Note
Go to the end to download the full example code
Custom Scoring Function for Regression#
This example uses the ‘diabetes’ data from sklearn datasets and performs a regression analysis using a Ridge Regression model. As scorers, it uses scikit-learn, julearn and a custom metric defined by the user.
# Authors: Shammi More <s.more@fz-juelich.de>
# Federico Raimondo <f.raimondo@fz-juelich.de>
#
# License: AGPL
import pandas as pd
import scipy
from sklearn.datasets import load_diabetes
from sklearn.metrics import make_scorer
from julearn.scoring import register_scorer
from julearn import run_cross_validation
from julearn.utils import configure_logging
Set the logging level to info to see extra information
configure_logging(level="INFO")
2023-07-19 12:42:16,113 - julearn - INFO - ===== Lib Versions =====
2023-07-19 12:42:16,113 - julearn - INFO - numpy: 1.25.1
2023-07-19 12:42:16,113 - julearn - INFO - scipy: 1.11.1
2023-07-19 12:42:16,113 - julearn - INFO - sklearn: 1.3.0
2023-07-19 12:42:16,113 - julearn - INFO - pandas: 2.0.3
2023-07-19 12:42:16,113 - julearn - INFO - julearn: 0.3.1.dev1
2023-07-19 12:42:16,113 - julearn - INFO - ========================
load the diabetes data from sklearn as a pandas dataframe
features, target = load_diabetes(return_X_y=True, as_frame=True)
Dataset contains ten variables age, sex, body mass index, average blood pressure, and six blood serum measurements (s1-s6) diabetes patients and a quantitative measure of disease progression one year after baseline which is the target we are interested in predicting.
print("Features: \n", features.head()) # type: ignore
print("Target: \n", target.describe()) # type: ignore
Features:
age sex bmi ... s4 s5 s6
0 0.038076 0.050680 0.061696 ... -0.002592 0.019907 -0.017646
1 -0.001882 -0.044642 -0.051474 ... -0.039493 -0.068332 -0.092204
2 0.085299 0.050680 0.044451 ... -0.002592 0.002861 -0.025930
3 -0.089063 -0.044642 -0.011595 ... 0.034309 0.022688 -0.009362
4 0.005383 -0.044642 -0.036385 ... -0.002592 -0.031988 -0.046641
[5 rows x 10 columns]
Target:
count 442.000000
mean 152.133484
std 77.093005
min 25.000000
25% 87.000000
50% 140.500000
75% 211.500000
max 346.000000
Name: target, dtype: float64
Let’s combine features and target together in one dataframe and define X and y
Train a ridge regression model on train dataset and use mean absolute error for scoring
2023-07-19 12:42:16,130 - julearn - INFO - ==== Input Data ====
2023-07-19 12:42:16,131 - julearn - INFO - Using dataframe as input
2023-07-19 12:42:16,131 - julearn - INFO - Features: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']
2023-07-19 12:42:16,131 - julearn - INFO - Target: target
2023-07-19 12:42:16,131 - julearn - INFO - Expanded features: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']
2023-07-19 12:42:16,131 - julearn - INFO - X_types:{}
2023-07-19 12:42:16,131 - julearn - WARNING - The following columns are not defined in X_types: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']. They will be treated as continuous.
/home/runner/work/julearn/julearn/julearn/utils/logging.py:238: RuntimeWarning: The following columns are not defined in X_types: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']. They will be treated as continuous.
warn(msg, category=category)
2023-07-19 12:42:16,132 - julearn - INFO - ====================
2023-07-19 12:42:16,132 - julearn - INFO -
2023-07-19 12:42:16,132 - julearn - INFO - Adding step zscore that applies to ColumnTypes<types={'continuous'}; pattern=(?:__:type:__continuous)>
2023-07-19 12:42:16,132 - julearn - INFO - Step added
2023-07-19 12:42:16,132 - julearn - INFO - Adding step ridge that applies to ColumnTypes<types={'continuous'}; pattern=(?:__:type:__continuous)>
2023-07-19 12:42:16,132 - julearn - INFO - Step added
2023-07-19 12:42:16,133 - julearn - INFO - = Model Parameters =
2023-07-19 12:42:16,133 - julearn - INFO - ====================
2023-07-19 12:42:16,133 - julearn - INFO -
2023-07-19 12:42:16,133 - julearn - INFO - = Data Information =
2023-07-19 12:42:16,133 - julearn - INFO - Problem type: regression
2023-07-19 12:42:16,133 - julearn - INFO - Number of samples: 442
2023-07-19 12:42:16,133 - julearn - INFO - Number of features: 10
2023-07-19 12:42:16,133 - julearn - INFO - ====================
2023-07-19 12:42:16,133 - julearn - INFO -
2023-07-19 12:42:16,133 - julearn - INFO - Target type: float64
2023-07-19 12:42:16,134 - julearn - INFO - Using outer CV scheme KFold(n_splits=5, random_state=None, shuffle=False)
The scores dataframe has all the values for each CV split.
print(scores.head())
fit_time score_time ... fold cv_mdsum
0 0.005866 0.002948 ... 0 b10eef89b4192178d482d7a1587a248a
1 0.005472 0.002908 ... 1 b10eef89b4192178d482d7a1587a248a
2 0.005421 0.002907 ... 2 b10eef89b4192178d482d7a1587a248a
3 0.005425 0.002930 ... 3 b10eef89b4192178d482d7a1587a248a
4 0.005465 0.002977 ... 4 b10eef89b4192178d482d7a1587a248a
[5 rows x 8 columns]
Mean value of mean absolute error across CV
print(scores["test_score"].mean() * -1) # type: ignore
44.264653948271885
Now do the same thing, but use mean absolute error and Pearson product-moment correlation coefficient (squared) as scoring functions
2023-07-19 12:42:16,194 - julearn - INFO - ==== Input Data ====
2023-07-19 12:42:16,194 - julearn - INFO - Using dataframe as input
2023-07-19 12:42:16,194 - julearn - INFO - Features: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']
2023-07-19 12:42:16,194 - julearn - INFO - Target: target
2023-07-19 12:42:16,194 - julearn - INFO - Expanded features: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']
2023-07-19 12:42:16,194 - julearn - INFO - X_types:{}
2023-07-19 12:42:16,195 - julearn - WARNING - The following columns are not defined in X_types: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']. They will be treated as continuous.
