electricsheepafrica/africa-guinea-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 - gin pretty_name: "Guinea - Real Time Prices" dataset_info: splits: - name: train num_examples: 3679 - name: test num_examples: 919 --- # Guinea - Real Time Prices **Publisher:** World Bank Group · **Source:** [HDX](https://data.humdata.org/dataset/guinea-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: **GIN**. *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)** | 4,599 | | **Columns** | 140 (127 numeric, 10 categorical, 3 datetime) | | **Train split** | 3,679 rows | | **Test split** | 919 rows | | **Geographic scope** | GIN | | **Publisher** | World Bank Group | | **HDX last updated** | 2026-04-01 | --- ## Variables **Geographic** — `iso3` (GIN), `country` (Guinea), `lat` (range 7.75–12.48), `lon` (range -14.3–-8.53), `year` (range 2008.0–2026.0) and 28 others. **Temporal** — `dates`, `month` (range 1.0–12.0). **Demographic** — `data_coverage` (range 23.56–23.56), `data_coverage_recent` (range 34.14–34.14). **Identifier / Metadata** — `adm1_name` (Kindia, Nzerekore, Boke), `adm2_name` (Conakry, Boke, Beyla), `mkt_name` (Beyla, Gueckedou, Tanène), `geo_id` (gid_86900000-86400000, gid_85700000-101300000, gid_110100000-142400000), `esa_source` (HDX) and 1 others. **Other** — `components` (beans (1 KG, Index Weight = 1), bread (1 Unit, Index Weight = 1), cassava_meal (1 KG, Index Weight = 1), fish (1 KG, Index Weight = 1), fonio (1 KG, Index Weight = 1), groundnuts (1 KG, Index Weight = 1), maize (1 KG, Index Weight = 1), meat_beef (1 KG, Index Weight = 0.5), meat_beef_fao (1 Kg, Index Weight = 0.5), oil (1 L, Index Weight = 0.5), oil_fao (1 Liter, Index Weight = 0.5), onions (1 KG, Index Weight = 1), potatoes (1 KG, Index Weight = 1), rice (1 KG, Index Weight = 0.5), rice_fao (1 Kg, Index Weight = 0.5), salt (1 KG, Index Weight = 1), sugar (1 KG, Index Weight = 1), tomatoes (1 KG, Index Weight = 1)), `start_dense_data`, `beans` (range 3000.0–32000.0), `bread` (range 1667.0–17833.0), `maize` (range 1833.33–70000.0) and 92 others. --- ## Quick Start ```python from datasets import load_dataset ds = load_dataset("electricsheepafrica/africa-guinea-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% | GIN | | `country` | object | 0.0% | Guinea | | `adm1_name` | object | 0.0% | Kindia, Nzerekore, Boke | | `adm2_name` | object | 0.0% | Conakry, Boke, Beyla | | `mkt_name` | object | 0.0% | Beyla, Gueckedou, Tanène | | `lat` | float64 | 4.8% | 7.75 – 12.48 (mean 9.721) | | `lon` | float64 | 4.8% | -14.3 – -8.53 (mean -11.839) | | `geo_id` | object | 0.0% | gid_86900000-86400000, gid_85700000-101300000, gid_110100000-142400000 | | `dates` | datetime64[ns] | 0.0% | | | `year` | int64 | 0.0% | 2008.0 – 2026.0 (mean 2016.6301) | | `month` | int64 | 0.0% | 1.0 – 12.0 (mean 6.4384) | | `currency` | object | 0.0% | GNF | | `components` | object | 0.0% | beans (1 KG, Index Weight = 1), bread (1 Unit, Index Weight = 1), cassava_meal (1 KG, Index Weight = 1), fish (1 KG, Index Weight = 1), fonio (1 KG, Index Weight = 1), groundnuts (1 KG, Index Weight = 1), maize (1 KG, Index Weight = 1), meat_beef (1 KG, Index Weight = 0.5), meat_beef_fao (1 Kg, Index Weight = 0.5), oil (1 L, Index Weight = 0.5), oil_fao (1 Liter, Index Weight = 0.5), onions (1 KG, Index Weight = 1), potatoes (1 KG, Index Weight = 1), rice (1 KG, Index Weight = 0.5), rice_fao (1 Kg, Index Weight = 0.5), salt (1 KG, Index Weight = 1), sugar (1 KG, Index Weight = 1), tomatoes (1 KG, Index Weight = 1) | | `start_dense_data` | datetime64[ns] | 0.0% | | | `last_survey_point` | datetime64[ns] | 0.0% | | | `data_coverage` | float64 | 0.0% | 23.56 – 23.56 (mean 23.56) | | `data_coverage_recent` | float64 | 0.0% | 34.14 – 34.14 (mean 34.14) | | `index_confidence_score` | float64 | 0.0% | 0.95 – 0.95 (mean 0.95) | | `spatially_interpolated` | int64 | 0.0% | 0.0 – 0.0 (mean 0.0) | | `beans` | float64 | 78.4% | 3000.0 – 32000.0 (mean 10052.3796) | | `bread` | float64 | 78.0% | 1667.0 – 17833.0 (mean 3425.4843) | | `maize` | float64 | 77.3% | 1833.33 – 70000.0 (mean 6486.8629) | | `oil` | float64 | 79.9% | 4413.0 – 40000.0 (mean 11106.8097) | | `rice` | float64 | 73.6% | 2647.0 – 29167.0 (mean 6714.5058) | | `o_beans` | float64 | 7.3% | 3304.71 – 31868.47 (mean 9302.4192) | | `h_beans` | float64 | 7.3% | 3739.94 – 34149.82 (mean 9806.0215) | | `l_beans` | float64 | 7.3% | 3040.86 – 29567.31 (mean 8816.6677) | | `c_beans` | float64 | 7.3% | 3046.6 – 31876.33 (mean 9320.2585) | | `inflation_beans` | float64 | 12.8% | -66.19 – 228.23 (mean 7.7132) | | `trust_beans` | float64 | 7.3% | 8.1 – 10.0 (mean 8.5982) | | `o_bread` | float64 | 7.3% | 1287.06 – 6290.68 (mean 3079.5393) | | `h_bread` | float64 | 7.3% | | | `l_bread` | float64 | 7.3% | | | `c_bread` | float64 | 7.3% | | | `inflation_bread` | float64 | 12.8% | | | `trust_bread` | float64 | 7.3% | | | `o_cassava_meal` | float64 | 7.3% | | | `h_cassava_meal` | float64 | 7.3% | | | `l_cassava_meal` | float64 | 7.3% | | | `c_cassava_meal` | float64 | 7.3% | | | `inflation_cassava_meal` | float64 | 12.8% | | | `trust_cassava_meal` | float64 | 7.3% | | | `o_fish` | float64 | 7.3% | | | `h_fish` | float64 | 7.3% | | | `l_fish` | float64 | 7.3% | | | `c_fish` | float64 | 7.3% | | | `inflation_fish` | float64 | 12.8% | | | `trust_fish` | float64 | 7.3% | | | `o_fonio` | float64 | 7.3% | | | `h_fonio` | float64 | 7.3% | | | `l_fonio` | float64 | 7.3% | | | `c_fonio` | float64 | 7.3% | | | `inflation_fonio` | float64 | 12.8% | | | `trust_fonio` | float64 | 7.3% | | | `o_groundnuts` | float64 | 7.3% | | | `h_groundnuts` | float64 | 7.3% | | | `l_groundnuts` | float64 | 7.3% | | | `c_groundnuts` | float64 | 7.3% | | | `inflation_groundnuts` | float64 | 12.8% | | | `trust_groundnuts` | float64 | 7.3% | | | `o_maize` | float64 | 7.3% | | | `h_maize` | float64 | 7.3% | | | `l_maize` | float64 | 7.3% | | | `c_maize` | float64 | 7.3% | | | `inflation_maize` | float64 | 12.8% | | | `trust_maize` | float64 | 7.3% | | | `o_meat_beef` | float64 | 7.3% | | | `h_meat_beef` | float64 | 7.3% | | | `l_meat_beef` | float64 | 7.3% | | | `c_meat_beef` | float64 | 7.3% | | | `inflation_meat_beef` | float64 | 12.8% | | | `trust_meat_beef` | float64 | 