You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1117 lines
32 KiB
1117 lines
32 KiB
from __future__ import annotations
|
|
|
|
from abc import (
|
|
ABC,
|
|
abstractmethod,
|
|
)
|
|
import sys
|
|
from textwrap import dedent
|
|
from typing import (
|
|
TYPE_CHECKING,
|
|
Iterable,
|
|
Iterator,
|
|
Mapping,
|
|
Sequence,
|
|
)
|
|
|
|
from pandas._config import get_option
|
|
|
|
from pandas._typing import (
|
|
Dtype,
|
|
WriteBuffer,
|
|
)
|
|
|
|
from pandas.core.indexes.api import Index
|
|
|
|
from pandas.io.formats import format as fmt
|
|
from pandas.io.formats.printing import pprint_thing
|
|
|
|
if TYPE_CHECKING:
|
|
from pandas.core.frame import (
|
|
DataFrame,
|
|
Series,
|
|
)
|
|
|
|
|
|
frame_max_cols_sub = dedent(
|
|
"""\
|
|
max_cols : int, optional
|
|
When to switch from the verbose to the truncated output. If the
|
|
DataFrame has more than `max_cols` columns, the truncated output
|
|
is used. By default, the setting in
|
|
``pandas.options.display.max_info_columns`` is used."""
|
|
)
|
|
|
|
|
|
show_counts_sub = dedent(
|
|
"""\
|
|
show_counts : bool, optional
|
|
Whether to show the non-null counts. By default, this is shown
|
|
only if the DataFrame is smaller than
|
|
``pandas.options.display.max_info_rows`` and
|
|
``pandas.options.display.max_info_columns``. A value of True always
|
|
shows the counts, and False never shows the counts."""
|
|
)
|
|
|
|
null_counts_sub = dedent(
|
|
"""
|
|
null_counts : bool, optional
|
|
.. deprecated:: 1.2.0
|
|
Use show_counts instead."""
|
|
)
|
|
|
|
|
|
frame_examples_sub = dedent(
|
|
"""\
|
|
>>> int_values = [1, 2, 3, 4, 5]
|
|
>>> text_values = ['alpha', 'beta', 'gamma', 'delta', 'epsilon']
|
|
>>> float_values = [0.0, 0.25, 0.5, 0.75, 1.0]
|
|
>>> df = pd.DataFrame({"int_col": int_values, "text_col": text_values,
|
|
... "float_col": float_values})
|
|
>>> df
|
|
int_col text_col float_col
|
|
0 1 alpha 0.00
|
|
1 2 beta 0.25
|
|
2 3 gamma 0.50
|
|
3 4 delta 0.75
|
|
4 5 epsilon 1.00
|
|
|
|
Prints information of all columns:
|
|
|
|
>>> df.info(verbose=True)
|
|
<class 'pandas.core.frame.DataFrame'>
|
|
RangeIndex: 5 entries, 0 to 4
|
|
Data columns (total 3 columns):
|
|
# Column Non-Null Count Dtype
|
|
--- ------ -------------- -----
|
|
0 int_col 5 non-null int64
|
|
1 text_col 5 non-null object
|
|
2 float_col 5 non-null float64
|
|
dtypes: float64(1), int64(1), object(1)
|
|
memory usage: 248.0+ bytes
|
|
|
|
Prints a summary of columns count and its dtypes but not per column
|
|
information:
|
|
|
|
>>> df.info(verbose=False)
|
|
<class 'pandas.core.frame.DataFrame'>
|
|
RangeIndex: 5 entries, 0 to 4
|
|
Columns: 3 entries, int_col to float_col
|
|
dtypes: float64(1), int64(1), object(1)
|
|
memory usage: 248.0+ bytes
|
|
|
|
Pipe output of DataFrame.info to buffer instead of sys.stdout, get
|
|
buffer content and writes to a text file:
|
|
|
|
>>> import io
|
|
>>> buffer = io.StringIO()
|
|
>>> df.info(buf=buffer)
|
|
>>> s = buffer.getvalue()
|
|
>>> with open("df_info.txt", "w",
|
|
... encoding="utf-8") as f: # doctest: +SKIP
|
|
... f.write(s)
|
|
260
|
|
|
|
The `memory_usage` parameter allows deep introspection mode, specially
|
|
useful for big DataFrames and fine-tune memory optimization:
|
|
|
|
>>> random_strings_array = np.random.choice(['a', 'b', 'c'], 10 ** 6)
|
|
>>> df = pd.DataFrame({
|
|
... 'column_1': np.random.choice(['a', 'b', 'c'], 10 ** 6),
|
|
... 'column_2': np.random.choice(['a', 'b', 'c'], 10 ** 6),
|
|
... 'column_3': np.random.choice(['a', 'b', 'c'], 10 ** 6)
|
|
... })
|
|
>>> df.info()
|
|
<class 'pandas.core.frame.DataFrame'>
|
|
RangeIndex: 1000000 entries, 0 to 999999
|
|
Data columns (total 3 columns):
|
|
# Column Non-Null Count Dtype
|
|
--- ------ -------------- -----
|
|
0 column_1 1000000 non-null object
|
|
1 column_2 1000000 non-null object
|
|
2 column_3 1000000 non-null object
|
|
dtypes: object(3)
|
|
memory usage: 22.9+ MB
|
|
|
|
>>> df.info(memory_usage='deep')
|
|
<class 'pandas.core.frame.DataFrame'>
|
|
RangeIndex: 1000000 entries, 0 to 999999
|
|
Data columns (total 3 columns):
|
|
# Column Non-Null Count Dtype
|
|
--- ------ -------------- -----
|
|
0 column_1 1000000 non-null object
|
|
1 column_2 1000000 non-null object
|
|
2 column_3 1000000 non-null object
|
|
dtypes: object(3)
|
|
memory usage: 165.9 MB"""
|
|
)
|
|
|
|
|
|
frame_see_also_sub = dedent(
|
|
"""\
|
|
DataFrame.describe: Generate descriptive statistics of DataFrame
|
|
columns.
