def get_dataset_reproduction(summary: dict) -> Renderable:
version = summary["package"]["pandas_profiling_version"]
config = quote(summary["package"]["pandas_profiling_config"])
date_start = summary["analysis"]["date_start"]
date_end = summary["analysis"]["date_end"]
duration = summary["analysis"]["duration"]
reproduction_table = Table(
[
{"name": "Analysis started", "value": fmt(date_start)},
{"name": "Analysis finished", "value": fmt(date_end)},
{"name": "Duration", "value": fmt_timespan(duration)},
{
"name": "Software version",
"value": f'<a href="https://github.com/pandas-profiling/pandas-profiling">pandas-profiling v{version}</a>',
},
{
"name": "Download configuration",
"value": f'<a download="config.json" href="data:text/plain;charset=utf-8,{config}">config.json</a>',
},
],
name="Reproduction",
anchor_id="overview_reproduction",
)
return Container(
[reproduction_table],
name="Reproduction",
anchor_id="reproduction",
sequence_type="grid",
)
def render_generic(config: Settings, summary: dict) -> dict:
info = VariableInfo(
anchor_id=summary["varid"],
alerts=summary["alerts"],
var_type="Unsupported",
var_name=summary["varname"],
description=summary["description"],
)
table = Table([
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": "n_missing" in summary["alert_fields"],
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": "p_missing" in summary["alert_fields"],
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
])
return {
"top": Container([info, table, HTML("")], sequence_type="grid"),
"bottom": None,
}
def get_dataset_column_definitions(definitions: dict) -> Container:
"""Generate an overview section for the variable description
Args:
definitions: the variable descriptions.
Returns:
A container object
"""
variable_descriptions = [
Table(
[
{"name": column, "value": fmt(value)}
for column, value in definitions.items()
],
name="Variable descriptions",
anchor_id="variable_definition_table",
)
]
return Container(
variable_descriptions,
name="Variables",
anchor_id="variable_descriptions",
sequence_type="grid",
)
def get_table(items):
table = GridspecLayout(len(items), 2)
for row_id, item in enumerate(items):
table[row_id, 0] = widgets.HTML(item["name"])
table[row_id, 1] = widgets.HTML(fmt(item["value"]))
return table
def get_table(items):
table = QTableWidget()
table.setRowCount(len(items))
table.setColumnCount(2)
for row_id, item in enumerate(items):
table.setItem(row_id, 0, QTableWidgetItem(item["name"]))
table.setItem(row_id, 1, QTableWidgetItem(fmt(item["value"])))
return table
def get_dataset_schema(metadata: dict) -> Container:
about_dataset = []
for key in ["description", "creator", "author"]:
if key in metadata and len(metadata[key]) > 0:
about_dataset.append({
"name": key.capitalize(),
"value": fmt(metadata[key])
})
if "url" in metadata:
about_dataset.append({
"name":
"URL",
"value":
f'<a href="{metadata["url"]}">{metadata["url"]}</a>',
})
if "copyright_holder" in metadata and len(
metadata["copyright_holder"]) > 0:
if "copyright_year" not in metadata:
about_dataset.append({
"name":
"Copyright",
"value":
fmt(f"(c) {metadata['copyright_holder']}"),
})
else:
about_dataset.append({
"name":
"Copyright",
"value":
fmt(f"(c) {metadata['copyright_holder']} {metadata['copyright_year']}"
),
})
return Container(
[Table(about_dataset, name="Dataset", anchor_id="metadata_dataset")],
name="Dataset",
anchor_id="dataset",
sequence_type="grid",
)
def get_table(items):
from PyQt5.QtWidgets import QHeaderView
table = QTableWidget()
table.setRowCount(len(items))
table.setColumnCount(2)
horizontal = table.horizontalHeader()
horizontal.setSectionResizeMode(QHeaderView.Stretch)
horizontal.setVisible(False)
vertical = table.verticalHeader()
vertical.setVisible(False)
for row_id, item in enumerate(items):
table.setItem(row_id, 0, QTableWidgetItem(item["name"]))
table.setItem(row_id, 1, QTableWidgetItem(fmt(item["value"])))
return table
def render_complex(config: Settings, summary: dict) -> dict:
varid = summary["varid"]
template_variables = {}
image_format = config.plot.image_format
# Top
info = VariableInfo(
