Created
September 29, 2020 14:33
-
-
Save napsternxg/22b623a31487c0fc9a26babeb38cdf11 to your computer and use it in GitHub Desktop.
Get humans with sex, gender, ethnic_group, and image in Wikidata https://w.wiki/eLe
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pathlib import Path | |
import shutil | |
import requests | |
REQUIRED_COLS = ['human', 'image', 'sex_or_gender', 'ethnic_group', 'date_of_birth', 'occupation', 'loc_aid',] | |
def parse_row(row): | |
data = {} | |
for c in REQUIRED_COLS: | |
value = row[c]["value"] | |
if row[c]["type"] == "uri": | |
value = value.rsplit("/", 1)[-1] | |
data[c] = value | |
url = row["url"] | |
extension = Path(url.rsplit('/', 1)[-1]).suffix | |
local_path = f"{data['human']}{extension}" | |
data["url"] = url | |
data["local_path"] = local_path | |
return data | |
OUTPUT_DIR=Path("./data/wikidata_gender_ethnicity_images/") | |
def download_image(data): | |
url = data['url'] | |
local_path = OUTPUT_DIR / data["local_path"] | |
if local_path.exists(): | |
print(f"{url} already saved at {local_path}") | |
return | |
# Code based on https://stackoverflow.com/a/13137873 | |
r = requests.get(url, stream=True) | |
if r.status_code == 200: | |
with open(local_path, 'wb') as fp: | |
r.raw.decode_content = True | |
shutil.copyfileobj(r.raw, fp) | |
print(f"Saved {url} to {local_path}") | |
if __name__ == "__main__": | |
for row in wikidata_data["results"]["bindings"]: | |
data = parse_row(row) | |
download_image(data) | |
import pandas as pd | |
df = pd.DataFrame([ | |
parse_row(row) | |
for row in wikidata_data["results"]["bindings"] | |
]) | |
df["file_exists"] = df["local_path"].apply(lambda x: (OUTPUT_DIR / x).exists()) | |
print(df["ethnic_group"].value_counts()) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#defaultView:ImageGrid | |
SELECT ?human | |
(SAMPLE(?humanLabel) AS ?humanLabel) | |
(SAMPLE(?image) AS ?image) | |
(SAMPLE(?sex_or_gender) AS ?sex_or_gender) | |
(SAMPLE(?sex_or_genderLabel) AS ?sex_or_genderLabel) | |
(SAMPLE(?ethnic_group) AS ?ethnic_group) | |
(SAMPLE(?ethnic_groupLabel) AS ?ethnic_groupLabel) | |
(SAMPLE(?date_of_birth) AS ?date_of_birth) | |
(SAMPLE(?occupation) AS ?occupation) | |
(SAMPLE(?occupationLabel) AS ?occupationLabel) | |
(SAMPLE(?loc_aid) AS ?loc_aid) | |
WHERE { | |
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". } | |
?human wdt:P31 wd:Q5; | |
wdt:P18 ?image; | |
wdt:P21 ?sex_or_gender; | |
wdt:P172 ?ethnic_group; | |
wdt:P569 ?date_of_birth; | |
wdt:P244 ?loc_aid | |
OPTIONAL { ?human wdt:P106 ?occupation. } | |
FILTER(?date_of_birth > "1950-01-01"^^xsd:dateTime) | |
FILTER(?ethnic_group IN(wd:Q49078, wd:Q49085, wd:Q58669)) | |
FILTER(?sex_or_gender IN(wd:Q6581097, wd:Q6581072)) | |
FILTER(?occupation NOT IN(wd:Q488111)) | |
} | |
GROUP BY ?human | |
LIMIT 5000 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment