def test_set_variable():
r = ProfileReport(pool_size=3)
assert config["pool_size"].get(int) == 3
assert config["html"]["minify_html"].get(bool)
r.set_variable("pool_size", 1)
assert config["pool_size"].get(int) == 1
r.set_variable("html.minify_html", False)
assert not config["html"]["minify_html"].get(bool)
r.set_variable("html", {"minify_html": True})
assert config["html"]["minify_html"].get(bool)
def test_config_shorthands():
r = ProfileReport(
samples=None, correlations=None, missing_diagrams=None, duplicates=None
)
assert config["samples"]["head"].get(int) == 0
assert config["samples"]["tail"].get(int) == 0
assert config["duplicates"]["head"].get(int) == 0
assert not config["correlations"]["spearman"]["calculate"].get(bool)
assert not config["missing_diagrams"]["bar"].get(bool)
r = ProfileReport()
r.set_variable("samples", None)
r.set_variable("duplicates", None)
r.set_variable("correlations", None)
r.set_variable("missing_diagrams", None)
assert config["samples"]["head"].get(int) == 0
assert config["samples"]["tail"].get(int) == 0
assert config["duplicates"]["head"].get(int) == 0
assert not config["correlations"]["spearman"]["calculate"].get(bool)
assert not config["missing_diagrams"]["bar"].get(bool)
"hours-per-week",
"native-country",
],
)
# Prepare missing values
df = df.replace("\\?", np.nan, regex=True)
# Initialize the report
profile = ProfileReport(df, title="Census Dataset", explorative=True)
# show column definition
definitions = json.load(open(f"census_column_definition.json"))
profile.set_variable(
"dataset",
{
"description":
'Predict whether income exceeds $50K/yr based on census data. Also known as "Census Income" dataset. Extraction was done by Barry Becker from the 1994 Census database. A set of reasonably clean records was extracted using the following conditions: ((AAGE>16) && (AGI>100) && (AFNLWGT>1)&& (HRSWK>0)). Prediction task is to determine whether a person makes over 50K a year.',
"copyright_year": "1996",
"author": "Ronny Kohavi and Barry Becker",
"creator": "Barry Becker",
"url": "https://archive.ics.uci.edu/ml/datasets/adult",
},
)
profile.set_variable("variables.descriptions", definitions)
# Only show the descriptions in the overview
profile.set_variable("show_variable_description", False)
profile.to_file(Path("./census_report.html"))
# PP only accepts absolute paths
series = series.apply(lambda x: x.absolute()).apply(str)
df = pd.DataFrame(series)
# Generate the profile report
profile = ProfileReport(
df,
title="Example showcasing EXIF data (Kaggle 5 Celebrity Faces Dataset)",
# Disable what's not in our focus
duplicates=None,
correlations=None,
samples=None,
missing_diagrams=None,
# Enable files and images (off by default, as it uses relatively expensive computations when not interested)
explorative=True,
)
# We can also configure the report like this
profile.set_variable(
"variables.descriptions",
{
"files": "The 5 Celebrity Faces Dataset found on Kaggle (dansbecker/5-celebrity-faces-dataset)."
},
)
# Save the report
profile.to_file("celebrity-faces.html")
# The analysis reveals that quite some photos contain "hidden" EXIF information.
# This can be both interesting as troublesome, depending on the situation.
# Generate the profile report
profile = ProfileReport(
df,
title=
"Example of summarization of an image dataset (Kaggle Cat and Dog dataset)",
# We will not need those
samples=None,
missing_diagrams=None,
)
# Give our variable a description
profile.set_variable(
"variables.descriptions",
{
"files":
"Paths linking to the cats and dogs found https://www.kaggle.com/tongpython/cat-and-dog."
},
)
# If the number of samples is above this threshold, the scatter plots are replaced with hexbin plots
# We are just over the threshold of 10.000 samples, so let's increase the limit.
profile.set_variable("plot.scatter_threshold", 25000)
# Enable files and images (off by default, as it uses relatively expensive computations when not interested)
profile.set_variable("vars.path.active", True)
profile.set_variable("vars.file.active", True)
profile.set_variable("vars.image.active", True)
# No exif found, so turn off expensive computation
profile.set_variable("vars.image.exif", False)
#
# If a column is not present as specified by the schema, a `SchemaError` is raised.
# %%
corrupted_data = fatal_encounters.drop("Subject's age", axis="columns")
try:
clean_columns(corrupted_data)
except pa.errors.SchemaError as exc:
print(exc)
# %% [markdown] slideshow={"slide_type": "slide"}
# ### Explore the Data with [`pandas-profiling`](https://github.com/pandas-profiling/pandas-profiling)
# %% tags=["hide_input"]
profile = ProfileReport(fatal_encounters_clean_columns, minimal=True)
profile.set_variable("html.navbar_show", False)
profile.to_notebook_iframe()
# %% [markdown] slideshow={"slide_type": "slide"}
# ### Declare the Training Data Schema
# %% slideshow={"slide_type": "skip"}
genders = ["female", "male", "transgender", "transexual"]
races = [
"african_american_black", "asian_pacific_islander",
"european_american_white", "hispanic_latino", "middle_eastern",
"native_american_alaskan", "race_unspecified",
]
causes_of_death = [
'asphyxiated_restrained', 'beaten_bludgeoned_with_instrument',
'burned_smoke_inhalation', 'chemical_agent_pepper_spray',
