zero-one.geni.dataset — zero.one/geni 0.0.9

->java-list clj

(->java-list coll)

->row clj

(->row coll)

agg clj

(agg dataframe & args)

agg-all clj

(agg-all dataframe agg-fn)

approx-quantile clj

(approx-quantile dataframe col-or-cols probs rel-error)

cache clj

(cache dataframe)

col-regex clj

(col-regex dataframe col-name)

collect clj

(collect dataframe)

collect-col clj

(collect-col dataframe col-name)

collect-vals clj

(collect-vals dataframe)

column-names clj

(column-names dataframe)

columns clj

(columns dataframe)

conj-record clj

(conj-record map-of-values record)

cross-join clj

(cross-join left right)

cube clj

(cube dataframe & exprs)

describe clj

(describe dataframe & col-names)

distinct clj

(distinct dataframe)

drop clj

(drop dataframe & col-names)

drop-duplicates clj

(drop-duplicates dataframe & col-names)

drop-na clj

(drop-na dataframe)

(drop-na dataframe min-non-nulls-or-cols)

(drop-na dataframe min-non-nulls cols)

dtypes clj

(dtypes dataframe)

empty? clj

except clj

(except dataframe other)

except-all clj

(except-all dataframe other)

explain clj

(explain dataframe)

(explain dataframe extended)

fill-na clj

(fill-na dataframe value)

(fill-na dataframe value cols)

filter clj

(filter dataframe expr)

first-non-nil clj

(first-non-nil values)

first-vals clj

(first-vals dataframe)

group-by clj

(group-by dataframe & exprs)

infer-schema clj

(infer-schema col-names values)

infer-spark-type clj

(infer-spark-type value)

infer-struct-field clj

(infer-struct-field col-name value)

intersect clj

(intersect dataframe other)

intersect-all clj

(intersect-all dataframe other)

is-empty clj

(is-empty dataframe)

is-local clj

(is-local dataframe)

java-type->spark-type clj

join clj

(join left right join-cols)

(join left right join-cols join-type)

join-with clj

(join-with left right condition)

(join-with left right condition join-type)

limit clj

(limit dataframe n-rows)

local? clj

map->dataset clj

(map->dataset spark map-of-values)

order-by clj

(order-by dataframe & exprs)

partitions clj

(partitions dataframe)

persist clj

(persist dataframe)

pivot clj

(pivot grouped expr)

(pivot grouped expr values)

print-schema clj

(print-schema dataframe)

random-split clj

(random-split dataframe weights)

(random-split dataframe weights seed)

records->dataset clj

(records->dataset spark records)

remove clj

(remove dataframe expr)

rename-columns clj

(rename-columns dataframe rename-map)

repartition clj

(repartition dataframe & args)

repartition-by-range clj

(repartition-by-range dataframe & args)

replace clj

(replace dataframe cols replacement)

rollup clj

(rollup dataframe & exprs)

sample clj

(sample dataframe fraction)

(sample dataframe fraction with-replacement)

select clj

(select dataframe & exprs)

select-expr clj

(select-expr dataframe & exprs)

show clj

(show dataframe)

(show dataframe options)

show-vertical clj

(show-vertical dataframe)

(show-vertical dataframe options)

sort clj

sort-within-partitions clj

(sort-within-partitions dataframe & exprs)

spark-session clj

(spark-session dataframe)

sql-context clj

(sql-context dataframe)

summary clj

(summary dataframe & stat-names)

table->dataset clj

(table->dataset spark table col-names)

take clj

(take dataframe n-rows)

take-vals clj

(take-vals dataframe n-rows)

transpose clj

(transpose xs)

union clj

(union & dfs)

union-by-name clj

(union-by-name & dfs)

where clj

with-column clj

(with-column dataframe col-name expr)

with-column-renamed clj

(with-column-renamed dataframe old-name new-name)