electricsheepafrica/africa-monthly-cross-border-trade-for-united-republic-of-tanzania-299

---
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-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- eastern-africa
- trade
- tza
pretty_name: "United Republic of Tanzania Monthly FEWS NET Cross Border Trade Data"
dataset_info:
splits:
- name: train
num_examples: 34144
- name: test
num_examples: 8536
---

# United Republic of Tanzania Monthly FEWS NET Cross Border Trade Data

**Publisher:** FEWS NET · **Source:** [HDX](https://data.humdata.org/dataset/monthly_cross_border_trade_for_united_republic_of_tanzania_299) · **License:** `cc-by` · **Updated:** 2026-02-05

---

## Abstract

United Republic of Tanzania Monthly cross border trade data collected by FEWS NET since 2005.

Each row in this dataset represents first-level administrative unit observations. Temporal coverage is indicated by the `start_date`, `period_date` column(s). Geographic scope: **TZA**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 42,680 |
| **Columns** | 38 (5 numeric, 31 categorical, 2 datetime) |
| **Train split** | 34,144 rows |
| **Test split** | 8,536 rows |
| **Geographic scope** | TZA |
| **Publisher** | FEWS NET |
| **HDX last updated** | 2026-02-05 |

---

## Variables

**Geographic** — `reporting_country` (Tanzania, United Republic of, Kenya, Malawi), `reporting_country_code` (TZ, KE, MW), `source_country_code` (TZ, KE, BI), `destination_country_code` (KE, BI, TZ), `flow_type` and 8 others.

**Temporal** — `start_date`, `period_date`, `value_one_month_ago` (range 0.2–83640500.0), `pct_change_from_one_month_ago` (range -100.0–40188788.8889).

**Outcome / Measurement** — `value` (range 0.0–334562000.0).

**Identifier / Metadata** — `source` (Tanzania, United Republic of, Kenya, Burundi), `indicator_name` (TradeFlowQuantity), `source_organization`, `source_document`, `dataseries_name` and 4 others.

**Other** — `border_point` (Kibande, Taveta, Manyovu), `destination` (Kenya, Burundi, Tanzania, United Republic of), `cpcv2` (P23161AA, R01122AC, R01701AA), `product` (Rice (Milled), Maize Grain (White), Beans (mixed)), `collection_status` and 6 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-monthly-cross-border-trade-for-united-republic-of-tanzania-299")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `reporting_country` | object | 0.0% | Tanzania, United Republic of, Kenya, Malawi |
| `reporting_country_code` | object | 0.0% | TZ, KE, MW |
| `border_point` | object | 4.8% | Kibande, Taveta, Manyovu |
| `source` | object | 0.0% | Tanzania, United Republic of, Kenya, Burundi |
| `source_country_code` | object | 0.0% | TZ, KE, BI |
| `destination` | object | 0.0% | Kenya, Burundi, Tanzania, United Republic of |
| `destination_country_code` | object | 0.0% | KE, BI, TZ |
| `cpcv2` | object | 0.0% | P23161AA, R01122AC, R01701AA |
| `product` | object | 0.0% | Rice (Milled), Maize Grain (White), Beans (mixed) |
| `indicator_name` | object | 0.0% | TradeFlowQuantity |
| `start_date` | datetime64[ns] | 0.0% | |
| `period_date` | datetime64[ns] | 0.0% | |
| `value` | float64 | 0.0% | 0.0 – 334562000.0 (mean 64106.3632) |
| `flow_type` | object | 0.0% | |
| `trade_type` | object | 0.0% | |
| `collection_status` | object | 0.0% | |
| `source_organization` | object | 0.0% | |
| `source_document` | object | 0.0% | |
| `dataseries_name` | object | 0.0% | |
| `dataseries` | int64 | 0.0% | 27989.0 – 7051434.0 (mean 6290835.0721) |
| `unit` | object | 0.0% | |
| `unit_type` | object | 0.0% | |
| `unit_name` | object | 0.0% | |
| `status` | object | 0.0% | |
| `common_unit` | object | 0.0% | |
| `common_unit_quantity` | float64 | 0.0% | 0.0 – 334562000.0 (mean 279649.6762) |
| `reporting_country_geographic_group` | object | 0.0% | |
| `reporting_country_fewsnet_region` | object | 0.0% | |
| `source_geographic_group` | object | 0.0% | |
| `source_fewsnet_region` | object | 0.0% | |
| `destination_geographic_group` | object | 0.0% | |
| `destination_fewsnet_region` | object | 0.0% | |
| `value_one_month_ago` | float64 | 76.7% | 0.2 – 83640500.0 (mean 63837.2234) |
| `pct_change_from_one_month_ago` | float64 | 76.7% | -100.0 – 40188788.8889 (mean 5965.1906) |
| `collection_schedule` | object | 0.0% | |
| `data_usage_policy` | object | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `value` | 0.0 | 334562000.0 | 64106.3632 | 0.0 |
| `dataseries` | 27989.0 | 7051434.0 | 6290835.0721 | 6606785.0 |
| `common_unit_quantity` | 0.0 | 334562000.0 | 279649.6762 | 0.0 |
| `value_one_month_ago` | 0.2 | 83640500.0 | 63837.2234 | 274.25 |
| `pct_change_from_one_month_ago` | -100.0 | 40188788.8889 | 5965.1906 | 215.6977 |

---

## 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`. 10 column(s) with >80% missing values were removed: `id`, `value_one_year_ago`, `value_two_years_ago`, `value_three_years_ago`, `value_four_years_ago`, `value_five_years_ago`.... 2 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_one_month_ago`, `pct_change_from_one_month_ago`.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/monthly_cross_border_trade_for_united_republic_of_tanzania_299) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_monthly_cross_border_trade_for_united_republic_of_tanzania_299,
title = {United Republic of Tanzania Monthly FEWS NET Cross Border Trade Data},
author = {FEWS NET},
year = {2026},
url = {https://data.humdata.org/dataset/monthly_cross_border_trade_for_united_republic_of_tanzania_299},
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.*