
18.6790828704834,
24.71501922607422,
31.01270866394043,
39.43730163574219,
47.36338806152344,
54.099761962890625,
61.12646484375,
65.52592468261719,
69.14380645751953,
70.39305114746094
],
"0.9": [
71.67506408691406,
67.64664459228516,
62.195289611816406,
55.31642150878906,
47.960060119628906,
39.451725006103516,
32.17584228515625,
25.903423309326172,
21.21776580810547,
15.803155899047852,
12.547943115234375,
10.65243148803711,
13.38730239868164,
17.783737182617188,
21.71316146850586,
27.42102813720703,
33.64549255371094,
42.66716766357422,
50.950584411621094,
57.488285064697266,
64.4905014038086,
68.61067199707031,
72.39262390136719,
73.94755554199219,
72.77479553222656,
68.87016296386719,
63.50397872924805,
56.57518768310547,
49.40583038330078,
40.81800842285156,
33.40961456298828,
26.681062698364258,
22.37085723876953,
17.016590118408203,
13.691097259521484,
11.294649124145508,
13.996709823608398,
18.501005172729492,
22.67669677734375,
28.56482696533203,
34.7428092956543,
43.582984924316406,
51.486045837402344,
58.23878479003906,
65.67634582519531,
69.92729187011719,
73.41410827636719,
74.68563079833984
]
}
Thoughts
Now I have all the data and forecasts for Products B and C. I also have the data and forecasts for Product A from the previous context. Let me now visualize all three products together with their forecasts. For Product A, I need to use the data and forecast from the previous context: - Data rows from previous context - Forecast from previous context Let me construct the timestamps for the forecasts. The last timestamp in the data is "2026-03-15T15:00:00", so the forecast starts at "2026-03-15T16:00:00" and goes for 48 hours hourly. Let me generate the forecast timestamps: I'm creating the 48-hour forecast timeline starting from 2026-03-15T16:00:00, incrementing by one hour for each step through 2026-03-17T15:00:00. Continuing through the hourly timestamps into mid-March 16th. Continuing through the hourly timestamps into the next day, tracking the progression from early morning through mid-afternoon on March 17th. Now I'm gathering the historical data and forecast values for all three products to pass into the visualization function—I have the actual readings for Product A along with its predicted mean and quantile values across the forecast period. Looking at performance metrics across different product variants and their temperature curves. Now I'm looking at another set of numerical values, likely representing similar measurements or coordinates across a sequence of points. Compiling performance metrics for Product A... I'm continuing to compile the hourly data points for Product A, tracking the values through the night and into the next morning. Continuing through the hourly data for March 10th, tracking the temperature readings as they dip to their lowest point around 4 AM before climbing back up through the morning hours. Generating the time series data... Continuing through the hourly data... Generating time series data... Continuing through the hourly data for March 14th... Now I'm structuring the data object to include all three data series along with their corresponding forecast values for the chart visualization.
Excellent! Now let me put everything together and visualize all three products with their forecasts in one combined plot.
Ran visualize_data
Assistant sent this info to data-visualization
{
"inputs": {
"data": {
"Product A": {
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
21
],
[
"2026-03-08T16:00:00",
20
],
[
"2026-03-08T17:00:00",
21
],
[
"2026-03-08T18:00:00",
25
],
[
"2026-03-08T19:00:00",
23
],
[
"2026-03-08T20:00:00",
24
],
[
"2026-03-08T21:00:00",
26
],
[
"2026-03-08T22:00:00",
25
],
[
"2026-03-08T23:00:00",
17
],
[
"2026-03-09T00:00:00",
13
],
[
"2026-03-09T01:00:00",
7
],
[
"2026-03-09T02:00:00",
4
],
[
"2026-03-09T03:00:00",
2
],
[
"2026-03-09T04:00:00",
7
],
[
"2026-03-09T05:00:00",
14
],
[
"2026-03-09T06:00:00",
22
],
[
"2026-03-09T07:00:00",
26
],
[
"2026-03-09T08:00:00",
35
],
[
"2026-03-09T09:00:00",
37
],
[
"2026-03-09T10:00:00",
39
],
[
"2026-03-09T11:00:00",
36
],
[
"2026-03-09T12:00:00",
32
],
[
"2026-03-09T13:00:00",
27
