mars.dataframe.
DataFrame
__init__
Initialize self. See help(type(self)) for accurate signature.
Methods
__init__([data, index, columns, dtype, …])
Initialize self.
abs()
abs
add(other[, axis, level, fill_value])
add
Get Addition of dataframe and other, element-wise (binary operator add).
agg([func, axis])
agg
aggregate([func, axis])
aggregate
all([axis, bool_only, skipna, level, …])
all
any([axis, bool_only, skipna, level, …])
any
append(other[, ignore_index, …])
append
apply(func[, axis, raw, result_type, args, …])
apply
astype(dtype[, copy, errors])
astype
Cast a pandas object to a specified dtype dtype.
dtype
bfill([axis, inplace, limit, downcast])
bfill
copy()
copy
copy_from(obj)
copy_from
copy_to(target)
copy_to
corr([method, min_periods])
corr
Compute pairwise correlation of columns, excluding NA/null values.
corrwith(other[, axis, drop, method])
corrwith
Compute pairwise correlation.
count([axis, level, numeric_only, combine_size])
count
cummax([axis, skipna])
cummax
cummin([axis, skipna])
cummin
cumprod([axis, skipna])
cumprod
cumsum([axis, skipna])
cumsum
describe([percentiles, include, exclude])
describe
diff([periods, axis])
diff
First discrete difference of element.
div(other[, axis, level, fill_value])
div
Get Floating division of dataframe and other, element-wise (binary operator truediv).
dot(other)
dot
Compute the matrix multiplication between the DataFrame and other.
drop([labels, axis, index, columns, level, …])
drop
Drop specified labels from rows or columns.
drop_duplicates([subset, keep, inplace, …])
drop_duplicates
Return DataFrame with duplicate rows removed.
dropna([axis, how, thresh, subset, inplace])
dropna
Remove missing values.
eq(other[, axis, level])
eq
Get Equal to of dataframe and other, element-wise (binary operator eq).
ewm([com, span, halflife, alpha, …])
ewm
Provide exponential weighted functions.
execute([session])
execute
expanding([min_periods, center, axis])
expanding
Provide expanding transformations.
explode(column[, ignore_index])
explode
Transform each element of a list-like to a row, replicating index values.
ffill([axis, inplace, limit, downcast])
ffill
fillna([value, method, axis, inplace, …])
fillna
Fill NA/NaN values using the specified method.
floordiv(other[, axis, level, fill_value])
floordiv
Get Integer division of dataframe and other, element-wise (binary operator floordiv).
from_records(records, **kw)
from_records
from_tensor(in_tensor[, index, columns])
from_tensor
ge(other[, axis, level])
ge
Get Greater than or equal to of dataframe and other, element-wise (binary operator ge).
groupby([by, level, as_index, sort, group_keys])
groupby
gt(other[, axis, level])
gt
Get Greater than of dataframe and other, element-wise (binary operator gt).
head([n])
head
Return the first n rows.
insert(loc, column, value[, allow_duplicates])
insert
Insert column into DataFrame at specified location.
isin(values)
isin
Whether each element in the DataFrame is contained in values.
isna()
isna
Detect missing values.
isnull()
isnull
iterrows([batch_size, session])
iterrows
Iterate over DataFrame rows as (index, Series) pairs.
itertuples([index, name, batch_size, session])
itertuples
Iterate over DataFrame rows as namedtuples.
join(other[, on, how, lsuffix, rsuffix, …])
join
kurt([axis, skipna, level, numeric_only, …])
kurt
kurtosis([axis, skipna, level, …])
kurtosis
le(other[, axis, level])
le
Get Less than or equal to of dataframe and other, element-wise (binary operator le).
lt(other[, axis, level])
lt
Get Less than of dataframe and other, element-wise (binary operator lt).
map_chunk(func[, args])
map_chunk
Apply function to each chunk.
mask(cond[, other, inplace, axis, level, …])
mask
Replace values where the condition is True.
max([axis, skipna, level, numeric_only, …])
max
mean([axis, skipna, level, numeric_only, …])
mean
melt([id_vars, value_vars, var_name, …])
melt
Unpivot a DataFrame from wide to long format, optionally leaving identifiers set.
memory_usage([index, deep])
memory_usage
Return the memory usage of each column in bytes.
merge(right[, how, on, left_on, right_on, …])
merge
min([axis, skipna, level, numeric_only, …])
min
mod(other[, axis, level, fill_value])
mod
Get Modulo of dataframe and other, element-wise (binary operator mod).
