def make_table(
header=None,
rows=None,
row_order=None,
digits=4,
space=4,
title="",
max_width=1e100,
row_ids=None,
legend="",
missing_data="",
column_templates=None,
dtype=None,
data_frame=None,
format="simple",
):
"""
Parameters
----------
header
column headings
rows
a 2D dict, list or tuple. If a dict, it must have column
headings as top level keys, and common row labels as keys in each
column.
row_order
the order in which rows will be pulled from the twoDdict
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
max_width
maximum column width for printing
row_ids
if True, the 0'th column is used as row identifiers and keys
for slicing.
legend
table legend
column_templates
dict of column headings
or a function that will handle the formatting.
dtype
optional numpy array typecode.
limit
exits after this many lines. Only applied for non pickled data
file types.
data_frame
a pandas DataFrame, supersedes header/rows
format
output format when using str(Table)
"""
table = _Table(
header=header,
rows=rows,
digits=digits,
row_order=row_order,
title=title,
dtype=dtype,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
row_ids=row_ids,
legend=legend,
data_frame=data_frame,
format=format,
)
return table
def load_table(
filename,
sep=None,
reader=None,
digits=4,
space=4,
title="",
missing_data="",
max_width=1e100,
row_ids=None,
legend="",
column_templates=None,
dtype=None,
static_column_types=False,
limit=None,
format="simple",
**kwargs,
):
"""
Parameters
----------
filename
path to file containing a tabular data
sep
the delimiting character between columns
reader
a parser for reading filename. This approach assumes the first
row returned by the reader will be the header row.
static_column_types
if True, and reader is None, identifies columns
with a numeric/bool data types from the first non-header row.
This assumes all subsequent entries in that column are of the same type.
Default is False.
header
column headings
rows
a 2D dict, list or tuple. If a dict, it must have column
headings as top level keys, and common row labels as keys in each
column.
row_order
the order in which rows will be pulled from the twoDdict
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
missing_data
character assigned if a row has no entry for a column
max_width
maximum column width for printing
row_ids
if True, the 0'th column is used as row identifiers and keys
for slicing.
legend
table legend
column_templates
dict of column headings
or a function that will handle the formatting.
dtype
optional numpy array typecode.
limit
exits after this many lines. Only applied for non pickled data
file types.
data_frame
a pandas DataFrame, supersedes header/rows
format
output format when using str(Table)
"""
sep = sep or kwargs.pop("delimiter", None)
file_format, compress_format = get_format_suffixes(filename)
if not (reader or static_column_types):
if file_format == "pickle":
f = open_(filename, mode="rb")
loaded_table = pickle.load(f)
f.close()
return _Table(**loaded_table)
elif file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
header, rows, loaded_title, legend = load_delimited(filename,
delimiter=sep,
limit=limit,
**kwargs)
title = title or loaded_title
else:
f = open_(filename, newline=None)
if not reader:
if file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
elif not sep:
raise ValueError("static_column_types option requires a value "
"for sep")
reader = autogen_reader(f,
sep,
limit=limit,
with_title=kwargs.get("with_title", False))
rows = [row for row in reader(f)]
f.close()
header = rows.pop(0)
return make_table(
header=header,
rows=rows,
digits=digits,
title=title,
dtype=dtype,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
row_ids=row_ids,
legend=legend,
format=format,
)
return table
def LoadTable(
filename=None,
sep=None,
reader=None,
header=None,
rows=None,
row_order=None,
digits=4,
space=4,
title="",
missing_data="",
max_width=1e100,
row_ids=None,
legend="",
column_templates=None,
dtype=None,
static_column_types=False,
limit=None,
data_frame=None,
format="simple",
**kwargs,
):
"""
.. deprecated:: 2019.8.30a
``LoadTable`` will be removed in ``cogent3`` 2020.1.1. It's replaced by
``load_table`` and ``make_table``.