summary["varid"],
summary["varname"],
"Complex number (ℂ)",
summary["warnings"],
summary["description"],
)
table1 = Table(
[
{"name": "Distinct", "value": fmt(summary["n_distinct"])},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
},
{"name": "Missing", "value": fmt(summary["n_missing"])},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
},
]
)
table2 = Table(
[
{
"name": "Mean",
"value": fmt_numeric(
summary["mean"], precision=config.report.precision
),
},
{
"name": "Minimum",
"value": fmt_numeric(summary["min"], precision=config.report.precision),
},
{
"name": "Maximum",
"value": fmt_numeric(summary["max"], precision=config.report.precision),
},
{
"name": "Zeros",
"value": fmt_numeric(
summary["n_zeros"], precision=config.report.precision
),
},
{"name": "Zeros (%)", "value": fmt_percent(summary["p_zeros"])},
]
)
placeholder = HTML("")
template_variables["top"] = Container(
[info, table1, table2, placeholder], sequence_type="grid"
)
# Bottom
items = [
Image(
scatter_complex(config, summary["scatter_data"]),
image_format=image_format,
alt="Scatterplot",
caption="Scatterplot in the complex plane",
name="Scatter",
anchor_id=f"{varid}scatter",
)
]
bottom = Container(items, sequence_type="tabs", anchor_id=summary["varid"])
template_variables["bottom"] = bottom
return template_variables
def render_categorical(config: Settings, summary: dict) -> dict:
varid = summary["varid"]
n_obs_cat = config.vars.cat.n_obs
image_format = config.plot.image_format
words = config.vars.cat.words
characters = config.vars.cat.characters
length = config.vars.cat.length
template_variables = render_common(config, summary)
info = VariableInfo(
summary["varid"],
summary["varname"],
"Categorical",
summary["alerts"],
summary["description"],
)
table = Table([
{
"name": "Distinct",
"value": fmt(summary["n_distinct"]),
"alert": "n_distinct" in summary["alert_fields"],
},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
"alert": "p_distinct" in summary["alert_fields"],
},
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": "n_missing" in summary["alert_fields"],
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": "p_missing" in summary["alert_fields"],
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
])
fqm = FrequencyTableSmall(
freq_table(
freqtable=summary["value_counts_without_nan"],
n=summary["count"],
max_number_to_print=n_obs_cat,
),
redact=config.vars.cat.redact,
)
template_variables["top"] = Container([info, table, fqm],
sequence_type="grid")
# ============================================================================================
frequency_table = FrequencyTable(
template_variables["freq_table_rows"],
name="Common Values",
anchor_id=f"{varid}common_values",
redact=config.vars.cat.redact,
)
unique_stats = render_categorical_frequency(config, summary, varid)
overview_items = []
if length:
length_table, length_histo = render_categorical_length(
config, summary, varid)
overview_items.append(length_table)
if characters:
overview_table_char, unitab = render_categorical_unicode(
config, summary, varid)
overview_items.append(overview_table_char)
overview_items.append(unique_stats)
if not config.vars.cat.redact:
rows = ("1st row", "2nd row", "3rd row", "4th row", "5th row")
sample = Table(
[{
"name": name,
"value": fmt(value),
"alert": False,
} for name, value in zip(rows, summary["first_rows"])],
name="Sample",
)
overview_items.append(sample)
string_items: List[Renderable] = [frequency_table]
if length:
string_items.append(length_histo)
max_unique = config.plot.pie.max_unique
if max_unique > 0 and summary["n_distinct"] <= max_unique:
string_items.append(
Image(
pie_plot(
config,
summary["value_counts_without_nan"],
legend_kws={"loc": "upper right"},
),
image_format=image_format,
alt="Pie chart",
name="Pie chart",
anchor_id=f"{varid}pie_chart",
))
bottom_items = [
Container(
overview_items,
name="Overview",
anchor_id=f"{varid}overview",
sequence_type="batch_grid",
batch_size=len(overview_items),
titles=False,
),
Container(
string_items,
name="Categories",
anchor_id=f"{varid}string",
