Time-series classification

Predict a class for a whole sequence — for example one outcome per patient stay, device or session from its multivariate time series. The dataset is a single CSV with one row per time step; the rows of one sequence share a sequence_id and are ordered by timestamp within that sequence. The label is per sequence and repeats on every row of it.

Folder layout

/data/shared/icu-sepsis/
└── vitals.csv

Data CSV

sequence_id,timestamp,heart_rate,resp_rate,temperature,spo2,lactate,label
patient_001,2024-03-10 08:00:00,69.0,25.3,36.1,94.8,3.43,1
patient_001,2024-03-10 09:00:00,71.6,25.6,38.6,95.0,,1
patient_001,2024-03-10 10:00:00,78.1,20.6,39.1,90.3,3.53,1
patient_002,2024-03-11 08:00:00,105.9,19.0,37.1,98.5,2.47,0
patient_002,2024-03-11 09:00:00,80.7,16.3,37.4,90.3,,0

Column	Meaning
`sequence_id`	Fixed name. The entity whose rows form one sequence (patient, device, session). Declared in `schema` as `VARCHAR`; no row may leave it empty.
`timestamp`	Fixed name. Orders the rows within a sequence. Declared in `schema` either as a calendar type (`TIMESTAMP`, `DATETIME`, `DATE` — use ISO 8601 values) or as a numeric step index (`INT`, `FLOAT`, …). Must be non-decreasing within each sequence; sequences may be interleaved. No missing values.
feature columns	Numeric, declared in `schema`. Empty cells are allowed (a lab value not measured at every step).
label column (`label` here)	Named by `label:`, not declared in `schema`. Constant within each sequence. At least two distinct values across the dataset.

Sequences may have different lengths. Keep each sequence complete within one ingest. Record counts on the platform are sequences, while the ingest progress line counts rows, and a sequence split across two ingests is counted twice.

Ingest with the CLI

Pass the CSV file, or a folder that holds only that CSV. Ingest the training and the test split separately:

tracebloc data ingest ./vitals_train.csv --task time_series_classification --name icu_vitals_sepsis_train --intent train --label-column label \
  --schema 'sequence_id:VARCHAR(64),timestamp:TIMESTAMP,heart_rate:FLOAT,resp_rate:FLOAT,temperature:FLOAT,spo2:FLOAT,lactate:FLOAT,label:INT'
tracebloc data ingest ./vitals_test.csv --task time_series_classification --name icu_vitals_sepsis_test --intent test --label-column label \
  --schema 'sequence_id:VARCHAR(64),timestamp:TIMESTAMP,heart_rate:FLOAT,resp_rate:FLOAT,temperature:FLOAT,spo2:FLOAT,lactate:FLOAT,label:INT'

Without --schema, the CLI infers a type for every column. Passing it, as above, pins sequence_id as text and timestamp as a calendar type. Quote it: VARCHAR(64) contains shell characters. --schema replaces the inferred schema, so list every column you want stored. Including the label column in --schema is fine: the ingestor drops it from the stored schema.

ingest.yaml

apiVersion: tracebloc.io/v1
kind: IngestConfig
category: time_series_classification
table: icu_vitals_sepsis_train
intent: train
csv: /data/shared/icu-sepsis/vitals.csv
schema:
  sequence_id: VARCHAR(64)   # group key — fixed name
  timestamp: TIMESTAMP       # order key within a sequence — fixed name; INT for a step index
  heart_rate: FLOAT
  resp_rate: FLOAT
  temperature: FLOAT
  spo2: FLOAT
  lactate: FLOAT             # blank cells allowed
label: label

Field	Required	Meaning
`csv`	yes	Path to the data CSV.
`schema`	yes (with the CLI, inferred for you)	Must declare both `sequence_id` and `timestamp`, plus the numeric feature columns. A non-text type for `sequence_id` is accepted with a warning.
`label`	yes	Name of the per-sequence outcome column. String shorthand — this is a classification task.
`time_column`	leave out	The order column is always `timestamp`; any other value is rejected at preflight.
`data_id`	no	Must not use `strategy: column` with `column: sequence_id` — row ids are unique per row, so every sequence would collapse to one row.
`columns`, `spec.csv_options`	no	See the contract.

What the ingestor checks

Check	Rejects
Sequence group	A CSV without `sequence_id`; rows with an empty `sequence_id`; a `data_id` column strategy pointed at `sequence_id`.
Label constant within group	Any sequence whose label value changes between its rows (including a mix of a value and empty cells).
Per-group time ordered	A missing or unparseable `timestamp` on any row; rows within a sequence that are not sorted ascending by `timestamp`; day-first/month-first ambiguous dates when `timestamp` is a calendar type.
Numeric columns	A non-numeric value in any schema column other than `sequence_id` and `timestamp`. Empty cells are allowed.
Data types	Duplicate headers, schema columns missing from the CSV, values that do not match their type (every schema column except `timestamp`).
Label diversity	Fewer than two distinct label values.

Plus the checks every ingest runs. After the rows are stored, an integrity pass removes any sequence that lost rows to a failed insert, so a sequence is stored whole or not at all, and the run then exits with an error.

Sample dataset

The template ships 30 hourly rows of synthetic ICU vitals for six sequences (3 to 7 steps each) with five FLOAT features (heart_rate, resp_rate, temperature, spo2, lactate — the last with legal blanks) and a binary per-sequence label — the rows shown above are taken from it. The ingest.yaml above ingests it as is; only csv: changes to wherever you staged the file.

Model settings for this dataset

When you link a model, the platform checks it against the dataset (see model parameters by task):

num_feature_points must equal the number of stored columns minus the label, sequence_id and timestamp. For the sample, that is 5.
output_classes must equal the number of distinct labels. For the sample, that is 2.
sequence_length is the number of time steps the model sees per sequence. Shorter sequences are zero-padded to it, and longer ones keep their most recent steps. The sample’s sequences have 3 to 7 steps.

The model-zoo templates default to 9 features and a sequence_length of 60, so edit them. Feature columns reach the model sorted by column name, whatever order the CSV or schema uses.

Next steps

Ingest the data: Prepare Data
Shared rules for every template: Dataset templates

Overview

Create a Use Case

Join a Use Case

Environment Setup

Tools & Help

Releases

Time-series classification

Folder layout

Data CSV

Ingest with the CLI

ingest.yaml

What the ingestor checks

Sample dataset

Model settings for this dataset

Next steps

​Folder layout

​Data CSV

​Ingest with the CLI

​ingest.yaml

​What the ingestor checks

​Sample dataset

​Model settings for this dataset

​Next steps

Folder layout

Data CSV

Ingest with the CLI

ingest.yaml

What the ingestor checks

Sample dataset

Model settings for this dataset

Next steps