"""
sep = sep or kwargs.pop("delimiter", None)
if filename is not None:
file_format, compress_format = get_format_suffixes(filename)
if filename is not None and not (reader or static_column_types):
if file_format == "pickle":
f = open_(filename, mode="rb")
loaded_table = pickle.load(f)
f.close()
return _Table(**loaded_table)
elif file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
header, rows, loaded_title, legend = load_delimited(
filename, delimiter=sep, limit=limit, **kwargs
)
title = title or loaded_title
elif filename and (reader or static_column_types):
f = open_(filename, newline=None)
if not reader:
if file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
elif not sep:
raise ValueError(
"static_column_types option requires a value " "for sep"
)
reader = autogen_reader(
f, sep, limit=limit, with_title=kwargs.get("with_title", False)
)
rows = [row for row in reader(f)]
f.close()
header = rows.pop(0)
table = _Table(
header=header,
rows=rows,
digits=digits,
row_order=row_order,
title=title,
dtype=dtype,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
row_ids=row_ids,
legend=legend,
data_frame=data_frame,
format=format,
)
return table
def load_table(
filename,
sep=None,
reader=None,
digits=4,
space=4,
title="",
missing_data="",
max_width=1e100,
index_name=None,
legend="",
column_templates=None,
static_column_types=False,
limit=None,
format="simple",
skip_inconsistent=False,
**kwargs,
):
"""
Parameters
----------
filename
path to file containing a tabular data
sep
the delimiting character between columns
reader
a parser for reading filename. This approach assumes the first
row returned by the reader will be the header row.
static_column_types
if True, and reader is None, identifies columns
with a numeric/bool data types from the first non-header row.
This assumes all subsequent entries in that column are of the same type.
Default is False.
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
missing_data
character assigned if a row has no entry for a column
max_width
maximum column width for printing
index_name
column name with values to be used as row identifiers and keys
for slicing. All column values must be unique.
legend
table legend
column_templates
dict of column headings
or a function that will handle the formatting.
limit
exits after this many lines. Only applied for non pickled data
file types.
format
output format when using str(Table)
skip_inconsistent
skips rows that have different length to header row
"""
import pathlib
if not any(isinstance(filename, t) for t in (str, pathlib.PurePath)):
raise TypeError(
"filename must be string or Path, perhaps you want make_table()")
if "index" in kwargs:
deprecated("argument", "index", "index_name", "2021.11")
index_name = kwargs.pop("index", index_name)
sep = sep or kwargs.pop("delimiter", None)
file_format, compress_format = get_format_suffixes(filename)
if file_format == "json":
return load_from_json(filename, (_Table, ))
elif file_format in ("pickle", "pkl"):
f = open_(filename, mode="rb")
loaded_table = pickle.load(f)
f.close()
r = _Table()
r.__setstate__(loaded_table)
return r
if reader:
with open_(filename, newline=None) as f:
data = [row for row in reader(f)]
header = data[0]
data = {column[0]: column[1:] for column in zip(*data)}
else:
if file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
header, rows, loaded_title, legend = load_delimited(filename,
sep=sep,
limit=limit,
**kwargs)
if skip_inconsistent:
num_fields = len(header)
rows = [r for r in rows if len(r) == num_fields]
else:
lengths = set(map(len, [header] + rows))
if len(lengths) != 1:
msg = f"inconsistent number of fields {lengths}"
raise ValueError(msg)
title = title or loaded_title
data = {column[0]: column[1:] for column in zip(header, *rows)}
for key, value in data.items():
data[key] = cast_str_to_array(value, static_type=static_column_types)
return make_table(
header=header,
data=data,
digits=digits,
title=title,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
index_name=index_name,
legend=legend,
format=format,
)
def make_table(
header=None,
data=None,
row_order=None,
digits=4,
space=4,
title="",
max_width=1e100,
index_name=None,
legend="",
missing_data="",
column_templates=None,
data_frame=None,
format="simple",
**kwargs,
):
"""
Parameters
----------
header
column headings
data
a 2D dict, list or tuple. If a dict, it must have column
headings as top level keys, and common row labels as keys in each
column.
row_order
the order in which rows will be pulled from the twoDdict
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
max_width
maximum column width for printing
index_name
column name with values to be used as row identifiers and keys
for slicing. All column values must be unique.
legend
table legend
missing_data
replace missing data with this
column_templates
dict of column headings
or a function that will handle the formatting.
limit
exits after this many lines. Only applied for non pickled data
file types.