|
|
DataFrame.memory_usage: Memory usage of DataFrame columns."""
|
|
)
|
|
|
|
|
|
frame_sub_kwargs = {
|
|
"klass": "DataFrame",
|
|
"type_sub": " and columns",
|
|
"max_cols_sub": frame_max_cols_sub,
|
|
"show_counts_sub": show_counts_sub,
|
|
"null_counts_sub": null_counts_sub,
|
|
"examples_sub": frame_examples_sub,
|
|
"see_also_sub": frame_see_also_sub,
|
|
"version_added_sub": "",
|
|
}
|
|
|
|
|
|
series_examples_sub = dedent(
|
|
"""\
|
|
>>> int_values = [1, 2, 3, 4, 5]
|
|
>>> text_values = ['alpha', 'beta', 'gamma', 'delta', 'epsilon']
|
|
>>> s = pd.Series(text_values, index=int_values)
|
|
>>> s.info()
|
|
<class 'pandas.core.series.Series'>
|
|
Int64Index: 5 entries, 1 to 5
|
|
Series name: None
|
|
Non-Null Count Dtype
|
|
-------------- -----
|
|
5 non-null object
|
|
dtypes: object(1)
|
|
memory usage: 80.0+ bytes
|
|
|
|
Prints a summary excluding information about its values:
|
|
|
|
>>> s.info(verbose=False)
|
|
<class 'pandas.core.series.Series'>
|
|
Int64Index: 5 entries, 1 to 5
|
|
dtypes: object(1)
|
|
memory usage: 80.0+ bytes
|
|
|
|
Pipe output of Series.info to buffer instead of sys.stdout, get
|
|
buffer content and writes to a text file:
|
|
|
|
>>> import io
|
|
>>> buffer = io.StringIO()
|
|
>>> s.info(buf=buffer)
|
|
>>> s = buffer.getvalue()
|
|
>>> with open("df_info.txt", "w",
|
|
... encoding="utf-8") as f: # doctest: +SKIP
|
|
... f.write(s)
|
|
260
|
|
|
|
The `memory_usage` parameter allows deep introspection mode, specially
|
|
useful for big Series and fine-tune memory optimization:
|
|
|
|
>>> random_strings_array = np.random.choice(['a', 'b', 'c'], 10 ** 6)
|
|
>>> s = pd.Series(np.random.choice(['a', 'b', 'c'], 10 ** 6))
|
|
>>> s.info()
|
|
<class 'pandas.core.series.Series'>
|
|
RangeIndex: 1000000 entries, 0 to 999999
|
|
Series name: None
|
|
Non-Null Count Dtype
|
|
-------------- -----
|
|
1000000 non-null object
|
|
dtypes: object(1)
|
|
memory usage: 7.6+ MB
|
|
|
|
>>> s.info(memory_usage='deep')
|
|
<class 'pandas.core.series.Series'>
|
|
RangeIndex: 1000000 entries, 0 to 999999
|
|
Series name: None
|
|
Non-Null Count Dtype
|
|
-------------- -----
|
|
1000000 non-null object
|
|
dtypes: object(1)
|
|
memory usage: 55.3 MB"""
|
|
)
|
|
|
|
|
|
series_see_also_sub = dedent(
|
|
"""\
|
|
Series.describe: Generate descriptive statistics of Series.
|
|
Series.memory_usage: Memory usage of Series."""
|
|
)
|
|
|
|
|
|
series_sub_kwargs = {
|
|
"klass": "Series",
|
|
"type_sub": "",
|
|
"max_cols_sub": "",
|
|
"show_counts_sub": show_counts_sub,
|
|
"null_counts_sub": "",
|
|
"examples_sub": series_examples_sub,
|
|
"see_also_sub": series_see_also_sub,
|
|
"version_added_sub": "\n.. versionadded:: 1.4.0\n",
|
|
}
|
|
|
|
|
|
INFO_DOCSTRING = dedent(
|
|
"""
|
|
Print a concise summary of a {klass}.
