electricsheepafrica/africa-libya-real-time-prices

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- energy
- food-security
- lby
pretty_name: "Libya - Real Time Prices"
dataset_info:
splits:
- name: train
num_examples: 3729
- name: test
num_examples: 932
---

# Libya - Real Time Prices

**Publisher:** World Bank Group · **Source:** [HDX](https://data.humdata.org/dataset/libya-real-time-prices) · **License:** `cc-by` · **Updated:** 2026-04-01

---

## Abstract

Real Time Prices (RTP) is a live dataset compiled and updated weekly by the World Bank Development Economics Data Group (DECDG) using a combination of direct price measurement and Machine Learning estimation of missing price data. The historical and current estimates are based on price information gathered from the World Food Program (WFP), UN-Food and Agricultural Organization (FAO), select National Statistical Offices, and are continually updated and revised as more price information becomes available. Real-time exchange rate data used in this process are from official and public sources.

RTP includes three sub-series, Real Time Food Prices (RTFP) includes prices on a variety of food items that primarily include country-specific staple foods, Real Time Energy Prices (RTEP) includes fuel prices, and Real Time Exchange Rates (RTFX) and includes unofficial exchange rate estimates as well as possible other unofficial deflators.

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

*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)** | 4,662 |
| **Columns** | 185 (172 numeric, 10 categorical, 3 datetime) |
| **Train split** | 3,729 rows |
| **Test split** | 932 rows |
| **Geographic scope** | LBY |
| **Publisher** | World Bank Group |
| **HDX last updated** | 2026-04-01 |

---

## Variables

**Geographic** — `iso3` (LBY), `country` (Libya), `lat` (range 24.2–32.92), `lon` (range 9.49–23.96), `year` (range 2017.0–2026.0) and 33 others.

**Temporal** — `dates`, `month` (range 1.0–12.0).

**Demographic** — `data_coverage` (range 49.44–49.44), `data_coverage_recent` (range 30.33–30.33).

**Identifier / Metadata** — `adm1_name` (West, South, East), `adm2_name` (Tripoli, Al Jabal Al Gharbi, Murzuq), `mkt_name` (Abusliem, Tarhuna, Murzuq), `geo_id` (gid_328700000132300000, gid_324300000136400000, gid_259100000139200000), `esa_source` (HDX) and 1 others.

