def _download_open_data(
logger: ErrorLogger,
url_tpl: str,
output_folder: Path,
ibge_code: str,
max_volumes: int = 12,
**download_opts,
) -> Dict[str, str]:
logger.log_debug(f"Downloading Brazil data for {ibge_code}...")
# Since we are guessing the URL, we forgive errors in the download
output = {}
download_opts = dict(download_opts, ignore_failure=True)
map_func = partial(download_snapshot, output_folder=output_folder, **download_opts)
map_iter = [url_tpl.format(f"{ibge_code}-{idx + 1}") for idx in range(max_volumes)]
for idx, file_path in enumerate(thread_map(map_func, map_iter)):
if file_path is not None:
output[f"{ibge_code}-{idx + 1}"] = file_path
# Filter out empty files, which can happen if download fails in an unexpected way
output = {name: path for name, path in output.items() if Path(path).stat().st_size > 0}
# If the output is not split into volumes, fall back to single file URL
if output:
return output
else:
url = url_tpl.format(ibge_code)
return {ibge_code: download_snapshot(url, output_folder, **download_opts)}
def wikidata_property(prop: str,
entities: List[str],
query: str = _default_query,
error_logger: ErrorLogger = ErrorLogger(),
**tqdm_kwargs) -> Iterable[Tuple[str, Any]]:
"""
Query a single property from Wikidata, and return all entities which are part of the provided
list which contain that property.
Arguments:
prop: Wikidata property, for example P1082 for population.
entities: List of Wikidata identifiers to query the desired property.
query: [Optional] SPARQL query used to retrieve `prop`.
error_logger: [Optional] ErrorLogger instance to use for logging.
Returns:
Iterable[Tuple[str, Any]]: Iterable of <Wikidata ID, property value>
"""
# Limit parallelization to avoid hitting rate limits
tqdm_kwargs["max_workers"] = 6
map_func = partial(_query_property,
prop,
query=query,
error_logger=error_logger)
for entity, prop in zip(entities,
thread_map(map_func, entities, **tqdm_kwargs)):
yield entity, prop
def convert_tables_to_json(
csv_folder: Path, output_folder: Path,
logger: ErrorLogger = ErrorLogger()) -> Iterable[Path]:
def try_json_covert(schema: Dict[str, str], csv_file: Path) -> Path:
# JSON output defaults to same as the CSV file but with extension swapped
json_output = output_folder / str(
csv_file.relative_to(csv_folder)).replace(".csv", ".json")
json_output.parent.mkdir(parents=True, exist_ok=True)
# Converting to JSON is not critical and it may fail in some corner cases
# As long as the "important" JSON files are created, this should be OK
try:
logger.log_debug(f"Converting {csv_file} to JSON")
convert_csv_to_json_records(schema, csv_file, json_output)
return json_output
except Exception as exc:
error_message = f"Unable to convert CSV file {csv_file} to JSON"
logger.log_error(error_message, traceback=traceback.format_exc())
return None
# Convert all CSV files to JSON using values format
map_iter = list(csv_folder.glob("**/*.csv"))
map_func = partial(try_json_covert, get_schema())
for json_output in thread_map(map_func,
map_iter,
max_workers=2,
desc="JSON conversion"):
if json_output is not None:
yield json_output
def _query_property(prop: str,
entity: str,
query: str = _default_query,
error_logger: ErrorLogger = None) -> Any:
# Time to wait before retry in case of failure
wait_time = 8
# Build the query from template
query = query.format(prop=prop, entity=entity)
# Keep trying request until succeeds, or _max_retries is reached
for i in range(_max_retries):
response = None
try:
params = {"query": query, "format": "json"}
response = requests.get(_wikidata_url,
headers=_request_header,
params=params)
data = response.json()
# Return the first binding available (there should be only one)
for item in data["results"]["bindings"]:
return item["prop"]["value"]
except Exception as exc:
# If limit is reached, then log error
if i + 1 < _max_retries:
if error_logger is not None:
error_logger.errlog(
response.text if response is not None else exc)
else:
traceback.print_exc()
# Otherwise use exponential backoff in case of error
else:
sleep(wait_time)
wait_time *= 2
return None
def wikidata_property(
prop: str,
entities: List[str],
query_template: str = _WD_QUERY,
logger: ErrorLogger = ErrorLogger(),
offset: int = 0,
**tqdm_kwargs,
) -> Any:
"""
Query a single property from Wikidata, and return all entities which are part of the provided
list which contain that property.
Arguments:
prop: Wikidata property, for example P1082 for population.
entities: List of Wikidata identifiers to query the desired property.
query: [Optional] SPARQL query used to retrieve `prop`.
logger: [Optional] ErrorLogger instance to use for logging.
offset: [Optional] Number of items to skip in the result set.
