| abs(col) | ⬜️ |
| acos(col) | ⬜️ |
| acosh(col) | ⬜️ |
| add_months(start, months) | ⬜️ |
| aggregate(col, initialValue, merge[, finish]) | ✅ |
| approxCountDistinct(col[, rsd]) | ⬜️ |
| approx_count_distinct(col[, rsd]) | ⬜️ |
| array(*cols) | ⬜️ |
| array_contains(col, value) | ⬜️ |
| array_distinct(col) | ⬜️ |
| array_except(col1, col2) | ⬜️ |
| array_intersect(col1, col2) | ⬜️ |
| array_join(col, delimiter[, null_replacement]) | ⬜️ |
| array_max(col) | ⬜️ |
| array_min(col) | ⬜️ |
| array_position(col, value) | ⬜️ |
| array_remove(col, element) | ⬜️ |
| array_repeat(col, count) | ⬜️ |
| array_sort(col) | ⬜️ |
| array_union(col1, col2) | ⬜️ |
| arrays_overlap(a1, a2) | ⬜️ |
| arrays_zip(*cols) | ⬜️ |
| asc(col) | ⬜️ |
| asc_nulls_first(col) | ⬜️ |
| asc_nulls_last(col) | ⬜️ |
| ascii(col) | ⬜️ |
| asin(col) | ⬜️ |
| asinh(col) | ⬜️ |
| assert_true(col[, errMsg]) | ⬜️ |
| atan(col) | ⬜️ |
| atanh(col) | ⬜️ |
| atan2(col1, col2) | ⬜️ |
| avg(col) | ✅ |
| base64(col) | ⬜️ |
| bin(col) | ⬜️ |
| bitwiseNOT(col) | ⬜️ |
| broadcast(df) | ⬜️ |
| bround(col[, scale]) | ⬜️ |
| bucket(numBuckets, col) | ⬜️ |
| cbrt(col) | ⬜️ |
| ceil(col) | ⬜️ |
| coalesce(*cols) | ⬜️ |
| col(col) | ⬜️ |
| collect_list(col) | ⬜️ |
| collect_set(col) | ⬜️ |
| column(col) | ✅ |
| concat(*cols) | ⬜️ |
| concat_ws(sep, *cols) | ⬜️ |
| conv(col, fromBase, toBase) | ⬜️ |
| corr(col1, col2) | ✅ |
| cos(col) | ⬜️ |
| cosh(col) | ⬜️ |
| count(col) | ✅ |
| countDistinct(col, *cols) | ⬜️ |
| covar_pop(col1, col2) | ⬜️ |
| covar_samp(col1, col2) | ⬜️ |
| crc32(col) | ⬜️ |
| create_map(*cols) | ⬜️ |
| cume_dist() | ⬜️ |
| current_date() | ⬜️ |
| current_timestamp() | ⬜️ |
| date_add(start, days) | ⬜️ |
| date_format(date, format) | ⬜️ |
| date_sub(start, days) | ⬜️ |
| date_trunc(format, timestamp) | ⬜️ |
| datediff(end, start) | ⬜️ |
| dayofmonth(col) | ⬜️ |
| dayofweek(col) | ⬜️ |
| dayofyear(col) | ⬜️ |
| days(col) | ⬜️ |
| decode(col, charset) | ⬜️ |
| degrees(col) | ⬜️ |
| dense_rank() | ⬜️ |
| desc(col) | ⬜️ |
| desc_nulls_first(col) | ⬜️ |
| desc_nulls_last(col) | ⬜️ |
| element_at(col, extraction) | ⬜️ |
| encode(col, charset) | ⬜️ |
| exists(col, f) | ⬜️ |
| exp(col) | ⬜️ |
| explode(col) | ⬜️ |
| explode_outer(col) | ⬜️ |
| expm1(col) | ⬜️ |
| expr(str) | ✅ |
| factorial(col) | ⬜️ |
| filter(col, f) | ⬜️ |
| first(col[, ignorenulls]) | ⬜️ |
| flatten(col) | ⬜️ |
| floor(col) | ⬜️ |
| forall(col, f) | ⬜️ |
| format_number(col, d) | ⬜️ |
| format_string(format, *cols) | ⬜️ |
| from_csv(col, schema[, options]) | ⬜️ |
| from_json(col, schema[, options]) | ⬜️ |
| from_unixtime(timestamp[, format]) | ⬜️ |
| from_utc_timestamp(timestamp, tz) | ⬜️ |
| get_json_object(col, path) | ⬜️ |
| greatest(*cols) | ⬜️ |
| grouping(col) | ⬜️ |
| grouping_id(*cols) | ⬜️ |
| hash(*cols) | ⬜️ |
| hex(col) | ⬜️ |
| hour(col) | ⬜️ |
| hours(col) | ⬜️ |
| hypot(col1, col2) | ⬜️ |
| initcap(col) | ⬜️ |
| input_file_name() | ⬜️ |
| instr(str, substr) | ⬜️ |
| isnan(col) | ⬜️ |
| isnull(col) | ⬜️ |
| json_tuple(col, *fields) | ⬜️ |
| kurtosis(col) | ⬜️ |
| lag(col[, offset, default]) | ⬜️ |
| last(col[, ignorenulls]) | ⬜️ |
| last_day(date) | ⬜️ |
| lead(col[, offset, default]) | ⬜️ |
| least(*cols) | ⬜️ |
| length(col) | ⬜️ |
