apache_beam.dataframe.frames module

apache_beam.dataframe.frames.populate_not_implemented(pd_type)

class apache_beam.dataframe.frames.DeferredDataFrameOrSeries(expr)

Bases: apache_beam.dataframe.frame_base.DeferredFrame

drop(labels, axis, index, columns, errors, **kwargs)

droplevel(level, axis)

fillna(value, method, axis, limit, **kwargs)

ffill(**kwargs)

bfill(**kwargs)

pad(**kwargs)

backfill(**kwargs)

groupby(by, level, axis, as_index, group_keys, **kwargs)

abs(**kwargs)

astype(**kwargs)

copy(**kwargs)

tz_localize(ambiguous, **kwargs)

size

empty

bool()

equals(other)

sort_values(axis, **kwargs)

sort_index(axis, **kwargs)

dtype

ndim

dtypes

index

hist(**kwargs)

first(**kwargs)

last(**kwargs)

head(**kwargs)

tail(**kwargs)

class apache_beam.dataframe.frames.DeferredSeries(expr)

Bases: apache_beam.dataframe.frames.DeferredDataFrameOrSeries

keys()

append(to_append, ignore_index, verify_integrity, **kwargs)

align(other, join, axis, level, method, **kwargs)

array

rename(**kwargs)

between(**kwargs)

dot(other)

std(*args, **kwargs)

var(axis, skipna, level, ddof, **kwargs)

corr(other, method, min_periods)

cov(other, min_periods, ddof)

dropna(**kwargs)

items(**kwargs)

iteritems(**kwargs)

isin(**kwargs)

isnull(**kwargs)

isna(**kwargs)

notnull(**kwargs)

notna(**kwargs)

tolist(**kwargs)

to_numpy(**kwargs)

to_string(**kwargs)

aggregate(func, axis=0, *args, **kwargs)

agg(func, axis=0, *args, **kwargs)

axes

clip(**kwargs)

all(*args, **kwargs)

any(*args, **kwargs)

count(*args, **kwargs)

min(*args, **kwargs)

max(*args, **kwargs)

prod(*args, **kwargs)

product(*args, **kwargs)

sum(*args, **kwargs)

mean(*args, **kwargs)

median(*args, **kwargs)

cummax(**kwargs)

cummin(**kwargs)

cumsum(**kwargs)

cumprod(**kwargs)

diff(**kwargs)

filter(**kwargs)

memory_usage(**kwargs)

nlargest(keep, **kwargs)

nsmallest(keep, **kwargs)

plot

pop(**kwargs)

rename_axis(**kwargs)

replace(to_replace, value, limit, method, **kwargs)

round(**kwargs)

searchsorted(**kwargs)

shift(**kwargs)

take(**kwargs)

to_dict(**kwargs)

to_frame(**kwargs)

unique(as_series=False)

update(other)

unstack(**kwargs)

values

view(**kwargs)

str

apply(**kwargs)

map(**kwargs)

T

add(**kwargs)

add_prefix(**kwargs)

add_suffix(**kwargs)

and(**kwargs)

argmax(**kwargs)

argmin(**kwargs)

argsort(**kwargs)

asfreq(**kwargs)

asof(**kwargs)

at

at_time(**kwargs)

attrs

autocorr(**kwargs)

between_time(**kwargs)

cat

combine(**kwargs)

combine_first(**kwargs)

compare(**kwargs)

convert_dtypes(**kwargs)

describe(**kwargs)

div(**kwargs)

divide(**kwargs)

divmod(**kwargs)

drop_duplicates(**kwargs)

dt

duplicated(**kwargs)

eq(**kwargs)

ewm(**kwargs)

expanding(**kwargs)

explode(**kwargs)

factorize(**kwargs)

first_valid_index(**kwargs)

flags

floordiv(**kwargs)

ge(**kwargs)

get(**kwargs)

gt(**kwargs)

hasnans

iat

idxmax(**kwargs)

idxmin(**kwargs)

iloc

infer_objects(**kwargs)

interpolate(**kwargs)

is_monotonic

is_monotonic_decreasing

is_monotonic_increasing

is_unique

item(**kwargs)

kurt(**kwargs)

kurtosis(**kwargs)

last_valid_index(**kwargs)

le(**kwargs)

loc

lt(**kwargs)

mad(**kwargs)

mask(**kwargs)

mod(**kwargs)

mode(**kwargs)

mul(**kwargs)

multiply(**kwargs)

name

nbytes

ne(**kwargs)

nunique(**kwargs)

or(**kwargs)

pct_change(**kwargs)

pipe(**kwargs)

pow(**kwargs)

quantile(**kwargs)

radd(**kwargs)

rand(**kwargs)

rank(**kwargs)

ravel(**kwargs)

rdiv(**kwargs)

rdivmod(**kwargs)

reindex(**kwargs)

reindex_like(**kwargs)

reorder_levels(**kwargs)

