How to use the pandera.Hypothesis function in pandera
To help you get started, we’ve selected a few pandera examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
pandera-dev / pandera / tests / test_pandera.py View on Github 
# Initialise the different ways of calling a test:
schema_pass_ttest_on_alpha_val_1 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis.two_sample_ttest(
sample1="M",
sample2="F",
groupby="sex",
relationship="greater_than",
alpha=0.5),
]),
"sex": Column(String)
})
schema_pass_ttest_on_alpha_val_2 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis(test=stats.ttest_ind,
samples=["M", "F"],
groupby="sex",
relationship="greater_than",
relationship_kwargs={"alpha": 0.5}
),
]),
"sex": Column(String)
})
schema_pass_ttest_on_alpha_val_3 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis.two_sample_ttest(
sample1="M",
sample2="F",
groupby="sex",
relationship="greater_than",# Initialise the different ways of calling a test:
schema_pass_ttest_on_alpha_val_1 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis.two_sample_ttest(
sample1="M",
sample2="F",
groupby="sex",
relationship="greater_than",
alpha=0.5),
]),
"sex": Column(String)
})
schema_pass_ttest_on_alpha_val_2 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis(test=stats.ttest_ind,
samples=["M", "F"],
groupby="sex",
relationship="greater_than",
relationship_kwargs={"alpha": 0.5}
),
]),
"sex": Column(String)
})
schema_pass_ttest_on_alpha_val_3 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis.two_sample_ttest(
sample1="M",
sample2="F",
groupby="sex",
relationship="greater_than",schema_fail_ttest_on_alpha_val_1 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis.two_sample_ttest(
sample1="M",
sample2="F",
groupby="sex",
relationship="greater_than",
alpha=0.05),
]),
"sex": Column(String)
})
schema_fail_ttest_on_alpha_val_2 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis(test=stats.ttest_ind,
samples=["M", "F"],
groupby="sex",
relationship="greater_than",
relationship_kwargs={"alpha": 0.05}),
]),
"sex": Column(String)
})
schema_fail_ttest_on_alpha_val_3 = DataFrameSchema({
"height_in_feet": Column(Float, [
Hypothesis.two_sample_ttest(
sample1="M",
sample2="F",
groupby="sex",
relationship="greater_than",
alpha=0.05),columns={
"col1": Column(Int),
"col2": Column(Int),
},
checks=[
# two-sample test
Hypothesis(
test=stats.ttest_ind,
samples=["col1", "col2"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
relationship_kwargs={"alpha": 0.5},
),
# one-sample test
Hypothesis(
test=stats.ttest_1samp,
samples=["col1"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
test_kwargs={"popmean": 50},
relationship_kwargs={"alpha": 0.01},
),
]
)
hypothesis_check_schema.validate(df)
# raise error when using groupby
hypothesis_check_schema_groupby = DataFrameSchema(
columns={def test_dataframe_hypothesis_checks():
df = pd.DataFrame({
"col1": range(100, 201),
"col2": range(0, 101),
})
hypothesis_check_schema = DataFrameSchema(
columns={
"col1": Column(Int),
"col2": Column(Int),
},
checks=[
# two-sample test
Hypothesis(
test=stats.ttest_ind,
samples=["col1", "col2"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
relationship_kwargs={"alpha": 0.5},
),
# one-sample test
Hypothesis(
test=stats.ttest_1samp,
samples=["col1"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
test_kwargs={"popmean": 50},
relationship_kwargs={"alpha": 0.01},relationship_kwargs={"alpha": 0.01},
),
]
)
hypothesis_check_schema.validate(df)
# raise error when using groupby
hypothesis_check_schema_groupby = DataFrameSchema(
columns={
"col1": Column(Int),
"col2": Column(Int),
},
checks=[
# two-sample test
Hypothesis(
test=stats.ttest_ind,
samples=["col1", "col2"],
groupby="col3",
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
relationship_kwargs={"alpha": 0.5},
),
]
)
with pytest.raises(errors.SchemaDefinitionError):
hypothesis_check_schema_groupby.validate(df)columns={
"col1": Column(Int),
"col2": Column(Int),
},
checks=[
# two-sample test
Hypothesis(
test=stats.ttest_ind,
samples=["col1", "col2"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
relationship_kwargs={"alpha": 0.5},
),
# one-sample test
Hypothesis(
test=stats.ttest_1samp,
samples=["col1"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
test_kwargs={"popmean": 50},
relationship_kwargs={"alpha": 0.01},
),
]
)
hypothesis_check_schema.validate(df)
# raise error when using groupby
hypothesis_check_schema_groupby = DataFrameSchema(
columns={def test_dataframe_hypothesis_checks():
df = pd.DataFrame({
"col1": range(100, 201),
"col2": range(0, 101),
})
hypothesis_check_schema = DataFrameSchema(
columns={
"col1": Column(Int),
"col2": Column(Int),
},
checks=[
# two-sample test
Hypothesis(
test=stats.ttest_ind,
samples=["col1", "col2"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
relationship_kwargs={"alpha": 0.5},
),
# one-sample test
Hypothesis(
test=stats.ttest_1samp,
samples=["col1"],
relationship=lambda stat, pvalue, alpha=0.01: (
stat > 0 and pvalue / 2 < alpha
),
test_kwargs={"popmean": 50},
relationship_kwargs={"alpha": 0.01},pandera
A light-weight and flexible data validation and testing tool for statistical data objects.
Package Health Score
91 / 100Popular pandera functions
- pandera.Check
- pandera.check_input
- pandera.check_output
- pandera.Column
- pandera.DataFrameSchema
- pandera.DateTime
- pandera.dtypes
- pandera.dtypes.PandasDtype
- pandera.errors
- pandera.errors.SchemaError
- pandera.errors.SchemaInitError
- pandera.Float
- pandera.Hypothesis
- pandera.Hypothesis.two_sample_ttest
- pandera.Index
- pandera.Int
- pandera.pandera.PandasDtype
- pandera.pandera.SchemaError
- pandera.SeriesSchema
- pandera.String