|
|
|
|
This method prints information about a {klass} including
|
|
the index dtype{type_sub}, non-null values and memory usage.
|
|
{version_added_sub}\
|
|
|
|
Parameters
|
|
----------
|
|
data : {klass}
|
|
{klass} to print information about.
|
|
verbose : bool, optional
|
|
Whether to print the full summary. By default, the setting in
|
|
``pandas.options.display.max_info_columns`` is followed.
|
|
buf : writable buffer, defaults to sys.stdout
|
|
Where to send the output. By default, the output is printed to
|
|
sys.stdout. Pass a writable buffer if you need to further process
|
|
the output.\
|
|
{max_cols_sub}
|
|
memory_usage : bool, str, optional
|
|
Specifies whether total memory usage of the {klass}
|
|
elements (including the index) should be displayed. By default,
|
|
this follows the ``pandas.options.display.memory_usage`` setting.
|
|
|
|
True always show memory usage. False never shows memory usage.
|
|
A value of 'deep' is equivalent to "True with deep introspection".
|
|
Memory usage is shown in human-readable units (base-2
|
|
representation). Without deep introspection a memory estimation is
|
|
made based in column dtype and number of rows assuming values
|
|
consume the same memory amount for corresponding dtypes. With deep
|
|
memory introspection, a real memory usage calculation is performed
|
|
at the cost of computational resources.
|
|
{show_counts_sub}{null_counts_sub}
|
|
|
|
Returns
|
|
-------
|
|
None
|
|
This method prints a summary of a {klass} and returns None.
|
|
|
|
See Also
|
|
--------
|
|
{see_also_sub}
|
|
|
|
Examples
|
|
--------
|
|
{examples_sub}
|
|
"""
|
|
)
|
|
|
|
|
|
def _put_str(s: str | Dtype, space: int) -> str:
|
|
"""
|
|
Make string of specified length, padding to the right if necessary.
|
|
|
|
Parameters
|
|
----------
|
|
s : Union[str, Dtype]
|
|
String to be formatted.
|
|
space : int
|
|
Length to force string to be of.
|
|
|
|
Returns
|
|
-------
|
|
str
|
|
String coerced to given length.
|
|
|
|
Examples
|
|
--------
|
|
>>> pd.io.formats.info._put_str("panda", 6)
|
|
'panda '
|
|
>>> pd.io.formats.info._put_str("panda", 4)
|
|
'pand'
|
|
"""
|
|
return str(s)[:space].ljust(space)
|
|
|
|
|
|
def _sizeof_fmt(num: int | float, size_qualifier: str) -> str:
|
|
"""
|
|
Return size in human readable format.
|
|
|
|
Parameters
|
|
----------
|
|
num : int
|
|
Size in bytes.
|
|
size_qualifier : str
|
|
Either empty, or '+' (if lower bound).
|
|
|
|
Returns
|
|
-------
|
|
str
|
|
Size in human readable format.
|
|
|
|
Examples
|
|
--------
|
|
>>> _sizeof_fmt(23028, '')
|
|
'22.5 KB'
|
|
|
|
>>> _sizeof_fmt(23028, '+')
|
|
'22.5+ KB'
|
|
"""
|
|
for x in ["bytes", "KB", "MB", "GB", "TB"]:
|
|
if num < 1024.0:
|
|
return f"{num:3.1f}{size_qualifier} {x}"
|
|
num /= 1024.0
|
|
return f"{num:3.1f}{size_qualifier} PB"
|
|
|
|
|
|
def _initialize_memory_usage(
|
|
memory_usage: bool | str | None = None,
|
|
) -> bool | str:
|
|
"""Get memory usage based on inputs and display options."""
|
|
if memory_usage is None:
|
|
memory_usage = get_option("display.memory_usage")
|
|
return memory_usage
|
|
|
|
|
|
class BaseInfo(ABC):
|
|
"""
|
|
Base class for DataFrameInfo and SeriesInfo.
|
|
|
|
Parameters
|
|
----------
|
|
data : DataFrame or Series
|
|
Either dataframe or series.
|
|
memory_usage : bool or str, optional
|
|
If "deep", introspect the data deeply by interrogating object dtypes
|
|
for system-level memory consumption, and include it in the returned
|
|
values.
|
|
"""
|
|
|
|
data: DataFrame | Series
|
|
memory_usage: bool | str
|
|
|
|
@property
|
|
@abstractmethod
|
|
def dtypes(self) -> Iterable[Dtype]:
|
|
"""
|
|
Dtypes.
|
|
|
|
Returns
|
|
-------
|
|
dtypes : sequence
|
|
Dtype of each of the DataFrame's columns (or one series column).
|
|
"""
|
|
|
|
@property
|
|
@abstractmethod
|
|
def dtype_counts(self) -> Mapping[str, int]:
|
|
"""Mapping dtype - number of counts."""