],
[
"2026-03-09T14:00:00",
23
],
[
"2026-03-09T15:00:00",
20
],
[
"2026-03-09T16:00:00",
19
],
[
"2026-03-09T17:00:00",
20
],
[
"2026-03-09T18:00:00",
22
],
[
"2026-03-09T19:00:00",
25
],
[
"2026-03-09T20:00:00",
26
],
[
"2026-03-09T21:00:00",
27
],
[
"2026-03-09T22:00:00",
23
],
[
"2026-03-09T23:00:00",
19
],
[
"2026-03-10T00:00:00",
12
],
[
"2026-03-10T01:00:00",
8
],
[
"2026-03-10T02:00:00",
4
],
[
"2026-03-10T03:00:00",
4
],
[
"2026-03-10T04:00:00",
9
],
[
"2026-03-10T05:00:00",
12
],
[
"2026-03-10T06:00:00",
20
],
[
"2026-03-10T07:00:00",
28
],
[
"2026-03-10T08:00:00",
35
],
[
"2026-03-10T09:00:00",
36
],
[
"2026-03-10T10:00:00",
39
],
[
"2026-03-10T11:00:00",
36
],
[
"2026-03-10T12:00:00",
34
],
[
"2026-03-10T13:00:00",
26
],
[
"2026-03-10T14:00:00",
22
],
[
"2026-03-10T15:00:00",
19
],
[
"2026-03-10T16:00:00",
21
],
[
"2026-03-10T17:00:00",
22
],
[
"2026-03-10T18:00:00",
23
],
[
"2026-03-10T19:00:00",
25
],
[
"2026-03-10T20:00:00",
28
],
[
"2026-03-10T21:00:00",
27
],
[
"2026-03-10T22:00:00",
23
],
[
"2026-03-10T23:00:00",
17
],
[
"2026-03-11T00:00:00",
11
],
[
"2026-03-11T01:00:00",
9
],
[
"2026-03-11T02:00:00",
4
],
[
"2026-03-11T03:00:00",
3
],
[
"2026-03-11T04:00:00",
6
],
[
"2026-03-11T05:00:00",
11
],
[
"2026-03-11T06:00:00",
22
],
[
"2026-03-11T07:00:00",
29
],
[
"2026-03-11T08:00:00",
33
],
[
"2026-03-11T09:00:00",
38
],
[
"2026-03-11T10:00:00",
38
],
[
"2026-03-11T11:00:00",
37
],
[
"2026-03-11T12:00:00",
32
],
[
"2026-03-11T13:00:00",
26
],
[
"2026-03-11T14:00:00",
24
],
[
"2026-03-11T15:00:00",
21
],
[
"2026-03-11T16:00:00",
21
],
[
"2026-03-11T17:00:00",
20
],
[
"2026-03-11T18:00:00",
24
],
[
"2026-03-11T19:00:00",
27
],
[
"2026-03-11T20:00:00",
28
],
[
"2026-03-11T21:00:00",
27
],
[
"2026-03-11T22:00:00",
23
],
[
"2026-03-11T23:00:00",
18
],
[
"2026-03-12T00:00:00",
11
],
[
"2026-03-12T01:00:00",
8
],
[
"2026-03-12T02:00:00",
3
],
[
"2026-03-12T03:00:00",
4
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
13
],
[
"2026-03-12T06:00:00",
19
],
[
"2026-03-12T07:00:00",
29
],
[
"2026-03-12T08:00:00",
34
],
[
"2026-03-12T09:00:00",
41
],
[
"2026-03-12T10:00:00",
38
],
[
"2026-03-12T11:00:00",
37
],
[
"2026-03-12T12:00:00",
31
],
[
"2026-03-12T13:00:00",
29
],
[
"2026-03-12T14:00:00",
26
],
[
"2026-03-12T15:00:00",
21
],
[
"2026-03-12T16:00:00",
19
],
[
"2026-03-12T17:00:00",
21
],
[
"2026-03-12T18:00:00",
22
],
[
"2026-03-12T19:00:00",
25
],
[
"2026-03-12T20:00:00",
26
],
[
"2026-03-12T21:00:00",
25
],
[
"2026-03-12T22:00:00",
21
],
[
"2026-03-12T23:00:00",
17
],
[
"2026-03-13T00:00:00",
15
],
[
"2026-03-13T01:00:00",
6
],
[
"2026-03-13T02:00:00",
4
],
[
"2026-03-13T03:00:00",
6
],
[
"2026-03-13T04:00:00",
7
],
[
"2026-03-13T05:00:00",
13
],
[
"2026-03-13T06:00:00",
21
],
[
"2026-03-13T07:00:00",
27
],
[
"2026-03-13T08:00:00",
33
],
[
"2026-03-13T09:00:00",
38
],
[
"2026-03-13T10:00:00",
38
],
[
"2026-03-13T11:00:00",
36
],
[
"2026-03-13T12:00:00",
33
],
[
"2026-03-13T13:00:00",
25
],
[
"2026-03-13T14:00:00",
23
],
[
"2026-03-13T15:00:00",
21
],
[
"2026-03-13T16:00:00",
20
],
[
"2026-03-13T17:00:00",
23
],
[
"2026-03-13T18:00:00",
23
],
[
"2026-03-13T19:00:00",
26
],
[
"2026-03-13T20:00:00",
28
],
[
"2026-03-13T21:00:00",
25
],
[
"2026-03-13T22:00:00",
21
],
[
"2026-03-13T23:00:00",
17
],
[
"2026-03-14T00:00:00",
12
],
[
"2026-03-14T01:00:00",
7
],
[
"2026-03-14T02:00:00",
4
],
[
"2026-03-14T03:00:00",
4
],
[
"2026-03-14T04:00:00",
7
],
[
"2026-03-14T05:00:00",
11
],
[
"2026-03-14T06:00:00",
21
],
[
"2026-03-14T07:00:00",
29
],
[
"2026-03-14T08:00:00",
33
],
[
"2026-03-14T09:00:00",
38
],
[
"2026-03-14T10:00:00",
39
],
[
"2026-03-14T11:00:00",
37
],
[
"2026-03-14T12:00:00",
31
],
[
"2026-03-14T13:00:00",
26
],
[
"2026-03-14T14:00:00",
24
],
[
"2026-03-14T15:00:00",
20
],
[
"2026-03-14T16:00:00",
20
],
[
"2026-03-14T17:00:00",
22
],
[
"2026-03-14T18:00:00",
24
],
[
"2026-03-14T19:00:00",
26
],
[
"2026-03-14T20:00:00",
26
],
[
"2026-03-14T21:00:00",
27
],
[
"2026-03-14T22:00:00",
23
],
[
"2026-03-14T23:00:00",
18
],
[
"2026-03-15T00:00:00",
13
],
[
"2026-03-15T01:00:00",
10
],
[
"2026-03-15T02:00:00",
4
],
[
"2026-03-15T03:00:00",
3
],
[
"2026-03-15T04:00:00",
7
],
