electricsheepafrica/africa-uganda-real-time-prices
收藏资源简介：
--- 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 task_ids: [] tags: - africa - humanitarian - hdx - electric-sheep-africa - energy - food-security - uga pretty_name: "Uganda - Real Time Prices" dataset_info: splits: - name: train num_examples: 8131 - name: test num_examples: 2032 --- # Uganda - Real Time Prices **Publisher:** World Bank Group · **Source:** [HDX](https://data.humdata.org/dataset/uganda-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: **UGA**. *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)** | 10,164 | | **Columns** | 89 (76 numeric, 10 categorical, 3 datetime) | | **Train split** | 8,131 rows | | **Test split** | 2,032 rows | | **Geographic scope** | UGA | | **Publisher** | World Bank Group | | **HDX last updated** | 2026-04-01 | --- ## Variables **Geographic** — `iso3` (UGA), `country` (Uganda), `lat` (range -1.25–3.57), `lon` (range 29.99–34.83), `year` (range 2007.0–2026.0) and 20 others. **Temporal** — `dates`, `month` (range 1.0–12.0). **Demographic** — `data_coverage` (range 17.36–17.36), `data_coverage_recent` (range 32.95–32.95). **Identifier / Metadata** — `adm1_name` (Arua, Hoima, Nakapiripirit), `adm2_name` (Dodoth, Terego, Bukanga), `mkt_name` (Adjumani (refugee settlement), Arua, Masaka), `geo_id` (gid_33400000317800000, gid_30200000309100000, gid_-3500000317400000), `esa_source` (HDX) and 1 others. **Other** — `components` (beans (1 KG, Index Weight = 1), cassava_flour (1 KG, Index Weight = 0.5), cassava_flour_fao (1 Kg, Index Weight = 0.5), maize (1 KG, Index Weight = 1), maize_flour (1 KG, Index Weight = 1), millet (1 KG, Index Weight = 0.5), millet_fao (1 Kg, Index Weight = 0.5), oil (1 L, Index Weight = 1), sorghum (1 KG, Index Weight = 0.5), sorghum_fao (1 Kg, Index Weight = 0.5)), `start_dense_data`, `beans` (range 143.82–6678.0), `maize_flour` (range 600.0–4625.0), `o_beans` (range 824.61–6652.06) and 49 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-uganda-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% | UGA | | `country` | object | 0.0% | Uganda | | `adm1_name` | object | 0.0% | Arua, Hoima, Nakapiripirit | | `adm2_name` | object | 0.0% | Dodoth, Terego, Bukanga | | `mkt_name` | object | 0.0% | Adjumani (refugee settlement), Arua, Masaka | | `lat` | float64 | 2.3% | -1.25 – 3.57 (mean 1.5444) | | `lon` | float64 | 2.3% | 29.99 – 34.83 (mean 32.4309) | | `geo_id` | object | 0.0% | gid_33400000317800000, gid_30200000309100000, gid_-3500000317400000 | | `dates` | datetime64[ns] | 0.0% | | | `year` | int64 | 0.0% | 2007.0 – 2026.0 (mean 2016.1299) | | `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.4416) | | `currency` | object | 0.0% | UGX | | `components` | object | 0.0% | beans (1 KG, Index Weight = 1), cassava_flour (1 KG, Index