|
|
|
|
@property
|
|
@abstractmethod
|
|
def non_null_counts(self) -> Sequence[int]:
|
|
"""Sequence of non-null counts for all columns or column (if series)."""
|
|
|
|
@property
|
|
@abstractmethod
|
|
def memory_usage_bytes(self) -> int:
|
|
"""
|
|
Memory usage in bytes.
|
|
|
|
Returns
|
|
-------
|
|
memory_usage_bytes : int
|
|
Object's total memory usage in bytes.
|
|
"""
|
|
|
|
@property
|
|
def memory_usage_string(self) -> str:
|
|
"""Memory usage in a form of human readable string."""
|
|
return f"{_sizeof_fmt(self.memory_usage_bytes, self.size_qualifier)}\n"
|
|
|
|
@property
|
|
def size_qualifier(self) -> str:
|
|
size_qualifier = ""
|
|
if self.memory_usage:
|
|
if self.memory_usage != "deep":
|
|
# size_qualifier is just a best effort; not guaranteed to catch
|
|
# all cases (e.g., it misses categorical data even with object
|
|
# categories)
|
|
if (
|
|
"object" in self.dtype_counts
|
|
or self.data.index._is_memory_usage_qualified()
|
|
):
|
|
size_qualifier = "+"
|
|
return size_qualifier
|
|
|
|
@abstractmethod
|
|
def render(
|
|
self,
|
|
*,
|
|
buf: WriteBuffer[str] | None,
|
|
max_cols: int | None,
|
|
verbose: bool | None,
|
|
show_counts: bool | None,
|
|
) -> None:
|
|
pass
|
|
|
|
|
|
class DataFrameInfo(BaseInfo):
|
|
"""
|
|
Class storing dataframe-specific info.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
data: DataFrame,
|
|
memory_usage: bool | str | None = None,
|
|
):
|
|
self.data: DataFrame = data
|
|
self.memory_usage = _initialize_memory_usage(memory_usage)
|
|
|
|
@property
|
|
def dtype_counts(self) -> Mapping[str, int]:
|
|
return _get_dataframe_dtype_counts(self.data)
|
|
|
|
@property
|
|
def dtypes(self) -> Iterable[Dtype]:
|
|
"""
|
|
Dtypes.
|
|
|
|
Returns
|
|
-------
|
|
dtypes
|
|
Dtype of each of the DataFrame's columns.
|
|
"""
|
|
return self.data.dtypes
|
|
|
|
@property
|
|
def ids(self) -> Index:
|
|
"""
|
|
Column names.
|
|
|
|
Returns
|
|
-------
|
|
ids : Index
|
|
DataFrame's column names.
|
|
"""
|
|
return self.data.columns
|
|
|
|
@property
|
|
def col_count(self) -> int:
|
|
"""Number of columns to be summarized."""
|
|
return len(self.ids)
|
|
|
|
@property
|
|
def non_null_counts(self) -> Sequence[int]:
|
|
"""Sequence of non-null counts for all columns or column (if series)."""
|
|
return self.data.count()
|
|
|
|
@property
|
|
def memory_usage_bytes(self) -> int:
|
|
if self.memory_usage == "deep":
|
|
deep = True
|
|
else:
|
|
deep = False
|
|
return self.data.memory_usage(index=True, deep=deep).sum()
|
|
|
|
def render(
|
|
self,
|
|
*,
|
|
buf: WriteBuffer[str] | None,
|
|
max_cols: int | None,
|
|
verbose: bool | None,
|
|
show_counts: bool | None,
|
|
) -> None:
|
|
printer = DataFrameInfoPrinter(
|
|
info=self,
|
|
max_cols=max_cols,
|
|
verbose=verbose,
|
|
show_counts=show_counts,
|
|
)
|
|
printer.to_buffer(buf)
|
|
|
|
|
|
class SeriesInfo(BaseInfo):
|
|
"""
|
|
Class storing series-specific info.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
data: Series,
|
|
memory_usage: bool | str | None = None,
|
|
):
|
|
self.data: Series = data
|
|
self.memory_usage = _initialize_memory_usage(memory_usage)
|
|
|
|
def render(
|
|
self,
|
|
*,
|
|
buf: WriteBuffer[str] | None = None,
|
|
max_cols: int | None = None,
|
|
verbose: bool | None = None,
|
|
show_counts: bool | None = None,
|
|
) -> None:
|
|
if max_cols is not None:
|
|
raise ValueError(
|
|
"Argument `max_cols` can only be passed "
|
|
"in DataFrame.info, not Series.info"
|
|
)
|
|
printer = SeriesInfoPrinter(
|
|
info=self,
|
|
verbose=verbose,
|
|
show_counts=show_counts,
|
|
)
|
|
printer.to_buffer(buf)
|
|
|
|
@property
|
|
def non_null_counts(self) -> Sequence[int]:
|
|
return [self.data.count()]
|
|
|
|
@property
|
|
def dtypes(self) -> Iterable[Dtype]:
|
|
return [self.data.dtypes]
|
|
|
|
@property
|
|
def dtype_counts(self):
|
|
from pandas.core.frame import DataFrame
|
|
|
|
return _get_dataframe_dtype_counts(DataFrame(self.data))
|
|
|
|
@property
|
|
def memory_usage_bytes(self) -> int:
|
|
"""Memory usage in bytes.
