Skip to content

rebase from main and push our changes to avoid metadata issue #81

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
claude-marie wants to merge 1 commit into
base: main
Choose a base branch
from
Open

rebase from main and push our changes to avoid metadata issue #81

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 37 additions & 9 deletions pipelines/snt_dhis2_formatting/code/snt_dhis2_formatting_population.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,15 @@
"cell_type": "code",
"execution_count": null,
"id": "52fae14b-d3bc-4a74-9c36-89e854e70636",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"source(file.path(\"~/workspace/pipelines/snt_dhis2_formatting/utils/snt_dhis2_formatting.r\"))\n",
"setup_var <- get_setup_variables(packages= c(\"arrow\", \"dplyr\", \"tidyr\", \"stringr\", \"stringi\", \"jsonlite\", \"httr\", \"reticulate\", \"glue\"))\n",
"source(\"~/workspace/pipelines/snt_dhis2_formatting/utils/snt_dhis2_formatting.r\")\n",
"setup_var <- snt_setup(SNT_ROOT_PATH = \"~/workspace\", packages = c(\"arrow\", \"dplyr\", \"tidyr\", \"stringr\", \"stringi\", \"jsonlite\", \"httr\", \"reticulate\", \"glue\"))\n",
"\n",
"# Load config\n",
"config_json <- load_snt_config(file.path(setup_var$CONFIG_PATH, \"SNT_config.json\"))\n",
Expand Down Expand Up @@ -49,7 +53,11 @@
"cell_type": "code",
"execution_count": null,
"id": "6febcacc-afff-4cbb-ac0d-bc2bb00edff4",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"dhis2_pyramid_data <- load_dataset_file(extracts_dataset_id, paste0(COUNTRY_CODE, \"_dhis2_raw_pyramid.parquet\"), verbose=FALSE)\n",
Expand Down Expand Up @@ -77,7 +85,11 @@
"cell_type": "code",
"execution_count": null,
"id": "6b1cda01-c507-4fb4-85d2-1a568df219dc",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"dhis2_data <- load_dataset_file(extracts_dataset_id, paste0(COUNTRY_CODE, \"_dhis2_raw_population.parquet\"), verbose=FALSE)\n",
Expand All @@ -100,7 +112,11 @@
"cell_type": "code",
"execution_count": null,
"id": "6e3f488b-95f1-4aff-b024-cf4e771fed63",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"population_table <- build_population_indicators(dhis2_data, dhis2_pyramid_data, config_json)\n",
Expand All @@ -123,7 +139,11 @@
"cell_type": "code",
"execution_count": null,
"id": "34713812-ca2f-452b-8a15-6d471409f5ff",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"admin_cols <- get_admin_config(config_json)\n",
Expand All @@ -146,7 +166,11 @@
"cell_type": "code",
"execution_count": null,
"id": "a32f4a3b-e9f1-4941-b2a2-80b4fa4eb2de",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Create pop template (util for pop transformation pipeline)\n",
Expand Down Expand Up @@ -191,7 +215,11 @@
"cell_type": "code",
"execution_count": null,
"id": "59891b6e-490e-4a22-8909-416520d168da",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# save template\n",
Expand Down
195 changes: 105 additions & 90 deletions pipelines/snt_dhis2_formatting/code/snt_dhis2_formatting_pyramid.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,15 @@
"cell_type": "code",
"execution_count": null,
"id": "fca7918b-f8bf-4e39-9601-febf5ca7877a",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"source(\"~/workspace/pipelines/snt_dhis2_formatting/utils/snt_dhis2_formatting.r\")\n",
"setup_var <- get_setup_variables(packages= c(\"lubridate\", \"zoo\", \"arrow\", \"dplyr\", \"stringi\", \"stringr\", \"jsonlite\", \"httr\", \"glue\"))\n",
"setup_var <- snt_setup(SNT_ROOT_PATH = \"~/workspace\", packages = c(\"lubridate\", \"zoo\", \"arrow\", \"dplyr\", \"stringi\", \"stringr\", \"jsonlite\", \"httr\", \"glue\"))\n",
"\n",
"# Load config\n",
"config_json <- load_snt_config(file.path(setup_var$CONFIG_PATH, \"SNT_config.json\"))\n",
Expand Down Expand Up @@ -67,7 +71,11 @@
"cell_type": "code",
"execution_count": null,
"id": "8faec80e-2b3e-4162-8767-d6c5c28eadcf",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"log_msg(glue(\"Start DHIS2 organisation units(pyramid) formatting.\")) \n",
Expand All @@ -89,7 +97,11 @@
"cell_type": "code",
"execution_count": null,
"id": "076dacc5-f449-4ab1-9168-9dbc766d295f",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Extract lon/lat from geometry\n",
Expand All @@ -102,95 +114,97 @@
"id": "c25113ed-090a-418c-9a5c-2b30e0f2f773",
"metadata": {},
"source": [
"### Try coordinates validation steps"
"### Coordinate validation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "43d9f9dc-97fc-4083-bc17-e78d0037e02d",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Step 1 - Try Load country border from folder (if exists)\n",
"shapes_sf <- read_geojson_safe(file.path(\"~/workspace/data/dhis2/extracts_formatted/\" , paste0(COUNTRY_CODE, \"_shapes.geojson\")))"
"shapes_sf <- read_geojson_safe(file.path(\"~/workspace/data/dhis2/extracts_formatted/\", paste0(COUNTRY_CODE, \"_shapes.geojson\")))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f8d11c71-0921-4a1e-b005-737b18392383",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Step 2 - Keep original coordinates already inside the country (If shapes are available)\n",
"log_msg(\"Running coordinate boundary validation\")\n",
"\n",
"if (!is.null(shapes_sf)) {\n",
" log_msg(\"Running coordinate boundary validation\")\n",
" \n",
" shapes_sf_boundary <- prepare_country_boundary(shapes_sf)\n",
" lon0 <- pyramid_data_coords$LONGITUDE\n",
" lat0 <- pyramid_data_coords$LATITUDE\n",
" within_original <- points_within_country_batch(lon0, lat0, shapes_sf_boundary)\n",
" has_coords <- !is.na(lon0) & !is.na(lat0)\n",
" \n",
" coord_fix_df <- tibble(\n",
" LONGITUDE_ORIGINAL = lon0,\n",
" LATITUDE_ORIGINAL = lat0,\n",
" LONGITUDE_FIXED = NA_real_,\n",
" LATITUDE_FIXED = NA_real_,\n",
" COORD_FIX_METHOD = NA_character_,\n",
" COORD_IS_VALID = FALSE\n",
" )\n",
" \n",
" ok_original <- has_coords & within_original \n",
" \n",
" if (any(ok_original)) {\n",
" coord_fix_df$LONGITUDE_FIXED[ok_original] <- lon0[ok_original]\n",
" coord_fix_df$LATITUDE_FIXED[ok_original] <- lat0[ok_original]\n",
" coord_fix_df$COORD_FIX_METHOD[ok_original] <- \"ORIGINAL\"\n",
" coord_fix_df$COORD_IS_VALID[ok_original] <- TRUE\n",
" }\n",
"} else {\n",
" log_msg(\"Skipped coordinate boundary validation: No reference shapes available.\")\n",
"shapes_sf_boundary <- prepare_country_boundary(shapes_sf)\n",