/home/runner/work/julearn/julearn/julearn/utils/logging.py:238: RuntimeWarning: The following columns are not defined in X_types: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']. They will be treated as continuous.
warn(msg, category=category)
2023-07-19 12:42:16,195 - julearn - INFO - ====================
2023-07-19 12:42:16,195 - julearn - INFO -
2023-07-19 12:42:16,195 - julearn - INFO - Adding step zscore that applies to ColumnTypes<types={'continuous'}; pattern=(?:__:type:__continuous)>
2023-07-19 12:42:16,196 - julearn - INFO - Step added
2023-07-19 12:42:16,196 - julearn - INFO - Adding step ridge that applies to ColumnTypes<types={'continuous'}; pattern=(?:__:type:__continuous)>
2023-07-19 12:42:16,196 - julearn - INFO - Step added
2023-07-19 12:42:16,196 - julearn - INFO - = Model Parameters =
2023-07-19 12:42:16,196 - julearn - INFO - ====================
2023-07-19 12:42:16,196 - julearn - INFO -
2023-07-19 12:42:16,196 - julearn - INFO - = Data Information =
2023-07-19 12:42:16,196 - julearn - INFO - Problem type: regression
2023-07-19 12:42:16,196 - julearn - INFO - Number of samples: 442
2023-07-19 12:42:16,196 - julearn - INFO - Number of features: 10
2023-07-19 12:42:16,197 - julearn - INFO - ====================
2023-07-19 12:42:16,197 - julearn - INFO -
2023-07-19 12:42:16,197 - julearn - INFO - Target type: float64
2023-07-19 12:42:16,197 - julearn - INFO - Using outer CV scheme KFold(n_splits=5, random_state=None, shuffle=False)
Now the scores dataframe has all the values for each CV split, but two scores unders the column names ‘test_neg_mean_absolute_error’ and ‘test_r2_corr’.
print(scores[["test_neg_mean_absolute_error", "test_r2_corr"]].mean())
test_neg_mean_absolute_error -44.264654
test_r2_corr 0.486498
dtype: float64
If we want to define a custom scoring metric, we need to define a function that takes the predicted and the actual values as input and returns a value. In this case, we want to compute Pearson correlation coefficient (r).
def pearson_scorer(y_true, y_pred):
return scipy.stats.pearsonr( # type: ignore
y_true.squeeze(), y_pred.squeeze()
)[0]
Before using it, we need to convert it to a sklearn scorer and register it with julearn.
register_scorer(scorer_name="pearsonr", scorer=make_scorer(pearson_scorer))
2023-07-19 12:42:16,251 - julearn - INFO - registering scorer named pearsonr
Now we can use it as another scoring metric.
2023-07-19 12:42:16,251 - julearn - INFO - ==== Input Data ====
2023-07-19 12:42:16,251 - julearn - INFO - Using dataframe as input
2023-07-19 12:42:16,251 - julearn - INFO - Features: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']
2023-07-19 12:42:16,251 - julearn - INFO - Target: target
2023-07-19 12:42:16,252 - julearn - INFO - Expanded features: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']
2023-07-19 12:42:16,252 - julearn - INFO - X_types:{}
2023-07-19 12:42:16,252 - julearn - WARNING - The following columns are not defined in X_types: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']. They will be treated as continuous.
/home/runner/work/julearn/julearn/julearn/utils/logging.py:238: RuntimeWarning: The following columns are not defined in X_types: ['age', 'sex', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']. They will be treated as continuous.
warn(msg, category=category)
2023-07-19 12:42:16,252 - julearn - INFO - ====================
2023-07-19 12:42:16,253 - julearn - INFO -
2023-07-19 12:42:16,253 - julearn - INFO - Adding step zscore that applies to ColumnTypes<types={'continuous'}; pattern=(?:__:type:__continuous)>
2023-07-19 12:42:16,253 - julearn - INFO - Step added
2023-07-19 12:42:16,253 - julearn - INFO - Adding step ridge that applies to ColumnTypes<types={'continuous'}; pattern=(?:__:type:__continuous)>
2023-07-19 12:42:16,253 - julearn - INFO - Step added
2023-07-19 12:42:16,253 - julearn - INFO - = Model Parameters =
2023-07-19 12:42:16,253 - julearn - INFO - ====================
2023-07-19 12:42:16,254 - julearn - INFO -
2023-07-19 12:42:16,254 - julearn - INFO - = Data Information =
2023-07-19 12:42:16,254 - julearn - INFO - Problem type: regression
2023-07-19 12:42:16,254 - julearn - INFO - Number of samples: 442
2023-07-19 12:42:16,254 - julearn - INFO - Number of features: 10
2023-07-19 12:42:16,254 - julearn - INFO - ====================
2023-07-19 12:42:16,254 - julearn - INFO -
2023-07-19 12:42:16,254 - julearn - INFO - Target type: float64
2023-07-19 12:42:16,254 - julearn - INFO - Using outer CV scheme KFold(n_splits=5, random_state=None, shuffle=False)
Total running time of the script: ( 0 minutes 0.203 seconds)