mul(other[, axis, level, fill_value])
mul
Get Multiplication of dataframe and other, element-wise (binary operator mul).
multiply(other[, axis, level, fill_value])
multiply
ne(other[, axis, level])
ne
Get Not equal to of dataframe and other, element-wise (binary operator ne).
notna()
notna
Detect existing (non-missing) values.
notnull()
notnull
nunique([axis, dropna, combine_size])
nunique
Count distinct observations over requested axis.
pop(item)
pop
Return item and drop from frame.
pow(other[, axis, level, fill_value])
pow
Get Exponential power of dataframe and other, element-wise (binary operator pow).
prod([axis, skipna, level, min_count, …])
prod
product([axis, skipna, level, min_count, …])
product
quantile([q, axis, numeric_only, interpolation])
quantile
Return values at the given quantile over requested axis.
radd(other[, axis, level, fill_value])
radd
Get Addition of dataframe and other, element-wise (binary operator radd).
rdiv(other[, axis, level, fill_value])
rdiv
Get Floating division of dataframe and other, element-wise (binary operator rtruediv).
rebalance([factor, axis, num_partitions, …])
rebalance
Make Data more balanced across entire cluster.
rechunk(chunk_size[, threshold, …])
rechunk
reindex(*args, **kwargs)
reindex
Conform Series/DataFrame to new index with optional filling logic.
rename([mapper, index, columns, axis, copy, …])
rename
Alter axes labels.
reset_index([level, drop, inplace, …])
reset_index
Reset the index, or a level of it.
rfloordiv(other[, axis, level, fill_value])
rfloordiv
Get Integer division of dataframe and other, element-wise (binary operator rfloordiv).
rmod(other[, axis, level, fill_value])
rmod
Get Modulo of dataframe and other, element-wise (binary operator rmod).
rmul(other[, axis, level, fill_value])
rmul
Get Multiplication of dataframe and other, element-wise (binary operator rmul).
rolling(window[, min_periods, center, …])
rolling
Provide rolling window calculations.
round([decimals])
round
Round a DataFrame to a variable number of decimal places.
rpow(other[, axis, level, fill_value])
rpow
Get Exponential power of dataframe and other, element-wise (binary operator rpow).
rsub(other[, axis, level, fill_value])
rsub
Get Subtraction of dataframe and other, element-wise (binary operator rsubtract).
rtruediv(other[, axis, level, fill_value])
rtruediv
select_dtypes([include, exclude])
select_dtypes
Return a subset of the DataFrame’s columns based on the column dtypes.
sem([axis, skipna, level, ddof, …])
sem
set_index(keys[, drop, append, inplace, …])
set_index
shift([periods, freq, axis, fill_value])
shift
Shift index by desired number of periods with an optional time freq.
skew([axis, skipna, level, numeric_only, …])
skew
sort_index([axis, level, ascending, …])
sort_index
Sort object by labels (along an axis).
sort_values(by[, axis, ascending, inplace, …])
sort_values
Sort by the values along either axis.
stack([level, dropna])
stack
Stack the prescribed level(s) from columns to index.
std([axis, skipna, level, ddof, …])
std
sub(other[, axis, level, fill_value])
sub
Get Subtraction of dataframe and other, element-wise (binary operator subtract).
sum([axis, skipna, level, min_count, …])
sum
tail([n])
tail
Return the last n rows.
tiles()
tiles
to_cpu()
to_cpu
to_csv(path[, sep, na_rep, float_format, …])
to_csv
Write object to a comma-separated values (csv) file.
to_gpu()
to_gpu
to_pandas([session])
to_pandas
to_parquet(path[, engine, compression, …])
to_parquet
Write a DataFrame to the binary parquet format, each chunk will be written to a Parquet file.
to_sql(name, con[, schema, if_exists, …])
to_sql
Write records stored in a DataFrame to a SQL database.
to_tensor()
to_tensor
to_vineyard([vineyard_socket])
to_vineyard
transform(func[, axis, dtypes])
transform
truediv(other[, axis, level, fill_value])
truediv
tshift([periods, freq, axis])
tshift
Shift the time index, using the index’s frequency if available.
var([axis, skipna, level, ddof, …])
var
where(cond[, other, inplace, axis, level, …])
where
Replace values where the condition is False.
Attributes
at
Access a single value for a row/column label pair.
columns
data
dtypes
Return the dtypes in the DataFrame.
iat
iloc
index
loc
ndim
Return an int representing the number of axes / array dimensions.
shape
size