7.3% | | | `o_meat_beef_fao` | float64 | 7.3% | | | `h_meat_beef_fao` | float64 | 7.3% | | | `l_meat_beef_fao` | float64 | 7.3% | | | `c_meat_beef_fao` | float64 | 7.3% | | | `inflation_meat_beef_fao` | float64 | 12.8% | | | `trust_meat_beef_fao` | float64 | 7.3% | | | `o_oil` | float64 | 7.3% | | | `h_oil` | float64 | 7.3% | | | `l_oil` | float64 | 7.3% | | | `c_oil` | float64 | 7.3% | | | `inflation_oil` | float64 | 12.8% | | | `trust_oil` | float64 | 7.3% | | | `o_oil_fao` | float64 | 7.3% | | | `h_oil_fao` | float64 | 7.3% | | | `l_oil_fao` | float64 | 7.3% | | | `c_oil_fao` | float64 | 7.3% | | | `inflation_oil_fao` | float64 | 12.8% | | | `trust_oil_fao` | float64 | 7.3% | | | `o_onions` | float64 | 7.3% | | | `h_onions` | float64 | 7.3% | | | `l_onions` | float64 | 7.3% | | | `c_onions` | float64 | 7.3% | | | `inflation_onions` | float64 | 12.8% | | | `trust_onions` | float64 | 7.3% | | | `o_potatoes` | float64 | 7.3% | | | `h_potatoes` | float64 | 7.3% | | | `l_potatoes` | float64 | 7.3% | | | `c_potatoes` | float64 | 7.3% | | | `inflation_potatoes` | float64 | 12.8% | | | `trust_potatoes` | float64 | 7.3% | | | `o_rice` | float64 | 7.3% | | | `h_rice` | float64 | 7.3% | | | `l_rice` | float64 | 7.3% | | | `c_rice` | float64 | 7.3% | | | `inflation_rice` | float64 | 12.8% | | | `trust_rice` | float64 | 7.3% | | | `o_rice_fao` | float64 | 7.3% | | | `h_rice_fao` | float64 | 7.3% | | | `l_rice_fao` | float64 | 7.3% | | | `c_rice_fao` | float64 | 7.3% | | | `inflation_rice_fao` | float64 | 12.8% | | | `trust_rice_fao` | float64 | 7.3% | | | `o_salt` | float64 | 7.3% | | | `h_salt` | float64 | 7.3% | | | `l_salt` | float64 | 7.3% | | | `c_salt` | float64 | 7.3% | | | `inflation_salt` | float64 | 12.8% | | | `trust_salt` | float64 | 7.3% | | | `o_sugar` | float64 | 7.3% | | | `h_sugar` | float64 | 7.3% | | | `l_sugar` | float64 | 7.3% | | | `c_sugar` | float64 | 7.3% | | | `inflation_sugar` | float64 | 12.8% | | | `trust_sugar` | float64 | 7.3% | | | `o_tomatoes` | float64 | 7.3% | | | `h_tomatoes` | float64 | 7.3% | | | `l_tomatoes` | float64 | 7.3% | | | `c_tomatoes` | float64 | 7.3% | | | `inflation_tomatoes` | float64 | 12.8% | | | `trust_tomatoes` | float64 | 7.3% | | | `o_food_price_index` | float64 | 7.3% | | | `h_food_price_index` | float64 | 7.3% | | | `l_food_price_index` | float64 | 7.3% | | | `c_food_price_index` | float64 | 7.3% | | | `inflation_food_price_index` | float64 | 12.8% | | | `trust_food_price_index` | float64 | 7.3% | | | `esa_source` | object | 0.0% | HDX | | `esa_processed` | object | 0.0% | 2026-04-06 | --- ## Numeric Summary | Column | Min | Max | Mean | Median | |---|---|---|---|---| | `lat` | 7.75 | 12.48 | 9.721 | 9.575 | | `lon` | -14.3 | -8.53 | -11.839 | -12.575 | | `year` | 2008.0 | 2026.0 | 2016.6301 | 2017.0 | | `month` | 1.0 | 12.0 | 6.4384 | 6.0 | | `data_coverage` | 23.56 | 23.56 | 23.56 | 23.56 | | `data_coverage_recent` | 34.14 | 34.14 | 34.14 | 34.14 | | `index_confidence_score` | 0.95 | 0.95 | 0.95 | 0.95 | | `spatially_interpolated` | 0.0 | 0.0 | 0.0 | 0.0 | | `beans` | 3000.0 | 32000.0 | 10052.3796 | 9000.0 | | `bread` | 1667.0 | 17833.0 | 3425.4843 | 3000.0 | | `maize` | 1833.33 | 70000.0 | 6486.8629 | 6167.0 | | `oil` | 4413.0 | 40000.0 | 11106.8097 | 10500.0 | | `rice` | 2647.0 | 29167.0 | 6714.5058 | 6667.0 | | `o_beans` | 3304.71 | 31868.47 | 9302.4192 | 7918.5 | | `h_beans` | 3739.94 | 34149.82 | 9806.0215 | 8292.66 | --- ## 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`. 