{ "name": "Data Darbar", "version": 1, "generated": "2026-09-13", "license": "Derived data CC BY 4.0 \u00b7 code MIT", "tables": [ { "name": "budget_lines", "file": "budget_lines.parquet", "bytes": 118845, "rows": 23271, "description": "Federal budget line items from the Budget in Brief documents, FY2009-10 \u2192 FY2026-27.", "notes": "Rs million. Each printed row carried 1\u20134 numeric columns; is_own_year_be = TRUE marks the document's own-year Budget Estimate, which is the only column safe to string into a time series. The low-numbered 'Budget at a Glance' tables extract noisily and item wording drifts between years \u2014 match with ILIKE and sanity-check.", "unit": "Rs million", "source": "Finance Division, Budget in Brief (PDF)", "columns": [ { "name": "doc_fy", "type": "VARCHAR", "description": "fiscal year of the source document" }, { "name": "table_no", "type": "BIGINT", "description": "table number in the PDF" }, { "name": "table_title", "type": "VARCHAR", "description": "table title" }, { "name": "item", "type": "VARCHAR", "description": "line item as printed" }, { "name": "col_index", "type": "BIGINT", "description": "0-based column position in the printed row" }, { "name": "n_cols", "type": "BIGINT", "description": "how many numeric columns that row had" }, { "name": "col_label", "type": "VARCHAR", "description": "inferred column meaning" }, { "name": "value_rs_mn", "type": "DOUBLE", "description": "value, Rs million" }, { "name": "is_own_year_be", "type": "BOOLEAN", "description": "TRUE = own-year Budget Estimate (the reliable column)" } ] }, { "name": "census_enrolment_5_16_by_sex", "file": "census_enrolment_5_16_by_sex.parquet", "bytes": 22611, "rows": 130, "description": "Census 2023 Table 13(b): population and enrolment aged 5\u201316 by sex and rural/urban, one row per district on the 2017 boundary frame.", "notes": "Successor districts are summed into their 2017 parents (constituents lists them), so rates are on the same frame as school_access_district; 130 rows. *_in_school_pct = enrolled \u00f7 population aged 5\u201316. *_never and *_out_of_school follow PBS's definitions (never attended; never attended plus dropped out). This is the age-matched outcome the piece uses; Table 12's all-ages complement runs about 0.7 points higher.", "unit": "persons; per cent", "source": "PBS Population and Housing Census 2023, district Table 13(b), via github.com/fahad-mirza/pakistan_census_2023_tables", "columns": [ { "name": "district", "type": "VARCHAR", "description": "district (parent frame)" }, { "name": "girls_pop_5_16", "type": "DOUBLE", "description": "girls pop, ages 5\u201316" }, { "name": "girls_enrolled_5_16", "type": "DOUBLE", "description": "girls enrolled, ages 5\u201316" }, { "name": "girls_never_5_16", "type": "DOUBLE", "description": "girls never, ages 5\u201316" }, { "name": "boys_pop_5_16", "type": "DOUBLE", "description": "boys pop, ages 5\u201316" }, { "name": "boys_enrolled_5_16", "type": "DOUBLE", "description": "boys enrolled, ages 5\u201316" }, { "name": "boys_never_5_16", "type": "DOUBLE", "description": "boys never, ages 5\u201316" }, { "name": "girls_rural_pop_5_16", "type": "DOUBLE", "description": "girls rural pop, ages 5\u201316" }, { "name": "girls_rural_enrolled_5_16", "type": "DOUBLE", "description": "girls rural enrolled, ages 5\u201316" }, { "name": "girls_rural_never_5_16", "type": "DOUBLE", "description": "girls rural never, ages 5\u201316" }, { "name": "boys_rural_pop_5_16", "type": "DOUBLE", "description": "boys rural pop, ages 5\u201316" }, { "name": "boys_rural_enrolled_5_16", "type": "DOUBLE", "description": "boys rural enrolled, ages 5\u201316" }, { "name": "boys_rural_never_5_16", "type": "DOUBLE", "description": "boys rural never, ages 5\u201316" }, { "name": "girls_urban_pop_5_16", "type": "DOUBLE", "description": "girls urban pop, ages 5\u201316" }, { "name": "girls_urban_enrolled_5_16", "type": "DOUBLE", "description": "girls urban enrolled, ages 5\u201316" }, { "name": "girls_urban_never_5_16", "type": "DOUBLE", "description": "girls urban never, ages 5\u201316" }, { "name": "boys_urban_pop_5_16", "type": "DOUBLE", "description": "boys urban pop, ages 5\u201316" }, { "name": "boys_urban_enrolled_5_16", "type": "DOUBLE", "description": "boys urban enrolled, ages 5\u201316" }, { "name": "boys_urban_never_5_16", "type": "DOUBLE", "description": "boys urban never, ages 5\u201316" }, { "name": "girls_out_of_school_5_16", "type": "DOUBLE", "description": "girls out of school, ages 5\u201316" }, { "name": "boys_out_of_school_5_16", "type": "DOUBLE", "description": "boys out of school, ages 5\u201316" }, { "name": "girls_rural_out_of_school_5_16", "type": "DOUBLE", "description": "girls rural out of school, ages 5\u201316" }, { "name": "boys_rural_out_of_school_5_16", "type": "DOUBLE", "description": "boys rural out of school, ages 5\u201316" }, { "name": "girls_urban_out_of_school_5_16", "type": "DOUBLE", "description": "girls urban out of school, ages 5\u201316" }, { "name": "boys_urban_out_of_school_5_16", "type": "DOUBLE", "description": "boys urban out of school, ages 5\u201316" }, { "name": "constituents", "type": "VARCHAR", "description": "census districts summed into the row" }, { "name": "girls_in_school_pct", "type": "DOUBLE", "description": "girls enrolled \u00f7 population 5\u201316, %" }, { "name": "boys_in_school_pct", "type": "DOUBLE", "description": "boys enrolled \u00f7 population 5\u201316, %" }, { "name": "girls_rural_in_school_pct", "type": "DOUBLE", "description": "girls rural enrolled \u00f7 population 5\u201316, %" }, { "name": "boys_rural_in_school_pct", "type": "DOUBLE", "description": "boys rural enrolled \u00f7 population 5\u201316, %" }, { "name": "girls_urban_in_school_pct", "type": "DOUBLE", "description": "girls urban enrolled \u00f7 population 5\u201316, %" }, { "name": "boys_urban_in_school_pct", "type": "DOUBLE", "description": "boys urban enrolled \u00f7 population 5\u201316, %" }, { "name": "enrol_gap_pp", "type": "DOUBLE", "description": "boys_in_school_pct \u2212 girls_in_school_pct" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar key" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "district_indicators", "file": "district_indicators.parquet", "bytes": 167771, "rows": 45748, "description": "Every district-level indicator in Data Darbar, one row per district \u00d7 indicator \u00d7 year.", "notes": "Long format so heterogeneous sources share one table. Filter `kind = 'indicator'` for the measures themselves; kind='quality' rows carry the sample size and small-n flag for the same prefix, and kind='provenance' rows record borrowed estimates. Survey groups suppress cells with n<30 upstream, so an absent row can mean 'suppressed' as well as 'not collected'. DOUBLE-COUNTING TRAP: where a district was split after Census 2017 (see the *_boundary_change provenance rows) both halves carry the SAME 2017 figure for the combined pre-split area, so summing a 2017 count across all districts overstates the total. Filter those rows out, or sum the 2023 year instead.", "unit": null, "source": "PBS Census 2017 & 2023, PSLM 2019-20, LFS 2020-21/2024-25, HIES 2024-25, PDHS 2017-18", "columns": [ { "name": "district_key", "type": "VARCHAR", "description": "normalised join key used across Data Darbar" }, { "name": "district", "type": "VARCHAR", "description": "display name" }, { "name": "province", "type": "VARCHAR", "description": "province / territory" }, { "name": "dataset", "type": "VARCHAR", "description": "source dataset (Census 2017/23, PSLM 2019-20, LFS, HIES, PDHS\u2026)" }, { "name": "group_key", "type": "VARCHAR", "description": "indicator group key in app.js" }, { "name": "group_label", "type": "VARCHAR", "description": "human label for the group" }, { "name": "indicator", "type": "VARCHAR", "description": "indicator key within the group" }, { "name": "label", "type": "VARCHAR", "description": "human label for the indicator" }, { "name": "year", "type": "VARCHAR", "description": "census year for two-year census groups, else NULL" }, { "name": "kind", "type": "VARCHAR", "description": "'indicator' | 'quality' (n_obs, low_n) | 'provenance'" }, { "name": "field", "type": "VARCHAR", "description": "raw field name in districts.json" }, { "name": "value", "type": "DOUBLE", "description": "numeric value (units implied by the label)" }, { "name": "value_text", "type": "VARCHAR", "description": "non-numeric value, if any" } ] }, { "name": "file_catalog", "file": "file_catalog.parquet", "bytes": 11910, "rows": 322, "description": "Index of every source file collected for the warehouse, with its upstream URL.", "notes": "parsed_into_db = FALSE means the file is catalogued but its contents are not in any table here (mostly scanned PDFs). Use this to check coverage before concluding data is missing.", "unit": null, "source": "PBS, Finance Division", "columns": [ { "name": "dataset", "type": "VARCHAR", "description": "collection it belongs to" }, { "name": "category", "type": "VARCHAR", "description": "sub-category" }, { "name": "period", "type": "VARCHAR", "description": "period covered" }, { "name": "item", "type": "VARCHAR", "description": "what the file contains" }, { "name": "filename", "type": "VARCHAR", "description": "file name" }, { "name": "format", "type": "VARCHAR", "description": "PDF/TXT/xlsx" }, { "name": "source_url", "type": "VARCHAR", "description": "upstream URL at PBS / Finance Division" }, { "name": "status", "type": "VARCHAR", "description": "download status" }, { "name": "notes", "type": "VARCHAR", "description": "free text" }, { "name": "parsed_into_db", "type": "BOOLEAN", "description": "TRUE if its contents are in a table here" } ] }, { "name": "health_access_district", "file": "health_access_district.parquet", "bytes": 11793, "rows": 147, "description": "Travel time to the nearest health facility by district (147): population-weighted medians and means and shares of people beyond 30, 60 and 120 minutes, motorised and walking.", "notes": "Travel time is MODELLED: the cost of crossing each 1 km cell on the friction surface, summed along the least-cost path to the nearest mapped health facility. The facility set behind the surfaces is OpenStreetMap and Google Maps hospitals and clinics, public and private together, with no information on staffing, opening hours or quality \u2014 so this measures geographic access to a mapped point, not to a working service. Motorised assumes a vehicle is available; walking-only assumes none. Population weights are WorldPop 2020, which puts Gilgit-Baltistan at about 1.1 million against 1.7 million in the 2023 census, so the north's headcounts are understated. Thresholds are strictly greater than 30, 60 or 120 minutes. *_popw_median is the population-weighted median (the piece's headline measure: 22 minutes motorised, 128 walking nationally); *_median the unweighted median of cells. Shares were fractions in the piece's file and are per cent here. Join mpi_districts on district_key for the poverty gradient (Spearman 0.76 between MPI and motorised time; the poorest MPI quintile is 47 minutes from care motorised against 5 for the least poor). The seven ex-FATA merged districts are Khyber Pakhtunkhwa and carry merged_district = 1.", "unit": "minutes; per cent", "source": "Malaria Atlas Project accessibility surfaces (Weiss et al. 2020, Nature Medicine 26: motorised 2019, walking-only 2020), clipped to Pakistan; WorldPop 2020 UN-adjusted 1 km population; Data Darbar boundaries. Built for Adaad's September 2026 issue.", "columns": [ { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar district key \u2014 joins district_indicators, mpi_districts, school_access_district" }, { "name": "district", "type": "VARCHAR", "description": "district name" }, { "name": "province", "type": "VARCHAR", "description": "province or territory" }, { "name": "merged_district", "type": "BIGINT", "description": "1 for the seven ex-FATA merged districts" }, { "name": "n_px", "type": "BIGINT", "description": "valid 1 km cells" }, { "name": "pop_2020", "type": "BIGINT", "description": "WorldPop 2020 population on those cells" }, { "name": "mot_mean", "type": "DOUBLE", "description": "motorised minutes, unweighted mean of cells" }, { "name": "mot_median", "type": "DOUBLE", "description": "motorised minutes, unweighted median of cells" }, { "name": "mot_popw_mean", "type": "DOUBLE", "description": "motorised minutes, population-weighted mean" }, { "name": "mot_popw_median", "type": "DOUBLE", "description": "motorised minutes, population-weighted median" }, { "name": "wal_mean", "type": "DOUBLE", "description": "walking minutes, unweighted mean" }, { "name": "wal_median", "type": "DOUBLE", "description": "walking minutes, unweighted median" }, { "name": "wal_popw_mean", "type": "DOUBLE", "description": "walking minutes, population-weighted mean" }, { "name": "wal_popw_median", "type": "DOUBLE", "description": "walking minutes, population-weighted median" }, { "name": "mot_pct_pop_gt30", "type": "DOUBLE", "description": "% of people more than 30 motorised minutes from care" }, { "name": "mot_pct_pop_gt60", "type": "DOUBLE", "description": "% more than 60 motorised minutes" }, { "name": "mot_pct_pop_gt120", "type": "DOUBLE", "description": "% more than 120 motorised minutes" }, { "name": "wal_pct_pop_gt30", "type": "DOUBLE", "description": "% more than 30 walking minutes" }, { "name": "wal_pct_pop_gt60", "type": "DOUBLE", "description": "% more than 60 walking minutes" }, { "name": "wal_pct_pop_gt120", "type": "DOUBLE", "description": "% more