def test_one_sample_hypothesis():
"""Check one sample ttest."""
schema = DataFrameSchema({
"height_in_feet": Column(
Float, [
Hypothesis.one_sample_ttest(
popmean=5,
relationship="greater_than",
alpha=0.1),
]
),
})
subset_schema = DataFrameSchema({
"group": Column(String),
"height_in_feet": Column(
Float, [
Hypothesis.one_sample_ttest(
sample="A",
groupby="group",
popmean=5,
relationship="greater_than",
alpha=0.1),
]
),
})
df = (
pd.DataFrame({
"height_in_feet": [8.1, 7, 6.5, 6.7, 5.1],
"group": ["A", "A", "B", "B", "A"],
})
)
schema.validate(df)
subset_schema.validate(df)
percent_accidental = fatal_encounters_clean.disposition_accidental.mean()
display(Markdown(f"{percent_accidental * 100:0.02f}%"))
# %% [markdown] slideshow={"slide_type": "subslide"}
# **Hypothesis**: "the `disposition_accidental` target has a
# class balance of ~2.75%"
# %%
from pandera import Hypothesis
# use the Column object as a stand-alone schema object
target_schema = Column(
pa.Bool,
name="disposition_accidental",
checks=Hypothesis.one_sample_ttest(
popmean=0.0275, relationship="equal", alpha=0.01
)
)
target_schema(fatal_encounters_clean);
# %% [markdown] slideshow={"slide_type": "skip"}
# What's the age distribution in the dataset?
# %% tags=["hide_input"] slideshow={"slide_type": "skip"}
fatal_encounters_clean.age.plot.hist(figsize=(8, 5)).set_xlabel("age");
# %% [markdown] slideshow={"slide_type": "skip"}
# **Hypothesis** check: "the `age` column is right-skewed"
# %% slideshow={"slide_type": "skip"}