**Other** — `components` (beans (400 G, Index Weight = 10), beans_fao (400 gms, Index Weight = 0.01), bread (5 pcs, Index Weight = 16), chickpeas (400 G, Index Weight = 20), chili (1 KG, Index Weight = 8), couscous (1 KG, Index Weight = 8), eggs (30 pcs, Index Weight = 2.67), fish_tuna_canned (200 G, Index Weight = 40), meat_chicken (1 KG, Index Weight = 8), meat_lamb (1 KG, Index Weight = 8), milk (1 L, Index Weight = 8), oil (1 L, Index Weight = 8), onions (1 KG, Index Weight = 4), onions_fao (1 Kg, Index Weight = 4), pasta (500 G, Index Weight = 16), potatoes (1 KG, Index Weight = 8), rice (1 KG, Index Weight = 8), salt (1 KG, Index Weight = 8), sugar (1 KG, Index Weight = 8), tea (250 G, Index Weight = 32), tomatoes (1 KG, Index Weight = 8), tomatoes_paste (400 G, Index Weight = 20), wheat_flour (1 KG, Index Weight = 8)), `start_dense_data`, `beans` (range 0.83–6.12), `bread` (range 0.31–6.25), `chickpeas` (range 0.44–8.0) and 132 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-libya-real-time-prices")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `iso3` | object | 0.0% | LBY |
| `country` | object | 0.0% | Libya |
| `adm1_name` | object | 0.0% | West, South, East |
| `adm2_name` | object | 0.0% | Tripoli, Al Jabal Al Gharbi, Murzuq |
| `mkt_name` | object | 0.0% | Abusliem, Tarhuna, Murzuq |
| `lat` | float64 | 2.4% | 24.2 – 32.92 (mean 30.9788) |
| `lon` | float64 | 2.4% | 9.49 – 23.96 (mean 14.7739) |
| `geo_id` | object | 0.0% | gid_328700000132300000, gid_324300000136400000, gid_259100000139200000 |
| `dates` | datetime64[ns] | 0.0% | |
| `year` | int64 | 0.0% | 2017.0 – 2026.0 (mean 2021.1351) |
| `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.3784) |
| `currency` | object | 0.0% | LYD |
| `components` | object | 0.0% | beans (400 G, Index Weight = 10), beans_fao (400 gms, Index Weight = 0.01), bread (5 pcs, Index Weight = 16), chickpeas (400 G, Index Weight = 20), chili (1 KG, Index Weight = 8), couscous (1 KG, Index Weight = 8), eggs (30 pcs, Index Weight = 2.67), fish_tuna_canned (200 G, Index Weight = 40), meat_chicken (1 KG, Index Weight = 8), meat_lamb (1 KG, Index Weight = 8), milk (1 L, Index Weight = 8), oil (1 L, Index Weight = 8), onions (1 KG, Index Weight = 4), onions_fao (1 Kg, Index Weight = 4), pasta (500 G, Index Weight = 16), potatoes (1 KG, Index Weight = 8), rice (1 KG, Index Weight = 8), salt (1 KG, Index Weight = 8), sugar (1 KG, Index Weight = 8), tea (250 G, Index Weight = 32), tomatoes (1 KG, Index Weight = 8), tomatoes_paste (400 G, Index Weight = 20), wheat_flour (1 KG, Index Weight = 8) |
| `start_dense_data` | datetime64[ns] | 0.0% | |
| `last_survey_point` | datetime64[ns] | 0.0% | |
| `data_coverage` | float64 | 0.0% | 49.44 – 49.44 (mean 49.44) |
| `data_coverage_recent` | float64 | 0.0% | 30.33 – 30.33 (mean 30.33) |
| `index_confidence_score` | float64 | 0.0% | 0.91 – 0.91 (mean 0.91) |
| `spatially_interpolated` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) |
| `beans` | float64 | 62.1% | 0.83 – 6.12 (mean 2.6651) |
| `bread` | float64 | 58.6% | 0.31 – 6.25 (mean 1.3812) |
| `chickpeas` | float64 | 60.8% | 0.44 – 8.0 (mean 2.6052) |
| `couscous` | float64 | 53.9% | 1.25 – 18.88 (mean 4.8176) |
| `eggs` | float64 | 58.2% | 1.17 – 27.0 (mean 13.4605) |
| `fish_tuna_canned` | float64 | 51.5% | 1.5 – 12.18 (mean 4.3806) |
| `meat_chicken` | float64 | 50.0% | 2.5 – 42.0 (mean 12.7803) |