Weight = 0.5), cassava_flour_fao (1 Kg, Index Weight = 0.5), maize (1 KG, Index Weight = 1), maize_flour (1 KG, Index Weight = 1), millet (1 KG, Index Weight = 0.5), millet_fao (1 Kg, Index Weight = 0.5), oil (1 L, Index Weight = 1), sorghum (1 KG, Index Weight = 0.5), sorghum_fao (1 Kg, Index Weight = 0.5) | | `start_dense_data` | datetime64[ns] | 0.0% | | | `last_survey_point` | datetime64[ns] | 0.0% | | | `data_coverage` | float64 | 0.0% | 17.36 – 17.36 (mean 17.36) | | `data_coverage_recent` | float64 | 0.0% | 32.95 – 32.95 (mean 32.95) | | `index_confidence_score` | float64 | 0.0% | 0.92 – 0.92 (mean 0.92) | | `spatially_interpolated` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) | | `beans` | float64 | 78.6% | 143.82 – 6678.0 (mean 3199.9037) | | `maize_flour` | float64 | 78.9% | 600.0 – 4625.0 (mean 2363.3877) | | `o_beans` | float64 | 0.0% | 824.61 – 6652.06 (mean 2533.2348) | | `h_beans` | float64 | 0.0% | 851.86 – 7108.98 (mean 2701.5267) | | `l_beans` | float64 | 0.0% | 734.71 – 6197.57 (mean 2370.2096) | | `c_beans` | float64 | 0.0% | 734.71 – 6590.85 (mean 2532.8432) | | `inflation_beans` | float64 | 5.2% | -64.88 – 216.18 (mean 8.4331) | | `trust_beans` | float64 | 0.0% | 7.9 – 10.0 (mean 8.4282) | | `o_cassava_flour` | float64 | 0.0% | 271.28 – 5619.97 (mean 1513.5723) | | `h_cassava_flour` | float64 | 0.0% | 318.0 – 6279.71 (mean 1628.1869) | | `l_cassava_flour` | float64 | 0.0% | 236.43 – 4960.23 (mean 1401.5815) | | `c_cassava_flour` | float64 | 0.0% | 267.49 – 5718.39 (mean 1513.288) | | `inflation_cassava_flour` | float64 | 5.2% | | | `trust_cassava_flour` | float64 | 0.0% | | | `o_cassava_flour_fao` | float64 | 0.0% | | | `h_cassava_flour_fao` | float64 | 0.0% | | | `l_cassava_flour_fao` | float64 | 0.0% | | | `c_cassava_flour_fao` | float64 | 0.0% | | | `inflation_cassava_flour_fao` | float64 | 5.2% | | | `trust_cassava_flour_fao` | float64 | 0.0% | | | `o_maize` | float64 | 0.0% | | | `h_maize` | float64 | 0.0% | | | `l_maize` | float64 | 0.0% | | | `c_maize` | float64 | 0.0% | | | `inflation_maize` | float64 | 5.2% | | | `trust_maize` | float64 | 0.0% | | | `o_maize_flour` | float64 | 0.0% | | | `h_maize_flour` | float64 | 0.0% | | | `l_maize_flour` | float64 | 0.0% | | | `c_maize_flour` | float64 | 0.0% | | | `inflation_maize_flour` | float64 | 5.2% | | | `trust_maize_flour` | float64 | 0.0% | | | `o_millet` | float64 | 0.0% | | | `h_millet` | float64 | 0.0% | | | `l_millet` | float64 | 0.0% | | | `c_millet` | float64 | 0.0% | | | `inflation_millet` | float64 | 5.2% | | | `trust_millet` | float64 | 0.0% | | | `o_millet_fao` | float64 | 0.0% | | | `h_millet_fao` | float64 | 0.0% | | | `l_millet_fao` | float64 | 0.0% | | | `c_millet_fao` | float64 | 0.0% | | | `inflation_millet_fao` | float64 | 5.2% | | | `trust_millet_fao` | 