Returns:
Iterable[Tuple[str, Any]]: Iterable of <Wikidata ID, property value>
"""
# Time to wait before retry in case of failure
wait_time = _INIT_WAIT_TIME
# Build the query from template
tpl = query_template + " LIMIT {limit} OFFSET {offset}"
query = tpl.format(prop=prop, limit=_LIMIT, offset=offset)
# Keep trying request until succeeds, or _max_retries is reached
for i in range(_MAX_RETRIES):
response = None
try:
start_time = time.monotonic()
params = {"query": query, "format": "json"}
req_opts = dict(headers=_REQUEST_HEADER,
params=params,
timeout=_WD_TIMEOUT)
response = requests.get(_WD_URL, **req_opts)
elapsed_time = time.monotonic() - start_time
log_opts = dict(status=response.status_code,
url=_WD_URL,
time=elapsed_time,
**params)
logger.log_info(f"Wikidata SPARQL server response", **log_opts)
data = response.json()
# Return the first binding available (there should be only one)
for item in pbar(data["results"]["bindings"], **tqdm_kwargs):
pid = item["pid"]["value"].split("/")[-1]
if pid in entities:
yield pid, item["prop"]["value"]
# Unless we got `_LIMIT` results, keep adding offset until we run our of results
if len(data["results"]["bindings"]) == _LIMIT:
yield from wikidata_property(
prop,
entities,
query_template=query_template,
logger=logger,
offset=offset + _LIMIT,
**tqdm_kwargs,
)
# If no exceptions were thrown, we have reached the end
logger.log_info(f"Wikidata SPARQL results end reached")
return
except Exception as exc:
# If we have reached the error limit, log and re-raise the error
if i + 1 >= _MAX_RETRIES:
msg = response.text if response is not None else "Unknown error"
logger.log_error(msg,
exc=exc,
traceback=traceback.format_exc())
raise exc
# Use exponential backoff in case of error
logger.log_info(
f"({i + 1}) Request error. Retry in {wait_time} seconds...",
exc=exc)
time.sleep(wait_time)
wait_time *= 2
GCP_SELF_DESTRUCT_SCRIPT,
GCS_BUCKET_PROD,
GCS_BUCKET_TEST,
SRC,
V3_TABLE_LIST,
)
from lib.error_logger import ErrorLogger
from lib.gcloud import delete_instance, get_internal_ip, start_instance_from_image
from lib.io import export_csv, gzip_file, temporary_directory
from lib.memory_efficient import table_read_column
from lib.net import download
from lib.pipeline import DataPipeline
from lib.pipeline_tools import get_table_names
app = Flask(__name__)
logger = ErrorLogger("appengine")
BLOB_OP_MAX_RETRIES = 10
ENV_TOKEN = "GCP_TOKEN"
ENV_PROJECT = "GOOGLE_CLOUD_PROJECT"
ENV_SERVICE_ACCOUNT = "GCS_SERVICE_ACCOUNT"
COMPRESS_EXTENSIONS = ("json", )
# Used when parsing string parameters into boolean type
BOOL_STRING_MAP = {
"true": True,
"false": False,
"1": True,
"0": False,
"": False,
"null": False
}
table_breakout,
table_concat,
table_cross_product,
table_drop_nan_columns,
table_grouped_tail,
table_join,
table_merge,
table_read_column,
table_rename,
table_sort,
)
from lib.pipeline_tools import get_schema
from lib.time import date_range
# Used for debugging purposes
_logger = ErrorLogger("publish")
def _subset_grouped_key(main_table_path: Path,
output_folder: Path,
desc: str = None) -> Iterable[Path]:
""" Outputs a subsets of the table with only records with a particular key """
# Read the header of the main file to get the columns
with open(main_table_path, "r") as fd:
header = next(fd)
# Do a first sweep to get the number of keys so we can accurately report progress
key_set = set()
for line in read_lines(main_table_path, skip_empty=True):
key, data = line.split(",", 1)
def make_main_table(
tables_folder: Path,
output_path: Path,
logger: ErrorLogger = ErrorLogger()) -> None:
"""
Build a flat view of all tables combined, joined by <key> or <key, date>.
Arguments:
tables_folder: Input folder where all CSV files exist.
Returns:
DataFrame: Flat table with all data combined.
"""
# Use a temporary directory for intermediate files
with TemporaryDirectory() as workdir:
workdir = Path(workdir)
# Merge all output files into a single table
keys_table_path = workdir / "keys.csv"
keys_table = read_file(tables_folder / "index.csv", usecols=["key"])
export_csv(keys_table, keys_table_path)
logger.log_info("Created keys table")
# Add a date to each region from index to allow iterative left joins
max_date = (datetime.datetime.now() +
datetime.timedelta(days=1)).date().isoformat()
date_list = date_range("2020-01-01", max_date)
date_table_path = workdir / "dates.csv"
export_csv(DataFrame(date_list, columns=["date"]), date_table_path)
logger.log_info("Created dates table")
# Create a temporary working table file which can be used during the steps
temp_file_path = workdir / "main.tmp.csv"
table_cross_product(keys_table_path, date_table_path, temp_file_path)
logger.log_info("Created cross product table")
# Add all the index columns to seed the main table
main_table_path = workdir / "main.csv"
table_join(temp_file_path,
tables_folder / "index.csv", ["key"],
main_table_path,
how="outer")
logger.log_info("Joined with table index")
non_dated_columns = set(get_table_columns(main_table_path))
for table_file_path in pbar([*tables_folder.glob("*.csv")],
desc="Make main table"):
table_name = table_file_path.stem
if table_name not in EXCLUDE_FROM_MAIN_TABLE:
table_columns = get_table_columns(table_file_path)
if "date" in table_columns:
join_on = ["key", "date"]
else:
join_on = ["key"]
# Keep track of columns which are not indexed by date
non_dated_columns = non_dated_columns | set(table_columns)
# Iteratively perform left outer joins on all tables
table_join(main_table_path,
table_file_path,
join_on,
temp_file_path,
how="outer")
shutil.move(temp_file_path, main_table_path)
logger.log_info(f"Joined with table {table_name}")
# Drop rows with null date or without a single dated record
# TODO: figure out a memory-efficient way to do this
# Ensure that the table is appropriately sorted ans write to output location
table_sort(main_table_path, output_path)
logger.log_info("Sorted main table")