| `meat_lamb` | float64 | 62.6% | 2.0 – 100.0 (mean 43.5603) |
| `milk` | float64 | 56.9% | 1.38 – 10.0 (mean 4.4341) |
| `oil` | float64 | 54.1% | 0.01 – 17.0 (mean 7.0906) |
| `onions` | float64 | 61.5% | 0.75 – 9.0 (mean 2.7086) |
| `pasta` | float64 | 61.3% | 0.94 – 7.5 (mean 2.1179) |
| `potatoes` | float64 | 51.9% | |
| `rice` | float64 | 52.1% | |
| `salt` | float64 | 58.3% | |
| `sugar` | float64 | 61.0% | |
| `tea` | float64 | 64.3% | |
| `tomatoes` | float64 | 49.5% | |
| `tomatoes_paste` | float64 | 54.7% | |
| `wheat_flour` | float64 | 50.7% | |
| `o_beans` | float64 | 0.0% | |
| `h_beans` | float64 | 0.0% | |
| `l_beans` | float64 | 0.0% | |
| `c_beans` | float64 | 0.0% | |
| `inflation_beans` | float64 | 10.8% | |
| `trust_beans` | float64 | 0.0% | |
| `o_beans_fao` | float64 | 0.0% | |
| `h_beans_fao` | float64 | 0.0% | |
| `l_beans_fao` | float64 | 0.0% | |
| `c_beans_fao` | float64 | 0.0% | |
| `inflation_beans_fao` | float64 | 10.8% | |
| `trust_beans_fao` | float64 | 0.0% | |
| `o_bread` | float64 | 0.0% | |
| `h_bread` | float64 | 0.0% | |
| `l_bread` | float64 | 0.0% | |
| `c_bread` | float64 | 0.0% | |
| `inflation_bread` | float64 | 10.8% | |
| `trust_bread` | float64 | 0.0% | |
| `o_chickpeas` | float64 | 0.0% | |
| `h_chickpeas` | float64 | 0.0% | |
| `l_chickpeas` | float64 | 0.0% | |
| `c_chickpeas` | float64 | 0.0% | |
| `inflation_chickpeas` | float64 | 10.8% | |
| `trust_chickpeas` | float64 | 0.0% | |
| `o_chili` | float64 | 0.0% | |
| `h_chili` | float64 | 0.0% | |
| `l_chili` | float64 | 0.0% | |
| `c_chili` | float64 | 0.0% | |
| `inflation_chili` | float64 | 10.8% | |
| `trust_chili` | float64 | 0.0% | |
| `o_couscous` | float64 | 0.0% | |
| `h_couscous` | float64 | 0.0% | |
| `l_couscous` | float64 | 0.0% | |
| `c_couscous` | float64 | 0.0% | |
| `inflation_couscous` | float64 | 10.8% | |
| `trust_couscous` | float64 | 0.0% | |
| `o_eggs` | float64 | 0.0% | |
| `h_eggs` | float64 | 0.0% | |
| `l_eggs` | float64 | 0.0% | |
| `c_eggs` | float64 | 0.0% | |
| `inflation_eggs` | float64 | 10.8% | |
| `trust_eggs` | float64 | 0.0% | |
| `o_fish_tuna_canned` | float64 | 0.0% | |
| `h_fish_tuna_canned` | float64 | 0.0% | |
| `l_fish_tuna_canned` | float64 | 0.0% | |
| `c_fish_tuna_canned` | float64 | 0.0% | |
| `inflation_fish_tuna_canned` | float64 | 10.8% | |
| `trust_fish_tuna_canned` | float64 | 0.0% | |
| `o_meat_chicken` | float64 | 0.0% | |
| `h_meat_chicken` | float64 | 0.0% | |
| `l_meat_chicken` | float64 | 0.0% | |
| `c_meat_chicken` | float64 | 0.0% | |
| `inflation_meat_chicken` | float64 | 10.8% | |
| `trust_meat_chicken` | float64 | 0.0% | |
| `o_meat_lamb` | float64 | 0.0% | |
| `h_meat_lamb` | float64 | 0.0% | |
| `l_meat_lamb` | float64 | 0.0% | |
| `c_meat_lamb` | float64 | 0.0% | |
| `inflation_meat_lamb` | float64 | 10.8% | |
| `trust_meat_lamb` | float64 | 0.0% | |
| `o_milk` | float64 | 0.0% | |
| `h_milk` | float64 | 0.0% | |
| `l_milk` | float64 | 0.0% | |
| `c_milk` | float64 | 0.0% | |
| `inflation_milk` | float64 | 10.8% | |
| `trust_milk` | float64 | 0.0% | |
| `o_oil` | float64 | 0.0% | |
| `h_oil` | float64 | 0.0% | |
| `l_oil` | float64 | 0.0% | |
| `c_oil` | float64 | 0.0% | |
| `inflation_oil` | float64 | 10.8% | |
| `trust_oil` | float64 | 0.0% | |
| `o_onions` | float64 | 0.0% | |
| `h_onions` | float64 | 0.0% | |
| `l_onions` | float64 | 0.0% | |
| `c_onions` | float64 | 0.0% | |
