electricsheepafrica/africa-fewsnet-staple-food-price-data-for-mauritania-weekly-1506

---
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
- mrt
pretty_name: "Mauritania Weekly FEWS NET Staple Food Price Data"
dataset_info:
splits:
- name: train
num_examples: 48848
- name: test
num_examples: 12212
---

# Mauritania Weekly FEWS NET Staple Food Price Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_mauritania_weekly_1506) · **License:** `cc-by` · **Updated:** 2026-04-01

---

## Abstract

Mauritania Weekly staple food price data collected by FEWS NET since 2002.

Each row in this dataset represents country-level aggregates. Temporal coverage is indicated by the `period_date` column(s). Geographic scope: **MRT**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 61,061 |
| **Columns** | 17 (3 numeric, 13 categorical, 1 datetime) |
| **Train split** | 48,848 rows |
| **Test split** | 12,212 rows |
| **Geographic scope** | MRT |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-04-01 |

---

## Variables

**Geographic** — `country` (Mauritania), `admin_1` (Brakna, Hodh ech Chargui, Adrar), `longitude` (range -17.0382–-7.0234), `latitude` (range 15.6651–20.9457), `price_type` (Retail) and 2 others.

**Temporal** — `period_date`.

**Outcome / Measurement** — `value` (range 1.0–75000.0).

**Identifier / Metadata** — `source_document` (Famine Early Warning Systems Network (FEWS NET), Mauritania, Price), `product_source` (Local, Import), `esa_source`, `esa_processed`.

**Other** — `market` (Adel Bagrou, Boghé, Magta-lahjar), `cpcv2` (R01112AA, P23110AA, R01142AN), `product` (Wheat Grain, Wheat Flour, Sorghum (Taghalit, Mixed)), `unit` (kg, ea, 50_kg).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-fewsnet-staple-food-price-data-for-mauritania-weekly-1506")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `country` | object | 0.0% | Mauritania |
| `market` | object | 0.0% | Adel Bagrou, Boghé, Magta-lahjar |
| `admin_1` | object | 0.0% | Brakna, Hodh ech Chargui, Adrar |
| `longitude` | float64 | 0.0% | -17.0382 – -7.0234 (mean -12.5862) |
| `latitude` | float64 | 0.0% | 15.6651 – 20.9457 (mean 17.4155) |
| `cpcv2` | object | 0.0% | R01112AA, P23110AA, R01142AN |
| `product` | object | 0.0% | Wheat Grain, Wheat Flour, Sorghum (Taghalit, Mixed) |
| `source_document` | object | 0.0% | Famine Early Warning Systems Network (FEWS NET), Mauritania, Price |
| `period_date` | datetime64[ns] | 0.0% | |
| `price_type` | object | 0.0% | Retail |
| `product_source` | object | 0.0% | Local, Import |
| `unit` | object | 0.0% | kg, ea, 50_kg |
| `unit_type` | object | 0.0% | Weight, Item, Volume |
| `currency` | object | 0.0% | |
| `value` | float64 | 28.2% | 1.0 – 75000.0 (mean 2135.7188) |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `longitude` | -17.0382 | -7.0234 | -12.5862 | -13.0916 |
| `latitude` | 15.6651 | 20.9457 | 17.4155 | 16.6185 |
| `value` | 1.0 | 75000.0 | 2135.7188 | 73.29 |

---

## 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 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.
- The following columns have >20% missing values and should be treated with caution in modelling: `value`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_mauritania_weekly_1506) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_fewsnet_staple_food_price_data_for_mauritania_weekly_1506,
title = {Mauritania Weekly FEWS NET Staple Food Price Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_mauritania_weekly_1506},
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:
- 采集所得
language:
- 英语
license: cc-by-4.0
multilinguality:
- 单语言
size_categories:
- 10000条至100000条
source_datasets:
- 原创数据集
task_categories:
- 表格回归
- 其他
task_ids: []
tags:
- 非洲
- 人道主义
- HDX
- electric-sheep-africa
- 经济学
- 粮食安全
- 指标
- 市场
- 毛里塔尼亚（MRT）
pretty_name: "毛里塔尼亚周度FEWS NET主粮价格数据集"
dataset_info:
splits:
- name: train
num_examples: 48848
- name: test
num_examples: 12212

# 毛里塔尼亚周度FEWS NET主粮价格数据集

**发布方：** FEWS NET · **来源：** [HDX](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_mauritania_weekly_1506) · **许可协议：** `cc-by` · **更新时间：** 2026-04-01

---

## 摘要

本数据集为饥荒早期预警网络（Famine Early Warning Systems Network，简称FEWS NET）自2002年起收集的毛里塔尼亚周度主粮价格数据。