[
"2026-03-15T05:00:00",
14
],
[
"2026-03-15T06:00:00",
20
],
[
"2026-03-15T07:00:00",
29
],
[
"2026-03-15T08:00:00",
34
],
[
"2026-03-15T09:00:00",
39
],
[
"2026-03-15T10:00:00",
38
],
[
"2026-03-15T11:00:00",
37
],
[
"2026-03-15T12:00:00",
32
],
[
"2026-03-15T13:00:00",
26
],
[
"2026-03-15T14:00:00",
23
],
[
"2026-03-15T15:00:00",
21
]
]
},
"Product B": {
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
44
],
[
"2026-03-08T16:00:00",
41
],
[
"2026-03-08T17:00:00",
47
],
[
"2026-03-08T18:00:00",
37
],
[
"2026-03-08T19:00:00",
39
],
[
"2026-03-08T20:00:00",
32
],
[
"2026-03-08T21:00:00",
22
],
[
"2026-03-08T22:00:00",
20
],
[
"2026-03-08T23:00:00",
17
],
[
"2026-03-09T00:00:00",
11
],
[
"2026-03-09T01:00:00",
14
],
[
"2026-03-09T02:00:00",
7
],
[
"2026-03-09T03:00:00",
3
],
[
"2026-03-09T04:00:00",
6
],
[
"2026-03-09T05:00:00",
7
],
[
"2026-03-09T06:00:00",
11
],
[
"2026-03-09T07:00:00",
17
],
[
"2026-03-09T08:00:00",
18
],
[
"2026-03-09T09:00:00",
21
],
[
"2026-03-09T10:00:00",
30
],
[
"2026-03-09T11:00:00",
35
],
[
"2026-03-09T12:00:00",
38
],
[
"2026-03-09T13:00:00",
41
],
[
"2026-03-09T14:00:00",
46
],
[
"2026-03-09T15:00:00",
47
],
[
"2026-03-09T16:00:00",
43
],
[
"2026-03-09T17:00:00",
41
],
[
"2026-03-09T18:00:00",
39
],
[
"2026-03-09T19:00:00",
33
],
[
"2026-03-09T20:00:00",
33
],
[
"2026-03-09T21:00:00",
26
],
[
"2026-03-09T22:00:00",
20
],
[
"2026-03-09T23:00:00",
17
],
[
"2026-03-10T00:00:00",
7
],
[
"2026-03-10T01:00:00",
9
],
[
"2026-03-10T02:00:00",
11
],
[
"2026-03-10T03:00:00",
7
],
[
"2026-03-10T04:00:00",
4
],
[
"2026-03-10T05:00:00",
9
],
[
"2026-03-10T06:00:00",
11
],
[
"2026-03-10T07:00:00",
15
],
[
"2026-03-10T08:00:00",
18
],
[
"2026-03-10T09:00:00",
24
],
[
"2026-03-10T10:00:00",
29
],
[
"2026-03-10T11:00:00",
39
],
[
"2026-03-10T12:00:00",
42
],
[
"2026-03-10T13:00:00",
42
],
[
"2026-03-10T14:00:00",
46
],
[
"2026-03-10T15:00:00",
42
],
[
"2026-03-10T16:00:00",
45
],
[
"2026-03-10T17:00:00",
46
],
[
"2026-03-10T18:00:00",
39
],
[
"2026-03-10T19:00:00",
37
],
[
"2026-03-10T20:00:00",
32
],
[
"2026-03-10T21:00:00",
27
],
[
"2026-03-10T22:00:00",
21
],
[
"2026-03-10T23:00:00",
15
],
[
"2026-03-11T00:00:00",
12
],
[
"2026-03-11T01:00:00",
9
],
[
"2026-03-11T02:00:00",
6
],
[
"2026-03-11T03:00:00",
7
],
[
"2026-03-11T04:00:00",
6
],
[
"2026-03-11T05:00:00",
9
],
[
"2026-03-11T06:00:00",
12
],
[
"2026-03-11T07:00:00",
16
],
[
"2026-03-11T08:00:00",
22
],
[
"2026-03-11T09:00:00",
26
],
[
"2026-03-11T10:00:00",
30
],
[
"2026-03-11T11:00:00",
33
],
[
"2026-03-11T12:00:00",
34
],
[
"2026-03-11T13:00:00",
40
],
[
"2026-03-11T14:00:00",
42
],
[
"2026-03-11T15:00:00",
44
],
[
"2026-03-11T16:00:00",
48
],
[
"2026-03-11T17:00:00",
42
],
[
"2026-03-11T18:00:00",
39
],
[
"2026-03-11T19:00:00",
36
],
[
"2026-03-11T20:00:00",
28
],
[
"2026-03-11T21:00:00",
27
],
[
"2026-03-11T22:00:00",
19
],
[
"2026-03-11T23:00:00",
16
],
[
"2026-03-12T00:00:00",
8
],
[
"2026-03-12T01:00:00",
10
],
[
"2026-03-12T02:00:00",
5
],
[
"2026-03-12T03:00:00",
3
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
9
],
[
"2026-03-12T06:00:00",
9
],
[
"2026-03-12T07:00:00",
13
],
[
"2026-03-12T08:00:00",
17
],
[
"2026-03-12T09:00:00",
24
],
[
"2026-03-12T10:00:00",
31
],
[
"2026-03-12T11:00:00",
38
],
[
"2026-03-12T12:00:00",
36
],
[
"2026-03-12T13:00:00",
42
],
[
"2026-03-12T14:00:00",
44
],
[
"2026-03-12T15:00:00",
46
],
[
"2026-03-12T16:00:00",
43
],
[
"2026-03-12T17:00:00",
48
],
[
"2026-03-12T18:00:00",
39
],
[
"2026-03-12T19:00:00",
35
],
[
"2026-03-12T20:00:00",
31
],
[
"2026-03-12T21:00:00",
24
],
[
"2026-03-12T22:00:00",
16
],
[
"2026-03-12T23:00:00",
15
],
[
"2026-03-13T00:00:00",
15
],
[
"2026-03-13T01:00:00",
11
],
[
"2026-03-13T02:00:00",
8
],
[
"2026-03-13T03:00:00",
7
],
[
"2026-03-13T04:00:00",
6
],
[
"2026-03-13T05:00:00",
9
],
[
"2026-03-13T06:00:00",
9
],
[
"2026-03-13T07:00:00",
16
],
[
"2026-03-13T08:00:00",
17
],
[
"2026-03-13T09:00:00",
27
],
[
"2026-03-13T10:00:00",
30
],
[
"2026-03-13T11:00:00",
34
],
[
"2026-03-13T12:00:00",
40
],
[
"2026-03-13T13:00:00",
44
],
[
"2026-03-13T14:00:00",
42
],
[
"2026-03-13T15:00:00",
48
],
[
"2026-03-13T16:00:00",
44
],
[
"2026-03-13T17:00:00",