|
|
|
|
Returns
|
|
-------
|
|
memory_usage_bytes : int
|
|
Object's total memory usage in bytes.
|
|
"""
|
|
if self.memory_usage == "deep":
|
|
deep = True
|
|
else:
|
|
deep = False
|
|
return self.data.memory_usage(index=True, deep=deep)
|
|
|
|
|
|
class InfoPrinterAbstract:
|
|
"""
|
|
Class for printing dataframe or series info.
|
|
"""
|
|
|
|
def to_buffer(self, buf: WriteBuffer[str] | None = None) -> None:
|
|
"""Save dataframe info into buffer."""
|
|
table_builder = self._create_table_builder()
|
|
lines = table_builder.get_lines()
|
|
if buf is None: # pragma: no cover
|
|
buf = sys.stdout
|
|
fmt.buffer_put_lines(buf, lines)
|
|
|
|
@abstractmethod
|
|
def _create_table_builder(self) -> TableBuilderAbstract:
|
|
"""Create instance of table builder."""
|
|
|
|
|
|
class DataFrameInfoPrinter(InfoPrinterAbstract):
|
|
"""
|
|
Class for printing dataframe info.
|
|
|
|
Parameters
|
|
----------
|
|
info : DataFrameInfo
|
|
Instance of DataFrameInfo.
|
|
max_cols : int, optional
|
|
When to switch from the verbose to the truncated output.
|
|
verbose : bool, optional
|
|
Whether to print the full summary.
|
|
show_counts : bool, optional
|
|
Whether to show the non-null counts.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
info: DataFrameInfo,
|
|
max_cols: int | None = None,
|
|
verbose: bool | None = None,
|
|
show_counts: bool | None = None,
|
|
):
|
|
self.info = info
|
|
self.data = info.data
|
|
self.verbose = verbose
|
|
self.max_cols = self._initialize_max_cols(max_cols)
|
|
self.show_counts = self._initialize_show_counts(show_counts)
|
|
|
|
@property
|
|
def max_rows(self) -> int:
|
|
"""Maximum info rows to be displayed."""
|
|
return get_option("display.max_info_rows", len(self.data) + 1)
|
|
|
|
@property
|
|
def exceeds_info_cols(self) -> bool:
|
|
"""Check if number of columns to be summarized does not exceed maximum."""
|
|
return bool(self.col_count > self.max_cols)
|
|
|
|
@property
|
|
def exceeds_info_rows(self) -> bool:
|
|
"""Check if number of rows to be summarized does not exceed maximum."""
|
|
return bool(len(self.data) > self.max_rows)
|
|
|
|
@property
|
|
def col_count(self) -> int:
|
|
"""Number of columns to be summarized."""
|
|
return self.info.col_count
|
|
|
|
def _initialize_max_cols(self, max_cols: int | None) -> int:
|
|
if max_cols is None:
|
|
return get_option("display.max_info_columns", self.col_count + 1)
|
|
return max_cols
|
|
|
|
def _initialize_show_counts(self, show_counts: bool | None) -> bool:
|
|
if show_counts is None:
|
|
return bool(not self.exceeds_info_cols and not self.exceeds_info_rows)
|
|
else:
|
|
return show_counts
|
|
|
|
def _create_table_builder(self) -> DataFrameTableBuilder:
|
|
"""
|
|
Create instance of table builder based on verbosity and display settings.
|
|
"""
|
|
if self.verbose:
|
|
return DataFrameTableBuilderVerbose(
|
|
info=self.info,
|
|
with_counts=self.show_counts,
|
|
)
|
|
elif self.verbose is False: # specifically set to False, not necessarily None
|
|
return DataFrameTableBuilderNonVerbose(info=self.info)
|
|
else:
|
|
if self.exceeds_info_cols:
|
|
return DataFrameTableBuilderNonVerbose(info=self.info)
|
|
else:
|
|
return DataFrameTableBuilderVerbose(
|
|
info=self.info,
|
|
with_counts=self.show_counts,
|
|
)
|
|
|
|
|
|
class SeriesInfoPrinter(InfoPrinterAbstract):
|
|
"""Class for printing series info.
|
|
|
|
Parameters
|
|
----------
|
|
info : SeriesInfo
|
|
Instance of SeriesInfo.
|
|
verbose : bool, optional
|
|
Whether to print the full summary.