sequence_type="batch_grid",
batch_size=len(string_items),
),
]
if words:
woc = freq_table(
freqtable=summary["word_counts"],
n=summary["word_counts"].sum(),
max_number_to_print=10,
)
fqwo = FrequencyTable(
woc,
name="Common words",
anchor_id=f"{varid}cwo",
redact=config.vars.cat.redact,
)
bottom_items.append(
Container(
[fqwo],
name="Words",
anchor_id=f"{varid}word",
sequence_type="grid",
))
if characters:
bottom_items.append(
Container(
[unitab],
name="Characters",
anchor_id=f"{varid}characters",
sequence_type="grid",
))
# Bottom
template_variables["bottom"] = Container(bottom_items,
sequence_type="tabs",
anchor_id=f"{varid}bottom")
return template_variables
def render_path(config: Settings, summary: dict) -> dict:
varid = summary["varid"]
n_freq_table_max = config.n_freq_table_max
redact = config.vars.cat.redact
template_variables = render_categorical(config, summary)
keys = ["name", "parent", "suffix", "stem", "anchor"]
for path_part in keys:
template_variables[f"freqtable_{path_part}"] = freq_table(
freqtable=summary[f"{path_part}_counts"],
n=summary["n"],
max_number_to_print=n_freq_table_max,
)
# Top
template_variables["top"].content["items"][0].content["var_type"] = "Path"
# Bottom
path_overview_tab = Container(
[
Table(
[
{
"name": "Common prefix",
"value": fmt(summary["common_prefix"]),
"alert": False,
},
{
"name": "Unique stems",
"value": fmt_numeric(
summary["n_stem_unique"], precision=config.report.precision
),
"alert": False,
},
{
"name": "Unique names",
"value": fmt_numeric(
summary["n_name_unique"], precision=config.report.precision
),
"alert": False,
},
{
"name": "Unique extensions",
"value": fmt_numeric(
summary["n_suffix_unique"],
precision=config.report.precision,
),
"alert": False,
},
{
"name": "Unique directories",
"value": fmt_numeric(
summary["n_parent_unique"],
precision=config.report.precision,
),
"alert": False,
},
{
"name": "Unique anchors",
"value": fmt_numeric(
summary["n_anchor_unique"],
precision=config.report.precision,
),
"alert": False,
},
]
)
],
anchor_id=f"{varid}tbl",
name="Overview",
sequence_type="list",
)
path_items = [
path_overview_tab,
FrequencyTable(
template_variables["freq_table_rows"],
name="Full",
anchor_id=f"{varid}full_frequency",
redact=redact,
),
FrequencyTable(
template_variables["freqtable_stem"],
name="Stem",
anchor_id=f"{varid}stem_frequency",
redact=redact,
),
FrequencyTable(
template_variables["freqtable_name"],
name="Name",
anchor_id=f"{varid}name_frequency",
redact=redact,
),
FrequencyTable(
template_variables["freqtable_suffix"],
name="Extension",
anchor_id=f"{varid}suffix_frequency",
redact=redact,
),
FrequencyTable(
template_variables["freqtable_parent"],
name="Parent",
anchor_id=f"{varid}parent_frequency",
redact=redact,
),
FrequencyTable(
template_variables["freqtable_anchor"],
name="Anchor",
anchor_id=f"{varid}anchor_frequency",
redact=redact,
),
]
path_tab = Container(
path_items,
name="Path",
sequence_type="tabs",
anchor_id=f"{varid}path",
)
template_variables["bottom"].content["items"].append(path_tab)
return template_variables
def render_boolean(config: Settings, summary: dict) -> dict:
varid = summary["varid"]
n_obs_bool = config.vars.bool.n_obs
image_format = config.plot.image_format
# Prepare variables
template_variables = render_common(config, summary)
# Element composition
info = VariableInfo(
anchor_id=summary["varid"],
alerts=summary["alerts"],
var_type="Boolean",
var_name=summary["varname"],
description=summary["description"],
)
table = Table(
[
{
"name": "Distinct",
"value": fmt(summary["n_distinct"]),
"alert": "n_distinct" in summary["alert_fields"],
},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
"alert": "p_distinct" in summary["alert_fields"],
},
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": "n_missing" in summary["alert_fields"],
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": "p_missing" in summary["alert_fields"],
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
]
)
fqm = FrequencyTableSmall(
freq_table(
freqtable=summary["value_counts_without_nan"],
n=summary["n"],
max_number_to_print=n_obs_bool,
