rurlus / diptest Goto Github PK

IndexError
Traceback (most recent call last)
----> 6 dip, pval = diptest.diptest(s)

File /env/lib/python3.10/site-packages/diptest/diptest.py:198, in diptest(x, full_output, sort_x, allow_zero, boot_pval, n_boot, n_threads, seed, stream)
    196     pval = func(**kwargs)
    197 else:
--> 198     pval = Consts.compute_pval_interpolation(n, dip)
    200 if full_output:
    201     return dip, pval, r[1]

File /home/paulo/routers/env/lib/python3.10/site-packages/diptest/consts.py:83, in Consts.compute_pval_interpolation(cls, n, dip)
     80 i1 = min(cls._CRIT_VALS.shape[0], i1)
     82 # Interpolate on sqrt(n)
---> 83 n0, n1 = cls._SAMPLE_SIZE[[i0, i1]]
     85 y0 = np.sqrt(n0) * cls._CRIT_VALS[i0]
     86 sD = np.sqrt(n) * dip

IndexError: index 21 is out of bounds for axis 0 with size 21

## Full version (this got error)
s = df.signal
# only the dip statistic
dip = diptest.dipstat(s)

# both the dip statistic and p-value
dip, pval = diptest.diptest(s)
print(dip, pval)

## Filtered version (run well)
s = df.query("col1 == 'A'").signal
# only the dip statistic
dip = diptest.dipstat(s)

# both the dip statistic and p-value
dip, pval = diptest.diptest(s)
print(dip, pval)
# 0.15625745645430683 0.0

import diptest 
x = df['my_distribution_data'].values
dip, pval = diptest.diptest(x)
print(dip,pval)

if (ifault == 1) {
    throw std::runtime_error("N must be >= 1.");
} else if (ifault == 2) {
    throw std::runtime_error("x must be sorted in ascending error.");
}