|
|
show_counts : bool, optional
|
|
Whether to show the non-null counts.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
info: SeriesInfo,
|
|
verbose: bool | None = None,
|
|
show_counts: bool | None = None,
|
|
):
|
|
self.info = info
|
|
self.data = info.data
|
|
self.verbose = verbose
|
|
self.show_counts = self._initialize_show_counts(show_counts)
|
|
|
|
def _create_table_builder(self) -> SeriesTableBuilder:
|
|
"""
|
|
Create instance of table builder based on verbosity.
|
|
"""
|
|
if self.verbose or self.verbose is None:
|
|
return SeriesTableBuilderVerbose(
|
|
info=self.info,
|
|
with_counts=self.show_counts,
|
|
)
|
|
else:
|
|
return SeriesTableBuilderNonVerbose(info=self.info)
|
|
|
|
def _initialize_show_counts(self, show_counts: bool | None) -> bool:
|
|
if show_counts is None:
|
|
return True
|
|
else:
|
|
return show_counts
|
|
|
|
|
|
class TableBuilderAbstract(ABC):
|
|
"""
|
|
Abstract builder for info table.
|
|
"""
|
|
|
|
_lines: list[str]
|
|
info: BaseInfo
|
|
|
|
@abstractmethod
|
|
def get_lines(self) -> list[str]:
|
|
"""Product in a form of list of lines (strings)."""
|
|
|
|
@property
|
|
def data(self) -> DataFrame | Series:
|
|
return self.info.data
|
|
|
|
@property
|
|
def dtypes(self) -> Iterable[Dtype]:
|
|
"""Dtypes of each of the DataFrame's columns."""
|
|
return self.info.dtypes
|
|
|
|
@property
|
|
def dtype_counts(self) -> Mapping[str, int]:
|
|
"""Mapping dtype - number of counts."""
|
|
return self.info.dtype_counts
|
|
|
|
@property
|
|
def display_memory_usage(self) -> bool:
|
|
"""Whether to display memory usage."""
|
|
return bool(self.info.memory_usage)
|
|
|
|
@property
|
|
def memory_usage_string(self) -> str:
|
|
"""Memory usage string with proper size qualifier."""
|
|
return self.info.memory_usage_string
|
|
|
|
@property
|
|
def non_null_counts(self) -> Sequence[int]:
|
|
return self.info.non_null_counts
|
|
|
|
def add_object_type_line(self) -> None:
|
|
"""Add line with string representation of dataframe to the table."""
|
|
self._lines.append(str(type(self.data)))
|
|
|
|
def add_index_range_line(self) -> None:
|
|
"""Add line with range of indices to the table."""
|
|
self._lines.append(self.data.index._summary())
|
|
|
|
def add_dtypes_line(self) -> None:
|
|
"""Add summary line with dtypes present in dataframe."""
|
|
collected_dtypes = [
|
|
f"{key}({val:d})" for key, val in sorted(self.dtype_counts.items())
|
|
]
|
|
self._lines.append(f"dtypes: {', '.join(collected_dtypes)}")
|
|
|
|
|
|
class DataFrameTableBuilder(TableBuilderAbstract):
|
|
"""
|
|
Abstract builder for dataframe info table.
|
|
|
|
Parameters
|
|
----------
|
|
info : DataFrameInfo.
|
|
Instance of DataFrameInfo.
|
|
"""
|
|
|
|
def __init__(self, *, info: DataFrameInfo):
|
|
self.info: DataFrameInfo = info
|
|
|
|
def get_lines(self) -> list[str]:
|
|
self._lines = []
|
|
if self.col_count == 0:
|
|
self._fill_empty_info()
|
|
else:
|
|
self._fill_non_empty_info()
|
|
return self._lines
|
|
|
|
def _fill_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to empty dataframe."""
|
|
self.add_object_type_line()
|
|
self.add_index_range_line()
|
|
self._lines.append(f"Empty {type(self.data).__name__}")
|
|
|
|
@abstractmethod
|
|
def _fill_non_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to non-empty dataframe."""
|
|
|
|
@property
|
|
def data(self) -> DataFrame:
|
|
"""DataFrame."""
|
|
return self.info.data
|
|
|
|
@property
|
|
def ids(self) -> Index:
|
|
"""Dataframe columns."""
|
|
return self.info.ids
|
|
|
|
@property
|
|
def col_count(self) -> int:
|
|
"""Number of dataframe columns to be summarized."""
|
|
return self.info.col_count
|
|
|
|
def add_memory_usage_line(self) -> None:
|
|
"""Add line containing memory usage."""
|
|
self._lines.append(f"memory usage: {self.memory_usage_string}")
|
|
|
|
|
|
class DataFrameTableBuilderNonVerbose(DataFrameTableBuilder):
|
|
"""
|
|
Dataframe info table builder for non-verbose output.
|
|
"""
|
|
|
|
def _fill_non_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to non-empty dataframe."""