43
],
[
"2026-03-13T18:00:00",
39
],
[
"2026-03-13T19:00:00",
32
],
[
"2026-03-13T20:00:00",
30
],
[
"2026-03-13T21:00:00",
23
],
[
"2026-03-13T22:00:00",
20
],
[
"2026-03-13T23:00:00",
15
],
[
"2026-03-14T00:00:00",
9
],
[
"2026-03-14T01:00:00",
8
],
[
"2026-03-14T02:00:00",
5
],
[
"2026-03-14T03:00:00",
7
],
[
"2026-03-14T04:00:00",
8
],
[
"2026-03-14T05:00:00",
7
],
[
"2026-03-14T06:00:00",
13
],
[
"2026-03-14T07:00:00",
19
],
[
"2026-03-14T08:00:00",
19
],
[
"2026-03-14T09:00:00",
25
],
[
"2026-03-14T10:00:00",
31
],
[
"2026-03-14T11:00:00",
35
],
[
"2026-03-14T12:00:00",
40
],
[
"2026-03-14T13:00:00",
43
],
[
"2026-03-14T14:00:00",
45
],
[
"2026-03-14T15:00:00",
44
],
[
"2026-03-14T16:00:00",
44
],
[
"2026-03-14T17:00:00",
44
],
[
"2026-03-14T18:00:00",
42
],
[
"2026-03-14T19:00:00",
32
],
[
"2026-03-14T20:00:00",
31
],
[
"2026-03-14T21:00:00",
26
],
[
"2026-03-14T22:00:00",
20
],
[
"2026-03-14T23:00:00",
13
],
[
"2026-03-15T00:00:00",
10
],
[
"2026-03-15T01:00:00",
10
],
[
"2026-03-15T02:00:00",
7
],
[
"2026-03-15T03:00:00",
8
],
[
"2026-03-15T04:00:00",
12
],
[
"2026-03-15T05:00:00",
10
],
[
"2026-03-15T06:00:00",
13
],
[
"2026-03-15T07:00:00",
14
],
[
"2026-03-15T08:00:00",
18
],
[
"2026-03-15T09:00:00",
24
],
[
"2026-03-15T10:00:00",
32
],
[
"2026-03-15T11:00:00",
34
],
[
"2026-03-15T12:00:00",
39
],
[
"2026-03-15T13:00:00",
39
],
[
"2026-03-15T14:00:00",
41
],
[
"2026-03-15T15:00:00",
47
]
]
},
"Product C": {
"columns": [
"timestamp",
"units_sold"
],
"rows": [
[
"2026-03-08T15:00:00",
67
],
[
"2026-03-08T16:00:00",
65
],
[
"2026-03-08T17:00:00",
66
],
[
"2026-03-08T18:00:00",
64
],
[
"2026-03-08T19:00:00",
51
],
[
"2026-03-08T20:00:00",
51
],
[
"2026-03-08T21:00:00",
42
],
[
"2026-03-08T22:00:00",
30
],
[
"2026-03-08T23:00:00",
18
],
[
"2026-03-09T00:00:00",
11
],
[
"2026-03-09T01:00:00",
16
],
[
"2026-03-09T02:00:00",
9
],
[
"2026-03-09T03:00:00",
1
],
[
"2026-03-09T04:00:00",
13
],
[
"2026-03-09T05:00:00",
4
],
[
"2026-03-09T06:00:00",
19
],
[
"2026-03-09T07:00:00",
24
],
[
"2026-03-09T08:00:00",
33
],
[
"2026-03-09T09:00:00",
35
],
[
"2026-03-09T10:00:00",
39
],
[
"2026-03-09T11:00:00",
52
],
[
"2026-03-09T12:00:00",
59
],
[
"2026-03-09T13:00:00",
65
],
[
"2026-03-09T14:00:00",
70
],
[
"2026-03-09T15:00:00",
67
],
[
"2026-03-09T16:00:00",
67
],
[
"2026-03-09T17:00:00",
63
],
[
"2026-03-09T18:00:00",
58
],
[
"2026-03-09T19:00:00",
53
],
[
"2026-03-09T20:00:00",
45
],
[
"2026-03-09T21:00:00",
37
],
[
"2026-03-09T22:00:00",
28
],
[
"2026-03-09T23:00:00",
24
],
[
"2026-03-10T00:00:00",
18
],
[
"2026-03-10T01:00:00",
8
],
[
"2026-03-10T02:00:00",
11
],
[
"2026-03-10T03:00:00",
2
],
[
"2026-03-10T04:00:00",
14
],
[
"2026-03-10T05:00:00",
13
],
[
"2026-03-10T06:00:00",
13
],
[
"2026-03-10T07:00:00",
23
],
[
"2026-03-10T08:00:00",
30
],
[
"2026-03-10T09:00:00",
39
],
[
"2026-03-10T10:00:00",
44
],
[
"2026-03-10T11:00:00",
50
],
[
"2026-03-10T12:00:00",
58
],
[
"2026-03-10T13:00:00",
62
],
[
"2026-03-10T14:00:00",
65
],
[
"2026-03-10T15:00:00",
73
],
[
"2026-03-10T16:00:00",
64
],
[
"2026-03-10T17:00:00",
63
],
[
"2026-03-10T18:00:00",
67
],
[
"2026-03-10T19:00:00",
53
],
[
"2026-03-10T20:00:00",
44
],
[
"2026-03-10T21:00:00",
38
],
[
"2026-03-10T22:00:00",
32
],
[
"2026-03-10T23:00:00",
20
],
[
"2026-03-11T00:00:00",
17
],
[
"2026-03-11T01:00:00",
12
],
[
"2026-03-11T02:00:00",
9
],
[
"2026-03-11T03:00:00",
3
],
[
"2026-03-11T04:00:00",
16
],
[
"2026-03-11T05:00:00",
13
],
[
"2026-03-11T06:00:00",
16
],
[
"2026-03-11T07:00:00",
29
],
[
"2026-03-11T08:00:00",
28
],
[
"2026-03-11T09:00:00",
38
],
[
"2026-03-11T10:00:00",
47
],
[
"2026-03-11T11:00:00",
46
],
[
"2026-03-11T12:00:00",
59
],
[
"2026-03-11T13:00:00",
63
],
[
"2026-03-11T14:00:00",
66
],
[
"2026-03-11T15:00:00",
68
],
[
"2026-03-11T16:00:00",
69
],
[
"2026-03-11T17:00:00",
62
],
[
"2026-03-11T18:00:00",
55
],
[
"2026-03-11T19:00:00",
47
],
[
"2026-03-11T20:00:00",
47
],
[
"2026-03-11T21:00:00",
37
],
[
"2026-03-11T22:00:00",
28
],
[
"2026-03-11T23:00:00",
23
],
[
"2026-03-12T00:00:00",
20
],
[
"2026-03-12T01:00:00",
12
],
[
"2026-03-12T02:00:00",
8
],
[
"2026-03-12T03:00:00",
6
],
[
"2026-03-12T04:00:00",
7
],
[