720 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`, `maize`, `oil`, `rice`. - Refer to the [original HDX dataset page](https://data.humdata.org/dataset/guinea-real-time-prices) for the publisher's own methodology notes and caveats. --- ## Citation ```bibtex @dataset{hdx_africa_guinea_real_time_prices, title = {Guinea - Real Time Prices}, author = {World Bank Group}, year = {2026}, url = {https://data.humdata.org/dataset/guinea-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: - 爬取获取 language: - 英语 license: CC-BY-4.0 multilinguality: - 单语言 size_categories: - 1000<n<10000 source_datasets: - 原创数据集 task_categories: - 表格回归 task_ids: [] tags: - 非洲 - 人道主义 - HDX - electric-sheep-africa - 能源 - 粮食安全 - GIN pretty_name: "几内亚 - 实时价格" dataset_info: splits: - name: train num_examples: 3679 - name: test num_examples: 919 --- # 几内亚 - 实时价格数据集 **发布方**：世界银行集团 · **数据源**：[HDX（人道主义数据交换平台）](https://data.humdata.org/dataset/guinea-real-time-prices) · **许可协议**：`CC-BY` · **最后更新时间**：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（DECDG）每周编译更新的动态数据集，其整合了直接价格测量与缺失价格数据的机器学习（Machine Learning, ML）估算结果。历史与当前估算数据来源于世界粮食计划署（World Food Program, WFP）、联合国粮食及农业组织（UN-Food and Agricultural Organization, 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包含三个子系列：实时粮食价格（Real Time Food Prices, RTFP）、实时能源价格（Real Time Energy Prices, RTEP）以及实时汇率（Real Time Exchange Rates, RTFX）。其中，实时粮食价格（RTFP）涵盖各类食品的价格数据，主要包含几内亚特定主粮；实时能源价格（RTEP）包含燃料价格；实时汇率（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。 本数据集的每一行代表国家级聚合数据。时间覆盖范围由`dates`、`start_dense_data`字段标注。地理覆盖范围：**GIN（几内亚）**。 *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 | | **总样本量** | 4599条 | | **字段数** | 140个（127个数值型、10个分类型、3个日期时间型） | | **训练集拆分** | 3679条 | | **测试集拆分** | 919条 | | **地理覆盖范围** | GIN（几内亚） | | **发布方** | 世界银行集团 | | **HDX最后更新时间** | 2026-04-01 | --- ## 变量分类 ### 地理类变量 `iso3`（GIN）、`country`（几内亚）、`lat`（范围7.75–12.48）、`lon`（范围-14.3–-8.53）、`year`（范围2008.0–2026.0）及另外28个字段。 ### 时间类变量 `dates`、`month`（范围1.0–12.0）。 ### 人口统计类变量 `data_coverage`（范围23.56–23.56）、`data_coverage_recent`（范围34.14–34.14）。 ### 标识符与元数据类变量 `adm1_name`（金迪亚、恩泽雷科雷、博凯）、`adm2_name`（科纳克里、博凯、贝拉）、`mkt_name`（贝拉、盖凯杜、塔内内）、`geo_id`（gid_86900000-86400000、gid_85700000-101300000、gid_110100000-142400000）、`esa_source`（HDX）及另外1个字段。 ### 其他类变量 `components`（包含：豆类（1千克，指数权重=1）、面包（1单位，指数权重=1）、木薯粉（1千克，指数权重=1）、鱼类（1千克，指数权重=1）、福尼奥米（1千克，指数权重=1）、花生（1千克，指数权重=1）、玉米（1千克，指数权重=1）、牛肉（1千克，指数权重=0.5）、FAO牛肉价格（1千克，指数权重=0.5）、食用油（1升，指数权重=0.5）、FAO食用油价格（1升，指数权重=0.5）、洋葱（1千克，指数权重=1）、土豆（1千克，指数权重=1）、大米（1千克，指数权重=0.5）、FAO大米价格（1千克，指数权重=0.5）、盐（1千克，指数权重=1）、糖（1千克，指数权重=1）、番茄（1千克，指数权重=1））、`start_dense_data`、`beans`（范围3000.0–32000.0）、`bread`（范围1667.0–17833.0）、`maize`（范围1833.33–70000.0）及另外92个字段。 --- ## 快速入门 python from datasets import load_dataset # 加载几内亚实时价格数据集 ds = load_dataset("electricsheepafrica/africa-guinea-real-time-prices") # 将训练集转换为Pandas DataFrame格式 train = ds["train"].to_pandas() # 将测试集转换为Pandas DataFrame格式 test = ds["test"].to_pandas() # 打印训练集的形状 print(train.shape) # 查看训练集前5条数据 train.head() --- ## 字段结构详情 | 字段名 | 数据类型 | 缺失率 | 范围/示例值 | |---|---|---|---| | `iso3` | 字符串（object） | 0.0% | GIN | | `country` | 字符串（object） | 0.0% | 几内亚 | | `adm1_name` | 字符串（object） | 0.0% | 金迪亚、恩泽雷科雷、博凯 | | `adm2_name` | 字符串（object） | 0.0% | 科纳克里、博凯、贝拉 | | `mkt_name` | 字符串（object） | 0.0% | 贝拉、盖凯杜、塔内内 | | `lat` | 浮点型（float64） | 4.8% | 7.75 – 12.48（均值 9.721） | | `lon` | 浮点型（float64） | 4.8% | -14.3 – -8.53（均值 -11.839） | | `geo_id` | 字符串（object） | 0.0% | gid_86900000-86400000、gid_85700000-101300000、gid_110100000-142400000 | | `dates` | 日期时间型（datetime64[ns]） | 0.0% | 无 | | `year` | 整型（int64） | 0.0% | 2008.0 – 2026.0（均值 2016.6301） | | `month` | 整型（int64） | 0.0% | 1.0 – 12.0（均值 6.4384） | | `currency` | 字符串（object） | 0.0% | GNF | | `components` | 字符串（object） | 0.0% | 豆类（1千克，指数权重=1）、面包（1单位，指数权重=1）、木薯粉（1千克，指数权重=1）、鱼类（1千克，指数权重=1）、福尼奥米（1千克，指数权重=1）、花生（1千克，指数权重=1）、玉米（1千克，指数权重=1）、牛肉（1千克，指数权重=0.5）、FAO牛肉价格（1千克，指数权重=0.5）、食用油（1升，指数权重=0.5）、FAO食用油价格（1升，指数权重=0.5）、洋葱（1千克，指数权重=1）、土豆（1千克，指数权重=1）、大米（1千克，指数权重=0.5）、FAO大米价格（1千克，指数权重=0.5）、盐（1千克，指数权重=1）、糖（1千克，指数权重=1）、番茄（1千克，指数权重=1） | | 剩余字段 | 省略 | 省略 | 省略 | --- ## 数值统计摘要 | 字段名 | 最小值 | 最大值 | 均值 | 中位数 | |---|---|---|---|---| | `lat` | 7.75 | 12.48 | 9.721 | 9.575 | | `lon` | -14.3 | -8.53 | -11.839 | -12.575 | | `year` | 2008.0 | 2026.0 | 2016.6301 | 2017.0 | | `month` | 1.0 | 12.0 | 6.4384 | 6.0 | | `data_coverage` | 23.56 | 23.56 | 23.56 | 23.56 | | `data_coverage_recent` | 34.14 | 34.14 | 34.14 | 34.14 | | `index_confidence_score` | 0.95 | 0.95 | 0.95 | 0.95 | | `spatially_interpolated` | 0.0 | 0.0 | 0.0 | 0.0 | | `beans` | 3000.0 | 32000.0 | 10052.3796 | 9000.0 | | `bread` | 1667.0 | 17833.0 | 3425.4843 | 3000.0 | | `maize` | 1833.33 | 70000.0 | 6486.8629 | 6167.0 | | `oil` | 4413.0 | 40000.0 | 11106.8097 | 10500.0 | | `rice` | 2647.0 | 29167.0 | 6714.5058 | 6667.0 | | `o_beans` | 3304.71 | 31868.47 | 9302.4192 | 7918.5 | | `h_beans` | 3739.94 | 34149.82 | 9806.0215 | 8292.66 | --- ## 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。字段名均转为小写并标准化为蛇形命名法（snake_case）。通用缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。移除了720个缺失值占比超过80%的字段，例如`apples`（苹果）、`bananas`（香蕉）、`beans_egyptian`（埃及豆）、`beans_fao`（FAO豆类价格）、`bread_fao`（FAO面包价格）、`bulgur`（碾碎干小麦）等。基于解析成功率（阈值>85%），将3个字段从字符串类型转换为数值型或日期时间型。本数据集以80/20的比例划分为训练集与测试集，使用固定随机种子（42）进行拆分，并保存为Snappy压缩的Parquet格式。 --- ## 局限性说明 - 数据源自世界银行集团，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、定义不一致或抽样偏差问题。 - 以下字段缺失值占比超过20%，在建模时需谨慎使用：`beans`、`bread`、`maize`、`oil`、`rice`。 - 请参阅[原始HDX数据集页面](https://data.humdata.org/dataset/guinea-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_guinea_real_time_prices, title = {几内亚 - 实时价格数据集}, author = {世界银行集团}, year = {2026}, url = {https://data.humdata.org/dataset/guinea-real-time-prices}, note = {由Electric Sheep Africa（https://huggingface.co/electricsheepafrica）重新打包以适配机器学习场景} } --- *[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。*