| `inflation_onions` | float64 | 10.8% | |
| `trust_onions` | float64 | 0.0% | |
| `o_onions_fao` | float64 | 0.0% | |
| `h_onions_fao` | float64 | 0.0% | |
| `l_onions_fao` | float64 | 0.0% | |
| `c_onions_fao` | float64 | 0.0% | |
| `inflation_onions_fao` | float64 | 10.8% | |
| `trust_onions_fao` | float64 | 0.0% | |
| `o_pasta` | float64 | 0.0% | |
| `h_pasta` | float64 | 0.0% | |
| `l_pasta` | float64 | 0.0% | |
| `c_pasta` | float64 | 0.0% | |
| `inflation_pasta` | float64 | 10.8% | |
| `trust_pasta` | float64 | 0.0% | |
| `o_potatoes` | float64 | 0.0% | |
| `h_potatoes` | float64 | 0.0% | |
| `l_potatoes` | float64 | 0.0% | |
| `c_potatoes` | float64 | 0.0% | |
| `inflation_potatoes` | float64 | 10.8% | |
| `trust_potatoes` | float64 | 0.0% | |
| `o_rice` | float64 | 0.0% | |
| `h_rice` | float64 | 0.0% | |
| `l_rice` | float64 | 0.0% | |
| `c_rice` | float64 | 0.0% | |
| `inflation_rice` | float64 | 10.8% | |
| `trust_rice` | float64 | 0.0% | |
| `o_salt` | float64 | 0.0% | |
| `h_salt` | float64 | 0.0% | |
| `l_salt` | float64 | 0.0% | |
| `c_salt` | float64 | 0.0% | |
| `inflation_salt` | float64 | 10.8% | |
| `trust_salt` | float64 | 0.0% | |
| `o_sugar` | float64 | 0.0% | |
| `h_sugar` | float64 | 0.0% | |
| `l_sugar` | float64 | 0.0% | |
| `c_sugar` | float64 | 0.0% | |
| `inflation_sugar` | float64 | 10.8% | |
| `trust_sugar` | float64 | 0.0% | |
| `o_tea` | float64 | 0.0% | |
| `h_tea` | float64 | 0.0% | |
| `l_tea` | float64 | 0.0% | |
| `c_tea` | float64 | 0.0% | |
| `inflation_tea` | float64 | 10.8% | |
| `trust_tea` | float64 | 0.0% | |
| `o_tomatoes` | float64 | 0.0% | |
| `h_tomatoes` | float64 | 0.0% | |
| `l_tomatoes` | float64 | 0.0% | |
| `c_tomatoes` | float64 | 0.0% | |
| `inflation_tomatoes` | float64 | 10.8% | |
| `trust_tomatoes` | float64 | 0.0% | |
| `o_tomatoes_paste` | float64 | 0.0% | |
| `h_tomatoes_paste` | float64 | 0.0% | |
| `l_tomatoes_paste` | float64 | 0.0% | |
| `c_tomatoes_paste` | float64 | 0.0% | |
| `inflation_tomatoes_paste` | float64 | 10.8% | |
| `trust_tomatoes_paste` | float64 | 0.0% | |
| `o_wheat_flour` | float64 | 0.0% | |
| `h_wheat_flour` | float64 | 0.0% | |
| `l_wheat_flour` | float64 | 0.0% | |
| `c_wheat_flour` | float64 | 0.0% | |
| `inflation_wheat_flour` | float64 | 10.8% | |
| `trust_wheat_flour` | float64 | 0.0% | |
| `o_food_price_index` | float64 | 0.0% | |
| `h_food_price_index` | float64 | 0.0% | |
| `l_food_price_index` | float64 | 0.0% | |
| `c_food_price_index` | float64 | 0.0% | |
| `inflation_food_price_index` | float64 | 10.8% | |
| `trust_food_price_index` | float64 | 0.0% | |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-06 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `lat` | 24.2 | 32.92 | 30.9788 | 32.33 |
| `lon` | 9.49 | 23.96 | 14.7739 | 13.35 |
| `year` | 2017.0 | 2026.0 | 2021.1351 | 2021.0 |
| `month` | 1.0 | 12.0 | 6.3784 | 6.0 |
| `data_coverage` | 49.44 | 49.44 | 49.44 | 49.44 |
| `data_coverage_recent` | 30.33 | 30.33 | 30.33 | 30.33 |
| `index_confidence_score` | 0.91 | 0.91 | 0.91 | 0.91 |
| `spatially_interpolated` | 0.0 | 0.0 | 0.0 | 0.0 |
| `beans` | 0.83 | 6.12 | 2.6651 | 2.5 |
| `bread` | 0.31 | 6.25 | 1.3812 | 1.25 |
| `chickpeas` | 0.44 | 8.0 | 2.6052 | 2.5 |
| `couscous` | 1.25 | 18.88 | 4.8176 | 4.0 |
| `eggs` | 1.17 | 27.0 | 13.4605 | 13.25 |
| `fish_tuna_canned` | 1.5 | 12.18 | 4.3806 | 4.25 |
| `meat_chicken` | 2.5 | 42.0 | 12.7803 | 11.48 |