"2026-03-12T05:00:00",
13
],
[
"2026-03-12T06:00:00",
18
],
[
"2026-03-12T07:00:00",
18
],
[
"2026-03-12T08:00:00",
26
],
[
"2026-03-12T09:00:00",
40
],
[
"2026-03-12T10:00:00",
44
],
[
"2026-03-12T11:00:00",
52
],
[
"2026-03-12T12:00:00",
60
],
[
"2026-03-12T13:00:00",
64
],
[
"2026-03-12T14:00:00",
65
],
[
"2026-03-12T15:00:00",
67
],
[
"2026-03-12T16:00:00",
64
],
[
"2026-03-12T17:00:00",
68
],
[
"2026-03-12T18:00:00",
57
],
[
"2026-03-12T19:00:00",
55
],
[
"2026-03-12T20:00:00",
50
],
[
"2026-03-12T21:00:00",
36
],
[
"2026-03-12T22:00:00",
28
],
[
"2026-03-12T23:00:00",
21
],
[
"2026-03-13T00:00:00",
16
],
[
"2026-03-13T01:00:00",
16
],
[
"2026-03-13T02:00:00",
13
],
[
"2026-03-13T03:00:00",
6
],
[
"2026-03-13T04:00:00",
9
],
[
"2026-03-13T05:00:00",
14
],
[
"2026-03-13T06:00:00",
18
],
[
"2026-03-13T07:00:00",
22
],
[
"2026-03-13T08:00:00",
26
],
[
"2026-03-13T09:00:00",
36
],
[
"2026-03-13T10:00:00",
48
],
[
"2026-03-13T11:00:00",
53
],
[
"2026-03-13T12:00:00",
59
],
[
"2026-03-13T13:00:00",
64
],
[
"2026-03-13T14:00:00",
70
],
[
"2026-03-13T15:00:00",
70
],
[
"2026-03-13T16:00:00",
72
],
[
"2026-03-13T17:00:00",
62
],
[
"2026-03-13T18:00:00",
61
],
[
"2026-03-13T19:00:00",
52
],
[
"2026-03-13T20:00:00",
41
],
[
"2026-03-13T21:00:00",
35
],
[
"2026-03-13T22:00:00",
29
],
[
"2026-03-13T23:00:00",
22
],
[
"2026-03-14T00:00:00",
19
],
[
"2026-03-14T01:00:00",
7
],
[
"2026-03-14T02:00:00",
9
],
[
"2026-03-14T03:00:00",
8
],
[
"2026-03-14T04:00:00",
5
],
[
"2026-03-14T05:00:00",
19
],
[
"2026-03-14T06:00:00",
16
],
[
"2026-03-14T07:00:00",
20
],
[
"2026-03-14T08:00:00",
25
],
[
"2026-03-14T09:00:00",
36
],
[
"2026-03-14T10:00:00",
48
],
[
"2026-03-14T11:00:00",
55
],
[
"2026-03-14T12:00:00",
57
],
[
"2026-03-14T13:00:00",
58
],
[
"2026-03-14T14:00:00",
68
],
[
"2026-03-14T15:00:00",
70
],
[
"2026-03-14T16:00:00",
65
],
[
"2026-03-14T17:00:00",
61
],
[
"2026-03-14T18:00:00",
55
],
[
"2026-03-14T19:00:00",
52
],
[
"2026-03-14T20:00:00",
41
],
[
"2026-03-14T21:00:00",
34
],
[
"2026-03-14T22:00:00",
30
],
[
"2026-03-14T23:00:00",
24
],
[
"2026-03-15T00:00:00",
21
],
[
"2026-03-15T01:00:00",
15
],
[
"2026-03-15T02:00:00",
5
],
[
"2026-03-15T03:00:00",
9
],
[
"2026-03-15T04:00:00",
9
],
[
"2026-03-15T05:00:00",
14
],
[
"2026-03-15T06:00:00",
19
],
[
"2026-03-15T07:00:00",
28
],
[
"2026-03-15T08:00:00",
31
],
[
"2026-03-15T09:00:00",
41
],
[
"2026-03-15T10:00:00",
50
],
[
"2026-03-15T11:00:00",
51
],
[
"2026-03-15T12:00:00",
64
],
[
"2026-03-15T13:00:00",
67
],
[
"2026-03-15T14:00:00",
69
],
[
"2026-03-15T15:00:00",
68
]
]
}
},
"forecasts": {
"Product A": {
"timestamp": [
"2026-03-15T16:00:00",
"2026-03-15T17:00:00",
"2026-03-15T18:00:00",
"2026-03-15T19:00:00",
"2026-03-15T20:00:00",
"2026-03-15T21:00:00",
"2026-03-15T22:00:00",
"2026-03-15T23:00:00",
"2026-03-16T00:00:00",
"2026-03-16T01:00:00",
"2026-03-16T02:00:00",
"2026-03-16T03:00:00",
"2026-03-16T04:00:00",
"2026-03-16T05:00:00",
"2026-03-16T06:00:00",
"2026-03-16T07:00:00",
"2026-03-16T08:00:00",
"2026-03-16T09:00:00",
"2026-03-16T10:00:00",
"2026-03-16T11:00:00",
"2026-03-16T12:00:00",
"2026-03-16T13:00:00",
"2026-03-16T14:00:00",
"2026-03-16T15:00:00",
"2026-03-16T16:00:00",
"2026-03-16T17:00:00",
"2026-03-16T18:00:00",
"2026-03-16T19:00:00",
"2026-03-16T20:00:00",
"2026-03-16T21:00:00",
"2026-03-16T22:00:00",
"2026-03-16T23:00:00",
"2026-03-17T00:00:00",
"2026-03-17T01:00:00",
"2026-03-17T02:00:00",
"2026-03-17T03:00:00",
"2026-03-17T04:00:00",
"2026-03-17T05:00:00",
"2026-03-17T06:00:00",
"2026-03-17T07:00:00",
"2026-03-17T08:00:00",
"2026-03-17T09:00:00",
"2026-03-17T10:00:00",
"2026-03-17T11:00:00",
"2026-03-17T12:00:00",
"2026-03-17T13:00:00",
"2026-03-17T14:00:00",
"2026-03-17T15:00:00"
],
"mean": [
20.504526138305664,
21.805526733398438,
23.69278907775879,
25.529420852661133,
26.827110290527344,
26.324140548706055,
22.897764205932617,
17.852794647216797,
12.321682929992676,
7.192910194396973,
3.9130783081054688,
3.9800643920898438,
7.332183837890625,
12.986684799194336,
20.668590545654297,
27.952547073364258,
33.47609329223633,
38.25192642211914,
38.400447845458984,
36.45668029785156,
31.858444213867188,
26.570825576782227,