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 | 5.2% | | | `trust_oil` | float64 | 0.0% | | | `o_sorghum` | float64 | 0.0% | | | `h_sorghum` | float64 | 0.0% | | | `l_sorghum` | float64 | 0.0% | | | `c_sorghum` | float64 | 0.0% | | | `inflation_sorghum` | float64 | 5.2% | | | `trust_sorghum` | float64 | 0.0% | | | `o_sorghum_fao` | float64 | 0.0% | | | `h_sorghum_fao` | float64 | 0.0% | | | `l_sorghum_fao` | float64 | 0.0% | | | `c_sorghum_fao` | float64 | 0.0% | | | `inflation_sorghum_fao` | float64 | 5.2% | | | `trust_sorghum_fao` | 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 | 5.2% | | | `trust_food_price_index` | float64 | 0.0% | | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-05 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `lat` | -1.25 | 3.57 | 1.5444 | 1.54 | | `lon` | 29.99 | 34.83 | 32.4309 | 32.31 | | `year` | 2007.0 | 2026.0 | 2016.1299 | 2016.0 | | `month` | 1.0 | 12.0 | 6.4416 | 6.0 | | `data_coverage` | 17.36 | 17.36 | 17.36 | 17.36 | | `data_coverage_recent` | 32.95 | 32.95 | 32.95 | 32.95 | | `index_confidence_score` | 0.92 | 0.92 | 0.92 | 0.92 | | `spatially_interpolated` | 0.0 | 0.0 | 0.0 | 0.0 | | `beans` | 143.82 | 6678.0 | 3199.9037 | 3200.0 | | `maize_flour` | 600.0 | 4625.0 | 2363.3877 | 2200.0 | | `o_beans` | 824.61 | 6652.06 | 2533.2348 | 2350.24 | | `h_beans` | 851.86 | 7108.98 | 2701.5267 | 2527.05 | | `l_beans` | 734.71 | 6197.57 | 2370.2096 | 2185.585 | | `c_beans` | 734.71 | 6590.85 | 2532.8432 | 2348.9 | | `inflation_beans` | -64.88 | 216.18 | 8.4331 | 4.875 | --- ## 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`. 771 column(s) with >80% missing values were removed: `apples`, `bananas`, `beans_egyptian`, `beans_fao`, `bread`, `bread_fao`.... 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`, `maize_flour`. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/uganda-real-time-prices) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_uganda_real_time_prices, title = {Uganda - Real Time Prices}, author = {World Bank Group}, year = {2026}, url = {https://data.humdata.org/dataset/uganda-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: - 无注释 language_creators: - 公开采集 language: - 英语（en） license: CC BY 4.0 multilinguality: - 单语言 size_categories: - 10000<样本量<100000 source_datasets: - 原创数据集 task_categories: - 表格回归 task_ids: [] tags: - 非洲 - 人道主义 - HDX（Humanitarian Data Exchange，人道主义数据交换平台） - Electric Sheep Africa - 能源 - 粮食安全 - 乌干达（UGA） pretty_name: "乌干达——实时价格数据集" dataset_info: splits: - name: 训练集 num_examples: 8131 - name: 测试集 num_examples: 2032 # 乌干达——实时价格数据集 **发布方：世界银行集团 · 数据源：[HDX（Humanitarian Data Exchange，人道主义数据交换平台）](https://data.humdata.org/dataset/uganda-real-time-prices) · 许可证：`cc-by` · 更新时间：2026-04-01** --- ## 摘要 实时价格（Real Time Prices, RTP）是由世界银行发展经济学数据小组（DECDG）每周编译更新的实时数据集，通过直接价格测量与机器学习（Machine Learning）估算缺失价格数据相结合的方式生成。