| levenshtein(left, right) | ⬜️ |
| lit(col) | ⬜️ |
| locate(substr, str[, pos]) | ⬜️ |
| log(arg1[, arg2]) | ⬜️ |
| log10(col) | ⬜️ |
| log1p(col) | ⬜️ |
| log2(col) | ⬜️ |
| lower(col) | ⬜️ |
| lpad(col, len, pad) | ⬜️ |
| ltrim(col) | ⬜️ |
| map_concat(*cols) | ⬜️ |
| map_entries(col) | ⬜️ |
| map_filter(col, f) | ⬜️ |
| map_from_arrays(col1, col2) | ⬜️ |
| map_from_entries(col) | ⬜️ |
| map_keys(col) | ⬜️ |
| map_values(col) | ⬜️ |
| map_zip_with(col1, col2, f) | ⬜️ |
| max(col) | ✅ |
| md5(col) | ⬜️ |
| mean(col) | ⬜️ |
| min(col) | ✅ |
| minute(col) | ⬜️ |
| monotonically_increasing_id() | ⬜️ |
| month(col) | ⬜️ |
| months(col) | ⬜️ |
| months_between(date1, date2[, roundOff]) | ⬜️ |
| nanvl(col1, col2) | ⬜️ |
| next_day(date, dayOfWeek) | ⬜️ |
| nth_value(col, offset[, ignoreNulls]) | ⬜️ |
| ntile(n) | ⬜️ |
| overlay(src, replace, pos[, len]) | ⬜️ |
| pandas_udf([f, returnType, functionType]) | ⬜️ |
| percent_rank() | ⬜️ |
| percentile_approx(col, percentage[, accuracy]) | ⬜️ |
| posexplode(col) | ⬜️ |
| posexplode_outer(col) | ⬜️ |
| pow(col1, col2) | ⬜️ |
| quarter(col) | ⬜️ |
| radians(col) | ⬜️ |
| raise_error(errMsg) | ⬜️ |
| rand([seed]) | ⬜️ |
| randn([seed]) | ⬜️ |
| rank() | ⬜️ |
| regexp_extract(str, pattern, idx) | ⬜️ |
| regexp_replace(str, pattern, replacement) | ⬜️ |
| repeat(col, n) | ⬜️ |
| reverse(col) | ⬜️ |
| rint(col) | ⬜️ |
| round(col[, scale]) | ⬜️ |
| row_number() | ⬜️ |
| rpad(col, len, pad) | ⬜️ |
| rtrim(col) | ⬜️ |
| schema_of_csv(csv[, options]) | ⬜️ |
| schema_of_json(json[, options]) | ⬜️ |
| second(col) | ⬜️ |
| sequence(start, stop[, step]) | ⬜️ |
| sha1(col) | ⬜️ |
| sha2(col, numBits) | ⬜️ |
| shiftLeft(col, numBits) | ⬜️ |
| shiftRight(col, numBits) | ⬜️ |
| shiftRightUnsigned(col, numBits) | ⬜️ |
| shuffle(col) | ⬜️ |
| signum(col) | ⬜️ |
| sin(col) | ⬜️ |
| sinh(col) | ⬜️ |
| size(col) | ⬜️ |
| skewness(col) | ⬜️ |
| slice(x, start, length) | ⬜️ |
| sort_array(col[, asc]) | ⬜️ |
| soundex(col) | ⬜️ |
| spark_partition_id() | ⬜️ |
| split(str, pattern[, limit]) | ⬜️ |
| sqrt(col) | ⬜️ |
| stddev(col) | ⬜️ |
| stddev_pop(col) | ⬜️ |
| stddev_samp(col) | ⬜️ |
| struct(*cols) | ⬜️ |
| substring(str, pos, len) | ✅ |
| substring_index(str, delim, count) | ⬜️ |
| sum(col) | ✅ |
| sumDistinct(col) | ⬜️ |
| tan(col) | ⬜️ |
| tanh(col) | ⬜️ |
| timestamp_seconds(col) | ⬜️ |
| toDegrees(col) | ⬜️ |
| toRadians(col) | ⬜️ |
| to_csv(col[, options]) | ⬜️ |
| to_date(col[, format]) | ⬜️ |
| to_json(col[, options]) | ⬜️ |
| to_timestamp(col[, format]) | ⬜️ |
| to_utc_timestamp(timestamp, tz) | ⬜️ |
| transform(col, f) | ⬜️ |
| transform_keys(col, f) | ⬜️ |
| transform_values(col, f) | ⬜️ |
| translate(srcCol, matching, replace) | ⬜️ |
| trim(col) | ⬜️ |
| trunc(date, format) | ⬜️ |
| udf([f, returnType]) | ⬜️ |
| unbase64(col) | ⬜️ |
| unhex(col) | ⬜️ |
| unix_timestamp([timestamp, format]) | ⬜️ |
| upper(col) | ⬜️ |
| var_pop(col) | ⬜️ |
| var_samp(col) | ⬜️ |
| variance(col) | ⬜️ |
| weekofyear(col) | ⬜️ |
| when(condition, value) | ✅ |
| window(timeColumn, windowDuration[, …]) | ⬜️ |
| xxhash64(*cols) | ⬜️ |
| year(col) | ⬜️ |
| years(col) | ⬜️ |
| zip_with(left, right, f) | ⬜️ |
| from_avro(data, jsonFormatSchema[, options]) | ⬜️ |
| to_avro(data[, jsonFormatSchema]) | ⬜️ |