---

## 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`. 675 column(s) with >80% missing values were removed: `apples`, `bananas`, `beans_egyptian`, `beans_fao`, `bread_fao`, `bulgur`.... 3 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 World Bank Group 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: `beans`, `bread`, `chickpeas`, `couscous`, `eggs`, `fish_tuna_canned`, `meat_chicken`, `meat_lamb`....
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/libya-real-time-prices) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_libya_real_time_prices,
title = {Libya - Real Time Prices},
author = {World Bank Group},
year = {2026},
url = {https://data.humdata.org/dataset/libya-real-time-prices},
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: 无标注
language_creators: 现有数据源采集
language: 英语
license: CC BY 4.0
multilinguality: 单语言
size_categories: 1K<n<10K
source_datasets: 原始数据集
task_categories: 表格回归
task_ids: 无
tags:
- 非洲
- 人道主义
- HDX
- Electric Sheep Africa
- 能源
- 粮食安全
- LBY
pretty_name: "利比亚——实时价格数据集"
dataset_info:
splits:
- name: train
num_examples: 3729
- name: test
num_examples: 932

# 利比亚——实时价格数据集

**发布方：** 世界银行集团（World Bank Group）· **数据源：** [人道主义数据交换（HDX）](https://data.humdata.org/dataset/libya-real-time-prices) · **许可协议：** `CC BY 4.0` · **更新日期：** 2026-04-01

---

## 摘要

实时价格数据集（Real Time Prices, RTP）是由世界银行发展经济学数据小组（World Bank Development Economics Data Group, DECDG）每周编制并更新的动态数据集，其整合了直接价格测量与机器学习（Machine Learning）对缺失价格数据的估算方法。历史与当前的价格估算基于从世界粮食计划署（World Food Programme, WFP）、联合国粮食及农业组织（Food and Agriculture Organization of the United Nations, FAO）以及部分国家统计办公室采集的价格信息，并会随着更多价格数据的获取持续更新与修正。本流程中使用的实时汇率数据均来自官方公开渠道。

RTP包含三个子系列：实时食品价格（Real Time Food Prices, RTFP）涵盖以本国主食为主的各类食品价格；实时能源价格（Real Time Energy Prices, RTEP）包含燃料价格；实时汇率（Real Time Exchange Rates, RTFX）则包含非官方汇率估算值及其他可能的非官方平减指数。

