smazzanti

def xray(var):
    """Return name of variable and its state,
        for logging purposes."""
    
    import inspect, re

    string = inspect.getframeinfo(
        inspect.getouterframes(
        inspect.currentframe()
        )[1][0]).code_context[0]

smazzanti

def regression_roc_auc_score(y_true, y_pred, num_rounds = 10000):
  """
  Computes Regression-ROC-AUC-score.
  
  Parameters:
  ----------
  y_true: array-like of shape (n_samples,). Binary or continuous target variable.
  y_pred: array-like of shape (n_samples,). Target scores.
  num_rounds: int or string. If integer, number of random pairs of observations. 
              If string, 'exact', all possible pairs of observations will be evaluated.

smazzanti

def naive_roc_auc_score(y_true, y_pred):
    
  num_same_sign = 0
  num_pairs = 0
  
  for a in range(len(y_true)):
    for b in range(len(y_true)):
      if y_true[a] > y_true[b]:
        num_pairs += 1
        if y_pred[a] > y_pred[b]:

smazzanti

import pandas as pd
from sklearn.feature_selection import f_regression

# inputs:
#    X: pandas.DataFrame, features
#    y: pandas.Series, target variable
#    K: number of features to select

# compute F-statistics and initialize correlation matrix
F = pd.Series(f_regression(X, y)[0], index = X.columns)

smazzanti

import pandas as pd
from sklearn.feature_selection import f_regression

# inputs:
#    X: pandas.DataFrame, features
#    y: pandas.Series, target variable
#    K: number of features to select

# compute F-statistics and correlations
F = pd.Series(f_regression(X, y)[0], index = X.columns)

smazzanti

y_level_ones = x.replace(y.groupby(x).apply(lambda l: (l == 1).sum()))
y_level_zeros = x.replace(y.groupby(x).apply(lambda l: (l == 0).sum()))
y_ones = (y == 1).sum()
y_zeros = (y == 0).sum()
nominator = y_level_ones / y_ones
denominator = y_level_zeros / y_zeros
woe_encoder = np.log(nominator / denominator)

smazzanti

y_level_except_self = x.to_frame().apply(
  lambda row: y[x == row['x']].drop(row.name).to_list(), 
  axis = 1
)
leave_one_out_encoding = y_level_except_self.apply(np.mean)

smazzanti

y_mean = y.mean()
y_level_before_self = x.to_frame().apply(
  lambda row: y[(x == row['x']) & (y.index < row.name)].to_list(), 
  axis = 1
)
catboost_encoding = y_level_before_self.apply(
  lambda ylbs: (sum(ylbs) + y_mean * a) / (len(ylbs) + a)
)

smazzanti

model = smf.mixedlm(formula = 'y ~ 1', data = y.to_frame(), groups = x).fit()
intercept = model.params['Intercept']
random_effect = x.replace({k: float(v) for k, v in model.random_effects.items()})
glmm_encoding = intercept + random_effect

smazzanti

y_mean = y.mean()
y_var = y.var()
y_level_mean = x.replace(y.groupby(x).mean())
y_level_var = x.replace(y.groupby(x).var())

weight = 1 - (y_level_var / (y_var + y_level_var) * (len(set(x)) - 3) / (len(set(x)) - 1))
james_stein_encoding = y_level_mean * weight + y_mean * (1 - weight)