ethen8181 / machine-learning Goto Github PK

The formula for ECE (expected calibration error) includes the size of each bin as weight in the weighted average of the squared errors (|Bm|/n)

The function that uses this formula in the code is called "compute_calibration_error":
https://github.com/ethen8181/machine-learning/blob/master/model_selection/prob_calibration/calibration_module/utils.py#L66

(Link to the code line that sums the errors without weight for each bin size)

Although the bins are created so that they are of approximately equal size, they might differ slightly, and the code does not take this into account, i think the bin_error should be multiplied by the bin size, and the sum of all the errors divided by the number of samples (len of y_true for example) instead of the number of bins (in line 68).

I hope my issue is clear and easy to understand, if not, feel free to ask me for clarification.

Ethen, I have an interesting finding.

If we change the solver of LogisticRegression from 'liblinear' to the default 'lbfgs', theeffect will not be significant with pvalue=0.1605910849805837. What the reason behind this change? why you choose 'liblinear' instead of any other solver? Thanks!

class MultiHeadAttention(nn.Module):

in this class, it does not implement the scale of the multiplication of Query and Key.
and in the forward function, it seems that the funcation should return linear_proj , not output?

Hello!

I found an AI-Specific Code smell in your project.
The smell is called: Columns and DataType Not Explicitly Set

You can find more information about it in this paper: https://dl.acm.org/doi/abs/10.1145/3522664.3528620.

According to the paper, the smell is described as follows:

Example:

### Pandas Column Selection
import pandas as pd
df = pd.read_csv('data.csv')
+ df = df[['col1', 'col2', 'col3']]

### Pandas Set DataType
import pandas as pd
- df = pd.read_csv('data.csv')
+ df = pd.read_csv('data.csv', dtype={'col1': 'str', 'col2': 'int', 'col3': 'float'})

You can find the code related to this smell in this link: https://github.com/ethen8181/machine-learning/blob/916fc7fe0e5e788a1cc8b8f4d24d44f05c492d5e/model_selection/prob_calibration/calibration_module/utils.py#L280-L300.

I also found instances of this smell in other files, such as:

File: https://github.com/ethen8181/machine-learning/blob/master/big_data/sparkml/get_data.py#L21-L31 Line: 26
File: https://github.com/ethen8181/machine-learning/blob/master/data_science_is_software/src/features/build_features.py#L4-L14 Line: 9
File: https://github.com/ethen8181/machine-learning/blob/master/deep_learning/contrastive/clip/clip/utils.py#L5-L15 Line: 10
File: https://github.com/ethen8181/machine-learning/blob/master/model_selection/partial_dependence/partial_dependence.py#L307-L317 Line: 312
.

I hope this information is helpful!

z variable isn't used in interval calculation:

def sanity_check(size1, size2, significance = 0.05):
    n = size1 + size2
    confidence = 1 - significance
    z = stats.norm.ppf(confidence + significance / 2)
    confint = n * 0.5 + np.array([-1, 1]) * np.sqrt(n * 0.5 * 0.5)
    return confint

Source: http://ethen8181.github.io/machine-learning/ab_tests/frequentist_ab_test.html#Sanity-Check