electricsheepafrica/africa-kenya-current-situation-fewsnet-ipc-classification

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- food-security
- ken
pretty_name: "Kenya Current Situation FEWS NET Acute Food Insecurity Classifications Data"
dataset_info:
splits:
- name: train
num_examples: 22155
- name: test
num_examples: 5538
---

# Kenya Current Situation FEWS NET Acute Food Insecurity Classifications Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/kenya_current_situation_fewsnet_ipc_classification) · **License:** `cc-by` · **Updated:** 2026-04-03

---

## Abstract

Kenya Current Situation FEWS NET Acute Food Insecurity Classifications Data from 2011

Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `projection_start`, `projection_end` column(s). Geographic scope: **KEN**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 27,694 |
| **Columns** | 40 (9 numeric, 23 categorical, 7 datetime) |
| **Train split** | 22,155 rows |
| **Test split** | 5,538 rows |
| **Geographic scope** | KEN |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-04-03 |

---

## Variables

**Geographic** — `country` (Kenya), `country_code` (KE), `fewsnet_region` (East Africa), `unit_type` (fsc_admin_lhz, fsc_admin, idp_camp), `specialization_type` and 2 others.

**Temporal** — `datacollectionperiod` (range 158525.0–378017.0), `reporting_date`.

**Outcome / Measurement** — `value` (range 1.0–4.0).

**Identifier / Metadata** — `source_organization` (FEWS NET), `source_document` (Food Security Outlook, Kenya), `geographic_unit_full_name` (Northwestern Pastoral Zone, Nyiro, Samburu North, Samburu, Kenya, Northeastern Pastoral Zone, As - Habito, Mandera North, Mandera, Kenya, Lake Turkana Fishing, Katilia, Turkana East, Turkana, Kenya), `geographic_unit_name` (Western High Potential Zone, Central Highlands, High Potential Zone, Northeastern Pastoral Zone), `fnid` (KE2016C325020601, KE2016C309040109, KE2016C323030204) and 8 others.

**Other** — `geographic_group` (Eastern Africa), `classification_scale`, `is_allowing_for_assistance`, `projection_start`, `projection_end` and 12 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-kenya-current-situation-fewsnet-ipc-classification")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `source_organization` | object | 0.0% | FEWS NET |
| `source_document` | object | 0.0% | Food Security Outlook, Kenya |
| `country` | object | 0.0% | Kenya |
| `country_code` | object | 0.0% | KE |
| `geographic_group` | object | 0.0% | Eastern Africa |
| `fewsnet_region` | object | 0.0% | East Africa |
| `geographic_unit_full_name` | object | 0.0% | Northwestern Pastoral Zone, Nyiro, Samburu North, Samburu, Kenya, Northeastern Pastoral Zone, As - Habito, Mandera North, Mandera, Kenya, Lake Turkana Fishing, Katilia, Turkana East, Turkana, Kenya |
| `geographic_unit_name` | object | 0.0% | Western High Potential Zone, Central Highlands, High Potential Zone, Northeastern Pastoral Zone |
| `unit_type` | object | 0.0% | fsc_admin_lhz, fsc_admin, idp_camp |
| `fnid` | object | 0.0% | KE2016C325020601, KE2016C309040109, KE2016C323030204 |
| `classification_scale` | object | 0.0% | |
| `scenario_name` | object | 0.0% | |
| `preference_rating` | int64 | 0.0% | 90.0 – 90.0 (mean 90.0) |
| `is_allowing_for_assistance` | bool | 0.0% | |
| `projection_start` | datetime64[ns] | 0.0% | |
| `projection_end` | datetime64[ns] | 0.0% | |
| `status` | object | 0.0% | |
| `value` | float64 | 0.0% | 1.0 – 4.0 (mean 1.6475) |
| `description` | object | 0.0% | |
| `id` | int64 | 0.0% | 24356764.0 – 41441225.0 (mean 27346475.7801) |
| `datacollectionperiod` | int64 | 0.0% | 158525.0 – 378017.0 (mean 206349.7314) |
| `datacollection` | int64 | 0.0% | 168256.0 – 388818.0 (mean 216944.8049) |
| `scenario` | object | 0.0% | |
| `geographic_unit` | int64 | 0.0% | 22892.0 – 184237.0 (mean 29320.5663) |
| `datasourceorganization` | int64 | 0.0% | 1.0 – 1.0 (mean 1.0) |
| `datasourcedocument` | int64 | 0.0% | 6549.0 – 6549.0 (mean 6549.0) |
| `dataseries` | int64 | 0.0% | 6471043.0 – 6899733.0 (mean 6579163.2559) |
| `dataseries_name` | object | 0.0% | |
| `specialization_type` | object | 0.0% | |
| `dataseries_specialization_type` | object | 0.0% | |
| `data_usage_policy` | object | 0.0% | |
| `created` | datetime64[ns] | 0.0% | |
| `modified` | datetime64[ns] | 0.0% | |
| `status_changed` | datetime64[ns] | 0.0% | |
| `collection_status` | object | 0.0% | |
| `collection_status_changed` | datetime64[ns] | 0.0% | |
| `collection_schedule` | object | 0.0% | |
| `reporting_date` | datetime64[ns] | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `preference_rating` | 90.0 | 90.0 | 90.0 | 90.0 |
| `value` | 1.0 | 4.0 | 1.6475 | 1.0 |
| `id` | 24356764.0 | 41441225.0 | 27346475.7801 | 24707063.5 |
| `datacollectionperiod` | 158525.0 | 378017.0 | 206349.7314 | 160337.0 |
| `datacollection` | 168256.0 | 388818.0 | 216944.8049 | 168975.0 |
| `geographic_unit` | 22892.0 | 184237.0 | 29320.5663 | 32300.0 |
| `datasourceorganization` | 1.0 | 1.0 | 1.0 | 1.0 |
| `datasourcedocument` | 6549.0 | 6549.0 | 6549.0 | 6549.0 |
| `dataseries` | 6471043.0 | 6899733.0 | 6579163.2559 | 6515532.0 |

---

## Curation

Raw data was downloaded from HDX via the CKAN API and converted to Parquet. Column names were lowercased and standardised to snake_case. Common missing-value markers (`N/A`, `null`, `none`, `-`, `unknown`, `no data`, `#N/A`) were unified to `NaN`. 3 column(s) with >80% missing values were removed: `pct_phase3`, `pct_phase4`, `pct_phase5`. 7 column(s) were cast from string to numeric or datetime based on parse-success rate (>85% threshold). The dataset was split 80/20 into train and test partitions using a fixed random seed (42) and saved as Snappy-compressed Parquet.

---

## Limitations

- Data originates from FEWS NET and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/kenya_current_situation_fewsnet_ipc_classification) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_kenya_current_situation_fewsnet_ipc_classification,
title = {Kenya Current Situation FEWS NET Acute Food Insecurity Classifications Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/kenya_current_situation_fewsnet_ipc_classification},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}
```

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — Africa's ML dataset infrastructure. Lagos, Nigeria.*