eomer OS / Use the same workflow through code

Use the same workflow through code

Explore configuration examples for the eomer API. Draft examples remain labelled while the interface develops.

Request demo

Describe the workload

Identify the input dataset, forecast target and horizon.

Inspect an example

Compare illustrative code with the equivalent configuration in the Situation Room.

Confirm the integration

Agree the current endpoints and deployment requirements before production use.

eomer API

Your data.
Your analysis. Your workflow.

For data scientists who want to customise inputs, test assumptions, and integrate results into their own tools. Explore four Python notebooks, each with ten applications and three sample datasets.

Open API documentation
eomer_quickstart.ipynbInteractive mock notebook

Python / Energy

Compare price signals before you commit asset capacity.

Based on the supplied eomer quickstart. Select inputs to update the code and sample data, then update the preview. All data and results are synthetic; this page does not execute Python or call the API. The examples do not indicate live market coverage.

01

Connect the Python interface

Import the forecast and backtest helpers from the quickstart package. In your own notebook, read the API key from an environment variable and keep it outside shared code.

import os
import pandas as pd
from eomer_api import predict_df, backtest
from eomer_plots import plot_forecast

API_URL = os.environ["EOMER_API_URL"]
HEADERS = {"Authorization": f'Bearer {os.environ["EOMER_API_KEY"]}'}
02

Choose the decision and prepare history

Select the country, application, sample dataset, and horizon above. Table 1 shows the last three rows of the synthetic history; target represents price in EUR/MWh. In your own notebook, supply a CSV with these columns.

# Germany / Day-ahead prices
# Sample: Winter demand (synthetic)
CONTEXT_PATH = "energy_day-ahead_sample_1.csv"
PREDICTION_LENGTH = 96

context_df = pd.read_csv(
    CONTEXT_PATH,
    parse_dates=["timestamp"],
)
context_df.tail(3)
Table 1. Synthetic input preview · 1,024 historical observations
item_idtimestamp (UTC) · 15 mintarget (EUR/MWh)
germany_day-ahead2026-01-11 15:1557.24
germany_day-ahead2026-01-11 15:3054.81
germany_day-ahead2026-01-11 15:4552.22
03

Request a forecast with uncertainty

Pass the history and horizon to predict_df. The median describes the central forecast; P10 and P90 describe the requested uncertainty interval. The button below updates the synthetic preview for your selected inputs.

pred_df = predict_df(
    context_df,
    api_url=API_URL,
    headers=HEADERS,
    prediction_length=PREDICTION_LENGTH,
    quantile_levels=[0.1, 0.5, 0.9],
    freq="h",
)
pred_df.head()
Preview matches selected inputs
04

Review the forecast before the decision

Figure 1 shows the synthetic median and interval for Germany, Day-ahead prices, over 96 steps. Use the interval to review uncertainty alongside the operating constraints.

plot_forecast(
    context_df,
    pred_df,
    item_id=context_df["item_id"].iloc[0],
    y_label="EUR/MWh",
    lead_in_steps=3 * 96,
).show()
Figure 1. Day-ahead pricesGermany · 96 hours · EUR/MWh

Load the interactive forecast chart…

Hover to inspect values. Drag to zoom; use the toolbar to pan, reset the axes, or export a PNG. Select a legend entry to show or hide a series.

