Skip to content

Instantly share code, notes, and snippets.

SELECT count(*) FROM t1 INNER JOIN t2 ON t1.a = t2.b;
for t1_row in t1.rows:
for t2_row in t2.rows:
if (t1_row.a = t2_row.a):
output_match()
let hash_table = build_hash_table(t2.rows.a); // build hash table over column a in t2
for t1_row in t1.rows:
for t2_row in hash_table(t1_row.a): // lookup the corresponding entry for t1’s row
if (t1_row.a = t2_row.a):
output_match()
let hash_table = build_hash_table(t2.rows.a); // build hash table over column a in t2
for t1_row in t1.rows:
output_match(hash_table(t1_row.a)):
SELECT
tweets.location,
tweets.follower_count as size,
zipcodes.number as color
FROM
tweets
LEFT JOIN zipcodes on ST_Contains(zipcodes.polygon, tweets.location);
let hash_table = build_hash_table(zipcodes.rows.polygon); // build hash table over polygon column
for t1_row in t1.rows:
for t2_row in hash_table(t1_row.point):
if ST_Contains(t2_row.polygon, t1_row.point):
output_match()
with mlflow.start_run(run_name="Random_Forest_Undercount"):
from sklearn.ensemble import RandomForestRegressor
# model parameters
params = {'n_estimators': 1000, 'random_state': 41}
# log model params
for key in params:
mlflow.log_param(key, params[key])
# get predictions
y_pred = RFtree.predict(test_features)
# compute accuracy metric, then log
R2_score = r2_score(test_labels, y_pred)
print("R2_Score: ", R2_score)
mlflow.log_metric("r2", R2_score)
# plot and save plot graphic linked to model run
xgb.plot_importance(gbtree)
select
sum(number_injured) as number_injured,
avg(party_count) as avg_party_count,
b.osm_id
from la_collisions a,
la_street_buffer b
where
st_contains(b.omnisci_geo,st_setsrid(st_point(a.point_x, a.point_y), 4326))
group by
b.osm_id
select
max(probability) as probability,
b.FID
from
usgs_8ft_flame_length_probability a,
california_building_footprints b
where
ST_Contains(b.defensible_space, a.omnisci_geo)
group by
b.FID
pip install pyomnisci