import logging

logging.basicConfig()
logging.getLogger("SKLEARNEX").setLevel(logging.ERROR)

import json
import gzip
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.metrics import precision_recall_fscore_support, classification_report

from sklearn.metrics import ConfusionMatrixDisplay
from sklearn.model_selection import cross_val_predict

from IPython.display import display

def groupby_labels(y, yhat):

"""Based on https://stackoverflow.com/questions/38013778/is-there-any-numpy-group-by-function
"""
m = np.stack([y, yhat]).T
m = m[m[:, 0].argsort()]
grouped_preds = np.split(m[:, 1], np.unique(m[:, 0], return_index=True)[1])[1:]
labels = np.unique(m[:, 0])
return labels, grouped_preds

def mae_macro(y, yhat):

"""Macroaveraged MAE
"""
labels, preds = groupby_labels(y, yhat)
mean_diff = np.array([np.abs(label - pred).mean() for label, pred in zip(labels, preds)]).mean()
return mean_diff

def rmse_macro(y, yhat):

"""Macroaveraged RMSE
"""
labels, preds = groupby_labels(y, yhat)
mean_diff = np.array([np.power(label - pred, 2).mean() for label, pred in zip(labels, preds)]).mean()
return np.sqrt(mean_diff)

def evaluate_model(model, ytest, Xtest):

"""Given a trained model and test data, generate predictions
and print a report with evaluation results
"""
yhat = model.predict(Xtest)
print(classification_report(ytest, yhat, zero_division=0))
rmse = rmse_macro(ytest, yhat)
print(f"{'Macro RMSE':18} {rmse:.3}")
mae = mae_macro(ytest, yhat)
print(f"{'Macro MAE':18} {mae:.3}")

def print_cv_results(grid_search, col_width=100, max_rows=10):

"""Given a grid search object, print a table with the
cross-validation results
"""
results = pd.DataFrame(grid_search.cv_results_
)[['params', 'mean_train_score', 'mean_test_score']]

results["mean_train_score"] = -results["mean_train_score"]
results["mean_test_score"] = -results["mean_test_score"]

results["diff, %"] = 100*(results["mean_train_score"]-results["mean_test_score"]

)/results["mean_train_score"]

pd.set_option('display.max_colwidth', col_width)
pd.set_option('display.min_rows', max_rows)
pd.set_option('display.max_rows', max_rows)
display(results.sort_values('mean_test_score', ascending=True))

# create a scoring function

from sklearn.metrics import make_scorer

neg_rmse_macro = make_scorer(rmse_macro, greater_is_better=False)

!pip install scikit-optimize

Collecting scikit-optimize
Downloading scikit_optimize-0.10.2-py2.py3-none-any.whl.metadata (9.7 kB)
Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.10/dist-packages (from scikit-optimize) (1.4.2)
Collecting pyaml>=16.9 (from scikit-optimize)
Downloading pyaml-25.1.0-py3-none-any.whl.metadata (12 kB)
Requirement already satisfied: numpy>=1.20.3 in /usr/local/lib/python3.10/dist-packages (from scikit-optimize) (1.26.4)
Requirement already satisfied: scipy>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-optimize) (1.13.1)
Requirement already satisfied: scikit-learn>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-optimize) (1.6.0)
Requirement already satisfied: packaging>=21.3 in /usr/local/lib/python3.10/dist-packages (from scikit-optimize) (24.2)
Requirement already satisfied: PyYAML in /usr/local/lib/python3.10/dist-packages (from pyaml>=16.9->scikit-optimize) (6.0.2)
Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.0->sc
Downloading scikit_optimize-0.10.2-py2.py3-none-any.whl (107 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 107.8/107.8 kB 3.0 MB/s eta 0:00:00
Downloading pyaml-25.1.0-py3-none-any.whl (26 kB)
Installing collected packages: pyaml, scikit-optimize
Successfully installed pyaml-25.1.0 scikit-optimize-0.10.2

Load data

import pandas as pd # Import the pandas library and give it the alias 'pd'

trainset = pd.read_csv("/content/trainsetforbigdata.csv")
testset = pd.read_csv("/content/testsetforbigdata.csv")

trainset['grade'].value_counts()

count

grade

7 7044

8 4696

9 1920

6 1599

10 741

11 193

5 185

12 25

4 19

1 1

13 1

3 1

dtype: int64

Xtrain = trainset.drop("grade", axis=1)

ytrain = trainset["grade"].copy()
Xtest = testset.drop("grade", axis=1)
ytest = testset["grade"].copy()

Xtrain.shape, Xtest.shape

((16425, 15), (4323, 15))