本数据集的每一行均代表国家级聚合数据，时间覆盖范围由`dates`、`start_dense_data`列标识，地理范围为**LBY（利比亚）**。

*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** | 粮食安全与营养保障 |
| **观测单元** | 国家级聚合数据 |
| **总行数** | 4,662 |
| **列数** | 185 (172 numeric, 10 categorical, 3 datetime) |
| **训练集划分** | 3,729行 |
| **测试集划分** | 932行 |
| **地理范围** | LBY |
| **发布方** | 世界银行集团（World Bank Group） |
| **HDX最后更新日期** | 2026-04-01 |

---

## 变量说明

**地理类变量**：`iso3`（LBY）、`country`（利比亚）、`lat`（范围：24.2–32.92）、`lon`（范围：9.49–23.96）、`year`（范围：2017.0–2026.0），另有33个其他地理变量。

**时间类变量**：`dates`、`month`（范围：1.0–12.0）。

**统计类变量**：`data_coverage`（范围：49.44–49.44）、`data_coverage_recent`（范围：30.33–30.33）。

**标识符与元数据变量**：`adm1_name`（西部、南部、东部）、`adm2_name`（的黎波里、杰贝勒加爾比、穆尔祖克）、`mkt_name`（阿布斯里姆、塔尔胡纳、穆尔祖克）、`geo_id`（gid_328700000132300000、gid_324300000136400000、gid_259100000139200000）、`esa_source`（HDX），另有1个其他标识符变量。

**其他变量**：`components`（包含400克芸豆（权重10）、400克FAO芸豆（权重0.01）、5个面包（权重16）、400克鹰嘴豆（权重20）、1千克辣椒（权重8）、1千克古斯米（权重8）、30个鸡蛋（权重2.67）、200克罐装金枪鱼（权重40）、1千克鸡肉（权重8）、1千克羊肉（权重8）、1升牛奶（权重8）、1升食用油（权重8）、1千克洋葱（权重4）、1千克FAO洋葱（权重4）、500克意面（权重16）、1千克土豆（权重8）、1千克大米（权重8）、1千克盐（权重8）、1千克糖（权重8）、250克茶叶（权重32）、1千克番茄（权重8）、400克番茄酱（权重20）、1千克小麦粉（权重8））、`start_dense_data`、`beans`（范围：0.83–6.12）、`bread`（范围：0.31–6.25）、`chickpeas`（范围：0.44–8.0），另有132个其他变量。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-libya-real-time-prices")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据 Schema

| 列名 | 数据类型 | 空值占比 | 取值范围/样本值 |
|---|---|---|---|
| `iso3` | object | 0.0% | LBY |
| `country` | object | 0.0% | 利比亚 |
| `adm1_name` | object | 0.0% | 西部、南部、东部 |
| `adm2_name` | object | 0.0% | 的黎波里、杰贝勒加爾比、穆尔祖克 |
| `mkt_name` | object | 0.0% | 阿布斯里姆、塔尔胡纳、穆尔祖克 |
| `lat` | float64 | 2.4% | 24.2 – 32.92（均值：30.9788） |
| `lon` | float64 | 2.4% | 9.49 – 23.96（均值：14.7739） |
| `geo_id` | object | 0.0% | gid_328700000132300000、gid_324300000136400000、gid_259100000139200000 |
| `dates` | datetime64[ns] | 0.0% | - |
| `year` | int64 | 0.0% | 2017.0 – 2026.0（均值：2021.1351） |
| `month` | int64 | 0.0% | 1.0 – 12.0（均值：6.3784） |
| `currency` | object | 0.0% | LYD |
| `components` | object | 0.0% | 详见前文变量说明 |
| `start_dense_data` | datetime64[ns] | 0.0% | - |
| `last_survey_point` | datetime64[ns] | 0.0% | - |
| `data_coverage` | float64 | 0.0% | 49.44 – 49.44（均值：49.44） |
| `data_coverage_recent` | float64 | 0.0% | 30.33 – 30.33（均值：30.33） |
| `index_confidence_score` | float64 | 0.0% | 0.91 – 0.91（均值：0.91） |
| `spatially_interpolated` | int64 | 0.0% | 0.0 – 0.0（均值：0.0） |
| `beans` | float64 | 62.1% | 0.83 – 6.12（均值：2.6651） |
| `bread` | float64 | 58.6% | 0.31 – 6.25（均值：1.3812） |
| `chickpeas` | float64 | 60.8% | 0.44 – 8.0（均值：2.6052） |
| `couscous` | float64 | 53.9% | 1.25 – 18.88（均值：4.8176） |
| `eggs` | float64 | 58.2% | 1.17 – 27.0（均值：13.4605） |
| `fish_tuna_canned` | float64 | 51.5% | 1.5 – 12.18（均值：4.3806） |
| `meat_chicken` | float64 | 50.0% | 2.5 – 42.0（均值：12.7803） |
| 后续列内容省略，详见原文 | ... | ... | ... |