),
redact=False,
)
template_variables["top"] = Container([info, table, fqm], sequence_type="grid")
items: List[Renderable] = [
FrequencyTable(
template_variables["freq_table_rows"],
name="Common Values",
anchor_id=f"{varid}frequency_table",
redact=False,
)
]
max_unique = config.plot.pie.max_unique
if max_unique > 0:
items.append(
Image(
pie_plot(
config,
summary["value_counts_without_nan"],
legend_kws={"loc": "upper right"},
),
image_format=image_format,
alt="Chart",
name="Chart",
anchor_id=f"{varid}pie_chart",
)
)
template_variables["bottom"] = Container(
items, sequence_type="tabs", anchor_id=f"{varid}bottom"
)
return template_variables
def render_count(config: Settings, summary: dict) -> dict:
template_variables = render_common(config, summary)
image_format = config.plot.image_format
# Top
info = VariableInfo(
summary["varid"],
summary["varname"],
"Real number (ℝ / ℝ<sub>≥0</sub>)",
summary["warnings"],
summary["description"],
)
table1 = Table([
{
"name": "Distinct",
"value": fmt(summary["n_distinct"]),
"alert": False,
},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
"alert": False,
},
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": False,
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": False,
},
])
table2 = Table([
{
"name":
"Mean",
"value":
fmt_numeric(summary["mean"], precision=config.report.precision),
"alert":
False,
},
{
"name": "Minimum",
"value": fmt_numeric(summary["min"],
precision=config.report.precision),
"alert": False,
},
{
"name": "Maximum",
"value": fmt_numeric(summary["max"],
precision=config.report.precision),
"alert": False,
},
{
"name": "Zeros",
"value": fmt(summary["n_zeros"]),
"alert": False,
},
{
"name": "Zeros (%)",
"value": fmt_percent(summary["p_zeros"]),
"alert": False,
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
])
mini_histo = Image(
mini_histogram(config, *summary["histogram"]),
image_format=image_format,
alt="Mini histogram",
)
template_variables["top"] = Container([info, table1, table2, mini_histo],
sequence_type="grid")
seqs = [
Image(
histogram(config, *summary["histogram"]),
image_format=image_format,
alt="Histogram",
caption=
f"<strong>Histogram with fixed size bins</strong> (bins={len(summary['histogram'][1]) - 1})",
name="Histogram",
anchor_id="histogram",
)
]
fq = FrequencyTable(
template_variables["freq_table_rows"],
name="Common values",
anchor_id="common_values",
redact=False,
)
evs = Container(
[
FrequencyTable(
template_variables["firstn_expanded"],
name="Minimum 5 values",
anchor_id="firstn",
redact=False,
),
FrequencyTable(
template_variables["lastn_expanded"],
name="Maximum 5 values",
anchor_id="lastn",
redact=False,
),
],
sequence_type="tabs",
name="Extreme values",
anchor_id="extreme_values",
)
template_variables["bottom"] = Container(
[
Container(seqs,
sequence_type="tabs",
name="Histogram(s)",
anchor_id="histograms"),
fq,
evs,
],
sequence_type="tabs",
anchor_id=summary["varid"],
)
return template_variables
def render_date(config: Settings, summary: Dict[str, Any]) -> Dict[str, Any]:
varid = summary["varid"]
template_variables = {}
image_format = config.plot.image_format
# Top
info = VariableInfo(
summary["varid"],
summary["varname"],
"Date",
summary["warnings"],
summary["description"],
)
table1 = Table(
[
{
"name": "Distinct",
"value": fmt(summary["n_distinct"]),
"alert": False,
},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
"alert": False,
},
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": False,
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": False,
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
]
)
table2 = Table(
[
{"name": "Minimum", "value": fmt(summary["min"]), "alert": False},
{"name": "Maximum", "value": fmt(summary["max"]), "alert": False},
]
)
mini_histo = Image(
mini_histogram(
config, summary["histogram"][0], summary["histogram"][1], date=True
),
image_format=image_format,
alt="Mini histogram",
)
template_variables["top"] = Container(
[info, table1, table2, mini_histo], sequence_type="grid"
)
# Bottom
bottom = Container(
[
Image(
histogram(