"lon0 <- pyramid_data_coords$LONGITUDE\n",
"lat0 <- pyramid_data_coords$LATITUDE\n",
"within_original <- points_within_country_batch(lon0, lat0, shapes_sf_boundary)\n",
"has_coords <- !is.na(lon0) & !is.na(lat0)\n",
"\n",
"coord_fix_df <- tibble(\n",
" LONGITUDE_ORIGINAL = lon0,\n",
" LATITUDE_ORIGINAL = lat0,\n",
" LONGITUDE_FIXED = NA_real_,\n",
" LATITUDE_FIXED = NA_real_,\n",
" COORD_FIX_METHOD = NA_character_,\n",
" COORD_IS_VALID = FALSE\n",
")\n",
"\n",
"ok_original <- has_coords & within_original\n",
"\n",
"if (any(ok_original)) {\n",
" coord_fix_df$LONGITUDE_FIXED[ok_original] <- lon0[ok_original]\n",
" coord_fix_df$LATITUDE_FIXED[ok_original] <- lat0[ok_original]\n",
" coord_fix_df$COORD_FIX_METHOD[ok_original] <- \"ORIGINAL\"\n",
" coord_fix_df$COORD_IS_VALID[ok_original] <- TRUE\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1cea34fe-cc7c-4116-b018-5b8c895bb980",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Step 3 - For remaining points, try correction sequence\n",
"if (!is.null(shapes_sf)) {\n",
" \n",
" miss <- !has_coords\n",
" if (any(miss)) {\n",
" coord_fix_df$COORD_FIX_METHOD[miss] <- \"MISSING_COORDINATES\"\n",
" }\n",
"miss <- !has_coords\n",
"if (any(miss)) {\n",
" coord_fix_df$COORD_FIX_METHOD[miss] <- \"MISSING_COORDINATES\"\n",
"}\n",
"\n",
"need_fix <- !within_original & has_coords\n",
"log_msg(glue(\"Found {sum(need_fix)} / {length(need_fix)} coordinates that require fixing.\"))\n",
"\n",
"fix_results <- list()\n",
"if (any(need_fix)) {\n",
" idx_fix <- which(need_fix)\n",
" fix_results <- lapply(idx_fix, function(i) {\n",
" fix_coordinate_pair_in_country(lon0[i], lat0[i], shapes_sf_boundary, max_shift = 2)\n",
" })\n",
"\n",
" need_fix <- !within_original & has_coords \n",
" log_msg(glue(\"Found {sum(need_fix)} / {length(need_fix)} coordinates that require fixing.\"))\n",
" \n",
" if (any(need_fix)) {\n",
" idx_fix <- which(need_fix)\n",
" fix_results <- lapply(idx_fix, function(i) {\n",
" fix_coordinate_pair_in_country(lon0[i], lat0[i], shapes_sf_boundary, max_shift = 2)\n",
" })\n",
" \n",
" fixed_coords <- sum(sapply(fix_results, function(x) x$VALID == TRUE), na.rm = TRUE) \n",
" fixed_coords <- sum(sapply(fix_results, function(x) x$VALID == TRUE), na.rm = TRUE)\n",
" log_msg(glue(\"Points corrected: {fixed_coords} out of {sum(need_fix)}\"))\n",
" \n",
"\n",
" for (k in seq_along(idx_fix)) {\n",
" i <- idx_fix[k]\n",
" fr <- fix_results[[k]]\n",
" coord_fix_df$LONGITUDE_FIXED[i] <- fr$LONGITUDE\n",
" coord_fix_df$LATITUDE_FIXED[i] <- fr$LATITUDE\n",
" coord_fix_df$COORD_FIX_METHOD[i] <- fr$METHOD\n",
" coord_fix_df$COORD_IS_VALID[i] <- fr$VALID\n",
" }\n",
" }\n",
"}"
]
Expand All @@ -199,48 +213,49 @@
"cell_type": "code",
"execution_count": null,
"id": "eff4aff7-fe8d-4d47-b87f-b3fc8512d10e",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Display fixed points (if any)\n",
"if (exists(\"fixed_coords\") && length(fixed_coords) > 0) {\n",
" my_map <- plot_fixed_coordinates(fix_results, shapes_sf_boundary) \n",
"} "
"if (length(fix_results) > 0) {\n",