repeat(**kwargs)

resample(**kwargs)

reset_index(**kwargs)

rfloordiv(**kwargs)

rmod(**kwargs)

rmul(**kwargs)

rolling(**kwargs)

ror(**kwargs)

rpow(**kwargs)

rsub(**kwargs)

rtruediv(**kwargs)

sample(**kwargs)

sem(**kwargs)

set_axis(**kwargs)

set_flags(**kwargs)

shape

skew(**kwargs)

slice_shift(**kwargs)

sparse

squeeze(**kwargs)

sub(**kwargs)

subtract(**kwargs)

swapaxes(**kwargs)

swaplevel(**kwargs)

to_clipboard(**kwargs)

to_csv(**kwargs)

to_excel(**kwargs)

to_hdf(**kwargs)

to_json(**kwargs)

to_latex(**kwargs)

to_list(**kwargs)

to_markdown(**kwargs)

to_period(**kwargs)

to_pickle(**kwargs)

to_sql(**kwargs)

to_timestamp(**kwargs)

to_xarray(**kwargs)

transform(**kwargs)

transpose(**kwargs)

truediv(**kwargs)

truncate(**kwargs)

tshift(**kwargs)

tz_convert(**kwargs)

value_counts(**kwargs)

where(**kwargs)

xs(**kwargs)

class apache_beam.dataframe.frames.DeferredDataFrame(expr)

Bases: apache_beam.dataframe.frames.DeferredDataFrameOrSeries

T

columns

keys()

align(other, join, axis, copy, level, method, **kwargs)

append(other, ignore_index, verify_integrity, sort, **kwargs)

set_index(keys, **kwargs)

loc

iloc

axes

dtypes

assign(**kwargs)

explode(column, ignore_index)

aggregate(func, axis=0, *args, **kwargs)

agg(func, axis=0, *args, **kwargs)

applymap(**kwargs)

memory_usage(**kwargs)

info(**kwargs)

clip(**kwargs)

corr(method, min_periods)

cov(min_periods, ddof)

corrwith(other, axis, drop, method)

cummax(**kwargs)

cummin(**kwargs)

cumsum(**kwargs)

cumprod(**kwargs)

diff(**kwargs)

dot(other)

mode(axis=0, *args, **kwargs)

dropna(axis, **kwargs)

eval(expr, inplace, **kwargs)

query(expr, inplace, **kwargs)

isnull(**kwargs)

isna(**kwargs)

notnull(**kwargs)

notna(**kwargs)

items(**kwargs)

itertuples(**kwargs)

iterrows(**kwargs)

iteritems(**kwargs)

join(other, on, **kwargs)

merge(right, on, left_on, right_on, left_index, right_index, suffixes, **kwargs)

nlargest(keep, **kwargs)

nsmallest(keep, **kwargs)

nunique(**kwargs)

plot

pop(item)

quantile(axis, **kwargs)

rename(**kwargs)

rename_axis(**kwargs)

replace(limit, **kwargs)

reset_index(level=None, **kwargs)

round(decimals, *args, **kwargs)

select_dtypes(**kwargs)

shift(axis, **kwargs)

shape

stack(**kwargs)

all(*args, **kwargs)

any(*args, **kwargs)

count(*args, **kwargs)

max(*args, **kwargs)

min(*args, **kwargs)

prod(*args, **kwargs)

product(*args, **kwargs)

sum(*args, **kwargs)

mean(*args, **kwargs)

median(*args, **kwargs)

take(**kwargs)

to_records(**kwargs)

to_dict(**kwargs)

to_numpy(**kwargs)

to_string(**kwargs)

to_sparse(**kwargs)

transpose(**kwargs)

unstack(*args, **kwargs)

update(**kwargs)

values

add(**kwargs)

add_prefix(**kwargs)

add_suffix(**kwargs)

and(**kwargs)

apply(**kwargs)

asfreq(**kwargs)

asof(**kwargs)

at

at_time(**kwargs)

attrs

between_time(**kwargs)

boxplot(**kwargs)

combine(**kwargs)

combine_first(**kwargs)

compare(**kwargs)

convert_dtypes(**kwargs)

describe(**kwargs)

div(**kwargs)

divide(**kwargs)

divmod(**kwargs)

drop_duplicates(**kwargs)

duplicated(**kwargs)

eq(**kwargs)

ewm(**kwargs)

expanding(**kwargs)

filter(**kwargs)

first_valid_index(**kwargs)

flags

floordiv(**kwargs)

from_dict(**kwargs)

from_records(**kwargs)

ge(**kwargs)

get(**kwargs)

gt(**kwargs)

iat

idxmax(**kwargs)

idxmin(**kwargs)

infer_objects(**kwargs)

insert(**kwargs)

interpolate(**kwargs)

isin(**kwargs)

kurt(**kwargs)

kurtosis(**kwargs)

last_valid_index(**kwargs)

le(**kwargs)

lookup(**kwargs)