数据集中每一行代表国家级聚合数据。时间覆盖范围由`period_date`列标注。地理覆盖范围：毛里塔尼亚（MRT）。

*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** | 粮食安全与营养 |
| **观测单元** | 国家级聚合数据 |
| **总数据行数** | 61061 |
| **列数** | 17列（3个数值型、13个分类型、1个日期时间型） |
| **训练集划分** | 48848行 |
| **测试集划分** | 12212行 |
| **地理覆盖范围** | 毛里塔尼亚（MRT） |
| **发布方** | FEWS NET |
| **HDX最后更新时间** | 2026-04-01 |

---

## 变量分类

**地理类变量** — `country`（国家：毛里塔尼亚）、`admin_1`（一级行政区域：布拉克纳、霍德埃什沙鲁伊、阿德拉尔）、`longitude`（经度：范围-17.0382至-7.0234）、`latitude`（纬度：范围15.6651至20.9457）、`price_type`（价格类型：零售）及另外2个变量。
**时间类变量** — `period_date`（时间周期）。
**结果/测量变量** — `value`（价格数值：范围1.0至75000.0）。
**标识符/元数据变量** — `source_document`（源文档：饥荒早期预警网络（FEWS NET）、毛里塔尼亚、价格数据）、`product_source`（产品来源：本地、进口）、`esa_source`、`esa_processed`。
**其他变量** — `market`（市场：阿德尔巴格鲁、博盖、马格塔拉哈贾尔）、`cpcv2`（分类代码：R01112AA、P23110AA、R01142AN）、`product`（产品：小麦粒、小麦粉、高粱（塔加利特混合种））、`unit`（计量单位：千克、件、50千克装）。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-fewsnet-staple-food-price-data-for-mauritania-weekly-1506")
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 |
|---|---|---|---|
| `country` | 字符型（object） | 0.0% | 毛里塔尼亚 |
| `market` | 字符型（object） | 0.0% | 阿德尔巴格鲁、博盖、马格塔拉哈贾尔 |
| `admin_1` | 字符型（object） | 0.0% | 布拉克纳、霍德埃什沙鲁伊、阿德拉尔 |
| `longitude` | 浮点型（float64） | 0.0% | -17.0382 – -7.0234（均值：-12.5862） |
| `latitude` | 浮点型（float64） | 0.0% | 15.6651 – 20.9457（均值：17.4155） |
| `cpcv2` | 字符型（object） | 0.0% | R01112AA、P23110AA、R01142AN |
| `product` | 字符型（object） | 0.0% | 小麦粒、小麦粉、高粱（塔加利特混合种） |
| `source_document` | 字符型（object） | 0.0% | 饥荒早期预警网络（FEWS NET）、毛里塔尼亚、价格数据 |
| `period_date` | 日期时间型（datetime64[ns]） | 0.0% | 无 |
| `price_type` | 字符型（object） | 0.0% | 零售 |
| `product_source` | 字符型（object） | 0.0% | 本地、进口 |
| `unit` | 字符型（object） | 0.0% | 千克、件、50千克装 |
| `unit_type` | 字符型（object） | 0.0% | 重量、件数、体积 |
| `currency` | 字符型（object） | 0.0% | 无 |
| `value` | 浮点型（float64） | 28.2% | 1.0 – 75000.0（均值：2135.7188） |
| `esa_source` | 字符型（object） | 0.0% | 无 |
| `esa_processed` | 字符型（object） | 0.0% | 无 |

---

## 数值型变量统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `longitude` | -17.0382 | -7.0234 | -12.5862 | -13.0916 |
| `latitude` | 15.6651 | 20.9457 | 17.4155 | 16.6185 |
| `value` | 1.0 | 75000.0 | 2135.7188 | 73.29 |

---

## 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采用蛇形命名法（snake_case）进行标准化。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列从字符型转换为数值型或日期时间型。本数据集采用固定随机种子（42）按80/20比例划分为训练集与测试集，并以Snappy压缩格式存储为Parquet文件。

---

## 数据集局限性

- 数据源自FEWS NET，未经过Electric Sheep Africa的独立验证。
- 自动化清洗无法修正原始数据收集中的错报值、定义不一致或采样偏差问题。
- 以下列存在超过20%的缺失值，在建模时需谨慎使用：`value`（价格数值）。
- 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_mauritania_weekly_1506)获取发布方提供的方法说明与注意事项。

---

## 引用格式

bibtex
@dataset{hdx_africa_fewsnet_staple_food_price_data_for_mauritania_weekly_1506,
title = {Mauritania Weekly FEWS NET Staple Food Price Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/fewsnet_staple_food_price_data_for_mauritania_weekly_1506},
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。*