历史与当前价格估算基于从世界粮食计划署（World Food Program, WFP）、联合国粮食及农业组织（Food and Agricultural Organization of the United Nations, FAO）以及部分国家统计办公室收集的价格信息，并会随着更多价格数据的获取持续更新与修订。本流程中使用的实时汇率数据均来自官方公开渠道。 RTP包含三个子序列：实时粮食价格（Real Time Food Prices, RTFP）涵盖各类食品的价格，主要包含特定国家的主食；实时能源价格（Real Time Energy Prices, RTEP）包含燃油价格；实时汇率（Real Time Exchange Rates, RTFX）则包含非官方汇率估算值以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`列标注。地理范围：**乌干达（UGA）**。 *本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适用于机器学习的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 | | **总样本量** | 10164条 | | **字段数** | 89个（76个数值型、10个分类型、3个日期型） | | **训练集划分** | 8131条 | | **测试集划分** | 2032条 | | **地理范围** | 乌干达（UGA） | | **发布方** | 世界银行集团 | | **HDX最后更新时间** | 2026-04-01 | --- ## 变量 **地理类字段** — `iso3`（UGA）、`country`（乌干达）、`lat`（取值范围：-1.25–3.57）、`lon`（取值范围：29.99–34.83）、`year`（取值范围：2007.0–2026.0）及另外20个字段。 **时间类字段** — `dates`、`month`（取值范围：1.0–12.0）。 **人口统计类字段** — `data_coverage`（取值范围：17.36–17.36）、`data_coverage_recent`（取值范围：32.95–32.95）。 **标识符与元数据类字段** — `adm1_name`（阿鲁阿、霍伊马、纳卡皮里皮里特）、`adm2_name`（多托斯、特雷戈、布坎加）、`mkt_name`（阿朱马尼（难民营）、阿鲁阿、马萨卡）、`geo_id`（gid_33400000317800000、gid_30200000309100000、gid_-3500000317400000）、`esa_source`（HDX）及另外1个字段。 **其他字段** — `components`（beans (1 KG, Index Weight = 1)：1公斤大豆，权重1；cassava_flour (1 KG, Index Weight = 0.5)：1公斤木薯粉，权重0.5；cassava_flour_fao (1 Kg, Index Weight = 0.5)：1公斤木薯粉（FAO来源），权重0.5；maize (1 KG, Index Weight = 1)：1公斤玉米，权重1；maize_flour (1 KG, Index Weight = 1)：1公斤玉米粉，权重1；millet (1 KG, Index Weight = 0.5)：1公斤小米，权重0.5；millet_fao (1 Kg, Index Weight = 0.5)：1公斤小米（FAO来源），权重0.5；oil (1 L, Index Weight = 1)：1升食用油，权重1；sorghum (1 KG, Index Weight = 0.5)：1公斤高粱，权重0.5；sorghum_fao (1 Kg, Index Weight = 0.5)：1公斤高粱（FAO来源），权重0.5），`start_dense_data`，`beans`（取值范围：143.82–6678.0）、`maize_flour`（取值范围：600.0–4625.0）、`o_beans`（取值范围：824.61–6652.06）及另外49个字段。 --- ## 快速入门 python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-uganda-real-time-prices") train = ds["train"].to_pandas() test = ds["test"].to_pandas() print(train.shape) train.head() --- ## 字段结构 | 字段名 | 数据类型 | 空值占比 | 取值/示例值 | |---|---|---|---| | `iso3` | 字符型（object） | 0.0% | UGA | | `country` | 字符型（object） | 0.0% | 乌干达 | | `adm1_name` | 字符型（object） | 0.0% | 阿鲁阿、霍伊马、纳卡皮里皮里特 | | `adm2_name` | 字符型（object） | 0.0% | 多托斯、特雷戈、布坎加 | | `mkt_name` | 字符型（object） | 0.0% | 阿朱马尼（难民营）、阿鲁阿、马萨卡 | | `lat` | 浮点型（float64） | 2.3% | -1.25 – 3.57（均值：1.5444） | | `lon` | 浮点型（float64） | 2.3% | 29.99 – 34.83（均值：32.4309） | | `geo_id` | 字符型（object） | 0.0% | gid_33400000317800000、gid_30200000309100000、gid_-3500000317400000 | | `dates` | 日期时间型（datetime64[ns]） | 0.0% | 无 | | `year` | 整型（int64） | 0.0% | 2007.0 – 2026.0（均值：2016.1299） | | `month` | 整型（int64） | 0.0% | 1.0 – 12.0（均值：6.4416） | | `currency` | 字符型（object） | 0.0% | UGX | | `components` | 字符型（object） | 