|
|
self.add_object_type_line()
|
|
self.add_index_range_line()
|
|
self.add_columns_summary_line()
|
|
self.add_dtypes_line()
|
|
if self.display_memory_usage:
|
|
self.add_memory_usage_line()
|
|
|
|
def add_columns_summary_line(self) -> None:
|
|
self._lines.append(self.ids._summary(name="Columns"))
|
|
|
|
|
|
class TableBuilderVerboseMixin(TableBuilderAbstract):
|
|
"""
|
|
Mixin for verbose info output.
|
|
"""
|
|
|
|
SPACING: str = " " * 2
|
|
strrows: Sequence[Sequence[str]]
|
|
gross_column_widths: Sequence[int]
|
|
with_counts: bool
|
|
|
|
@property
|
|
@abstractmethod
|
|
def headers(self) -> Sequence[str]:
|
|
"""Headers names of the columns in verbose table."""
|
|
|
|
@property
|
|
def header_column_widths(self) -> Sequence[int]:
|
|
"""Widths of header columns (only titles)."""
|
|
return [len(col) for col in self.headers]
|
|
|
|
def _get_gross_column_widths(self) -> Sequence[int]:
|
|
"""Get widths of columns containing both headers and actual content."""
|
|
body_column_widths = self._get_body_column_widths()
|
|
return [
|
|
max(*widths)
|
|
for widths in zip(self.header_column_widths, body_column_widths)
|
|
]
|
|
|
|
def _get_body_column_widths(self) -> Sequence[int]:
|
|
"""Get widths of table content columns."""
|
|
strcols: Sequence[Sequence[str]] = list(zip(*self.strrows))
|
|
return [max(len(x) for x in col) for col in strcols]
|
|
|
|
def _gen_rows(self) -> Iterator[Sequence[str]]:
|
|
"""
|
|
Generator function yielding rows content.
|
|
|
|
Each element represents a row comprising a sequence of strings.
|
|
"""
|
|
if self.with_counts:
|
|
return self._gen_rows_with_counts()
|
|
else:
|
|
return self._gen_rows_without_counts()
|
|
|
|
@abstractmethod
|
|
def _gen_rows_with_counts(self) -> Iterator[Sequence[str]]:
|
|
"""Iterator with string representation of body data with counts."""
|
|
|
|
@abstractmethod
|
|
def _gen_rows_without_counts(self) -> Iterator[Sequence[str]]:
|
|
"""Iterator with string representation of body data without counts."""
|
|
|
|
def add_header_line(self) -> None:
|
|
header_line = self.SPACING.join(
|
|
[
|
|
_put_str(header, col_width)
|
|
for header, col_width in zip(self.headers, self.gross_column_widths)
|
|
]
|
|
)
|
|
self._lines.append(header_line)
|
|
|
|
def add_separator_line(self) -> None:
|
|
separator_line = self.SPACING.join(
|
|
[
|
|
_put_str("-" * header_colwidth, gross_colwidth)
|
|
for header_colwidth, gross_colwidth in zip(
|
|
self.header_column_widths, self.gross_column_widths
|
|
)
|
|
]
|
|
)
|
|
self._lines.append(separator_line)
|
|
|
|
def add_body_lines(self) -> None:
|
|
for row in self.strrows:
|
|
body_line = self.SPACING.join(
|
|
[
|
|
_put_str(col, gross_colwidth)
|
|
for col, gross_colwidth in zip(row, self.gross_column_widths)
|
|
]
|
|
)
|
|
self._lines.append(body_line)
|
|
|
|
def _gen_non_null_counts(self) -> Iterator[str]:
|
|
"""Iterator with string representation of non-null counts."""
|
|
for count in self.non_null_counts:
|
|
yield f"{count} non-null"
|
|
|
|
def _gen_dtypes(self) -> Iterator[str]:
|
|
"""Iterator with string representation of column dtypes."""
|
|
for dtype in self.dtypes:
|
|
yield pprint_thing(dtype)
|
|
|
|
|
|
class DataFrameTableBuilderVerbose(DataFrameTableBuilder, TableBuilderVerboseMixin):
|
|
"""
|
|
Dataframe info table builder for verbose output.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
info: DataFrameInfo,
|
|
with_counts: bool,
|
|
):
|
|
self.info = info
|
|
self.with_counts = with_counts
|
|
self.strrows: Sequence[Sequence[str]] = list(self._gen_rows())
|
|
self.gross_column_widths: Sequence[int] = self._get_gross_column_widths()
|
|
|
|
def _fill_non_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to non-empty dataframe."""
|
|
self.add_object_type_line()
|
|
self.add_index_range_line()
|
|
self.add_columns_summary_line()
|
|
self.add_header_line()
|
|
self.add_separator_line()
|
|
self.add_body_lines()
|
|
self.add_dtypes_line()
|
|
if self.display_memory_usage:
|
|
self.add_memory_usage_line()
|
|
|
|
@property
|
|
def headers(self) -> Sequence[str]:
|
|
"""Headers names of the columns in verbose table."""