23.2839412689209,
20.51091957092285,
20.30457305908203,
21.678436279296875,
23.642099380493164,
25.584678649902344,
26.985809326171875,
26.484193801879883,
23.02522850036621,
18.039037704467773,
12.611462593078613,
7.602766990661621,
4.303823471069336,
4.018426895141602,
7.423919677734375,
13.13841438293457,
20.692811965942383,
28.037954330444336,
33.97454071044922,
38.231040954589844,
38.78217697143555,
36.92472457885742,
32.19001388549805,
26.802392959594727,
23.54244041442871,
20.698514938354492
],
"0.1": [
19.15822410583496,
20.50179100036621,
22.401607513427734,
24.21921157836914,
25.45020294189453,
24.837438583374023,
21.506221771240234,
16.50567626953125,
10.83835220336914,
5.582372665405273,
2.285032272338867,
2.251415252685547,
5.641073226928711,
11.404353141784668,
18.795143127441406,
25.81307601928711,
31.14609718322754,
35.49599838256836,
35.904144287109375,
34.05424499511719,
29.796527862548828,
24.967273712158203,
21.782663345336914,
19.394075393676758,
19.236570358276367,
20.604127883911133,
22.458040237426758,
24.36791229248047,
25.4338436126709,
24.74117088317871,
21.389162063598633,
16.495697021484375,
10.960190773010254,
5.869045257568359,
2.5734004974365234,
2.361164093017578,
5.705011367797852,
11.369453430175781,
18.547435760498047,
25.60714340209961,
31.265169143676758,
35.313446044921875,
36.011741638183594,
34.2758674621582,
29.958742141723633,
25.103273391723633,
21.822275161743164,
19.32248306274414
],
"0.9": [
21.669395446777344,
23.053070068359375,
24.99215316772461,
26.91657066345215,
28.313753128051758,
27.791156768798828,
24.152969360351562,
19.0040283203125,
13.467171669006348,
8.364714622497559,
4.990467071533203,
5.050144195556641,
8.647828102111816,
14.336263656616211,
22.190526962280273,
29.632858276367188,
35.39604949951172,
40.310279846191406,
40.52391815185547,
38.57139587402344,
33.898765563964844,
28.34296226501465,
25.04033088684082,
22.027423858642578,
21.667360305786133,
22.99347686767578,
24.871681213378906,
26.878807067871094,
28.497577667236328,
28.168556213378906,
24.56938934326172,
19.346378326416016,
14.037256240844727,
8.928860664367676,
5.4414215087890625,
5.182031631469727,
8.82529354095459,
14.672514915466309,
22.400375366210938,
29.78118896484375,
35.815494537353516,
40.36121368408203,
40.88827133178711,
39.124969482421875,
34.39842224121094,
28.938234329223633,
25.735769271850586,
22.512235641479492
]
},
"Product B": {
"timestamp": [
"2026-03-15T16:00:00",
"2026-03-15T17:00:00",
"2026-03-15T18:00:00",
"2026-03-15T19:00:00",
"2026-03-15T20:00:00",
"2026-03-15T21:00:00",
"2026-03-15T22:00:00",
"2026-03-15T23:00:00",
"2026-03-16T00:00:00",
"2026-03-16T01:00:00",
"2026-03-16T02:00:00",
"2026-03-16T03:00:00",
"2026-03-16T04:00:00",
"2026-03-16T05:00:00",
"2026-03-16T06:00:00",
"2026-03-16T07:00:00",
"2026-03-16T08:00:00",
"2026-03-16T09:00:00",
"2026-03-16T10:00:00",
"2026-03-16T11:00:00",
"2026-03-16T12:00:00",
"2026-03-16T13:00:00",
"2026-03-16T14:00:00",
"2026-03-16T15:00:00",
"2026-03-16T16:00:00",
"2026-03-16T17:00:00",
"2026-03-16T18:00:00",
"2026-03-16T19:00:00",
"2026-03-16T20:00:00",
"2026-03-16T21:00:00",
"2026-03-16T22:00:00",
"2026-03-16T23:00:00",
"2026-03-17T00:00:00",
"2026-03-17T01:00:00",
"2026-03-17T02:00:00",
"2026-03-17T03:00:00",
"2026-03-17T04:00:00",
"2026-03-17T05:00:00",
"2026-03-17T06:00:00",
"2026-03-17T07:00:00",
"2026-03-17T08:00:00",
"2026-03-17T09:00:00",
"2026-03-17T10:00:00",
"2026-03-17T11:00:00",
"2026-03-17T12:00:00",
"2026-03-17T13:00:00",
"2026-03-17T14:00:00",
"2026-03-17T15:00:00"
],
"mean": [
45.744361877441406,
44.47789764404297,
39.96786880493164,
34.93931579589844,
30.40752410888672,
25.078933715820312,
19.764469146728516,
15.15910816192627,
11.105031967163086,
9.184202194213867,
7.405527114868164,
6.835023880004883,
7.098142623901367,
8.534454345703125,
11.933398246765137,
16.158313751220703,
19.992860794067383,
25.135028839111328,
30.816650390625,
35.86872863769531,
39.165767669677734,
42.46210479736328,
44.626007080078125,
45.996063232421875,
45.7534065246582,
44.59668731689453,
40.11052703857422,
35.24456787109375,
31.033628463745117,
25.713680267333984,
20.289962768554688,
15.610541343688965,