than 120 walking minutes" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "health_access_tehsil", "file": "health_access_tehsil.parquet", "bytes": 26806, "rows": 553, "description": "Travel time to the nearest health facility by tehsil (553 ADM3 polygons): population-weighted means and shares of people beyond 30, 60 and 120 minutes, motorised and walking.", "notes": "Travel time is MODELLED: the cost of crossing each 1 km cell on the friction surface, summed along the least-cost path to the nearest mapped health facility. The facility set behind the surfaces is OpenStreetMap and Google Maps hospitals and clinics, public and private together, with no information on staffing, opening hours or quality \u2014 so this measures geographic access to a mapped point, not to a working service. Motorised assumes a vehicle is available; walking-only assumes none. Population weights are WorldPop 2020, which puts Gilgit-Baltistan at about 1.1 million against 1.7 million in the 2023 census, so the north's headcounts are understated. Thresholds are strictly greater than 30, 60 or 120 minutes. mot_/wal_ = motorised / walking-only surface; *_mean is the unweighted mean of valid cells, *_popw_mean the population-weighted mean; *_pct_pop_gtN the share of people more than N minutes away. Manora Cantonment has no valid cells: its blanks are missing estimates, not zero. The tehsil grid holds 1,175,119 cells and 219.6 million people, 4,671 cells fewer than the district build because the two boundary files rasterise differently, so tehsil rows do not recombine exactly to health_access_district (22.10 v 22.13 minutes nationally). The seven ex-FATA merged districts are Khyber Pakhtunkhwa and carry merged_district = 1. This is the table the map's Health \u2192 Travel Time to Care (tehsil) layer draws.", "unit": "minutes; per cent", "source": "Malaria Atlas Project accessibility surfaces (Weiss et al. 2020, Nature Medicine 26: motorised 2019, walking-only 2020), clipped to Pakistan; WorldPop 2020 UN-adjusted 1 km population; Data Darbar boundaries. Built for Adaad's September 2026 issue.", "columns": [ { "name": "dd_id", "type": "VARCHAR", "description": "ADM3 identifier \u2014 joins mouza_crosswalk.dd_id, tehsil_satellite.tehsil_id, school_access_tehsil.dd_id" }, { "name": "tehsil", "type": "VARCHAR", "description": "tehsil name" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar district key" }, { "name": "province", "type": "VARCHAR", "description": "province or territory" }, { "name": "merged_district", "type": "BIGINT", "description": "1 for the seven ex-FATA merged districts" }, { "name": "n_px", "type": "BIGINT", "description": "valid 1 km cells" }, { "name": "pop_2020", "type": "DOUBLE", "description": "WorldPop 2020 population on those cells" }, { "name": "mot_mean", "type": "DOUBLE", "description": "motorised minutes, unweighted mean of cells" }, { "name": "mot_popw_mean", "type": "DOUBLE", "description": "motorised minutes, population-weighted mean" }, { "name": "wal_mean", "type": "DOUBLE", "description": "walking minutes, unweighted mean of cells" }, { "name": "wal_popw_mean", "type": "DOUBLE", "description": "walking minutes, population-weighted mean" }, { "name": "mot_pct_pop_gt30", "type": "DOUBLE", "description": "% of people more than 30 motorised minutes from care" }, { "name": "mot_pct_pop_gt60", "type": "DOUBLE", "description": "% more than 60 motorised minutes" }, { "name": "mot_pct_pop_gt120", "type": "DOUBLE", "description": "% more than 120 motorised minutes" }, { "name": "wal_pct_pop_gt30", "type": "DOUBLE", "description": "% more than 30 walking minutes" }, { "name": "wal_pct_pop_gt60", "type": "DOUBLE", "description": "% more than 60 walking minutes" }, { "name": "wal_pct_pop_gt120", "type": "DOUBLE", "description": "% more than 120 walking minutes" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "lsm_qim", "file": "lsm_qim.parquet", "bytes": 3354, "rows": 119, "description": "Monthly Quantum Index of Manufacturing (large-scale manufacturing).", "notes": "Index; mom/yoy/cum_chg are percentages.", "unit": null, "source": "PBS Quantum Index of Manufacturing", "columns": [ { "name": "month", "type": "VARCHAR", "description": "YYYY-MM" }, { "name": "qim", "type": "DOUBLE", "description": "index level" }, { "name": "mom", "type": "DOUBLE", "description": "% change on previous month" }, { "name": "yoy", "type": "DOUBLE", "description": "% change on same month a year earlier" }, { "name": "cum_qim", "type": "DOUBLE", "description": "fiscal-year-to-date index" }, { "name": "cum_chg", "type": "DOUBLE", "description": "% change in the FYTD index" } ] }, { "name": "lsm_sector_indices", "file": "lsm_sector_indices.parquet", "bytes": 24087, "rows": 6685, "description": "LSM indices by manufacturing sector, annual and monthly, with CMI weights.", "notes": "weight is the sector's share in the index (per the stated base year).", "unit": null, "source": "PBS LSM / Census of Manufacturing Industries", "columns": [ { "name": "base", "type": "VARCHAR", "description": "index base year" }, { "name": "fy", "type": "VARCHAR", "description": "fiscal year" }, { "name": "sector", "type": "VARCHAR", "description": "manufacturing sector" }, { "name": "weight", "type": "DOUBLE", "description": "weight in the overall index" }, { "name": "annual_index", "type": "DOUBLE", "description": "annual index level" }, { "name": "month", "type": "VARCHAR", "description": "YYYY-MM (monthly rows)" }, { "name": "monthly_index", "type": "DOUBLE", "description": "monthly index level" } ] }, { "name": "mouza_crosswalk", "file": "mouza_crosswalk.parquet", "bytes": 17991, "rows": 595, "description": "Maps each PBS tehsil to the ADM3 polygon Data Darbar maps it on.", "notes": "MANY-TO-ONE by design: PBS enumerates 595 tehsils against the boundary file's 553, because it carries sub-tehsils created after the polygons were drawn. Since every Mouza Census figure is a count of mouzas, summing several PBS tehsils into one polygon is the correct operation \u2014 group by tehsil_id and sum before taking any share. match records how each row was resolved: exact_name, variant (same place spelled differently), contained, fuzzy, only_tehsil_in_district, parent (a sub-tehsil folded into the unit it was carved from), and approx (no polygon exists for the area, so it was placed in a neighbour \u2014 treat those tehsils' placement as a judgement call). All 48,738 mouzas are assigned. The 10 unresolved rows all have zero mouzas.", "unit": null, "source": "PBS Mouza Census 2020 frame \u00d7 geoBoundaries PAK ADM3", "columns": [ { "name": "tehsil_code", "type": "VARCHAR", "description": "PBS tehsil code \u2014 joins to mouza_tehsil.tehsil_code" }, { "name": "tehsil", "type": "VARCHAR", "description": "PBS tehsil name" }, { "name": "district_code", "type": "VARCHAR", "description": "PBS district code" }, { "name": "district", "type": "VARCHAR", "description": "PBS district name" }, { "name": "province", "type": "VARCHAR", "description": "province name" }, { "name": "mouzas", "type": "VARCHAR", "description": "mouzas enumerated (0 = not enumerated)" }, { "name": "dd_id", "type": "VARCHAR", "description": "ADM3 identifier \u2014 joins to tehsil_satellite.tehsil_id" }, { "name": "dd_name", "type": "VARCHAR", "description": "boundary-file tehsil name" }, { "name": "dd_district", "type": "VARCHAR", "description": "boundary-file district key" }, { "name": "match", "type": "VARCHAR", "description": "how the row was matched (see notes)" }, { "name": "dd_candidates", "type": "VARCHAR", "description": "boundary-file names considered, where the match failed" } ] }, { "name": "mouza_tehsil", "file": "mouza_tehsil.parquet", "bytes": 190122, "rows": 595, "description": "Mouza Census 2020 facility counts, one row per PBS tehsil.", "notes": "Every column is a COUNT OF MOUZAS (revenue villages), never of people or households \u2014 a mouza of 12,000 and a mouza of 300 each count once. PBS publishes numerators without a denominator, and its own indicator blocks disagree about how many mouzas answered: only 33 of the 544 enumerated tehsils give a single consistent base, and blocks can differ by up to 181. Take each block's own row sum as its base rather than TotalMauzaCount. Existance/NotExistance pairs are exclusive; drinking water, health facility type, fuel, street surface and media are multiple response, so they can sum past the base. The frame is rural \u2014 cities are not revenue villages \u2014 but mouzas that urbanise stay in it (4.9% urban, 2.4% partly urban). 51 tehsils return all zeros: AJK and GB were not enumerated, nor were Mand and Tump in Kech or Kallag in Panjgur. Join to the ADM3 geography through mouza_crosswalk. Column names keep PBS's own casing and spelling; DuckDB matches them case-insensitively.", "unit": null, "source": "PBS Mouza Census 2020 (mc2020.pbos.gov.pk)", "columns": [ { "name": "province_code", "type": "BIGINT", "description": "PBS province code" }, { "name": "province", "type": "VARCHAR", "description": "province name" }, { "name": "division_code", "type": "VARCHAR", "description": "PBS division code" }, { "name": "division", "type": "VARCHAR", "description": "division name" }, { "name": "district_code", "type": "VARCHAR", "description": "PBS district code (999 = the Cholistan pseudo-district)" }, { "name": "district", "type": "VARCHAR", "description": "district name" }, { "name": "tehsil_code", "type": "VARCHAR", "description": "PBS tehsil code, unique nationally" }, { "name": "tehsil", "type": "VARCHAR", "description": "tehsil name as PBS writes it" }, { "name": "TotalMauzaCount", "type": "BIGINT", "description": "mouzas enumerated in the tehsil" }, { "name": "CompletedMouzaCount", "type": "BIGINT", "description": "of which completed" }, { "name": "CompletedWithErrorMouzaCount", "type": "BIGINT", "description": "of which flagged with an error at source" }, { "name": "RuralMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "UrbanMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "PartlyUrbanMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "ForestMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "ForestPopulatedMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "ForestUnPopulatedMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "UnPopulatedMouzaCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "RuralPopulatedMouzaCount", "type": "BIGINT", "description": "mouzas that are rural and populated" }, { "name": "TotalArea", "type": "BIGINT", "description": "total area, acres" }, { "name": "CultivatedArea", "type": "BIGINT", "description": "cultivated area, acres" }, { "name": "NonCultivatedArea", "type": "BIGINT", "description": "non-cultivated area, acres" }, { "name": "PopulatedArea", "type": "BIGINT", "description": "built-up area, acres" }, { "name": "WheatCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "RiceCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "CottonCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "SugarCaneCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "CornCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "PulsesCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "FarmsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "VegetablesCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "CanalCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "RiverCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "TubewellCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "StreamsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "WatercourseCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "AridCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "FloodedCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "OthersCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "DripSystemCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "SprinklerSystemCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "OtherSystemCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "SweetWaterCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "BarkishWaterCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "PoultryFarmsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "LiveStockFarmsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "FishFarmsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "MetaledRoadsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "CementedRoadsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "BrickedRoadsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "DirtRoadsCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "MauzaStatus_RuralCount", "type": "BIGINT", "description": "mouzas by settlement status (exclusive; sums to TotalMauzaCount)" }, { "name": "MauzaStatus_UrbanCount", "type": "BIGINT", "description": "mouzas by settlement status (exclusive; sums to TotalMauzaCount)" }, { "name": "MauzaStatus_PartiallyUrbanCount", "type": "BIGINT", "description": "mouzas by settlement status (exclusive; sums to TotalMauzaCount)" }, { "name": "MauzaStatus_ForestCount", "type": "BIGINT", "description": "mouzas by settlement status (exclusive; sums to TotalMauzaCount)" }, { "name": "MauzaStatus_UnPopulatedCount", "type": "BIGINT", "description": "mouzas by settlement status (exclusive; sums to TotalMauzaCount)" }, { "name": "HousingConstruction_Bricked", "type": "BIGINT", "description": "mouzas by predominant house construction material (exclusive)" }, { "name": "HousingConstruction_MudMade", "type": "BIGINT", "description": "mouzas by predominant house