|
|
if self.with_counts:
|
|
return [" # ", "Column", "Non-Null Count", "Dtype"]
|
|
return [" # ", "Column", "Dtype"]
|
|
|
|
def add_columns_summary_line(self) -> None:
|
|
self._lines.append(f"Data columns (total {self.col_count} columns):")
|
|
|
|
def _gen_rows_without_counts(self) -> Iterator[Sequence[str]]:
|
|
"""Iterator with string representation of body data without counts."""
|
|
yield from zip(
|
|
self._gen_line_numbers(),
|
|
self._gen_columns(),
|
|
self._gen_dtypes(),
|
|
)
|
|
|
|
def _gen_rows_with_counts(self) -> Iterator[Sequence[str]]:
|
|
"""Iterator with string representation of body data with counts."""
|
|
yield from zip(
|
|
self._gen_line_numbers(),
|
|
self._gen_columns(),
|
|
self._gen_non_null_counts(),
|
|
self._gen_dtypes(),
|
|
)
|
|
|
|
def _gen_line_numbers(self) -> Iterator[str]:
|
|
"""Iterator with string representation of column numbers."""
|
|
for i, _ in enumerate(self.ids):
|
|
yield f" {i}"
|
|
|
|
def _gen_columns(self) -> Iterator[str]:
|
|
"""Iterator with string representation of column names."""
|
|
for col in self.ids:
|
|
yield pprint_thing(col)
|
|
|
|
|
|
class SeriesTableBuilder(TableBuilderAbstract):
|
|
"""
|
|
Abstract builder for series info table.
|
|
|
|
Parameters
|
|
----------
|
|
info : SeriesInfo.
|
|
Instance of SeriesInfo.
|
|
"""
|
|
|
|
def __init__(self, *, info: SeriesInfo):
|
|
self.info: SeriesInfo = info
|
|
|
|
def get_lines(self) -> list[str]:
|
|
self._lines = []
|
|
self._fill_non_empty_info()
|
|
return self._lines
|
|
|
|
@property
|
|
def data(self) -> Series:
|
|
"""Series."""
|
|
return self.info.data
|
|
|
|
def add_memory_usage_line(self) -> None:
|
|
"""Add line containing memory usage."""
|
|
self._lines.append(f"memory usage: {self.memory_usage_string}")
|
|
|
|
@abstractmethod
|
|
def _fill_non_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to non-empty series."""
|
|
|
|
|
|
class SeriesTableBuilderNonVerbose(SeriesTableBuilder):
|
|
"""
|
|
Series info table builder for non-verbose output.
|
|
"""
|
|
|
|
def _fill_non_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to non-empty series."""
|
|
self.add_object_type_line()
|
|
self.add_index_range_line()
|
|
self.add_dtypes_line()
|
|
if self.display_memory_usage:
|
|
self.add_memory_usage_line()
|
|
|
|
|
|
class SeriesTableBuilderVerbose(SeriesTableBuilder, TableBuilderVerboseMixin):
|
|
"""
|
|
Series info table builder for verbose output.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
info: SeriesInfo,
|
|
with_counts: bool,
|
|
):
|
|
self.info = info
|
|
self.with_counts = with_counts
|
|
self.strrows: Sequence[Sequence[str]] = list(self._gen_rows())
|
|
self.gross_column_widths: Sequence[int] = self._get_gross_column_widths()
|
|
|
|
def _fill_non_empty_info(self) -> None:
|
|
"""Add lines to the info table, pertaining to non-empty series."""
|
|
self.add_object_type_line()
|
|
self.add_index_range_line()
|
|
self.add_series_name_line()
|
|
self.add_header_line()
|
|
self.add_separator_line()
|
|
self.add_body_lines()
|
|
self.add_dtypes_line()
|
|
if self.display_memory_usage:
|
|
self.add_memory_usage_line()
|
|
|
|
def add_series_name_line(self):
|
|
self._lines.append(f"Series name: {self.data.name}")
|
|
|
|
@property
|
|
def headers(self) -> Sequence[str]:
|
|
"""Headers names of the columns in verbose table."""
|
|
if self.with_counts:
|
|
return ["Non-Null Count", "Dtype"]
|
|
return ["Dtype"]
|
|
|
|
def _gen_rows_without_counts(self) -> Iterator[Sequence[str]]:
|
|
"""Iterator with string representation of body data without counts."""
|
|
yield from self._gen_dtypes()
|
|
|
|
def _gen_rows_with_counts(self) -> Iterator[Sequence[str]]:
|
|
"""Iterator with string representation of body data with counts."""
|
|
yield from zip(
|
|
self._gen_non_null_counts(),
|
|
self._gen_dtypes(),
|
|
)
|
|
|
|
|
|
def _get_dataframe_dtype_counts(df: DataFrame) -> Mapping[str, int]:
|
|
"""
|
|
Create mapping between datatypes and their number of occurrences.
|
|
"""
|
|
# groupby dtype.name to collect e.g. Categorical columns
|
|
return df.dtypes.value_counts().groupby(lambda x: x.name).sum()
|
|
|