0.0% | beans (1 KG, Index Weight = 1)、cassava_flour (1 KG, Index Weight = 0.5)等 | | `start_dense_data` | 日期时间型（datetime64[ns]） | 0.0% | 无 | | `last_survey_point` | 日期时间型（datetime64[ns]） | 0.0% | 无 | | `data_coverage` | 浮点型（float64） | 0.0% | 17.36 – 17.36（均值：17.36） | | `data_coverage_recent` | 浮点型（float64） | 0.0% | 32.95 – 32.95（均值：32.95） | | `index_confidence_score` | 浮点型（float64） | 0.0% | 0.92 – 0.92（均值：0.92） | | `spatially_interpolated` | 整型（int64） | 0.0% | 0.0 – 0.0（均值：0.0） | | `beans` | 浮点型（float64） | 78.6% | 143.82 – 6678.0（均值：3199.9037） | | `maize_flour` | 浮点型（float64） | 78.9% | 600.0 – 4625.0（均值：2363.3877） | | `o_beans` | 浮点型（float64） | 0.0% | 824.61 – 6652.06（均值：2533.2348） | | `h_beans` | 浮点型（float64） | 0.0% | 851.86 – 7108.98（均值：2701.5267） | | `l_beans` | 浮点型（float64） | 0.0% | 734.71 – 6197.57（均值：2370.2096） | | `c_beans` | 浮点型（float64） | 0.0% | 734.71 – 6590.85（均值：2532.8432） | | `inflation_beans` | 浮点型（float64） | 5.2% | -64.88 – 216.18（均值：8.4331） | | `trust_beans` | 浮点型（float64） | 0.0% | 7.9 – 10.0（均值：8.4282） | | 其余字段因篇幅省略，详见原文 | | | | --- ## 数值统计摘要 | 字段名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `lat` | -1.25 | 3.57 | 1.5444 | 1.54 | | `lon` | 29.99 | 34.83 | 32.4309 | 32.31 | | `year` | 2007.0 | 2026.0 | 2016.1299 | 2016.0 | | `month` | 1.0 | 12.0 | 6.4416 | 6.0 | | `data_coverage` | 17.36 | 17.36 | 17.36 | 17.36 | | `data_coverage_recent` | 32.95 | 32.95 | 32.95 | 32.95 | | `index_confidence_score` | 0.92 | 0.92 | 0.92 | 0.92 | | `spatially_interpolated` | 0.0 | 0.0 | 0.0 | 0.0 | | `beans` | 143.82 | 6678.0 | 3199.9037 | 3200.0 | | `maize_flour` | 600.0 | 4625.0 | 2363.3877 | 2200.0 | | `o_beans` | 824.61 | 6652.06 | 2533.2348 | 2350.24 | | `h_beans` | 851.86 | 7108.98 | 2701.5267 | 2527.05 | | `l_beans` | 734.71 | 6197.57 | 2370.2096 | 2185.585 | | `c_beans` | 734.71 | 6590.85 | 2532.8432 | 2348.9 | | `inflation_beans` | -64.88 | 216.18 | 8.4331 | 4.875 | --- ## 数据整理 原始数据通过CKAN API从HDX下载，并转换为Parquet格式。字段名统一转换为小写蛇形命名法。将常见缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）统一替换为`NaN`。删除了771个缺失值占比超过80%的字段：`apples`、`bananas`、`beans_egyptian`、`beans_fao`、`bread`、`bread_fao`等。基于解析成功率（阈值85%），将3个字段从字符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。 --- ## 局限性说明 - 本数据集源自世界银行集团，未由Electric Sheep Africa进行独立验证。 - 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。 - 以下字段的缺失值占比超过20%，在建模时需谨慎使用：`beans`、`maize_flour`。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/uganda-real-time-prices)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_uganda_real_time_prices, title = {乌干达——实时价格数据集}, author = {世界银行集团}, year = {2026}, url = {https://data.humdata.org/dataset/uganda-real-time-prices}, note = {由Electric Sheep Africa重新打包为机器学习可用格式（https://huggingface.co/electricsheepafrica）} } --- *[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施。尼日利亚拉各斯。*