construction material (exclusive)" }, { "name": "HousingConstruction_BricksAndMud", "type": "BIGINT", "description": "mouzas by predominant house construction material (exclusive)" }, { "name": "HousingConstruction_Others", "type": "BIGINT", "description": "mouzas by predominant house construction material (exclusive)" }, { "name": "EducationFacility_MalePrimaryExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MalePrimaryNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemalePrimaryExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemalePrimaryNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleMiddleExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleMiddleNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleMiddleExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleMiddleNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleHHSchoolExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleHHSchoolNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleHHSchoolExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleHHSchoolNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleCollegeExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleCollegeNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleCollegeExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleCollegeNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleTechInstituteExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleTechInstituteNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleTechInstituteExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleTechInstituteNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleDeniMudarsaExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_MaleDeniMudarsaNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleDeniMudarsaExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "EducationFacility_FemaleDeniMudarsaNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this school type (Existance / NotExistance pair)" }, { "name": "Livestock_VeterinaryCenterExistanceCount", "type": "BIGINT", "description": "mouzas with / without this veterinary facility" }, { "name": "Livestock_VeterinaryCenterNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this veterinary facility" }, { "name": "Livestock_PrivateFacilityExistanceCount", "type": "BIGINT", "description": "mouzas with / without this veterinary facility" }, { "name": "Livestock_PrivateFacilityNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this veterinary facility" }, { "name": "Livestock_MobileVeterinaryExistanceCount", "type": "BIGINT", "description": "mouzas with / without this veterinary facility" }, { "name": "Livestock_MobileVeterinaryNotExistanceCount", "type": "BIGINT", "description": "mouzas with / without this veterinary facility" }, { "name": "MediaSource_RadioCount", "type": "BIGINT", "description": "mouzas reached by this medium (multiple response)" }, { "name": "MediaSource_TVCount", "type": "BIGINT", "description": "mouzas reached by this medium (multiple response)" }, { "name": "MediaSource_CableCount", "type": "BIGINT", "description": "mouzas reached by this medium (multiple response)" }, { "name": "MediaSource_NewspaperCount", "type": "BIGINT", "description": "mouzas reached by this medium (multiple response)" }, { "name": "MediaSource_NoneCount", "type": "BIGINT", "description": "mouzas reached by this medium (multiple response)" }, { "name": "DepoAgencyShop_FertilizerCount", "type": "BIGINT", "description": "mouzas with this agricultural input supplier" }, { "name": "DepoAgencyShop_SeedCount", "type": "BIGINT", "description": "mouzas with this agricultural input supplier" }, { "name": "DepoAgencyShop_PesticideCount", "type": "BIGINT", "description": "mouzas with this agricultural input supplier" }, { "name": "WholesaleMarket_LivestockCount", "type": "BIGINT", "description": "mouzas with this wholesale market" }, { "name": "WholesaleMarket_GrainsCount", "type": "BIGINT", "description": "mouzas with this wholesale market" }, { "name": "WholesaleMarket_FruitsVegetableCount", "type": "BIGINT", "description": "mouzas with this wholesale market" }, { "name": "AvgDepthOfWater", "type": "BIGINT", "description": "mean water-table depth, feet" }, { "name": "MinDepthOfWater", "type": "BIGINT", "description": "minimum water-table depth, feet" }, { "name": "MaxDepthOfWater", "type": "BIGINT", "description": "maximum water-table depth, feet" }, { "name": "SourceOfDrinkingWater_GovtPipedSupply", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_PersonalPump", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_WaterFiltrationPlant", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_ROPlant", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_NearbyPump", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_Well", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_RiverCanal", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_SpringRavineKarez", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_PondToba", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "SourceOfDrinkingWater_Others", "type": "BIGINT", "description": "mouzas reporting this drinking-water source (multiple response)" }, { "name": "StatusTypeOfStreets_Metaled", "type": "BIGINT", "description": "mouzas reporting this street surface (multiple response)" }, { "name": "StatusTypeOfStreets_Cemented", "type": "BIGINT", "description": "mouzas reporting this street surface (multiple response)" }, { "name": "StatusTypeOfStreets_Bricked", "type": "BIGINT", "description": "mouzas reporting this street surface (multiple response)" }, { "name": "StatusTypeOfStreets_DirtRoad", "type": "BIGINT", "description": "mouzas reporting this street surface (multiple response)" }, { "name": "HealthFacility_PoupulationWelfareCentre", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_BHU", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_RHC", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_NGODispensary", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_ChildMotherCareCentre", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_PrivateDoctorMBBS", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_HospitalDispensary", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "HealthFacility_FacilityOfMidwife", "type": "BIGINT", "description": "mouzas reporting this health facility (multiple response)" }, { "name": "ElectrictiyAvailability_AllMouzas", "type": "BIGINT", "description": "mouzas by how much of the settlement has electricity (exclusive; PBS spelling)" }, { "name": "ElectrictiyAvailability_MostlyMouzas", "type": "BIGINT", "description": "mouzas by how much of the settlement has electricity (exclusive; PBS spelling)" }, { "name": "ElectrictiyAvailability_SomeMouzas", "type": "BIGINT", "description": "mouzas by how much of the settlement has electricity (exclusive; PBS spelling)" }, { "name": "ElectrictiyAvailability_NoneMouzas", "type": "BIGINT", "description": "mouzas by how much of the settlement has electricity (exclusive; PBS spelling)" }, { "name": "AlternateEnergySource_SolarEnergy", "type": "BIGINT", "description": "mouzas reporting this alternative energy source" }, { "name": "AlternateEnergySource_BioGas", "type": "BIGINT", "description": "mouzas reporting this alternative energy source" }, { "name": "AlternateEnergySource_Generator", "type": "BIGINT", "description": "mouzas reporting this alternative energy source" }, { "name": "AlternateEnergySource_Others", "type": "BIGINT", "description": "mouzas reporting this alternative energy source" }, { "name": "AlternateEnergySource_None", "type": "BIGINT", "description": "mouzas reporting this alternative energy source" }, { "name": "FuelAvailability_SuiGas", "type": "BIGINT", "description": "mouzas reporting this domestic fuel (multiple response)" }, { "name": "FuelAvailability_LPG", "type": "BIGINT", "description": "mouzas reporting this domestic fuel (multiple response)" }, { "name": "FuelAvailability_keroseneOil", "type": "BIGINT", "description": "mouzas reporting this domestic fuel (multiple response)" }, { "name": "FuelAvailability_Wood", "type": "BIGINT", "description": "mouzas reporting this domestic fuel (multiple response)" }, { "name": "FuelAvailability_Coal", "type": "BIGINT", "description": "mouzas reporting this domestic fuel (multiple response)" }, { "name": "FuelAvailability_AnimalDungCake", "type": "BIGINT", "description": "mouzas reporting this domestic fuel (multiple response)" }, { "name": "BazarAvailabilityCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "ColdStorageAvailabilityCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "ProcurementCentreAvailabilityCount", "type": "BIGINT", "description": "count of mouzas reporting this" }, { "name": "CommunityInfrastructure_AgriMachineryWorkshopAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_DieselPumpAgencyAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TransportFacilityAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TransportFacilityNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_CNGFacilityAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_CNGFacilityNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TelephoneFacility_FixedlineAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TelephoneFacility_FixedlineNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TelephoneFacility_PCOAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TelephoneFacility_PCONotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TelephoneFacility_MobileSignalsAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_TelephoneFacility_MobileSignalsNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_InternetFacility_FixedlineDSLAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_InternetFacility_FixedlineDSLNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_InternetFacility_CableNetAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_InternetFacility_CableNetNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_InternetFacility_MobileNetAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "CommunityInfrastructure_InternetFacility_MobileNetNotAvailableCount", "type": "BIGINT", "description": "mouzas with / without this facility" }, { "name": "NaturalDisaster_ExistanceCount", "type": "BIGINT", "description": "mouzas exposed to natural disaster, and to each type" }, { "name": "NaturalDisaster_NotExistanceCount", "type": "BIGINT", "description": "mouzas exposed to natural disaster, and to each type" }, { "name": "NaturalDisaster_DroughtCount", "type": "BIGINT", "description": "mouzas exposed to natural disaster, and to each type" }, { "name": "NaturalDisaster_FloodCount", "type": "BIGINT", "description": "mouzas exposed to natural disaster, and to each type" }, { "name": "NaturalDisaster_EarthquakeCount", "type": "BIGINT", "description": "mouzas exposed to natural disaster, and to each type" }, { "name": "NaturalDisaster_OthersCount", "type": "BIGINT", "description": "mouzas exposed to natural disaster, and to each type" }, { "name": "CreditSource_ZTBL", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_CooperativeBank", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_CommercialBank", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_MicrofinanceBank", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_NGO", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_RSP", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_Govt", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_Broker", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_Others", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_OnlineCommercialBankExistance", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_OnlineCommercialBankNotExistance", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_PostOfficeExistance", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_PostOfficeNotExistance", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_PoliceStationExistance", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "CreditSource_PoliceStationNotExistance", "type": "BIGINT", "description": "mouzas reporting this credit source, post office or police