---

## 数值型变量统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `lat` | 24.2 | 32.92 | 30.9788 | 32.33 |
| `lon` | 9.49 | 23.96 | 14.7739 | 13.35 |
| `year` | 2017.0 | 2026.0 | 2021.1351 | 2021.0 |
| `month` | 1.0 | 12.0 | 6.3784 | 6.0 |
| `data_coverage` | 49.44 | 49.44 | 49.44 | 49.44 |
| `data_coverage_recent` | 30.33 | 30.33 | 30.33 | 30.33 |
| `index_confidence_score` | 0.91 | 0.91 | 0.91 | 0.91 |
| `spatially_interpolated` | 0.0 | 0.0 | 0.0 | 0.0 |
| `beans` | 0.83 | 6.12 | 2.6651 | 2.5 |
| `bread` | 0.31 | 6.25 | 1.3812 | 1.25 |
| `chickpeas` | 0.44 | 8.0 | 2.6052 | 2.5 |
| `couscous` | 1.25 | 18.88 | 4.8176 | 4.0 |
| `eggs` | 1.17 | 27.0 | 13.4605 | 13.25 |
| `fish_tuna_canned` | 1.5 | 12.18 | 4.3806 | 4.25 |
| `meat_chicken` | 2.5 | 42.0 | 12.7803 | 11.48 |

---

## 数据整理流程

原始数据通过CKAN API从人道主义数据交换（HDX）平台下载，并转换为Parquet格式。所有列名均转换为小写并统一为蛇形命名法（snake_case）。常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。移除了675列缺失值占比超过80%的变量，包括`apples`、`bananas`、`beans_egyptian`、`beans_fao`、`bread_fao`、`bulgur`等。基于解析成功率（阈值>85%），将3列从字符型转换为数值型或日期时间型。数据集以固定随机种子（42）按照80/20的比例划分为训练集与测试集，并保存为Snappy压缩的Parquet格式。

---

## 数据集局限性

- 本数据集源自世界银行集团，尚未由Electric Sheep Africa（ESA）进行独立验证。
- 自动化数据清洗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。
- 以下列的缺失值占比超过20%，在建模过程中需谨慎使用：`beans`、`bread`、`chickpeas`、`couscous`、`eggs`、`fish_tuna_canned`、`meat_chicken`、`meat_lamb`等。
- 请参阅[HDX平台原始数据集页面](https://data.humdata.org/dataset/libya-real-time-prices)以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_libya_real_time_prices,
title = {利比亚——实时价格数据集},
author = {世界银行集团（World Bank Group)},
year = {2026},
url = {https://data.humdata.org/dataset/libya-real-time-prices},
note = {由Electric Sheep Africa重新打包为机器学习适配格式（https://huggingface.co/electricsheepafrica)}
}

---

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