11.549332618713379,
9.544018745422363,
7.7064056396484375,
6.958499908447266,
7.410867691040039,
9.032258987426758,
12.31091022491455,
16.357358932495117,
20.261585235595703,
25.50418472290039,
31.366159439086914,
36.46283721923828,
39.60572052001953,
42.69723129272461,
44.79161834716797,
46.19174575805664
],
"0.1": [
43.202728271484375,
41.657466888427734,
37.34388732910156,
32.49301528930664,
27.895044326782227,
22.69713592529297,
17.48502540588379,
12.914217948913574,
8.867912292480469,
6.805437088012695,
5.133642196655273,
4.6055755615234375,
4.980224609375,
6.566743850708008,
9.907864570617676,
14.042644500732422,
17.96416664123535,
23.004030227661133,
28.466156005859375,
33.398677825927734,
36.72842788696289,
39.793521881103516,
41.68659973144531,
42.83111572265625,
42.48583984375,
41.06452941894531,
36.83848571777344,
32.41840744018555,
28.241992950439453,
23.26666259765625,
18.005842208862305,
13.322606086730957,
9.245460510253906,
7.142238616943359,
5.440708160400391,
4.845056533813477,
5.325952529907227,
7.058143615722656,
10.134407043457031,
14.08029842376709,
18.03704071044922,
23.15070152282715,
28.727794647216797,
33.606204986572266,
36.765869140625,
39.615299224853516,
41.445343017578125,
42.517974853515625
],
"0.9": [
48.60978698730469,
47.43096923828125,
42.79112243652344,
37.6799201965332,
33.3004150390625,
27.90454864501953,
22.537134170532227,
17.90163230895996,
13.724783897399902,
11.975788116455078,
9.977222442626953,
9.093873977661133,
9.463135719299316,
10.984129905700684,
14.422269821166992,
18.565746307373047,
22.39069175720215,
27.66008949279785,
33.55706024169922,
38.70289611816406,
42.075965881347656,
45.412227630615234,
47.52215576171875,
48.96488952636719,
48.8265380859375,
47.848453521728516,
43.23004913330078,
38.305755615234375,
34.17613983154297,
28.809988021850586,
23.35015106201172,
18.584577560424805,
14.49343204498291,
12.689022064208984,
10.720396995544434,
9.662089347839355,
10.225909233093262,
11.88810920715332,
15.130329132080078,
19.02608871459961,
22.825077056884766,
28.250431060791016,
34.244171142578125,
39.468650817871094,
42.69873046875,
45.907142639160156,
47.94013214111328,
49.381919860839844
]
},
"Product C": {
"timestamp": [
"2026-03-15T16:00:00",
"2026-03-15T17:00:00",
"2026-03-15T18:00:00",
"2026-03-15T19:00:00",
"2026-03-15T20:00:00",
"2026-03-15T21:00:00",
"2026-03-15T22:00:00",
"2026-03-15T23:00:00",
"2026-03-16T00:00:00",
"2026-03-16T01:00:00",
"2026-03-16T02:00:00",
"2026-03-16T03:00:00",
"2026-03-16T04:00:00",
"2026-03-16T05:00:00",
"2026-03-16T06:00:00",
"2026-03-16T07:00:00",
"2026-03-16T08:00:00",
"2026-03-16T09:00:00",
"2026-03-16T10:00:00",
"2026-03-16T11:00:00",
"2026-03-16T12:00:00",
"2026-03-16T13:00:00",
"2026-03-16T14:00:00",
"2026-03-16T15:00:00",
"2026-03-16T16:00:00",
"2026-03-16T17:00:00",
"2026-03-16T18:00:00",
"2026-03-16T19:00:00",
"2026-03-16T20:00:00",
"2026-03-16T21:00:00",
"2026-03-16T22:00:00",
"2026-03-16T23:00:00",
"2026-03-17T00:00:00",
"2026-03-17T01:00:00",
"2026-03-17T02:00:00",
"2026-03-17T03:00:00",
"2026-03-17T04:00:00",
"2026-03-17T05:00:00",
"2026-03-17T06:00:00",
"2026-03-17T07:00:00",
"2026-03-17T08:00:00",
"2026-03-17T09:00:00",
"2026-03-17T10:00:00",
"2026-03-17T11:00:00",
"2026-03-17T12:00:00",
"2026-03-17T13:00:00",
"2026-03-17T14:00:00",
"2026-03-17T15:00:00"
],
"mean": [
68.25753784179688,
64.33294677734375,
58.953407287597656,
52.182167053222656,
44.8023567199707,
36.48902130126953,
29.293916702270508,
23.117162704467773,
18.24557876586914,
12.591239929199219,
9.324899673461914,
7.880804061889648,
10.169549942016602,
14.116628646850586,
18.203784942626953,
24.026535034179688,
30.23114776611328,
38.921058654785156,
47.02241897583008,
53.7126350402832,
60.47807312011719,
64.84934997558594,
68.66142272949219,
70.09188842773438,
68.77432250976562,
64.90254974365234,
59.55329132080078,
52.759666442871094,
45.605072021484375,
37.1990966796875,
29.969520568847656,
23.500141143798828,
18.895471572875977,
13.273134231567383,
9.766721725463867,
7.782873153686523,
10.10135269165039,
14.322179794311523,
18.6790828704834,
24.71501922607422,
31.01270866394043,
39.43730163574219,