station" }, { "name": "IndustryAndSourceOfEmployment_LargeScale", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MediumScale", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_SmallScale", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_CottageIndustries", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_None", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleServiceMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleServiceSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleServiceNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleAgricultureMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleAgricultureSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleAgricultureNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleTradeMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleTradeSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleTradeNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleIndustriesMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleIndustriesSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleIndustriesNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MalePersonalBusinessMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MalePersonalBusinessSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MalePersonalBusinessNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleOverseasMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleOverseasSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleOverseasNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleLabourMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleLabourSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_MaleLabourNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleServiceMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleServiceSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleServiceNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleAgricultureMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleAgricultureSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleAgricultureNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleTradeMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleTradeSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleTradeNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleIndustriesMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleIndustriesSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleIndustriesNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemalePersonalBusinessMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemalePersonalBusinessSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemalePersonalBusinessNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleOverseasMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleOverseasSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleOverseasNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleLabourMostlyCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleLabourSomeCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" }, { "name": "IndustryAndSourceOfEmployment_FemaleLabourNoneCount", "type": "BIGINT", "description": "mouzas by industry scale, and by how much of the workforce is in each sector" } ] }, { "name": "mpi_districts", "file": "mpi_districts.parquet", "bytes": 9876, "rows": 141, "description": "Alkire-Foster multidimensional poverty index by district, from PSLM 2019-20 microdata.", "notes": "M0 = H \u00d7 A. Censored headcounts c_* are the share of people who are both poor and deprived in that indicator (%). low_n=1 marks districts whose sample is too small to be reliable \u2014 filter them out for rankings.", "unit": null, "source": "PSLM/HIES 2019-20 microdata (PBS), Alkire-Foster method", "columns": [ { "name": "district_key", "type": "VARCHAR", "description": "join key to district_indicators.district_key" }, { "name": "name", "type": "VARCHAR", "description": "district name" }, { "name": "prov", "type": "VARCHAR", "description": "province" }, { "name": "mpi", "type": "DOUBLE", "description": "M0, adjusted headcount ratio (0-1)" }, { "name": "H", "type": "DOUBLE", "description": "headcount ratio \u2014 % of people who are MPI-poor" }, { "name": "A", "type": "DOUBLE", "description": "intensity \u2014 average share of weighted deprivations among the poor (%)" }, { "name": "rank", "type": "BIGINT", "description": "1 = poorest" }, { "name": "n_obs", "type": "BIGINT", "description": "households in the PSLM sample" }, { "name": "low_n", "type": "BIGINT", "description": "1 if sample below the reliability threshold" }, { "name": "c_schooling", "type": "DOUBLE", "description": "censored headcount: years of schooling (%)" }, { "name": "c_attendance", "type": "DOUBLE", "description": "censored headcount: school attendance (%)" }, { "name": "c_electricity", "type": "DOUBLE", "description": "censored headcount: electricity (%)" }, { "name": "c_cooking_fuel", "type": "DOUBLE", "description": "censored headcount: cooking fuel (%)" }, { "name": "c_sanitation", "type": "DOUBLE", "description": "censored headcount: sanitation (%)" }, { "name": "c_water", "type": "DOUBLE", "description": "censored headcount: drinking water (%)" }, { "name": "c_housing", "type": "DOUBLE", "description": "censored headcount: housing (%)" } ] }, { "name": "national_accounts", "file": "national_accounts.parquet", "bytes": 61883, "rows": 10526, "description": "National accounts / GDP series, 1951-52 \u2192 2025-26 (PBS 2015-16 base).", "notes": "Units vary BY TABLE: levels are Rs million (tables 2\u20135, 8\u201311), growth rates and shares are percentages (tables 6, 7a/b). Always read table_name before aggregating. Item labels on the Macro/Main-Aggregate sheets are best-effort.", "unit": null, "source": "PBS National Accounts annual tables (2015-16 base)", "columns": [ { "name": "table_sheet", "type": "VARCHAR", "description": "sheet name in the PBS workbook" }, { "name": "table_name", "type": "VARCHAR", "description": "published table title" }, { "name": "price_basis", "type": "VARCHAR", "description": "constant or current prices" }, { "name": "base_year", "type": "VARCHAR", "description": "price base" }, { "name": "item", "type": "VARCHAR", "description": "sector / indicator label as published" }, { "name": "year", "type": "VARCHAR", "description": "fiscal year, e.g. '2019-20'" }, { "name": "value", "type": "DOUBLE", "description": "value \u2014 unit depends on the table" } ] }, { "name": "sbp_observations", "file": "sbp_observations.parquet", "bytes": 994032, "rows": 306875, "description": "The macro time-series panel: every observation of every SBP series held here.", "notes": "One row per series \u00d7 date. UNITS ARE PER-SERIES \u2014 join to sbp_series_catalog and read `unit` before summing anything, because this table mixes rupees, dollars, percentages and index levels in one `value` column. value IS NULL where SBP suppressed or has not published the figure and `status` says which ('Normal', 'Missing value', \u2026) \u2014 a NULL is not a zero. Frequencies are mixed, so filter on the catalogue's `frequency` before resampling or averaging across series. DOUBLE-COUNTING TRAP (country-wise remittances, TS_GP_BOP_WR_M): the country series are hierarchical, so summing them all overstates the total by ~42% (FY2024-25: 54,384 vs the published 38,299 Mn USD). 'U.A.E.' already contains Dubai, Abu Dhabi, Sharjah and 'Other four U.A.E.'s States'; 'Other GCC Countries excluding Saudi Arabia & U.A.E.' already contains Bahrain, Kuwait, Oman and Qatar; 'ten European Countries' already contains Belgium, Denmark, France, Germany, Greece, Ireland, Italy, Netherland, Spain and Sweden \u2014 Norway and Switzerland are reported separately. The partition that reconciles exactly to the published total is: Saudi Arabia, U.A.E., U.K., U.S.A., Other GCC, ten European Countries, Norway, Switzerland, Australia, Canada, Japan, Malaysia, South Africa, South Korea, Other Countries. The same shape applies to province-wise banking (TS_GP_BAM_ADVDEP_HY), where 'all Pakistan' is the total of the regional series.", "unit": null, "source": "State Bank of Pakistan, EasyData API (easydata.sbp.org.pk)", "columns": [ { "name": "series_key", "type": "VARCHAR", "description": "joins to sbp_series_catalog.series_key" }, { "name": "dataset_code", "type": "VARCHAR", "description": "EasyData dataset code, denormalised for cheap filtering" }, { "name": "obs_date", "type": "DATE", "description": "observation date \u2014 END of the period (see catalogue notes)" }, { "name": "value", "type": "DOUBLE", "description": "the observation; unit depends on the series" }, { "name": "status", "type": "VARCHAR", "description": "SBP observation status; anything but 'Normal' needs care" }, { "name": "comment", "type": "VARCHAR", "description": "SBP status comment, usually empty" } ] }, { "name": "sbp_series_catalog", "file": "sbp_series_catalog.parquet", "bytes": 285055, "rows": 22974, "description": "Every SBP EasyData series held here: name, unit, frequency, coverage, method note.", "notes": "One row per series \u2014 browse this first, then join to sbp_observations on series_key. DATE CONVENTION: observations are stamped on the LAST day of their period, and annual series on the last day of the FISCAL year, so FY2023-24 appears as 2024-06-30. Not every annual series is fiscal though \u2014 population and literacy are calendar years. `available_upto` is SBP's own claim and several datasets are stale (province-wise banking stops at Jun-2023), so check it before presenting a series as current.", "unit": null, "source": "State Bank of Pakistan, EasyData API (easydata.sbp.org.pk)", "columns": [ { "name": "series_key", "type": "VARCHAR", "description": "join key to sbp_observations.series_key" }, { "name": "dataset_code", "type": "VARCHAR", "description": "EasyData dataset the series belongs to" }, { "name": "dataset_name", "type": "VARCHAR", "description": "published dataset title" }, { "name": "subject_area", "type": "VARCHAR", "description": "External Sector | Monetary and Financial Sector | Real Sector | Public Finance | Interest Rates | Pakistan's Debt Profile" }, { "name": "series_name", "type": "VARCHAR", "description": "published series title" }, { "name": "series_short_name", "type": "VARCHAR", "description": "abbreviated title" }, { "name": "frequency", "type": "VARCHAR", "description": "Daily | Weekly | Monthly | Quarterly | Half-yearly | Annual | As-Needed" }, { "name": "unit", "type": "VARCHAR", "description": "unit as published (PKR, USD, Percent, Index\u2026)" }, { "name": "variable_type", "type": "VARCHAR", "description": "Flow | Stock (level) Variable | ratio" }, { "name": "available_since", "type": "DATE", "description": "first observation date claimed by SBP" }, { "name": "available_upto", "type": "DATE", "description": "last observation date claimed by SBP" }, { "name": "last_refresh", "type": "DATE", "description": "when SBP last revised the series" }, { "name": "description", "type": "VARCHAR", "description": "SBP's own methodological note" } ], "datasets": [ { "code": "TS_GP_BOP_BPM6SUM_M", "name": "Monthly Summary of Balance of Payments as per BPM6", "subject": "External Sector", "series": 74, "since": "2013-07", "upto": "2026-07" }, { "code": "TS_GP_ER_FAERPKR_M", "name": "Bank Floating Average Exchange Rates (PKR per National Currency)", "subject": "External Sector", "series": 48, "since": "1947-08", "upto": "2026-07" }, { "code": "TS_GP_BOP_WR_M", "name": "Country-wise Workers' Remittances", "subject": "External Sector", "series": 36, "since": "1972-07", "upto": "2026-07" }, { "code": "TS_GP_BOP_XMGS_M", "name": "Export and Import of Goods and Services", "subject": "External Sector", "series": 32, "since": "2005-07", "upto": "2026-07" }, { "code": "TS_GP_EXT_PAKRES_M", "name": "Gold and Foreign Exchange Reserves of Pakistan", "subject": "External Sector", "series": 19, "since": "1948-06", "upto": "2026-07" }, { "code": "TS_GP_ES_KSORDA_M", "name": "Key Statistics on Roshan Digital Account (RDA)", "subject": "External Sector", "series": 11, "since": "2020-09", "upto": "2026-07" }, { "code": "TS_GP_ER_REERNEER_M", "name": "Nominal/Real Effective Exchange Rates Indices of Pak Rupees", "subject": "External Sector", "series": 4, "since": "2001-07", "upto": "2026-07" }, { "code": "TS_GP_ES_SWR_M", "name": "Seasonally Adjusted Workers\u2019 Remittances", "subject": "External Sector", "series": 2, "since": "2005-07", "upto": "2026-07" }, { "code": "TS_GP_IR_SIRPR_AH", "name": "Structure of Interest Rate: State Bank of Pakistan Policy Rates", "subject": "Interest Rates", "series": 3, "since": "1956-01", "upto": "2026-04" }, { "code": "TS_GP_BAM_ADVDEP_HY", "name": "Province-wise Advances and Deposits by Borrowers/Category of Deposit Holders", "subject": "Monetary and Financial Sector", "series": 162, "since": "2001-06", "upto": "2023-06" }, { "code": "TS_GP_MFS_PSD_Q", "name": "Payment Systems Quarterly Data", "subject": "Monetary and Financial Sector", "series": 112, "since": "2007-03", "upto": "2025-12" }, { "code": "TS_GP_BAM_WALDR_M", "name": "Weighted Average Lending and Deposit Rates", "subject": "Monetary and Financial Sector", "series": 80, "since": "2004-01", "upto": "2026-07" }, { "code": "TS_GP_MFS_SGADVNPL_Q", "name": "Segment-wise Advances and Non-Performing Loans (NPLs)", "subject": "Monetary and Financial Sector", "series": 72, "since": "2010-12", "upto": "2025-06" }, { "code": "TS_GP_BAM_CENGOVTD_M", "name": "Central Government Debt", "subject": "Monetary and Financial Sector", "series": 52, "since": "2010-06", "upto": "2026-06" }, { "code": "TS_GP_BAM_DCS_M", "name": "Depository Corporations Survey", "subject": "Monetary and Financial Sector", "series": 50, "since": "2008-06", "upto": "2026-07" }, { "code": "TS_GP_BAM_M2_Q", "name": "Quarterly Broad Money M2", "subject": "Monetary and Financial Sector", "series": 47, "since": "2014-06", "upto": "2026-06" }, { "code": "TS_GP_BAM_PKDLP_Q", "name": "Pakistan Debt and Liabilities Summary", "subject": "Monetary and Financial Sector", "series": 22, "since": "2009-06", "upto": "2026-06" }, { "code": "TS_GP_BAM_SIRKIBOR_D", "name": "Structure of Interest Rates: KIBORs and KIBIDs ", "subject": "Monetary and Financial Sector", "series": 18, "since": "2005-06", "upto": "2026-08" }, { "code": "TS_GP_MFS_ASTQLTYB_Q", "name": "Asset Quality of the Banking System", "subject": "Monetary and Financial Sector", "series": 15, "since": "2010-12", "upto": "2025-06" }, { "code": "TS_GP_BAM_M3_M", "name": "Monetary Aggregates (M3) - Monthly Profile", "subject": "Monetary and Financial Sector", "series": 11, "since": "2006-06", "upto": "2026-07" }, { "code": "TS_GP_MFS_EPUI_M", "name": "Economic Policy Uncertainty (EPU) Index", "subject": "Monetary and Financial Sector", "series": 2, "since": "2010-08", "upto": "2026-07" }, { "code": "TS_GP_PDL_NSSOA_M", "name": "Outstanding