Show forecast values
Figure 1 data. Synthetic forecast · EUR/MWh
Timestamp (UTC)P10P50P90
2026-01-11 16:0038.5252.0265.52
2026-01-11 16:1540.1553.6567.15
2026-01-11 16:3041.6955.1968.69
2026-01-11 16:4542.4155.9169.41
2026-01-11 17:0041.9655.4668.96
2026-01-11 17:1540.4753.9767.47
2026-01-11 17:3038.4951.9965.49
2026-01-11 17:4536.8250.3263.82
2026-01-11 18:0036.1849.6863.18
2026-01-11 18:1536.9250.4263.92
2026-01-11 18:3038.9152.4165.91
2026-01-11 18:4541.5655.0668.56
2026-01-11 19:0044.1057.6071.10
2026-01-11 19:1545.7959.2972.79
2026-01-11 19:3046.2859.7873.28
2026-01-11 19:4545.7159.2172.71
2026-01-11 20:0044.6558.1571.65
2026-01-11 20:1543.8957.3970.89
2026-01-11 20:3044.1357.6371.13
2026-01-11 20:4545.7259.2272.72
2026-01-11 21:0048.5062.0075.50
2026-01-11 21:1551.8865.3878.88
2026-01-11 21:3055.0668.5682.06
2026-01-11 21:4557.3470.8484.34
2026-01-11 22:0058.3571.8585.35
2026-01-11 22:1558.2671.7685.26
2026-01-11 22:3057.6371.1384.63
2026-01-11 22:4557.2670.7684.26
2026-01-11 23:0057.8471.3484.84
2026-01-11 23:1559.7173.2186.71
2026-01-11 23:3062.6976.1989.69
2026-01-11 23:4566.1979.6993.19
2026-01-12 00:0069.4082.9096.40
2026-01-12 00:1571.6285.1298.62
2026-01-12 00:3072.5186.0199.51
2026-01-12 00:4572.2485.7499.24
2026-01-12 01:0071.3984.8998.39
2026-01-12 01:1570.7684.2697.76
2026-01-12 01:3071.0384.5398.03
2026-01-12 01:4572.5386.0399.53
2026-01-12 02:0075.0788.57102.07
2026-01-12 02:1578.0691.56105.06
2026-01-12 02:3080.6994.19107.69
2026-01-12 02:4582.2795.77109.27
2026-01-12 03:0082.4795.97109.47
2026-01-12 03:1581.4794.97108.47
2026-01-12 03:3079.8893.38106.88
2026-01-12 03:4578.4991.99105.49
2026-01-12 04:0077.9991.49104.99
2026-01-12 04:1578.6992.19105.69
2026-01-12 04:3080.4093.90107.40
2026-01-12 04:4582.5296.02109.52
2026-01-12 05:0084.2597.75111.25
2026-01-12 05:1584.8998.39111.89
2026-01-12 05:3084.1597.65111.15
2026-01-12 05:4582.2395.73109.23
2026-01-12 06:0079.7393.23106.73
2026-01-12 06:1577.4690.96104.46
2026-01-12 06:3076.1189.61103.11
2026-01-12 06:4575.9789.47102.97
2026-01-12 07:0076.8590.35103.85
2026-01-12 07:1578.1491.64105.14
2026-01-12 07:3079.0492.54106.04
2026-01-12 07:4578.8892.38105.88
2026-01-12 08:0077.3790.87104.37
2026-01-12 08:1574.7188.21101.71
2026-01-12 08:3071.5585.0598.55
2026-01-12 08:4568.6882.1895.68
2026-01-12 09:0066.7880.2893.78
2026-01-12 09:1566.1479.6493.14
2026-01-12 09:3066.5680.0693.56
2026-01-12 09:4567.4280.9294.42
2026-01-12 10:0067.9281.4294.92
2026-01-12 10:1567.4080.9094.40
2026-01-12 10:3065.5879.0892.58
2026-01-12 10:4562.6976.1989.69
2026-01-12 11:0059.3672.8686.36
2026-01-12 11:1556.4069.9083.40
2026-01-12 11:3054.4867.9881.48
2026-01-12 11:4553.8967.3980.89
2026-01-12 12:0054.4067.9081.40
2026-01-12 12:1555.3768.8782.37
2026-01-12 12:3056.0269.5283.02
2026-01-12 12:4555.6969.1982.69
2026-01-12 13:0054.1167.6181.11
2026-01-12 13:1551.5165.0178.51
2026-01-12 13:3048.5562.0575.55
2026-01-12 13:4546.0259.5273.02
2026-01-12 14:0044.6058.1071.60
2026-01-12 14:1544.5358.0371.53
2026-01-12 14:3045.5959.0972.59
2026-01-12 14:4547.1360.6374.13
2026-01-12 15:0048.3661.8675.36
2026-01-12 15:1548.6262.1275.62
2026-01-12 15:3047.6661.1674.66
2026-01-12 15:4545.7259.2272.72
05

Compare with historical outcomes

The quickstart backtest evaluates three consecutive historical windows, each from its own cutoff. Table 2 calculates error from synthetic predictions and synthetic observations, with a seasonal baseline for comparison. Lower CRPS, MAE, and RMSE indicate lower error; these values do not measure production model performance.

scores, rows = backtest(
    context_df,
    api_url=API_URL,
    headers=HEADERS,
    prediction_length=96,
    windows=3,
    quantile_levels=[0.1, 0.5, 0.9],
)
pd.DataFrame(scores["per_window"])
Table 2. Synthetic backtest · 3 windows · 288 observations · EUR/MWh
MetricSeasonal baselineDemo prediction
Continuous ranked probability score (CRPS)4.253.08
Mean absolute error (MAE)4.252.48
Root mean squared error (RMSE)4.983.02
P10–P90 interval coverageNot provided100.0%

Baseline: repeat the value from 24 hours earlier, repeated from the last complete period before each window. Interval coverage is the share of synthetic observations inside the illustrative interval. CRPS evaluates the full predictive distribution. This demo assumes a uniform distribution whose P10 and P90 match the plotted interval; the baseline is a point forecast, for which CRPS equals MAE.

From analysis to action

Use the forecast to compare dispatch periods. Add asset limits, round-trip efficiency, and transaction costs before you estimate revenue.

Ready to evaluate your own data?Read the API guide