data_frame
a pandas DataFrame, supersedes header/rows
format
output format when using str(Table)
"""
if any(isinstance(a, str) for a in (header, data)):
raise TypeError(f"str type invalid, if its a path use load_table()")
if "index" in kwargs:
deprecated("argument", "index", "index_name", "2021.11")
index_name = kwargs.pop("index", index_name)
data = kwargs.get("rows", data)
if data_frame is not None:
from pandas import DataFrame
if not isinstance(data_frame, DataFrame):
raise TypeError(f"expecting a DataFrame, got{type(data_frame)}")
data = {c: data_frame[c].to_numpy() for c in data_frame}
return _Table(
header=header,
data=data,
digits=digits,
row_order=row_order,
title=title,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
index_name=index_name,
legend=legend,
data_frame=data_frame,
format=format,
)
def load_table(
filename,
sep=None,
reader=None,
digits=4,
space=4,
title="",
missing_data="",
max_width=1e100,
index=None,
legend="",
column_templates=None,
dtype=None,
static_column_types=False,
limit=None,
format="simple",
skip_inconsistent=False,
**kwargs,
):
"""
Parameters
----------
filename
path to file containing a tabular data
sep
the delimiting character between columns
reader
a parser for reading filename. This approach assumes the first
row returned by the reader will be the header row.
static_column_types
if True, and reader is None, identifies columns
with a numeric/bool data types from the first non-header row.
This assumes all subsequent entries in that column are of the same type.
Default is False.
header
column headings
rows
a 2D dict, list or tuple. If a dict, it must have column
headings as top level keys, and common row labels as keys in each
column.
row_order
the order in which rows will be pulled from the twoDdict
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
missing_data
character assigned if a row has no entry for a column
max_width
maximum column width for printing
index
if True, the 0'th column is used as row identifiers and keys
for slicing.
legend
table legend
column_templates
dict of column headings
or a function that will handle the formatting.
dtype
optional numpy array typecode.
limit
exits after this many lines. Only applied for non pickled data
file types.
data_frame
a pandas DataFrame, supersedes header/rows
format
output format when using str(Table)
skip_inconsistent
skips rows that have different length to header row
"""
sep = sep or kwargs.pop("delimiter", None)
file_format, compress_format = get_format_suffixes(filename)
if file_format in ("pickle", "pkl"):
f = open_(filename, mode="rb")
loaded_table = pickle.load(f)
f.close()
r = _Table()
r.__setstate__(loaded_table)
return r
if not reader:
if file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
header, rows, loaded_title, legend = load_delimited(
filename, delimiter=sep, limit=limit, **kwargs
)
if skip_inconsistent:
num_fields = len(header)
rows = [r for r in rows if len(r) == num_fields]
else:
lengths = set(map(len, [header] + rows))
if len(lengths) != 1:
msg = f"inconsistent number of fields {lengths}"
raise ValueError(msg)
title = title or loaded_title
data = {column[0]: column[1:] for column in zip(header, *rows)}
else:
f = open_(filename, newline=None)
data = [row for row in reader(f)]
header = data[0]
data = {column[0]: column[1:] for column in zip(*data)}
f.close()
for key, value in data.items():
data[key] = cast_str_to_array(value, static_type=static_column_types)
return make_table(
header=header,
data=data,
digits=digits,
title=title,
dtype=dtype,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
index=index,
legend=legend,
format=format,
)
def make_table(
header=None,
data=None,
row_order=None,
digits=4,
space=4,
title="",
max_width=1e100,
index=None,
legend="",
missing_data="",
column_templates=None,
dtype=None,
data_frame=None,
format="simple",
**kwargs,
):
"""
Parameters
----------
header
column headings
data
a 2D dict, list or tuple. If a dict, it must have column
headings as top level keys, and common row labels as keys in each
column.
row_order
the order in which rows will be pulled from the twoDdict
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
max_width
maximum column width for printing
index
if True, the 0'th column is used as row identifiers and keys
for slicing.
legend
table legend
column_templates
dict of column headings
or a function that will handle the formatting.
dtype
optional numpy array typecode.
limit
exits after this many lines. Only applied for non pickled data
file types.
data_frame
a pandas DataFrame, supersedes header/rows
format
output format when using str(Table)
"""
data = kwargs.get("rows", data)
if data_frame is not None:
from pandas import DataFrame
if not isinstance(data_frame, DataFrame):
raise TypeError(f"expecting a DataFrame, got{type(data_frame)}")
data = {c: data_frame[c].to_numpy() for c in data_frame}
table = _Table(
header=header,
data=data,
digits=digits,
row_order=row_order,
title=title,
dtype=dtype,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
index=index,
legend=legend,
data_frame=data_frame,
format=format,
)
return table