Position of National Saving Schemes", "subject": "Pakistan's Debt Profile", "series": 6, "since": "2013-07", "upto": "2026-06" }, { "code": "TS_GP_PF_CPRE_Y", "name": "Consolidated Provincial Receipts and Expenditures (FY 2011 - onwards)", "subject": "Public Finance", "series": 30, "since": "2011-06", "upto": "2024-06" }, { "code": "TS_GP_PF_SPF_Y", "name": "Summary of Public Finance (Consolidated Federal and Provincial Governments) (FY 2000 - onwards)", "subject": "Public Finance", "series": 13, "since": "2007-06", "upto": "2025-06" }, { "code": "TS_GP_RL_CCSIND_M", "name": "Consumer Confidence Survey \u2013 Indices", "subject": "Real Sector", "series": 118, "since": "2012-01", "upto": "2026-07" }, { "code": "TS_GP_RL_BCSIND_M", "name": "Business Confidence Survey \u2013 Indices", "subject": "Real Sector", "series": 107, "since": "2017-10", "upto": "2026-07" }, { "code": "TS_GP_PT_CPI_M", "name": "Inflation Snapshot (New Base: 2015-16)", "subject": "Real Sector", "series": 60, "since": "2016-07", "upto": "2026-07" }, { "code": "TS_GP_RLS_PSAUTO_M", "name": "Production and Sales of Auto Vehicles", "subject": "Real Sector", "series": 14, "since": "2004-07", "upto": "2026-07" }, { "code": "TS_GP_RLS_ELECGEN_M", "name": "Generation of Electricity by Sector", "subject": "Real Sector", "series": 13, "since": "2012-07", "upto": "2026-07" }, { "code": "TS_GP_RL_LSM1516_M", "name": "Quantum Index Series of Selected Large-scale Manufacturing Items (base 2015-16)", "subject": "Real Sector", "series": 11, "since": "2016-07", "upto": "2026-06" }, { "code": "TS_GP_RS_QGDP1516_Q", "name": "Quarterly GDP at Constant Basic Prices of 2015-16", "subject": "Real Sector", "series": 8, "since": "2015-09", "upto": "2026-03" }, { "code": "TS_GP_RLS_POLSALE_M", "name": "POL (Energy Products) Sales by Sector", "subject": "Real Sector", "series": 8, "since": "2013-07", "upto": "2026-05" }, { "code": "TS_GP_RLS_PAKGDP15_Y", "name": "Gross Domestic Product of Pakistan at constant basic prices of 2015-16", "subject": "Real Sector", "series": 6, "since": "2000-06", "upto": "2026-06" } ] }, { "name": "school_access_district", "file": "school_access_district.parquet", "bytes": 30428, "rows": 132, "description": "Distance to the nearest government school by sex, enrolment by sex, and school counts, one row per district (132).", "notes": "all_km, boys_km, girls_km are POPULATION-WEIGHTED MEDIAN straight-line distances (Lambert conformal conic, km) from every populated 1 km cell to the nearest school of that network; *_min are walking minutes on the Malaria Atlas friction surface. gap_km = girls_km \u2212 boys_km (positive = girls further). Networks are by name designation; for Sindh the same medians under the attendance and girls-or-mixed definitions are in girls_km_attend / girls_km_mixed (the designation gap of 0.8 km falls to zero under attendance). tt_caveat flags districts where the friction surface is unreliable (GB) or mountain/desert cells make minutes an upper bound. *_in_school_pct_5_16 are Census 2023 Table 13(b) enrolment rates (enrolled / population aged 5\u201316) with successor districts summed into parents, so 123 of the 132 rows carry them. living_standards_deprivation_pslm is the (censored) MPI component; material_deprivation_pslm is an uncensored index from PSLM 2019-20 (no toilet, no flush, no piped water, food insecurity). *_n_schools count schools whose POINT falls in the district polygon (the basis of the piece's Figure 1); schools_listed / _with_coords / _in_analysis count rows by the SOURCE's district. The two bases differ where geocoded points cross a boundary. Distances depend on the whole network, not the district's own schools, so a district with few schools can still be close to the next district's.", "unit": "km, walking minutes, per cent", "source": "Adaad school layer (schools_pk) \u00d7 WorldPop 2020 \u00d7 Malaria Atlas friction surface; PBS Census 2023 Table 13(b); PSLM 2019-20", "columns": [ { "name": "region", "type": "VARCHAR", "description": "analysis region" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar district key" }, { "name": "district", "type": "VARCHAR", "description": "display name" }, { "name": "all_km", "type": "DOUBLE", "description": "median km to nearest school, either sex" }, { "name": "boys_km", "type": "DOUBLE", "description": "median km to nearest boys' school" }, { "name": "girls_km", "type": "DOUBLE", "description": "median km to nearest girls' school" }, { "name": "gap_km", "type": "DOUBLE", "description": "girls_km \u2212 boys_km" }, { "name": "all_min", "type": "DOUBLE", "description": "median walking minutes, any school" }, { "name": "boys_min", "type": "DOUBLE", "description": "median walking minutes, boys' school" }, { "name": "girls_min", "type": "DOUBLE", "description": "median walking minutes, girls' school" }, { "name": "gap_min", "type": "DOUBLE", "description": "girls_min \u2212 boys_min" }, { "name": "tt_caveat", "type": "VARCHAR", "description": "travel-time caveat, if any" }, { "name": "girls_in_school_pct_5_16", "type": "DOUBLE", "description": "Census 2023 Table 13(b): girls 5\u201316 enrolled / girls 5\u201316, %" }, { "name": "boys_in_school_pct_5_16", "type": "DOUBLE", "description": "Census 2023 Table 13(b): boys 5\u201316 enrolled / boys 5\u201316, %" }, { "name": "enrol_gap_pp_boys_minus_girls", "type": "DOUBLE", "description": "boys_in_school_pct_5_16 \u2212 girls_in_school_pct_5_16, percentage points" }, { "name": "living_standards_deprivation_pslm", "type": "DOUBLE", "description": "MPI living-standards deprivation share (censored), PSLM 2019-20" }, { "name": "material_deprivation_pslm", "type": "DOUBLE", "description": "uncensored material deprivation index, PSLM 2019-20" }, { "name": "schools_listed", "type": "BIGINT", "description": "rows in schools_pk whose source district is this district" }, { "name": "schools_with_coords", "type": "BIGINT", "description": "of which positioned" }, { "name": "schools_in_analysis", "type": "BIGINT", "description": "of which in the analysis" }, { "name": "boys_high_median_km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "boys_middle_median_km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "boys_primary_median_km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "girls_high_median_km", "type": "DOUBLE", "description": "median km to nearest girls' high-or-above school" }, { "name": "girls_middle_median_km", "type": "DOUBLE", "description": "median km to nearest girls' middle-or-above school" }, { "name": "girls_primary_median_km", "type": "DOUBLE", "description": "median km to nearest girls' school, any level" }, { "name": "boys_high_share_over_5km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "boys_middle_share_over_5km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "boys_primary_share_over_5km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "girls_high_share_over_5km", "type": "DOUBLE", "description": "share more than 5 km from a girls' high-plus school" }, { "name": "girls_middle_share_over_5km", "type": "DOUBLE", "description": "share more than 5 km from a girls' middle-plus school" }, { "name": "girls_primary_share_over_5km", "type": "DOUBLE", "description": "share of population more than 5 km from a girls' school, any level" }, { "name": "girls_primary_n_schools", "type": "BIGINT", "description": "girls' schools (any level) whose point is inside the district polygon" }, { "name": "boys_primary_n_schools", "type": "BIGINT", "description": "as girls_, boys" }, { "name": "girls_middle_n_schools", "type": "BIGINT", "description": "girls' middle-plus schools inside the polygon (Figure 1)" }, { "name": "boys_middle_n_schools", "type": "BIGINT", "description": "as girls_, boys" }, { "name": "girls_high_n_schools", "type": "BIGINT", "description": "girls' high-plus schools inside the polygon" }, { "name": "boys_high_n_schools", "type": "BIGINT", "description": "as girls_, boys" }, { "name": "girls_km_mixed", "type": "DOUBLE", "description": "Sindh only: girls_km when Mixed schools join the girls' network" }, { "name": "boys_km_mixed", "type": "DOUBLE", "description": "Sindh only: boys_km, boys-or-mixed" }, { "name": "gap_km_mixed", "type": "DOUBLE", "description": "Sindh only: gap under the mixed definition" }, { "name": "girls_km_attend", "type": "DOUBLE", "description": "Sindh only: girls_km when any school enrolling girls counts" }, { "name": "boys_km_attend", "type": "DOUBLE", "description": "Sindh only: boys_km by attendance" }, { "name": "gap_km_attend", "type": "DOUBLE", "description": "Sindh only: gap under the attendance definition" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "school_access_tehsil", "file": "school_access_tehsil.parquet", "bytes": 33340, "rows": 498, "description": "Distance to the nearest government school by sex and level, and school counts, one row per tehsil (498 of 553 ADM3 polygons).", "notes": "The tehsil version of school_access_district, by the same method: population-weighted median straight-line km (Lambert conformal conic, 1 km WorldPop 2020 cells) to the nearest school of that sex and level in the cell's own REGION network \u2014 a tehsil's residents can use the next tehsil's schools, so its distance is not a function of its own school count. gap_*_km = girls \u2212 boys (positive = girls further). *_over5km_pct is the population share more than 5 km away. *_schools count schools whose point falls in the polygon. coverage_pct is the share of the polygon's population that lay inside the analysed region; rows under 50% (slivers of the merged districts and of AJK's other districts inside a neighbouring district polygon) are dropped, so 498 tehsils carry data and 55 do not. The 553 polygons are the Mouza Census ADM3 frame (mouza_crosswalk.dd_id) rather than PBS's 2023 tehsils. Read coord_tier before comparing across provinces: Punjab's positions are geocoded (half at settlement precision, the rest at markaz or tehsil centroids), so Punjab tehsil values are a district-scale picture, not a local one. Sindh networks are by name designation; the designated gap is an upper bound (see school_access_district's mixed and attendance columns). This is the table the map's Education \u2192 Distance to School layer draws.", "unit": "km, per cent", "source": "Adaad school layer (schools_pk) \u00d7 WorldPop 2020 \u00d7 Data Darbar ADM3 polygons", "columns": [ { "name": "dd_id", "type": "VARCHAR", "description": "ADM3 identifier \u2014 joins mouza_crosswalk.dd_id, tehsil_satellite.tehsil_id" }, { "name": "tehsil", "type": "VARCHAR", "description": "tehsil name in the ADM3 frame" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar district key" }, { "name": "region", "type": "VARCHAR", "description": "analysis region" }, { "name": "coord_tier", "type": "VARCHAR", "description": "coverage grade of the region's positions (A to C)" }, { "name": "pop", "type": "BIGINT", "description": "population of the analysed cells (WorldPop 2020)" }, { "name": "coverage_pct", "type": "DOUBLE", "description": "share of the polygon's population analysed" }, { "name": "girls_primary_km", "type": "DOUBLE", "description": "median km to nearest girls' school, any level" }, { "name": "boys_primary_km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "gap_primary_km", "type": "DOUBLE", "description": "girls \u2212 boys, any level" }, { "name": "girls_middle_km", "type": "DOUBLE", "description": "median km to nearest girls' middle-or-above school" }, { "name": "boys_middle_km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "gap_middle_km", "type": "DOUBLE", "description": "girls \u2212 boys, middle" }, { "name": "girls_high_km", "type": "DOUBLE", "description": "median km to nearest girls' high-or-above school" }, { "name": "boys_high_km", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "gap_high_km", "type": "DOUBLE", "description": "girls \u2212 boys, high" }, { "name": "girls_middle_over5km_pct", "type": "DOUBLE", "description": "population more than 5 km from a girls' middle-plus school, %" }, { "name": "boys_middle_over5km_pct", "type": "DOUBLE", "description": "as girls_, boys" }, { "name": "girls_primary_schools", "type": "BIGINT", "description": "girls' schools (any level) inside the polygon" }, { "name": "boys_primary_schools", "type": "BIGINT", "description": "as girls_, boys" }, { "name": "girls_middle_schools", "type": "BIGINT", "description": "girls' middle-plus schools inside the polygon" }, { "name": "boys_middle_schools", "type": "BIGINT", "description": "as girls_, boys" }, { "name": "girls_high_schools", "type": "BIGINT", "description": "girls' high-plus schools inside the polygon" }, { "name": "boys_high_schools", "type": "BIGINT", "description": "as girls_, boys" }, { "name": "girls_share_middle_pct", "type": "DOUBLE", "description": "girls' share of middle-plus schools inside the polygon, %" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "school_distance_stats", "file": "school_distance_stats.parquet", "bytes": 22568, "rows": 832, "description": "Distance-to-school distributions by region and district, sex and school level (primary, middle-plus, high-plus).", "notes": "One row per geography \u00d7 sex \u00d7 level. geography_type = 'region' rows are the seven analysis regions; 'district' rows carry district_key. mean_km and median_km are population-weighted over 1 km cells; share_over_2km/5km/10km are population shares beyond that straight-line distance. network_schools is the size of the REGION's network for that sex and level \u2014 the same number repeats