electricsheepafrica/africa-wfp-food-prices-for-niger

---
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-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- economics
- food-security
- indicators
- markets
- ner
pretty_name: "Niger - Food Prices"
dataset_info:
splits:
- name: train
num_examples: 36052
- name: test
num_examples: 9013
---

# Niger - Food Prices

**Publisher:** WFP - World Food Programme · **Source:** [HDX](https://data.humdata.org/dataset/wfp-food-prices-for-niger) · **License:** `cc-by-igo` · **Updated:** 2026-04-05

---

## Abstract

This dataset contains Food Prices data for Niger, sourced from the World Food Programme Price Database. The World Food Programme Price Database covers foods such as maize, rice, beans, fish, and sugar for 98 countries and some 3000 markets. It is updated weekly but contains to a large extent monthly data. The data goes back as far as 1992 for a few countries, although many countries started reporting from 2003 or thereafter.

Each row in this dataset represents subnational administrative unit observations. Temporal coverage is indicated by the `date` column(s). Geographic scope: **NER**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Subnational administrative unit observations |
| **Rows (total)** | 45,066 |
| **Columns** | 18 (6 numeric, 11 categorical, 1 datetime) |
| **Train split** | 36,052 rows |
| **Test split** | 9,013 rows |
| **Geographic scope** | NER |
| **Publisher** | WFP - World Food Programme |
| **HDX last updated** | 2026-04-05 |

---

## Variables

**Geographic** — `admin1` (Tillaberi, Zinder, Maradi), `admin2` (Niamey, Madarounfa, Tillaberi), `latitude` (range 11.88–18.74), `longitude` (range 0.73–13.11), `category` (cereals and tubers, pulses and nuts, miscellaneous food) and 4 others.

**Temporal** — `date`.

**Outcome / Measurement** — `priceflag` (actual), `price` (range 32.0–55000.0), `usdprice` (range 0.072–121.02).

**Identifier / Metadata** — `market_id` (range 543.0–1463.0), `esa_source` (HDX), `esa_processed`.

**Other** — `market` (Agadez Commune, Maradi Commune, Dosso Commune), `unit` (KG, 100 KG, L).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-prices-for-niger")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `date` | datetime64[ns] | 0.0% | |
| `admin1` | object | 0.0% | Tillaberi, Zinder, Maradi |
| `admin2` | object | 0.0% | Niamey, Madarounfa, Tillaberi |
| `market` | object | 0.0% | Agadez Commune, Maradi Commune, Dosso Commune |
| `market_id` | int64 | 0.0% | 543.0 – 1463.0 (mean 610.1538) |
| `latitude` | float64 | 0.0% | 11.88 – 18.74 (mean 14.0894) |
| `longitude` | float64 | 0.0% | 0.73 – 13.11 (mean 5.766) |
| `category` | object | 0.0% | cereals and tubers, pulses and nuts, miscellaneous food |
| `commodity` | object | 0.0% | Millet, Rice (imported), Maize |
| `commodity_id` | int64 | 0.0% | 51.0 – 511.0 (mean 79.2614) |
| `unit` | object | 0.0% | KG, 100 KG, L |
| `priceflag` | object | 0.0% | actual |
| `pricetype` | object | 0.0% | Retail, Wholesale |
| `currency` | object | 0.0% | XOF |
| `price` | float64 | 0.0% | 32.0 – 55000.0 (mean 1555.4758) |
| `usdprice` | float64 | 0.0% | 0.072 – 121.02 (mean 2.9829) |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `market_id` | 543.0 | 1463.0 | 610.1538 | 591.0 |
| `latitude` | 11.88 | 18.74 | 14.0894 | 13.81 |
| `longitude` | 0.73 | 13.11 | 5.766 | 6.15 |
| `commodity_id` | 51.0 | 511.0 | 79.2614 | 65.0 |
| `price` | 32.0 | 55000.0 | 1555.4758 | 248.0 |
| `usdprice` | 0.072 | 121.02 | 2.9829 | 0.48 |

---

## 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`. 1 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 WFP - World Food Programme 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/wfp-food-prices-for-niger) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_wfp_food_prices_for_niger,
title = {Niger - Food Prices},
author = {WFP - World Food Programme},
year = {2026},
url = {https://data.humdata.org/dataset/wfp-food-prices-for-niger},
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.*

---
annotations_creators:
- 无注释
language_creators:
- 现有资源抓取
language:
- 英语
license: CC-BY-4.0
multilinguality:
- 单语言
size_categories:
- 10K<n<100K
source_datasets:
- 原创数据集
task_categories:
- 表格回归（tabular-regression）
- 其他
task_ids: []
tags:
- 非洲
- 人道主义
- HDX（Humanitarian Data Exchange）
- Electric Sheep Africa
- 经济学
- 粮食安全
- 指标
- 市场
- 命名实体识别（NER，Named Entity Recognition）
pretty_name: "尼日尔——食品价格"
dataset_info:
splits:
- name: train
num_examples: 36052
- name: test
num_examples: 9013
---

# 尼日尔——食品价格

**发布方：世界粮食计划署（World Food Programme，WFP）** · **数据来源：[HDX（Humanitarian Data Exchange）](https://data.humdata.org/dataset/wfp-food-prices-for-niger)** · **许可证：`cc-by-igo`** · **最后更新：2026-04-05**