config, summary["histogram"][0], summary["histogram"][1], date=True
),
image_format=image_format,
alt="Histogram",
caption=f"<strong>Histogram with fixed size bins</strong> (bins={len(summary['histogram'][1]) - 1})",
name="Histogram",
anchor_id=f"{varid}histogram",
)
],
sequence_type="tabs",
anchor_id=summary["varid"],
)
template_variables["bottom"] = bottom
return template_variables
def render_real(config: Settings, summary: dict) -> dict:
varid = summary["varid"]
template_variables = render_common(config, summary)
image_format = config.plot.image_format
if summary["min"] >= 0:
name = "Real number (ℝ<sub>≥0</sub>)"
else:
name = "Real number (ℝ)"
# Top
info = VariableInfo(
summary["varid"],
summary["varname"],
name,
summary["alerts"],
summary["description"],
)
table1 = Table([
{
"name": "Distinct",
"value": fmt(summary["n_distinct"]),
"alert": "n_distinct" in summary["alert_fields"],
},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
"alert": "p_distinct" in summary["alert_fields"],
},
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": "n_missing" in summary["alert_fields"],
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": "p_missing" in summary["alert_fields"],
},
{
"name": "Infinite",
"value": fmt(summary["n_infinite"]),
"alert": "n_infinite" in summary["alert_fields"],
},
{
"name": "Infinite (%)",
"value": fmt_percent(summary["p_infinite"]),
"alert": "p_infinite" in summary["alert_fields"],
},
{
"name":
"Mean",
"value":
fmt_numeric(summary["mean"], precision=config.report.precision),
"alert":
False,
},
])
table2 = Table([
{
"name": "Minimum",
"value": fmt_numeric(summary["min"],
precision=config.report.precision),
"alert": False,
},
{
"name": "Maximum",
"value": fmt_numeric(summary["max"],
precision=config.report.precision),
"alert": False,
},
{
"name": "Zeros",
"value": fmt(summary["n_zeros"]),
"alert": "n_zeros" in summary["alert_fields"],
},
{
"name": "Zeros (%)",
"value": fmt_percent(summary["p_zeros"]),
"alert": "p_zeros" in summary["alert_fields"],
},
{
"name": "Negative",
"value": fmt(summary["n_negative"]),
"alert": False,
},
{
"name": "Negative (%)",
"value": fmt_percent(summary["p_negative"]),
"alert": False,
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
])
mini_histo = Image(
mini_histogram(config, *summary["histogram"]),
image_format=image_format,
alt="Mini histogram",
)
template_variables["top"] = Container([info, table1, table2, mini_histo],
sequence_type="grid")
quantile_statistics = Table(
[
{
"name":
"Minimum",
"value":
fmt_numeric(summary["min"], precision=config.report.precision),
},
{
"name":
"5-th percentile",
"value":
fmt_numeric(summary["5%"], precision=config.report.precision),
},
{
"name":
"Q1",
"value":
fmt_numeric(summary["25%"], precision=config.report.precision),
},
{
"name":
"median",
"value":
fmt_numeric(summary["50%"], precision=config.report.precision),
},
{
"name":
"Q3",
"value":
fmt_numeric(summary["75%"], precision=config.report.precision),
},
{
"name":
"95-th percentile",
"value":
fmt_numeric(summary["95%"], precision=config.report.precision),
},
{
"name":
"Maximum",
"value":
fmt_numeric(summary["max"], precision=config.report.precision),
},
{
"name":
"Range",
"value":
fmt_numeric(summary["range"],
precision=config.report.precision),
},
{
"name":
"Interquartile range (IQR)",
"value":
fmt_numeric(summary["iqr"], precision=config.report.precision),
},
],
name="Quantile statistics",
)
descriptive_statistics = Table(
[
{
"name":
"Standard deviation",
"value":
fmt_numeric(summary["std"], precision=config.report.precision),
},
{
"name":
"Coefficient of variation (CV)",
"value":
fmt_numeric(summary["cv"], precision=config.report.precision),
},
{
"name":
"Kurtosis",
"value":
fmt_numeric(summary["kurtosis"],
precision=config.report.precision),
},
{
"name":
"Mean",
"value":
fmt_numeric(summary["mean"],
precision=config.report.precision),
},
{
"name":
"Median Absolute Deviation (MAD)",
"value":
fmt_numeric(summary["mad"], precision=config.report.precision),
},
{
"name":
"Skewness",
"value":
fmt_numeric(summary["skewness"],
precision=config.report.precision),