on every district row of a region, because a district's residents can use the next district's schools. Per-district school counts are in school_access_district. tier and sector repeat the coverage ledger's grade and the 'government schools only' scope.", "unit": "km, population shares", "source": "Adaad school layer \u00d7 WorldPop 2020", "columns": [ { "name": "region", "type": "VARCHAR", "description": "analysis region" }, { "name": "geography_type", "type": "VARCHAR", "description": "region | district" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar key for district rows" }, { "name": "sex", "type": "VARCHAR", "description": "girls | boys" }, { "name": "level", "type": "VARCHAR", "description": "primary (any school) | middle (middle-plus) | high (high-plus)" }, { "name": "network_schools", "type": "BIGINT", "description": "schools in the region's network for this sex and level" }, { "name": "pop", "type": "BIGINT", "description": "population of the geography (WorldPop 2020 sum)" }, { "name": "mean_km", "type": "DOUBLE", "description": "population-weighted mean km" }, { "name": "median_km", "type": "DOUBLE", "description": "population-weighted median km" }, { "name": "share_over_2km", "type": "DOUBLE", "description": "population share more than 2 km away" }, { "name": "share_over_5km", "type": "DOUBLE", "description": "more than 5 km" }, { "name": "share_over_10km", "type": "DOUBLE", "description": "more than 10 km" }, { "name": "tier", "type": "VARCHAR", "description": "coverage grade" }, { "name": "sector", "type": "VARCHAR", "description": "scope" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "school_layer_coverage", "file": "school_layer_coverage.parquet", "bytes": 4730, "rows": 9, "description": "Coverage ledger: how many government schools each region lists, how many the layer positions, and where the positions come from.", "notes": "schools_known_to_exist is the department's own count (roster or annual census); schools_in_analysis is what the piece used; rows_in_schools_pk / rows_with_coords / rows_in_analysis are the same counts read back from the released table, so any difference is visible here (Sindh: 39,745 functional positioned schools, 39,741 with a sex designation). Two rows carry no positions at all: the ex-FATA merged districts (6,394 schools per KP's annual census, no public locations) and eight of AJK's ten districts (no public list). Islamabad's ~420 is the size of the federal network, not a roster count. quality_tier grades positional quality, not completeness: Punjab is 95% geocoded but only half of it at settlement precision.", "unit": null, "source": "Adaad, coverage ledger of the school layer, September 2026", "columns": [ { "name": "region", "type": "VARCHAR", "description": "region" }, { "name": "sector", "type": "VARCHAR", "description": "which schools the row covers" }, { "name": "schools_in_analysis", "type": "BIGINT", "description": "schools the piece used" }, { "name": "schools_known_to_exist", "type": "VARCHAR", "description": "schools the department lists" }, { "name": "source", "type": "VARCHAR", "description": "register" }, { "name": "gps_origin", "type": "VARCHAR", "description": "how positions were obtained" }, { "name": "quality_tier", "type": "VARCHAR", "description": "A (GPS at source) to C (partial geocoding)" }, { "name": "coverage_note", "type": "VARCHAR", "description": "caveats" }, { "name": "mapped", "type": "VARCHAR", "description": "yes | partial | no" }, { "name": "schools_pk_region", "type": "VARCHAR", "description": "region label in schools_pk" }, { "name": "rows_in_schools_pk", "type": "BIGINT", "description": "rows in the released table" }, { "name": "rows_with_coords", "type": "BIGINT", "description": "of which positioned" }, { "name": "rows_in_analysis", "type": "BIGINT", "description": "of which in the analysis" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "school_validation_district", "file": "school_validation_district.parquet", "bytes": 46945, "rows": 147, "description": "External-validity test of the school layer against the Mouza Census 2020, one row per mouza district (147): count floors and village-reported distances.", "notes": "The Mouza Census asked every rural mouza whether an institution for boys and one for girls exists at each level and, if not, how far the nearest is. It is sector-blind and counts villages, so it cannot audit the layer line by line; it puts a FLOOR under the count (a village with one has at least one) and gives an INDEPENDENT distance. ratio_* = schools in the layer \u00f7 mouzas reporting an institution of that sex and level: well under 1 means schools are missing or misclassified; above 1 is expected. The floor test is diagnostic only where private and co-educational provision is scarce \u2014 at primary level in Punjab a low ratio is private schools, and in Sindh 'girls undercounted relative to boys' fires by construction because designated boys' schools include the Mixed majority. status = 'absent from harvest' marks the 15 mouza districts the layer does not cover (7 merged districts, 8 AJK). village_* columns are means and medians of the villages' reported km; model_* are the layer's population-weighted medians and shares; *_gap_* are girls minus boys. Compare ranks and signs, not levels: village distances are unweighted, by road, any sector. Run on the released table (in_analysis rows), so these figures describe schools_pk, not the raw registers.", "unit": null, "source": "PBS Mouza Census 2020 microdata (Form-11 Part IV) \u00d7 schools_pk \u00d7 school_distance_stats", "columns": [ { "name": "region", "type": "VARCHAR", "description": "region" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar key" }, { "name": "mouza_district", "type": "VARCHAR", "description": "district(s) as PBS names them (successors joined with +)" }, { "name": "layer_district", "type": "VARCHAR", "description": "district name in the layer" }, { "name": "status", "type": "VARCHAR", "description": "matched | absent from harvest | harvest only (no mouza rows: the layer has schools but PBS enumerated no rural mouza there, e.g. Karachi's urban districts)" }, { "name": "rural_mouzas", "type": "DOUBLE", "description": "rural mouzas in the district" }, { "name": "flag", "type": "VARCHAR", "description": "test outcomes: boys/girls middle-plus or primary under half; girls undercounted relative to boys" }, { "name": "mouzas_with_B_primary", "type": "DOUBLE", "description": "mouzas reporting a boys' primary institution" }, { "name": "mouzas_with_B_middle", "type": "DOUBLE", "description": "mouzas reporting a boys' middle institution" }, { "name": "mouzas_with_B_high", "type": "DOUBLE", "description": "mouzas reporting a boys' high institution" }, { "name": "mouzas_with_G_primary", "type": "DOUBLE", "description": "mouzas reporting a girls' primary institution" }, { "name": "mouzas_with_G_middle", "type": "DOUBLE", "description": "mouzas reporting a girls' middle institution" }, { "name": "mouzas_with_G_high", "type": "DOUBLE", "description": "mouzas reporting a girls' high institution" }, { "name": "coll_B_high", "type": "BIGINT", "description": "boys' high schools in the layer" }, { "name": "coll_B_middle", "type": "BIGINT", "description": "boys' middle schools in the layer" }, { "name": "coll_B_primary", "type": "BIGINT", "description": "boys' primary schools in the layer" }, { "name": "coll_G_high", "type": "BIGINT", "description": "girls' high schools in the layer" }, { "name": "coll_G_middle", "type": "BIGINT", "description": "girls' middle schools in the layer" }, { "name": "coll_G_primary", "type": "BIGINT", "description": "girls' primary schools in the layer" }, { "name": "coll_midplus_B", "type": "BIGINT", "description": "boys' middle-plus schools in the layer" }, { "name": "ratio_midplus_B", "type": "DOUBLE", "description": "boys' midplus ratio: layer \u00f7 mouza floor" }, { "name": "ratio_high_B", "type": "DOUBLE", "description": "boys' high ratio: layer \u00f7 mouza floor" }, { "name": "ratio_primary_B", "type": "DOUBLE", "description": "boys' primary ratio: layer \u00f7 mouza floor" }, { "name": "coll_midplus_G", "type": "BIGINT", "description": "girls' middle-plus schools in the layer" }, { "name": "ratio_midplus_G", "type": "DOUBLE", "description": "girls' midplus ratio: layer \u00f7 mouza floor" }, { "name": "ratio_high_G", "type": "DOUBLE", "description": "girls' high ratio: layer \u00f7 mouza floor" }, { "name": "ratio_primary_G", "type": "DOUBLE", "description": "girls' primary ratio: layer \u00f7 mouza floor" }, { "name": "girls_to_boys_ratio_midplus", "type": "DOUBLE", "description": "ratio_midplus_G \u00f7 ratio_midplus_B" }, { "name": "village_mean_km_B_primary", "type": "DOUBLE", "description": "villages' reported km to nearest boys' primary institution, mean" }, { "name": "village_mean_km_B_middle", "type": "DOUBLE", "description": "villages' reported km to nearest boys' middle institution, mean" }, { "name": "village_mean_km_B_high", "type": "DOUBLE", "description": "villages' reported km to nearest boys' high institution, mean" }, { "name": "village_mean_km_G_primary", "type": "DOUBLE", "description": "villages' reported km to nearest girls' primary institution, mean" }, { "name": "village_mean_km_G_middle", "type": "DOUBLE", "description": "villages' reported km to nearest girls' middle institution, mean" }, { "name": "village_mean_km_G_high", "type": "DOUBLE", "description": "villages' reported km to nearest girls' high institution, mean" }, { "name": "village_median_km_B_primary", "type": "DOUBLE", "description": "villages' reported km to nearest boys' primary institution, median" }, { "name": "village_median_km_B_middle", "type": "DOUBLE", "description": "villages' reported km to nearest boys' middle institution, median" }, { "name": "village_median_km_B_high", "type": "DOUBLE", "description": "villages' reported km to nearest boys' high institution, median" }, { "name": "village_median_km_G_primary", "type": "DOUBLE", "description": "villages' reported km to nearest girls' primary institution, median" }, { "name": "village_median_km_G_middle", "type": "DOUBLE", "description": "villages' reported km to nearest girls' middle institution, median" }, { "name": "village_median_km_G_high", "type": "DOUBLE", "description": "villages' reported km to nearest girls' high institution, median" }, { "name": "village_share_over_5km_B_primary", "type": "DOUBLE", "description": "share of villages more than 5 km from a boys' primary institution" }, { "name": "village_share_over_5km_B_middle", "type": "DOUBLE", "description": "share of villages more than 5 km from a boys' middle institution" }, { "name": "village_share_over_5km_B_high", "type": "DOUBLE", "description": "share of villages more than 5 km from a boys' high institution" }, { "name": "village_share_over_5km_G_primary", "type": "DOUBLE", "description": "share of villages more than 5 km from a girls' primary institution" }, { "name": "village_share_over_5km_G_middle", "type": "DOUBLE", "description": "share of villages more than 5 km from a girls' middle institution" }, { "name": "village_share_over_5km_G_high", "type": "DOUBLE", "description": "share of villages more than 5 km from a girls' high institution" }, { "name": "model_median_km_boys_high_plus", "type": "DOUBLE", "description": "layer: median km for boys, high-plus" }, { "name": "model_median_km_boys_middle_plus", "type": "DOUBLE", "description": "layer: median km for boys, middle-plus" }, { "name": "model_median_km_boys_primary_plus", "type": "DOUBLE", "description": "layer: median km for boys, primary-plus" }, { "name": "model_median_km_girls_high_plus", "type": "DOUBLE", "description": "layer: median km for girls, high-plus" }, { "name": "model_median_km_girls_middle_plus", "type": "DOUBLE", "description": "layer: median km for girls, middle-plus" }, { "name": "model_median_km_girls_primary_plus", "type": "DOUBLE", "description": "layer: median km for girls, primary-plus" }, { "name": "model_share_over_5km_boys_high_plus", "type": "DOUBLE", "description": "layer: share over 5km for boys, high-plus" }, { "name": "model_share_over_5km_boys_middle_plus", "type": "DOUBLE", "description": "layer: share over 5km for boys, middle-plus" }, { "name": "model_share_over_5km_boys_primary_plus", "type": "DOUBLE", "description": "layer: share over 5km for boys, primary-plus" }, { "name": "model_share_over_5km_girls_high_plus", "type": "DOUBLE", "description": "layer: share over 5km for girls, high-plus" }, { "name": "model_share_over_5km_girls_middle_plus", "type": "DOUBLE", "description": "layer: share over 5km for girls, middle-plus" }, { "name": "model_share_over_5km_girls_primary_plus", "type": "DOUBLE", "description": "layer: share over 5km for girls, primary-plus" }, { "name": "village_gap_km_primary", "type": "DOUBLE", "description": "village mean km, girls \u2212 boys, primary" }, { "name": "model_gap_km_primary", "type": "DOUBLE", "description": "layer median km, girls \u2212 boys, primary" }, { "name": "village_gap_share5_primary", "type": "DOUBLE", "description": "village share beyond 5 km, girls \u2212 boys, primary" }, { "name": "model_gap_share5_primary", "type": "DOUBLE", "description": "layer share beyond 5 km, girls \u2212 boys, primary" }, { "name": "village_gap_km_middle", "type": "DOUBLE", "description": "village mean km, girls \u2212 boys, middle" }, { "name": "model_gap_km_middle", "type": "DOUBLE", "description": "layer median km, girls \u2212 