---

## 摘要

本数据集包含源自世界粮食计划署价格数据库的尼日尔食品价格数据。世界粮食计划署价格数据库覆盖98个国家约3000个市场的玉米、大米、豆类、鱼类及食糖等食品价格，每周更新且绝大多数为月度统计数据。部分国家的最早数据可追溯至1992年，多数国家则从2003年及之后开始上报数据。

本数据集的每一行代表次国家级行政单元的观测值，时间覆盖范围由`date`（日期）列标注。地理覆盖范围：**NER（尼日尔国家代码）**。

*本数据集已由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式。*

---

## 数据集特征

| | |
|---|---|
| **领域** | 粮食保障与营养 |
| **观测单元** | 次国家级行政单元观测值 |
| **总样本量** | 45,066 |
| **列数** | 共18列（6个数值型、11个分类型、1个日期时间型） |
| **训练集划分** | 36,052条样本 |
| **测试集划分** | 9,013条样本 |
| **地理覆盖范围** | NER |
| **发布方** | 世界粮食计划署（WFP） |
| **HDX最后更新时间** | 2026-04-05 |

---

## 变量说明

**地理类变量**：`admin1`（蒂拉贝里、津德尔、马拉迪，尼日尔一级行政区）、`admin2`（尼亚美、马达鲁纳法、蒂拉贝里）、`latitude`（纬度范围：11.88–18.74）、`longitude`（经度范围：0.73–13.11）、`category`（类别：谷物与块根作物、豆类与坚果、其他食品）及另外4个变量。
**时间类变量**：`date`（日期）。
**结果/测量变量**：`priceflag`（价格标记：实际值）、`price`（本地货币价格，范围：32.0–55000.0）、`usdprice`（美元计价价格，范围：0.072–121.02）。
**标识符/元数据变量**：`market_id`（市场ID，范围：543.0–1463.0）、`esa_source`（数据来源：HDX）、`esa_processed`（处理标记）。
**其他变量**：`market`（市场名称：阿加德兹公社、马拉迪公社、多索公社）、`unit`（计价单位：KG、100 KG、L）。

---

## 快速入门

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-wfp-food-prices-for-niger")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据模式

| 列名 | 数据类型 | 缺失率 | 取值范围/示例值 |
|---|---|---|---|
| `date` | datetime64[ns] | 0.0% | 无 |
| `admin1` | object（字符串型） | 0.0% | 蒂拉贝里、津德尔、马拉迪 |
| `admin2` | object（字符串型） | 0.0% | 尼亚美、马达鲁纳法、蒂拉贝里 |
| `market` | object（字符串型） | 0.0% | 阿加德兹公社、马拉迪公社、多索公社 |
| `market_id` | int64（整数型） | 0.0% | 543.0 – 1463.0（均值：610.1538） |
| `latitude` | float64（浮点型） | 0.0% | 11.88 – 18.74（均值：14.0894） |
| `longitude` | float64（浮点型） | 0.0% | 0.73 – 13.11（均值：5.766） |
| `category` | object（字符串型） | 0.0% | 谷物与块根作物、豆类与坚果、其他食品 |
| `commodity` | object（字符串型） | 0.0% | 小米、进口大米、玉米 |
| `commodity_id` | int64（整数型） | 0.0% | 51.0 – 511.0（均值：79.2614） |
| `unit` | object（字符串型） | 0.0% | KG、100 KG、L |
| `priceflag` | object（字符串型） | 0.0% | actual（实际值） |
| `pricetype` | object（字符串型） | 0.0% | 零售、批发 |
| `currency` | object（字符串型） | 0.0% | XOF（非洲金融共同体法郎） |
| `price` | float64（浮点型） | 0.0% | 32.0 – 55000.0（均值：1555.4758） |
| `usdprice` | float64（浮点型） | 0.0% | 0.072 – 121.02（均值：2.9829） |
| `esa_source` | object（字符串型） | 0.0% | HDX |
| `esa_processed` | object（字符串型） | 0.0% | 无 |

---

## 数值统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `market_id` | 543.0 | 1463.0 | 610.1538 | 591.0 |
| `latitude` | 11.88 | 18.74 | 14.0894 | 13.81 |
| `longitude` | 0.73 | 13.11 | 5.766 | 6.15 |
| `commodity_id` | 51.0 | 511.0 | 79.2614 | 65.0 |
| `price` | 32.0 | 55000.0 | 1555.4758 | 248.0 |
| `usdprice` | 0.072 | 121.02 | 2.9829 | 0.48 |

---

## 数据整理流程

原始数据通过CKAN API从HDX下载，并转换为Parquet格式。列名统一转换为小写并标准化为蛇形命名法（snake_case）。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。根据解析成功率（阈值>85%），将1列从字符串类型转换为数值型或日期时间型。本数据集以固定随机种子（42）按80/20比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式文件。

---

## 局限性说明

- 本数据集源自世界粮食计划署（WFP），未由Electric Sheep Africa进行独立验证。
- 自动化清洗流程无法修正原始数据收集中的错报值、定义不一致或抽样偏差问题。
- 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/wfp-food-prices-for-niger)查看发布方的官方方法说明与免责条款。

---

## 引用格式

bibtex
@dataset{hdx_africa_wfp_food_prices_for_niger,
title = {Niger - Food Prices},
author = {WFP - World Food Programme},
year = {2026},
url = {https://data.humdata.org/dataset/wfp-food-prices-for-niger},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施，尼日利亚拉各斯。*