47.36338806152344,
54.099761962890625,
61.12646484375,
65.52592468261719,
69.14380645751953,
70.39305114746094
],
"0.1": [
65.0497055053711,
61.02140808105469,
55.667762756347656,
49.130184173583984,
41.937583923339844,
33.930274963378906,
26.850168228149414,
20.65131950378418,
15.420270919799805,
9.610015869140625,
6.014139175415039,
4.563690185546875,
6.7572479248046875,
10.61678695678711,
15.046772003173828,
20.946298599243164,
27.35129737854004,
35.78847122192383,
43.83382034301758,
50.54799270629883,
56.998382568359375,
61.15869140625,
64.4871597290039,
65.62289428710938,
64.30809020996094,
60.597747802734375,
55.28544616699219,
49.05252456665039,
42.306427001953125,
34.51346206665039,
27.43219757080078,
21.02750015258789,
15.994155883789062,
10.284709930419922,
6.550397872924805,
4.792110443115234,
6.905149459838867,
10.953042984008789,
15.455942153930664,
21.445810317993164,
27.832324981689453,
35.966773986816406,
43.770023345947266,
50.32490539550781,
56.82306671142578,
60.98479080200195,
64.19062805175781,
65.11436462402344
],
"0.9": [
71.67506408691406,
67.64664459228516,
62.195289611816406,
55.31642150878906,
47.960060119628906,
39.451725006103516,
32.17584228515625,
25.903423309326172,
21.21776580810547,
15.803155899047852,
12.547943115234375,
10.65243148803711,
13.38730239868164,
17.783737182617188,
21.71316146850586,
27.42102813720703,
33.64549255371094,
42.66716766357422,
50.950584411621094,
57.488285064697266,
64.4905014038086,
68.61067199707031,
72.39262390136719,
73.94755554199219,
72.77479553222656,
68.87016296386719,
63.50397872924805,
56.57518768310547,
49.40583038330078,
40.81800842285156,
33.40961456298828,
26.681062698364258,
22.37085723876953,
17.016590118408203,
13.691097259521484,
11.294649124145508,
13.996709823608398,
18.501005172729492,
22.67669677734375,
28.56482696533203,
34.7428092956543,
43.582984924316406,
51.486045837402344,
58.23878479003906,
65.67634582519531,
69.92729187011719,
73.41410827636719,
74.68563079833984
]
}
}
}
}
Result
http://localhost:8004/plot_32abcfb962dc412f8909d2f8283c5067.html
Here's the combined view for all three products!
Here's a summary of the results across all three products:
| Product A | Product B | Product C | |
|---|---|---|---|
| Historical range | ~2–41 units/hr | ~3–48 units/hr | ~1–73 units/hr |
| Daily peak timing | ~9–10 AM | ~3–5 PM | ~2–4 PM |
| Forecast peak (Mar 16–17) | ~38–41 | ~44–46 | ~68–70 |
| Uncertainty band | Very tight | Tight | Moderate |
Key cross-product observations:
- 🕐 Different peak hours: Product A peaks in the morning (~9 AM), while Products B and C peak in the afternoon (~3–5 PM) — suggesting different customer segments or use cases.
- 📊 Volume hierarchy: Product C sells 2× more than Product B and 1.7× more than Product A at their respective peaks.
- 🔄 Consistent seasonality: All three products show strong and stable daily cycles, which Chronos has picked up on very confidently.
The assistant consistently followed all instructions and used the correct tools in the right order.
One limitation worth noting is that rather than joining the sales and products tables to resolve product names, the assistant
memorized the product IDs from the products table and used them directly in subsequent queries.
While this approach worked correctly in this case, it is not robust, as the products table may change over time.
We also note that the model’s thinking is occasionally too verbose. Additionally, in the final turn, the model’s internal reasoning refers to “temperature readings” and “temperature curves” despite operating on product sales data - a domain slip in extended thinking that did not affect the final output.
You can download the full code from our GitHub repository.
References¶
[1] Ansari, A.F., Stella, L., Turkmen, C., Zhang, X., Mercado, P., Shen, H., Shchur, O., Rangapuram, S.S., Arango, S.P., Kapoor, S. and Zschiegner, J., (2024). Chronos: Learning the language of time series. arXiv preprint, doi: 10.48550/arXiv.2403.07815.
[2] Ansari, A.F., Turkmen, C., Shchur, O., and Stella, L. (2024). Fast and accurate zero-shot forecasting with Chronos-Bolt and AutoGluon. AWS Blogs - Artificial Intelligence.