boys, middle" }, { "name": "village_gap_share5_middle", "type": "DOUBLE", "description": "village share beyond 5 km, girls \u2212 boys, middle" }, { "name": "model_gap_share5_middle", "type": "DOUBLE", "description": "layer share beyond 5 km, girls \u2212 boys, middle" }, { "name": "village_gap_km_high", "type": "DOUBLE", "description": "village mean km, girls \u2212 boys, high" }, { "name": "model_gap_km_high", "type": "DOUBLE", "description": "layer median km, girls \u2212 boys, high" }, { "name": "village_gap_share5_high", "type": "DOUBLE", "description": "village share beyond 5 km, girls \u2212 boys, high" }, { "name": "model_gap_share5_high", "type": "DOUBLE", "description": "layer share beyond 5 km, girls \u2212 boys, high" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "school_validation_summary", "file": "school_validation_summary.parquet", "bytes": 2130, "rows": 18, "description": "Rank agreement between the layer's district distances and the villages' own reports, by region and level.", "notes": "Spearman rank correlations across matched districts between the layer's population-weighted median distance to the nearest girls' school and the villages' reported distance (rank_corr_level_girls), between the two shares beyond 5 km (rank_corr_share5_girls), and between the two girls-minus-boys gaps (rank_corr_gap); sign_agree_gap is the share of districts where both sources agree on the SIGN of the gap. Read it as a scorecard: the ordering of districts by how far girls are from school is confirmed (0.65\u20130.77 nationally at middle and high level); the ordering by the SIZE of the gap is confirmed at primary and middle and only weakly at high level (Balochistan 0.05); the sign of Punjab's gap is not supported (0.31\u20130.57), because both sources put it within a kilometre of zero. GB has seven districts \u2014 treat its rows as indicative.", "unit": null, "source": "PBS Mouza Census 2020 microdata \u00d7 school_distance_stats", "columns": [ { "name": "region", "type": "VARCHAR", "description": "All or region" }, { "name": "level", "type": "VARCHAR", "description": "primary | middle | high" }, { "name": "n", "type": "BIGINT", "description": "districts compared" }, { "name": "rank_corr_level_girls", "type": "DOUBLE", "description": "Spearman, girls' median km: layer v villages" }, { "name": "rank_corr_share5_girls", "type": "DOUBLE", "description": "Spearman, share beyond 5 km" }, { "name": "rank_corr_gap", "type": "DOUBLE", "description": "Spearman, girls \u2212 boys km gap" }, { "name": "sign_agree_gap", "type": "DOUBLE", "description": "share of districts agreeing on the gap's sign" }, { "name": "rank_corr_gap_share5", "type": "DOUBLE", "description": "Spearman, girls \u2212 boys share beyond 5 km" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "school_validation_tehsil", "file": "school_validation_tehsil.parquet", "bytes": 27210, "rows": 403, "description": "The same count-floor test by tehsil, for the provinces whose registers carry a tehsil (Sindh, Punjab, Balochistan, GB).", "notes": "Locates holes inside districts. 'absent from harvest' here is mostly a NAME mismatch rather than a hole: PBS enumerates sub-tehsils the registers do not carry (88 of Balochistan's 139), and the Karachi sub-divisions do not exist in the SELD roster. Sindh matches 104 of its 110 rural talukas. Read flags with the same caveats as school_validation_district, and with min_m = 5 mouzas rather than 10.", "unit": null, "source": "PBS Mouza Census 2020 microdata \u00d7 schools_pk", "columns": [ { "name": "region", "type": "VARCHAR", "description": "region" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar key" }, { "name": "tehsil_key", "type": "VARCHAR", "description": "normalised tehsil name used to match" }, { "name": "mouza_tehsil", "type": "VARCHAR", "description": "tehsil as PBS names it" }, { "name": "layer_tehsil", "type": "VARCHAR", "description": "tehsil as the register names it" }, { "name": "status", "type": "VARCHAR", "description": "matched | absent from harvest" }, { "name": "rural_mouzas", "type": "DOUBLE", "description": "rural mouzas" }, { "name": "flag", "type": "VARCHAR", "description": "test outcomes" }, { "name": "mouzas_with_B_primary", "type": "DOUBLE", "description": "mouzas reporting a boys' primary institution" }, { "name": "mouzas_with_B_middle", "type": "DOUBLE", "description": "mouzas reporting a boys' middle institution" }, { "name": "mouzas_with_B_high", "type": "DOUBLE", "description": "mouzas reporting a boys' high institution" }, { "name": "mouzas_with_G_primary", "type": "DOUBLE", "description": "mouzas reporting a girls' primary institution" }, { "name": "mouzas_with_G_middle", "type": "DOUBLE", "description": "mouzas reporting a girls' middle institution" }, { "name": "mouzas_with_G_high", "type": "DOUBLE", "description": "mouzas reporting a girls' high institution" }, { "name": "coll_B_high", "type": "BIGINT", "description": "boys' high schools in the layer" }, { "name": "coll_B_middle", "type": "BIGINT", "description": "boys' middle schools in the layer" }, { "name": "coll_B_primary", "type": "BIGINT", "description": "boys' primary schools in the layer" }, { "name": "coll_G_high", "type": "BIGINT", "description": "girls' high schools in the layer" }, { "name": "coll_G_middle", "type": "BIGINT", "description": "girls' middle schools in the layer" }, { "name": "coll_G_primary", "type": "BIGINT", "description": "girls' primary schools in the layer" }, { "name": "coll_midplus_B", "type": "BIGINT", "description": "boys' middle-plus schools in the layer" }, { "name": "ratio_midplus_B", "type": "DOUBLE", "description": "boys' midplus ratio: layer \u00f7 mouza floor" }, { "name": "ratio_high_B", "type": "DOUBLE", "description": "boys' high ratio: layer \u00f7 mouza floor" }, { "name": "ratio_primary_B", "type": "DOUBLE", "description": "boys' primary ratio: layer \u00f7 mouza floor" }, { "name": "coll_midplus_G", "type": "BIGINT", "description": "girls' middle-plus schools in the layer" }, { "name": "ratio_midplus_G", "type": "DOUBLE", "description": "girls' midplus ratio: layer \u00f7 mouza floor" }, { "name": "ratio_high_G", "type": "DOUBLE", "description": "girls' high ratio: layer \u00f7 mouza floor" }, { "name": "ratio_primary_G", "type": "DOUBLE", "description": "girls' primary ratio: layer \u00f7 mouza floor" }, { "name": "girls_to_boys_ratio_midplus", "type": "DOUBLE", "description": "ratio_midplus_G \u00f7 ratio_midplus_B" }, { "name": "release", "type": "VARCHAR", "description": "release tag" } ] }, { "name": "schools_pk", "file": "schools_pk.parquet", "bytes": 2990512, "rows": 125317, "description": "Government schools of Pakistan with positions and provenance, one row per listed school (release 2026-09).", "notes": "READ coord_method AND coord_precision BEFORE USING lat/lng. Only 82,000 of the 121,000 positioned rows are school-level fixes (GPS at source in Balochistan and KP, RSU pins or positions multilaterated from SELD checker distances in Sindh); 20,000 Punjab, GB and AJK rows sit at the named SETTLEMENT, 8,000 Punjab rows at the MARKAZ (school-cluster) centroid and 9,800 Punjab rows at the TEHSIL centroid \u2014 those last two are useless for anything finer than a district. coord_tier is the region's overall grade from the coverage ledger (A to C). in_analysis marks the 118,673 rows that entered Adaad's distance analysis; analysis_note says why the rest did not (no position, closed, sex not stated, not government). gender is the school's name DESIGNATION (GG/GB, Boys/Girls); in Sindh most designated boys' schools are officially Mixed and enrol girls \u2014 gender_official carries SEMIS's Boys/Girls/Mixed field and boys_/girls_enrolled the roster's enrolment, so the girls' network can be redefined by attendance. level is the source's own label and level_std collapses it to primary/middle/high; middle_plus and high_plus are the analysis's classes. Coverage: settled KP only (the seven ex-FATA merged districts have no public locations), two of AJK's ten districts, 78 federal schools in Islamabad; see school_layer_coverage. district_key is the source's district mapped to Data Darbar's 147-district frame (successor districts folded into their parent); district_key_boundary is the polygon the point falls in, which is what per-district counts in the piece use \u2014 they differ for 3,500 rows. Every position in this table is either published by a provincial education department (Balochistan, KP, and Sindh's pins), solved from distances the Sindh department's own public distance checker returns, or geocoded from a settlement name in a public roster. The table adds nothing a department has not put online: no staff names, no contact details. Released under CC BY 4.0 as a compilation; the underlying records remain the departments'.", "unit": null, "source": "Provincial school registers: SED Balochistan open-data portal; Sindh SELD Institution Checker and Distance Checker with RSU district GIS pins; KP Education Monitoring Authority school locator and the JSiMS mirror of KP EMIS; Punjab School Information System; GB EMIS; Mirpur and Kotli exam boards; OpenStreetMap for Islamabad. Compiled for Adaad, September 2026.", "columns": [ { "name": "row_id", "type": "INTEGER", "description": "row number in this release (stable within a release only)" }, { "name": "school_id", "type": "VARCHAR", "description": "the source's own code: EMIS (Balochistan, KP, Punjab), SEMIS (Sindh), GB EMIS school code; blank for AJK and Islamabad" }, { "name": "province", "type": "VARCHAR", "description": "province or territory" }, { "name": "region", "type": "VARCHAR", "description": "analysis region as the piece labels it (KP (settled), AJK (Mirpur+Kotli), Islamabad (ICT))" }, { "name": "district", "type": "VARCHAR", "description": "district as the source writes it" }, { "name": "district_key", "type": "VARCHAR", "description": "Data Darbar district key of the source district (successors folded into parents) \u2014 joins district_indicators, mpi_districts, school_access_district" }, { "name": "district_key_boundary", "type": "VARCHAR", "description": "Data Darbar district whose polygon contains the point; NULL when no position or outside every polygon (coast, border)" }, { "name": "tehsil", "type": "VARCHAR", "description": "tehsil or taluka as the source writes it; blank for KP, AJK, Islamabad" }, { "name": "name", "type": "VARCHAR", "description": "school name as listed" }, { "name": "level", "type": "VARCHAR", "description": "level as the source labels it" }, { "name": "level_std", "type": "VARCHAR", "description": "primary | middle | high | other (Elementary \u2192 middle; Secondary, Higher Secondary, H.Sec. \u2192 high; Mosque \u2192 primary)" }, { "name": "primary_plus", "type": "BOOLEAN", "description": "true for every school (any level serves the primary class)" }, { "name": "middle_plus", "type": "BOOLEAN", "description": "middle level or above" }, { "name": "high_plus", "type": "BOOLEAN", "description": "high or higher-secondary level" }, { "name": "gender", "type": "VARCHAR", "description": "name designation: Boys | Girls | Unknown" }, { "name": "gender_official", "type": "VARCHAR", "description": "Sindh only: SEMIS gender field Boys | Girls | Mixed" }, { "name": "boys_enrolled", "type": "INTEGER", "description": "Sindh only: boys enrolled per the SELD roster" }, { "name": "girls_enrolled", "type": "INTEGER", "description": "Sindh only: girls enrolled per the SELD roster" }, { "name": "enrolment_total", "type": "INTEGER", "description": "total enrolment where the source gives it (Balochistan, Sindh)" }, { "name": "status", "type": "VARCHAR", "description": "source status: Functional | Viable Closed | Closed | Non-Viable (Sindh); Open | Closed | Inaccessible (KP, non-primary only)" }, { "name": "functional", "type": "BOOLEAN", "description": "false where the source marks the school closed or inaccessible; NULL where the source carries no status" }, { "name": "lat", "type": "DOUBLE", "description": "latitude, WGS84, 6 dp" }, { "name": "lng", "type": "DOUBLE", "description": "longitude, WGS84, 6 dp" }, { "name": "has_coords", "type": "BOOLEAN", "description": "lat and lng present" }, { "name": "coord_method", "type": "VARCHAR", "description": "gps_at_source | kpema_detail | jsims_mirror | rsu_pin_confirmed | multilaterated | geocoded_school_point | geocoded_settlement | geocoded_cluster | geocoded_markaz | geocoded_tehsil | osm_feature | NULL" }, { "name": "coord_precision", "type": "VARCHAR", "description": "what the position identifies: school | settlement | cluster | markaz | tehsil | none" }, { "name": "coord_tier", "type": "VARCHAR", "description": "region grade from the coverage ledger: A, A-, B, B-, C" }, { "name": "coord_resid_m", "type": "DOUBLE", "description": "Sindh only: RMS residual, metres, of the multilateration solve" }, { "name": "pin_vs_solved_m", "type": "DOUBLE", "description": "Sindh only: distance, metres, between the RSU pin and the solved position (NULL when no pin)" }, { "name": "geocode_match", "type": "VARCHAR", "description": "the geocoder's or checker's own match class, kept verbatim" }, { "name": "source", "type": "VARCHAR", "description": "register the row comes from" }, { "name": "source_url", "type": "VARCHAR", "description": "portal" }, { "name": "source_vintage", "type": "VARCHAR", "description": "when the register was read" }, { "name": "in_analysis", "type": "BOOLEAN", "description": "entered Adaad's distance analysis (functional, positioned, sex designated, government)" }, { "name": "analysis_sex", "type": "VARCHAR", "description": "network