binomial_test_fl()

This article describes the binomial_test_fl() user-defined function.

The function binomial_test_fl() is a UDF (user-defined function) that performs the binomial test.

Syntax

T | invoke binomial_test_fl(successes, trials [,success_prob [, alt_hypotheis ]])

Parameters

NameTypeRequiredDescription
successesstring✔️The name of the column containing the number of success results.
trialsstring✔️The name of the column containing the total number of trials.
p_valuestring✔️The name of the column to store the results.
success_probrealThe success probability. The default is 0.5.
alt_hypotheisstringThe alternate hypothesis can be two-sided, greater, or less. The default is two-sided.

Function definition

You can define the function by either embedding its code as a query-defined function, or creating it as a stored function in your database, as follows:

Query-defined

Define the function using the following let statement. No permissions are required.

let binomial_test_fl = (tbl:(*), successes:string, trials:string, p_value:string, success_prob:real=0.5, alt_hypotheis:string='two-sided')
{
    let kwargs = bag_pack('successes', successes, 'trials', trials, 'p_value', p_value, 'success_prob', success_prob, 'alt_hypotheis', alt_hypotheis);
    let code = ```if 1:
        from scipy import stats
        
        successes = kargs["successes"]
        trials = kargs["trials"]
        p_value = kargs["p_value"]
        success_prob = kargs["success_prob"]
        alt_hypotheis = kargs["alt_hypotheis"]
        
        def func(row, prob, h1):
            pv = stats.binom_test(row[successes], row[trials], p=prob, alternative=h1)
            return pv
        result = df
        result[p_value] = df.apply(func, axis=1, args=(success_prob, alt_hypotheis), result_type="expand")
    ```;
    tbl
    | evaluate python(typeof(*), code, kwargs)
};
// Write your query to use the function here.

Stored

Define the stored function once using the following .create function. Database User permissions are required.

.create-or-alter function with (folder = "Packages\\Stats", docstring = "Binomial test")
binomial_test_fl(tbl:(*), successes:string, trials:string, p_value:string, success_prob:real=0.5, alt_hypotheis:string='two-sided')
{
    let kwargs = bag_pack('successes', successes, 'trials', trials, 'p_value', p_value, 'success_prob', success_prob, 'alt_hypotheis', alt_hypotheis);
    let code = ```if 1:
        from scipy import stats
        
        successes = kargs["successes"]
        trials = kargs["trials"]
        p_value = kargs["p_value"]
        success_prob = kargs["success_prob"]
        alt_hypotheis = kargs["alt_hypotheis"]
        
        def func(row, prob, h1):
            pv = stats.binom_test(row[successes], row[trials], p=prob, alternative=h1)
            return pv
        result = df
        result[p_value] = df.apply(func, axis=1, args=(success_prob, alt_hypotheis), result_type="expand")
    ```;
    tbl
    | evaluate python(typeof(*), code, kwargs)
}

Example

The following example uses the invoke operator to run the function.

Query-defined

To use a query-defined function, invoke it after the embedded function definition.

let binomial_test_fl = (tbl:(*), successes:string, trials:string, p_value:string, success_prob:real=0.5, alt_hypotheis:string='two-sided')
{
    let kwargs = bag_pack('successes', successes, 'trials', trials, 'p_value', p_value, 'success_prob', success_prob, 'alt_hypotheis', alt_hypotheis);
    let code = ```if 1:
        from scipy import stats
        
        successes = kargs["successes"]
        trials = kargs["trials"]
        p_value = kargs["p_value"]
        success_prob = kargs["success_prob"]
        alt_hypotheis = kargs["alt_hypotheis"]
        
        def func(row, prob, h1):
            pv = stats.binom_test(row[successes], row[trials], p=prob, alternative=h1)
            return pv
        result = df
        result[p_value] = df.apply(func, axis=1, args=(success_prob, alt_hypotheis), result_type="expand")
    ```;
    tbl
    | evaluate python(typeof(*), code, kwargs)
};
datatable(id:string, x:int, n:int) [
'Test #1', 3, 5,
'Test #2', 5, 5,
'Test #3', 3, 15
]
| extend p_val=0.0
| invoke binomial_test_fl('x', 'n', 'p_val', success_prob=0.2, alt_hypotheis='greater')

Stored

datatable(id:string, x:int, n:int) [
'Test #1', 3, 5,
'Test #2', 5, 5,
'Test #3', 3, 15
]
| extend p_val=0.0
| invoke binomial_test_fl('x', 'n', 'p_val', success_prob=0.2, alt_hypotheis='greater')

Output

idxnp_val
Test #1350.05792
Test #2550.00032
Test #33150.601976790745087