" my_map <- plot_fixed_coordinates(fix_results, shapes_sf_boundary)\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "49ef06a2-072d-4296-a220-6d5ab1948db0",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "r"
}
},
"outputs": [],
"source": [
"# Step 6 - Apply final coordinates and flag invalids\n",
"if (!is.null(shapes_sf)) {\n",
" pyramid_data_coords$LONGITUDE <- coord_fix_df$LONGITUDE_FIXED\n",
" pyramid_data_coords$LATITUDE <- coord_fix_df$LATITUDE_FIXED\n",
" \n",
" invalid_coords <- pyramid_data_coords %>%\n",
" bind_cols(coord_fix_df %>% select(LONGITUDE_ORIGINAL, LATITUDE_ORIGINAL, COORD_FIX_METHOD, COORD_IS_VALID)) %>%\n",
" filter(!COORD_IS_VALID & !is.na(LONGITUDE_ORIGINAL) & !is.na(LATITUDE_ORIGINAL)) %>%\n",
" mutate(INVALID_COORD_REASON = \"NO_VALID_TRANSFORMATION_IN_COUNTRY\") %>% \n",
" select(-LONGITUDE, -LATITUDE)\n",
" \n",
" # Step 7 - Summary logs\n",
" n_total_coords <- sum(!is.na(coord_fix_df$LONGITUDE_ORIGINAL) & !is.na(coord_fix_df$LATITUDE_ORIGINAL))\n",
" n_kept_original <- sum(coord_fix_df$COORD_FIX_METHOD == \"ORIGINAL\", na.rm = TRUE)\n",
" n_corrected <- sum(coord_fix_df$COORD_IS_VALID & coord_fix_df$COORD_FIX_METHOD != \"ORIGINAL\", na.rm = TRUE)\n",
" n_invalid <- nrow(invalid_coords)\n",
" \n",
" log_msg(glue(\"Coordinate quality check over {n_total_coords} FOSAs: original valid={n_kept_original}, corrected={n_corrected}, invalid={n_invalid}.\"))\n",
" if (n_corrected > 0) {\n",
" log_msg(glue(\"Applied coordinate correction algorithm to {n_corrected} FOSAs (swap/sign/decimal left-to-right, k<=2).\"), \"warning\")\n",
" }\n",
" if (n_invalid > 0) {\n",
" log_msg(glue(\"{n_invalid} FOSAs remain invalid after correction attempts. LONGITUDE/LATITUDE set to NA.\"), \"warning\")\n",
" }\n",
"} else {\n",
" invalid_coords <- c()\n",
"pyramid_data_coords$LONGITUDE <- coord_fix_df$LONGITUDE_FIXED\n",
"pyramid_data_coords$LATITUDE <- coord_fix_df$LATITUDE_FIXED\n",
"\n",
"invalid_coords <- pyramid_data_coords %>%\n",
" bind_cols(coord_fix_df %>% select(LONGITUDE_ORIGINAL, LATITUDE_ORIGINAL, COORD_FIX_METHOD, COORD_IS_VALID)) %>%\n",
" filter(!COORD_IS_VALID & !is.na(LONGITUDE_ORIGINAL) & !is.na(LATITUDE_ORIGINAL)) %>%\n",
" mutate(INVALID_COORD_REASON = \"NO_VALID_TRANSFORMATION_IN_COUNTRY\") %>%\n",
" select(-LONGITUDE, -LATITUDE)\n",
"\n",
"n_total_coords <- sum(!is.na(coord_fix_df$LONGITUDE_ORIGINAL) & !is.na(coord_fix_df$LATITUDE_ORIGINAL))\n",
"n_kept_original <- sum(coord_fix_df$COORD_FIX_METHOD == \"ORIGINAL\", na.rm = TRUE)\n",
"n_corrected <- sum(coord_fix_df$COORD_IS_VALID & coord_fix_df$COORD_FIX_METHOD != \"ORIGINAL\", na.rm = TRUE)\n",
"n_invalid <- nrow(invalid_coords)\n",
"\n",
"log_msg(glue(\"Coordinate quality check over {n_total_coords} FOSAs: original valid={n_kept_original}, corrected={n_corrected}, invalid={n_invalid}.\"))\n",
"if (n_corrected > 0) {\n",
" log_msg(glue(\"Applied coordinate correction algorithm to {n_corrected} FOSAs (swap/sign/decimal left-to-right, k<=2).\"), \"warning\")\n",
"}\n",
"if (n_invalid > 0) {\n",
" log_msg(glue(\"{n_invalid} FOSAs remain invalid after correction attempts. LONGITUDE/LATITUDE set to NA.\"), \"warning\")\n",
"}\n",
"\n",
"head(pyramid_data_coords, 3)"
Expand Down
Loading