the school belongs to in the analysis: G | B" }, { "name": "analysis_note", "type": "VARCHAR", "description": "why in_analysis is false" }, { "name": "release", "type": "VARCHAR", "description": "release tag of this table" } ] }, { "name": "tehsil_nightlights", "file": "tehsil_nightlights.parquet", "bytes": 16840, "rows": 3864, "description": "Night-time light radiance by tehsil and year (June VIIRS composites).", "notes": "One row per tehsil \u00d7 year. Population-weighted mean radiance. Tehsils flagged nl_lowc in tehsil_satellite sit near the sensor's noise floor \u2014 their year-on-year movements are mostly noise.", "unit": null, "source": "NOAA VIIRS DNB monthly composites", "columns": [ { "name": "tehsil_id", "type": "VARCHAR", "description": "joins to tehsil_satellite.tehsil_id" }, { "name": "year", "type": "BIGINT", "description": "calendar year (June composite)" }, { "name": "radiance", "type": "DOUBLE", "description": "nW/cm\u00b2/sr, population-weighted mean" } ] }, { "name": "tehsil_satellite", "file": "tehsil_satellite.parquet", "bytes": 23023, "rows": 553, "description": "Tehsil-level (ADM3) satellite measures: relative wealth, population, night-lights.", "notes": "RWI is Meta's Relative Wealth Index \u2014 note it USES night-time lights as one of its own inputs, so rwi and the light columns are NOT independent measurements; a correlation between them is partly mechanical. Lights are June VIIRS radiance, population-weighted. The full year-by-year series is in tehsil_nightlights.", "unit": null, "source": "Meta/Data for Good RWI, WorldPop 2020, NOAA VIIRS DNB monthly composites", "columns": [ { "name": "tehsil_id", "type": "VARCHAR", "description": "GADM/ADM3 identifier \u2014 joins to tehsil_nightlights.tehsil_id" }, { "name": "name", "type": "VARCHAR", "description": "tehsil name" }, { "name": "dk", "type": "VARCHAR", "description": "district_key of the parent district (joins to district_indicators)" }, { "name": "prov", "type": "VARCHAR", "description": "province" }, { "name": "area", "type": "DOUBLE", "description": "area, km\u00b2" }, { "name": "rwi", "type": "DOUBLE", "description": "Meta Relative Wealth Index (mean, population-weighted)" }, { "name": "rwi_pct", "type": "DOUBLE", "description": "percentile of rwi within Pakistan" }, { "name": "pop", "type": "BIGINT", "description": "population (WorldPop 2020, UN-adjusted)" }, { "name": "popdens", "type": "DOUBLE", "description": "people per km\u00b2" }, { "name": "nl_growth", "type": "DOUBLE", "description": "% change in radiance, first to last available year" }, { "name": "nl_lowc", "type": "BIGINT", "description": "1 if radiance is near the noise floor (treat growth as unreliable)" }, { "name": "nl_latest", "type": "DOUBLE", "description": "radiance in the most recent June (VIIRS, nW/cm\u00b2/sr)" }, { "name": "nl_year", "type": "BIGINT", "description": "the year nl_latest refers to" } ] }, { "name": "trade_hs8", "file": "trade_hs8.parquet", "bytes": 10206418, "rows": 1134442, "description": "8-digit HS imports and exports, by commodity and partner country, FY2015-16 \u2192 FY2024-25.", "notes": "Values are THOUSAND rupees. fy_* are full fiscal-year (Jul\u2013Jun) cumulative figures; month_* are June alone. country IS NULL marks the commodity total row \u2014 country rows sum to it, so filter one or the other or you will double-count. Years missing here exist only as PDFs upstream (see file_catalog).", "unit": "thousand Rs", "source": "PBS External Trade Statistics (annual fixed-width TXT + D-10 workbooks)", "columns": [ { "name": "direction", "type": "VARCHAR", "description": "'import' or 'export'" }, { "name": "fiscal_year", "type": "VARCHAR", "description": "e.g. '2020-21' (Jul\u2013Jun)" }, { "name": "hs8", "type": "VARCHAR", "description": "8-digit HS code" }, { "name": "commodity", "type": "VARCHAR", "description": "commodity description as published" }, { "name": "country", "type": "VARCHAR", "description": "partner country; NULL = all-countries total for that HS8" }, { "name": "unit", "type": "VARCHAR", "description": "quantity unit" }, { "name": "month_qty", "type": "DOUBLE", "description": "June quantity" }, { "name": "month_value_kpkr", "type": "DOUBLE", "description": "June value, thousand Rs" }, { "name": "fy_qty", "type": "DOUBLE", "description": "fiscal-year cumulative quantity" }, { "name": "fy_value_kpkr", "type": "DOUBLE", "description": "fiscal-year cumulative value, thousand Rs" } ] } ], "examples": [ { "title": "Ten poorest districts", "sql": "SELECT rank, name, prov, mpi, H, A\nFROM mpi_districts\nWHERE low_n = 0 -- drop districts whose sample is too small to rank\nORDER BY rank LIMIT 10;" }, { "title": "Female literacy, 2017 vs 2023", "sql": "SELECT district, province,\n max(value) FILTER (year = '2017') AS lit_2017,\n max(value) FILTER (year = '2023') AS lit_2023,\n round(max(value) FILTER (year = '2023')\n - max(value) FILTER (year = '2017'), 1) AS change\nFROM district_indicators\nWHERE indicator = 'literacy_ratio_female'\nGROUP BY 1, 2\nORDER BY change DESC;" }, { "title": "Urbanisation vs multidimensional poverty", "sql": "SELECT d.district, d.province, d.value AS pct_urban_2023, m.mpi\nFROM district_indicators d\nJOIN mpi_districts m USING (district_key)\nWHERE d.indicator = 'urban_proportion' AND d.year = '2023'\n AND m.low_n = 0\nORDER BY m.mpi DESC;" }, { "title": "What Pakistan exports most, FY2024-25", "sql": "-- country IS NULL rows are the commodity totals; country rows are the\n-- partner split of the same money. Never add both.\nSELECT hs8, any_value(commodity) AS commodity,\n round(sum(fy_value_kpkr) / 1e6, 1) AS rs_bn\nFROM trade_hs8\nWHERE direction = 'export' AND fiscal_year = '2024-25'\n AND country IS NULL\nGROUP BY 1 ORDER BY rs_bn DESC LIMIT 20;" }, { "title": "Top import partners, FY2024-25 (Rs bn)", "sql": "SELECT country, round(sum(fy_value_kpkr) / 1e6, 1) AS rs_bn\nFROM trade_hs8\nWHERE direction = 'import' AND fiscal_year = '2024-25'\n AND country IS NOT NULL\nGROUP BY 1 ORDER BY rs_bn DESC LIMIT 15;" }, { "title": "Real GDP growth by year", "sql": "SELECT year, round(value, 2) AS growth_pct\nFROM national_accounts\nWHERE table_sheet = 'Table 6' AND item LIKE 'D GDP%'\nORDER BY year;" }, { "title": "Federal defence budget over time", "sql": "-- is_own_year_be keeps the document's own-year budget estimate,\n-- the only column that strings into a clean time series.\nSELECT doc_fy, item, value_rs_mn\nFROM budget_lines\nWHERE is_own_year_be AND item ILIKE '%defence%'\nORDER BY doc_fy;" }, { "title": "Rural electrification, worst tehsils (Mouza Census)", "sql": "-- Shares are of MOUZAS, not people. Aggregate to the polygon first:\n-- several PBS tehsils can share one boundary.\nSELECT x.dd_name AS tehsil, m.province,\n sum(m.\"ElectrictiyAvailability_NoneMouzas\") AS no_electricity,\n sum(m.\"ElectrictiyAvailability_AllMouzas\"\n + m.\"ElectrictiyAvailability_MostlyMouzas\"\n + m.\"ElectrictiyAvailability_SomeMouzas\"\n + m.\"ElectrictiyAvailability_NoneMouzas\") AS base,\n round(100.0 * sum(m.\"ElectrictiyAvailability_NoneMouzas\")\n / nullif(sum(m.\"ElectrictiyAvailability_AllMouzas\"\n + m.\"ElectrictiyAvailability_MostlyMouzas\"\n + m.\"ElectrictiyAvailability_SomeMouzas\"\n + m.\"ElectrictiyAvailability_NoneMouzas\"), 0), 1) AS pct_dark\nFROM mouza_tehsil m\nJOIN mouza_crosswalk x USING (tehsil_code)\nWHERE m.TotalMauzaCount > 0\nGROUP BY 1, 2 HAVING base >= 50\nORDER BY pct_dark DESC LIMIT 20;" }, { "title": "Girls' middle-plus schools by district (Figure 1 of the girls' school piece)", "sql": "-- Count by the polygon the point falls in (district_key_boundary), which is\n-- how the piece counts; district_key is the register's own district.\nSELECT district_key_boundary AS district,\n count(*) FILTER (analysis_sex = 'G') AS girls_schools,\n count(*) FILTER (analysis_sex = 'B') AS boys_schools\nFROM schools_pk\nWHERE in_analysis AND middle_plus AND district_key_boundary IS NOT NULL\nGROUP BY 1 ORDER BY girls_schools DESC;" }, { "title": "How precise are the positions, by province?", "sql": "-- Never map Punjab's tehsil-centroid rows as if they were GPS fixes.\nSELECT province, coord_precision, count(*) AS schools,\n round(100.0 * count(*) / sum(count(*)) OVER (PARTITION BY province), 1) AS pct\nFROM schools_pk\nGROUP BY 1, 2 ORDER BY province, schools DESC;" }, { "title": "Sindh: designated boys' schools that enrol girls", "sql": "-- In Sindh the name says GB (boys) but SEMIS calls most of them Mixed and the\n-- roster shows girls enrolled. This is why the piece reports the Sindh gap\n-- under three network definitions.\nSELECT district, count(*) AS boys_designated,\n count(*) FILTER (gender_official = 'Mixed') AS officially_mixed,\n count(*) FILTER (girls_enrolled > 0) AS enrolling_girls,\n sum(girls_enrolled) AS girls_in_them\nFROM schools_pk\nWHERE province = 'Sindh' AND gender = 'Boys' AND functional AND middle_plus\nGROUP BY 1 ORDER BY girls_in_them DESC;" }, { "title": "Where girls are furthest from a middle school, and how many are in school", "sql": "SELECT district, region, girls_middle_median_km, boys_middle_median_km, gap_km,\n girls_in_school_pct_5_16, boys_in_school_pct_5_16, tt_caveat\nFROM school_access_district\nORDER BY girls_middle_median_km DESC LIMIT 20;" }, { "title": "Does the Mouza Census agree? Districts where the layer fails its floor test", "sql": "-- ratio < 1 means fewer schools in the layer than villages reporting one:\n-- schools are missing or misclassified. Sindh's girls-v-boys flag fires by\n-- construction (see the notes); read the girls' ratio itself.\nSELECT region, mouza_district, ratio_midplus_G, ratio_midplus_B, ratio_high_G, flag\nFROM school_validation_district\nWHERE status = 'matched' AND ratio_midplus_G < 0.9\nORDER BY ratio_midplus_G;" }, { "title": "Tehsils where girls are furthest from a middle school", "sql": "-- Distances depend on the whole region's network, not the tehsil's own\n-- schools; Punjab rows are geocoded, so compare them at district scale.\nSELECT tehsil, district_key, region, girls_middle_km, boys_middle_km, gap_middle_km,\n girls_middle_schools, girls_middle_over5km_pct\nFROM school_access_tehsil\nWHERE coord_tier = 'A' -- GPS-quality positions only\nORDER BY girls_middle_km DESC LIMIT 25;" }, { "title": "Sindh multilateration: solved positions that disagree with the RSU pin", "sql": "-- 24% of RSU pins sit more than 300 m from the position solved from SELD's own\n-- distance checker; the table keeps both so the choice can be audited.\nSELECT district, name, level, coord_method, coord_resid_m, pin_vs_solved_m, lat, lng\nFROM schools_pk\nWHERE province = 'Sindh' AND pin_vs_solved_m > 5000\nORDER BY pin_vs_solved_m DESC LIMIT 25;" }, { "title": "Travel time to care by poverty quintile", "sql": "-- Districts grouped into MPI quintiles, weighted by population: the poorest\n-- fifth is nine times further from care than the least poor.\nWITH q AS (\n SELECT h.*, ntile(5) OVER (ORDER BY m.mpi) AS mpi_quintile\n FROM health_access_district h JOIN mpi_districts m USING (district_key)\n WHERE m.low_n = 0)\nSELECT mpi_quintile, count(*) AS districts,\n round(sum(mot_popw_mean * pop_2020) / sum(pop_2020), 1) AS motorised_min,\n round(sum(wal_popw_mean * pop_2020) / sum(pop_2020), 1) AS walking_min,\n round(sum(mot_pct_pop_gt60 * pop_2020) / sum(pop_2020), 1) AS pct_over_60_min_motorised\nFROM q GROUP BY 1 ORDER BY 1;" }, { "title": "Tehsils where most people are over an hour from care even with a vehicle", "sql": "SELECT tehsil, district_key, province, pop_2020, mot_popw_mean, mot_pct_pop_gt60, wal_pct_pop_gt120\nFROM health_access_tehsil\nWHERE mot_pct_pop_gt60 > 50\nORDER BY pop_2020 DESC LIMIT 25;" }, { "title": "Find a State Bank series by name", "sql": "-- sbp_observations is one row per series x date. Start here: find the\n-- series, note its unit and frequency, then join on series_key.\nSELECT series_key, series_name, unit, frequency, available_since, available_upto\nFROM sbp_series_catalog\nWHERE series_name ILIKE '%remittance%'\nORDER BY dataset_code, series_key;" }, { "title": "The rupee against the dollar since 1947", "sql": "SELECT o.obs_date, o.value AS pkr_per_usd\nFROM sbp_observations o\nJOIN sbp_series_catalog c USING (series_key)\nWHERE c.dataset_code = 'TS_GP_ER_FAERPKR_M' -- bank floating average rates, monthly\n AND c.series_name = 'Average Exchange rate of Pak Rupees per U.S. Dollar'\n -- (a sibling series, 'App (+) / Dep (-) ...', holds the monthly % change)\nORDER BY o.obs_date;" }, { "title": "Where remittances come from, FY2024-25", "sql": "-- The country series are hierarchical (U.A.E. contains Dubai/Abu Dhabi/Sharjah,\n-- 'Other GCC' contains Bahrain/Kuwait/Oman/Qatar, 'ten European Countries'\n-- contains Belgium..Sweden). Summing all of them overstates the total by 42%;\n-- these fifteen add up exactly to SBP's published figure.\nSELECT replace(c.series_name, 'Workers'' remittances received from ', '') AS source,\n round(sum(o.value)) AS mn_usd\nFROM sbp_observations o JOIN sbp_series_catalog c USING (series_key)\nWHERE c.dataset_code = 'TS_GP_BOP_WR_M'\n AND o.obs_date BETWEEN DATE '2024-07-01' AND DATE '2025-06-30'\n AND replace(c.series_name, 'Workers'' remittances received from ', '') IN (\n 'Saudi Arabia', 'U.A.E.', 'U.K.', 'U.S.A.',\n 'Other GCC Countries excluding Saudi Arabia & U.A.E.', 'ten European Countries',\n 'Norway', 'Switzerland', 'Australia', 'Canada', 'Japan', 'Malaysia',\n 'South Africa', 'South Korea', 'Other Countries')\nGROUP BY 1 ORDER BY mn_usd DESC;" } ] }