def render_categorical_length(config: Settings, summary: dict,
varid: str) -> Tuple[Renderable, Renderable]:
length_table = Table(
[
{
"name": "Max length",
"value": fmt_number(summary["max_length"]),
"alert": False,
},
{
"name": "Median length",
"value": fmt_number(summary["median_length"]),
"alert": False,
},
{
"name":
"Mean length",
"value":
fmt_numeric(summary["mean_length"],
precision=config.report.precision),
"alert":
False,
},
{
"name": "Min length",
"value": fmt_number(summary["min_length"]),
"alert": False,
},
],
name="Length",
anchor_id=f"{varid}lengthstats",
)
length_histo = Image(
histogram(config, *summary["histogram_length"]),
image_format=config.plot.image_format,
alt="length histogram",
name="Length",
caption="Histogram of lengths of the category",
anchor_id=f"{varid}length",
)
return length_table, length_histo
def render_categorical_unicode(config: Settings, summary: dict,
varid: str) -> Tuple[Renderable, Renderable]:
n_freq_table_max = config.n_freq_table_max
category_overview = FrequencyTable(
freq_table(
freqtable=summary["category_alias_counts"],
n=summary["category_alias_counts"].sum(),
max_number_to_print=n_freq_table_max,
),
name="Most occurring categories",
anchor_id=f"{varid}category_long_values",
redact=False,
)
cats = []
for category_alias_name, category_alias_counts in sorted(
summary["category_alias_char_counts"].items(),
key=lambda x: -len(x[1])):
category_alias_name = category_alias_name.replace("_", " ")
cats.append(
FrequencyTable(
freq_table(
freqtable=category_alias_counts,
n=category_alias_counts.sum(),
max_number_to_print=n_freq_table_max,
),
name=f"{category_alias_name}",
anchor_id=f"{varid}category_alias_values_{category_alias_name}",
redact=config.vars.cat.redact,
))
category_items = [
category_overview,
Container(
cats,
name="Most frequent character per category",
sequence_type="batch_grid",
anchor_id=f"{varid}categories",
batch_size=2,
subtitles=True,
),
]
script_overview = FrequencyTable(
freq_table(
freqtable=summary["script_counts"],
n=summary["script_counts"].sum(),
max_number_to_print=n_freq_table_max,
),
name="Most occurring scripts",
anchor_id=f"{varid}script_values",
redact=False,
)
scripts = [
FrequencyTable(
freq_table(
freqtable=script_counts,
n=script_counts.sum(),
max_number_to_print=n_freq_table_max,
),
name=f"{script_name}",
anchor_id=f"{varid}script_values_{script_name}",
redact=config.vars.cat.redact,
) for script_name, script_counts in sorted(
summary["script_char_counts"].items(), key=lambda x: -len(x[1]))
]
script_items = [
script_overview,
Container(
scripts,
name="Most frequent character per script",
sequence_type="batch_grid",
anchor_id=f"{varid}scripts",
batch_size=2,
subtitles=True,
),
]
block_overview = FrequencyTable(
freq_table(
freqtable=summary["block_alias_counts"],
n=summary["block_alias_counts"].sum(),
max_number_to_print=n_freq_table_max,
),
name="Most occurring blocks",
anchor_id=f"{varid}block_alias_values",
redact=False,
)
blocks = [
FrequencyTable(
freq_table(
freqtable=block_counts,
n=block_counts.sum(),
max_number_to_print=n_freq_table_max,
),
name=f"{block_name}",
anchor_id=f"{varid}block_alias_values_{block_name}",
redact=config.vars.cat.redact,
) for block_name, block_counts in
summary["block_alias_char_counts"].items()
]
block_items = [
block_overview,
Container(
blocks,
name="Most frequent character per block",
sequence_type="batch_grid",
anchor_id=f"{varid}blocks",
batch_size=2,
subtitles=True,
),
]
overview_table = Table(
[
{
"name": "Total characters",
"value": fmt_number(summary["n_characters"]),
"alert": False,
},
{
"name": "Distinct characters",
"value": fmt_number(summary["n_characters_distinct"]),
"alert": False,
},
{
"name": "Distinct categories",
"value":
f"{fmt_number(summary['n_category'])} {help(title='Unicode categories (click for more information)', url='https://en.wikipedia.org/wiki/Unicode_character_property#General_Category')}",
"alert": False,
},
{
"name": "Distinct scripts",
"value":
f"{fmt_number(summary['n_scripts'])} {help(title='Unicode scripts (click for more information)', url='https://en.wikipedia.org/wiki/Script_(Unicode)#List_of_scripts_in_Unicode')}",
"alert": False,
},
{
"name": "Distinct blocks",
"value":
f"{fmt_number(summary['n_block_alias'])} {help(title='Unicode blocks (click for more information)', url='https://en.wikipedia.org/wiki/Unicode_block')}",
"alert": False,
},
],
name="Characters and Unicode",
caption=
"The Unicode Standard assigns character properties to each code point, which can be used to analyse textual variables. ",
)
citems = [
Container(
[
FrequencyTable(
freq_table(
freqtable=summary["character_counts"],
n=summary["n_characters"],
max_number_to_print=n_freq_table_max,
),
name="Most occurring characters",
anchor_id=f"{varid}character_frequency",
redact=config.vars.cat.redact,
),
],
name="Characters",
anchor_id=f"{varid}characters",
sequence_type="named_list",
),
Container(
category_items,
name="Categories",
anchor_id=f"{varid}categories",
sequence_type="named_list",
),
Container(
script_items,
name="Scripts",
anchor_id=f"{varid}scripts",
sequence_type="named_list",
),
Container(
block_items,
name="Blocks",
anchor_id=f"{varid}blocks",
sequence_type="named_list",
),
]
return overview_table, Container(
citems,
name="Unicode",
sequence_type="tabs",
anchor_id=f"{varid}unicode",
)
def get_dataset_overview(config: Settings, summary: dict) -> Renderable:
table_metrics = [
{
"name": "Number of variables",
"value": fmt_number(summary["table"]["n_var"]),
},
{
"name": "Number of observations",
"value": fmt_number(summary["table"]["n"]),
},
{
"name": "Missing cells",
"value": fmt_number(summary["table"]["n_cells_missing"]),
},
{
"name": "Missing cells (%)",
"value": fmt_percent(summary["table"]["p_cells_missing"]),
},
]
if "n_duplicates" in summary["table"]:
table_metrics.extend(
[
{
"name": "Duplicate rows",
"value": fmt_number(summary["table"]["n_duplicates"]),
},
{
"name": "Duplicate rows (%)",
"value": fmt_percent(summary["table"]["p_duplicates"]),
},
]
)
table_metrics.extend(
[
{
"name": "Total size in memory",
"value": fmt_bytesize(summary["table"]["memory_size"]),
},
{
"name": "Average record size in memory",
"value": fmt_bytesize(summary["table"]["record_size"]),
},
]
)
dataset_info = Table(
table_metrics,
name="Dataset statistics",
)
dataset_types = Table(
[
{
"name": str(type_name),
"value": fmt_numeric(count, precision=config.report.precision),
}
for type_name, count in summary["table"]["types"].items()
],
name="Variable types",
)
return Container(
[dataset_info, dataset_types],
anchor_id="dataset_overview",
name="Overview",
sequence_type="grid",
)