lt(**kwargs)

mad(**kwargs)

mask(**kwargs)

melt(**kwargs)

mod(**kwargs)

mul(**kwargs)

multiply(**kwargs)

ne(**kwargs)

or(**kwargs)

pct_change(**kwargs)

pipe(**kwargs)

pivot(**kwargs)

pivot_table(**kwargs)

pow(**kwargs)

radd(**kwargs)

rand(**kwargs)

rank(**kwargs)

rdiv(**kwargs)

rdivmod(**kwargs)

reindex(**kwargs)

reindex_like(**kwargs)

reorder_levels(**kwargs)

resample(**kwargs)

rfloordiv(**kwargs)

rmod(**kwargs)

rmul(**kwargs)

rolling(**kwargs)

ror(**kwargs)

rpow(**kwargs)

rsub(**kwargs)

rtruediv(**kwargs)

sample(**kwargs)

sem(**kwargs)

set_axis(**kwargs)

set_flags(**kwargs)

skew(**kwargs)

slice_shift(**kwargs)

sparse

squeeze(**kwargs)

std(**kwargs)

style

sub(**kwargs)

subtract(**kwargs)

swapaxes(**kwargs)

swaplevel(**kwargs)

to_clipboard(**kwargs)

to_csv(path, *args, **kwargs)

to_excel(path, *args, **kwargs)

to_feather(path, *args, **kwargs)

to_gbq(**kwargs)

to_hdf(**kwargs)

to_html(path, *args, **kwargs)

to_json(path, orient=None, *args, **kwargs)

to_latex(**kwargs)

to_markdown(**kwargs)

to_msgpack(**kwargs)

to_parquet(path, *args, **kwargs)

to_period(**kwargs)

to_pickle(**kwargs)

to_sql(**kwargs)

to_stata(path, *args, **kwargs)

to_timestamp(**kwargs)

to_xarray(**kwargs)

transform(**kwargs)

truediv(**kwargs)

truncate(**kwargs)

tshift(**kwargs)

tz_convert(**kwargs)

value_counts(**kwargs)

var(**kwargs)

where(**kwargs)

xs(**kwargs)

class apache_beam.dataframe.frames.DeferredGroupBy(expr, kwargs, ungrouped: apache_beam.dataframe.expressions.Expression, ungrouped_with_index: apache_beam.dataframe.expressions.Expression, grouping_columns, grouping_indexes, projection=None)

Bases: apache_beam.dataframe.frame_base.DeferredFrame

This object represents the result of:

ungrouped.groupby(level=[grouping_indexes + grouping_columns],
                  **kwargs)[projection]

Parameters:

• expr – An expression to compute a pandas GroupBy object. Convenient for unliftable aggregations.
• ungrouped – An expression to compute the DataFrame pre-grouping, the (Multi)Index contains only the grouping columns/indexes.
• ungrouped_with_index – Same as ungrouped, except the index includes all of the original indexes as well as any grouping columns. This is important for operations that expose the original index, e.g. .apply(), but we only use it when necessary to avoid unnessary data transfer and GBKs.
• grouping_columns – list of column labels that were in the original groupby(..) by parameter. Only relevant for grouped DataFrames.
• grouping_indexes – list of index names (or index level numbers) to be grouped.
• kwargs – Keywords args passed to the original groupby(..) call.

agg(fn)

apply(fn, *args, **kwargs)

aggregate(fn)

hist(**kwargs)

plot(**kwargs)

first(**kwargs)

last(**kwargs)

head(**kwargs)

tail(**kwargs)

nth(**kwargs)

cumcount(**kwargs)

cummax(**kwargs)

cummin(**kwargs)

cumsum(**kwargs)

cumprod(**kwargs)

groups

all(*args, **kwargs)

any(*args, **kwargs)

backfill(**kwargs)

bfill(**kwargs)

boxplot(**kwargs)

corr

corrwith

count(*args, **kwargs)

cov

describe(**kwargs)

diff

ewm(**kwargs)

expanding(**kwargs)

ffill(**kwargs)

fillna

filter(**kwargs)

get_group(**kwargs)

idxmax(**kwargs)

idxmin(**kwargs)

indices

mad

max(*args, **kwargs)

mean(*args, **kwargs)

median(*args, **kwargs)

min(*args, **kwargs)

ngroup(**kwargs)

ngroups

nunique(**kwargs)

ohlc(**kwargs)

pad(**kwargs)

pct_change(**kwargs)

pipe(**kwargs)

prod(*args, **kwargs)

quantile(**kwargs)

rank(**kwargs)

resample(**kwargs)

rolling(**kwargs)

sample(**kwargs)

sem(**kwargs)

shift(**kwargs)

size(*args, **kwargs)

skew

std(*args, **kwargs)

sum(*args, **kwargs)

take

transform(**kwargs)

tshift

var(*args, **kwargs)

apache_beam.dataframe.frames.make_str_func(method)