"class":
"alert" if "skewness" in summary["alert_fields"] else "",
},
{
"name":
"Sum",
"value":
fmt_numeric(summary["sum"], precision=config.report.precision),
},
{
"name":
"Variance",
"value":
fmt_numeric(summary["variance"],
precision=config.report.precision),
},
{
"name": "Monotonicity",
"value": fmt_monotonic(summary["monotonic"]),
},
],
name="Descriptive statistics",
)
statistics = Container(
[quantile_statistics, descriptive_statistics],
anchor_id=f"{varid}statistics",
name="Statistics",
sequence_type="grid",
)
hist = Image(
histogram(config, *summary["histogram"]),
image_format=image_format,
alt="Histogram",
caption=
f"<strong>Histogram with fixed size bins</strong> (bins={len(summary['histogram'][1]) - 1})",
name="Histogram",
anchor_id=f"{varid}histogram",
)
fq = FrequencyTable(
template_variables["freq_table_rows"],
name="Common values",
anchor_id=f"{varid}common_values",
redact=False,
)
evs = Container(
[
FrequencyTable(
template_variables["firstn_expanded"],
name=f"Minimum {config.n_extreme_obs} values",
anchor_id=f"{varid}firstn",
redact=False,
),
FrequencyTable(
template_variables["lastn_expanded"],
name=f"Maximum {config.n_extreme_obs} values",
anchor_id=f"{varid}lastn",
redact=False,
),
],
sequence_type="tabs",
name="Extreme values",
anchor_id=f"{varid}extreme_values",
)
template_variables["bottom"] = Container(
[statistics, hist, fq, evs],
sequence_type="tabs",
anchor_id=f"{varid}bottom",
)
return template_variables
def render_url(config: Settings, summary: dict) -> dict:
varid = summary["varid"]
n_freq_table_max = config.n_freq_table_max
n_obs_cat = config.vars.cat.n_obs
redact = config.vars.cat.redact
template_variables = render_common(config, summary)
keys = ["scheme", "netloc", "path", "query", "fragment"]
for url_part in keys:
template_variables[f"freqtable_{url_part}"] = freq_table(
freqtable=summary[f"{url_part}_counts"],
n=summary["n"],
max_number_to_print=n_freq_table_max,
)
full_frequency_table = FrequencyTable(
template_variables["freq_table_rows"],
name="Full",
anchor_id=f"{varid}full_frequency",
redact=redact,
)
scheme_frequency_table = FrequencyTable(
template_variables["freqtable_scheme"],
name="Scheme",
anchor_id=f"{varid}scheme_frequency",
redact=redact,
)
netloc_frequency_table = FrequencyTable(
template_variables["freqtable_netloc"],
name="Netloc",
anchor_id=f"{varid}netloc_frequency",
redact=redact,
)
path_frequency_table = FrequencyTable(
template_variables["freqtable_path"],
name="Path",
anchor_id=f"{varid}path_frequency",
redact=redact,
)
query_frequency_table = FrequencyTable(
template_variables["freqtable_query"],
name="Query",
anchor_id=f"{varid}query_frequency",
redact=redact,
)
fragment_frequency_table = FrequencyTable(
template_variables["freqtable_fragment"],
name="Fragment",
anchor_id=f"{varid}fragment_frequency",
redact=redact,
)
items = [
full_frequency_table,
scheme_frequency_table,
netloc_frequency_table,
path_frequency_table,
query_frequency_table,
fragment_frequency_table,
]
template_variables["bottom"] = Container(items,
sequence_type="tabs",
name="url stats",
anchor_id=f"{varid}urlstats")
# Element composition
info = VariableInfo(
summary["varid"],
summary["varname"],
"URL",
summary["warnings"],
summary["description"],
)
table = Table([
{
"name": "Distinct",
"value": fmt(summary["n_distinct"]),
"alert": "n_distinct" in summary["warn_fields"],
},
{
"name": "Distinct (%)",
"value": fmt_percent(summary["p_distinct"]),
"alert": "p_distinct" in summary["warn_fields"],
},
{
"name": "Missing",
"value": fmt(summary["n_missing"]),
"alert": "n_missing" in summary["warn_fields"],
},
{
"name": "Missing (%)",
"value": fmt_percent(summary["p_missing"]),
"alert": "p_missing" in summary["warn_fields"],
},
{
"name": "Memory size",
"value": fmt_bytesize(summary["memory_size"]),
"alert": False,
},
])
fqm = FrequencyTableSmall(
freq_table(
freqtable=summary["value_counts_without_nan"],
n=summary["n"],
max_number_to_print=n_obs_cat,
),
redact=redact,
)
template_variables["top"] = Container([info, table, fqm],
sequence_type="grid")
return template_variables