3.Baseline
We'll use a simple baseline: dummy classi er :

from sklearn.dummy import DummyClassifier

dummy_clf = DummyClassifier(strategy="most_frequent")
dummy_clf.fit(Xtrain, ytrain)
yhat_train = dummy_clf.predict(Xtrain)

evaluate_model(dummy_clf, ytrain, Xtrain)

precision recall f1-score support

1 0.00 0.00 0.00 1

3 0.00 0.00 0.00 1
4 0.00 0.00 0.00 19
5 0.00 0.00 0.00 185
6 0.00 0.00 0.00 1599
7 0.43 1.00 0.60 7044
8 0.00 0.00 0.00 4696
9 0.00 0.00 0.00 1920
10 0.00 0.00 0.00 741
11 0.00 0.00 0.00 193
12 0.00 0.00 0.00 25
13 0.00 0.00 0.00 1

accuracy 0.43 16425

macro avg 0.04 0.08 0.05 16425
weighted avg 0.18 0.43 0.26 16425

Macro RMSE 3.62

Macro MAE 3.08

Model development

4.1 Unbalanced data - linear SVC

from sklearn.model_selection import GridSearchCV

from sklearn.svm import LinearSVC

lsvm = LinearSVC(random_state=7, max_iter=10000)

param_grid = {
'C': [0.001, 0.01, 0.1, 1, 10]
}

lsvc_grid_search = GridSearchCV(lsvm, param_grid, cv=10,

scoring=neg_rmse_macro,
return_train_score=True)
lsvc_grid_search.fit(Xtrain, ytrain)

print_cv_results(lsvc_grid_search, col_width=100, max_rows=150)

/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805: UserWarning: The least populated class in y h

warnings.warn(
params mean_train_score mean_test_score diff, %

4 {'C': 10} 2.010335 1.738254 13.534114

3 {'C': 1} 2.446453 1.784443 27.059985

2 {'C': 0.1} 2.453444 1.791716 26.971398

1 {'C': 0.01} 2.483156 1.861268 25.044227

0 {'C': 0.001} 2.818087 2.023574 28.193332

# cross-validation confusion matrix, training data

yhat = cross_val_predict(lsvc_grid_search.best_estimator_, Xtrain, ytrain, cv=10)
ConfusionMatrixDisplay.from_predictions(ytrain, yhat,
labels=lsvc_grid_search.best_estimator_.classes_,
normalize="true",
cmap=plt.cm.Blues);
 /usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805: UserWarning: The least populated class in y h
warnings.warn(

4.2 Class balancing - based on the linear SVC model , we will do hyperparameter tuning with random over sampler

from imblearn.pipeline import Pipeline

from imblearn.over_sampling import SMOTE, RandomOverSampler

pipeline = Pipeline([
('cb', RandomOverSampler(random_state=7)),
('lsvc', LinearSVC(random_state=7, max_iter=10000))
])

param_grid = [
{
'cb__sampling_strategy': ["auto"],
'lsvc__C': [0.00001, 0.0001, 0.001, 0.01, 0.1, 1, 10],
},
]

cb_grid_search = GridSearchCV(pipeline, param_grid, cv=10,

scoring=neg_rmse_macro,
return_train_score=True)

cb_grid_search.fit(Xtrain, ytrain)

print_cv_results(cb_grid_search, col_width=100)
 /usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805: UserWarning: The least populated class in y h
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
# cross-validation confusion matrix on the training data
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
yhat = warnings.warn(
cross_val_predict(cb_grid_search.best_estimator_, Xtrain, ytrain, cv=10)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
ConfusionMatrixDisplay.from_predictions(ytrain, yhat,
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
labels=cb_grid_search.best_estimator_.classes_,
warnings.warn( normalize="true",
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
cmap=plt.cm.Blues); FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3 10/dist packages/sklearn/utils/ tags py:354: FutureWarning: The RandomOverSampler or classes from whi
 /usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805:
warnings.warn( UserWarning: The least populated class in y h
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
warnings.warn( FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
4.3 Logistic regression
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
warnings.warn( FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn( FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
from /usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
sklearn.linear_model import LogisticRegression FutureWarning: `BaseEstimator._check_n_features` is deprecated
from /usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
sklearn.metrics
warnings.warn( import ConfusionMatrixDisplay FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
from /usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
sklearn.model_selection import cross_val_predict FutureWarning: `BaseEstimator._check_feature_names` is deprecat
import warnings.warn(
matplotlib.pyplot as plt
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
# Define the parameter grid for Logistic Regression
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
param_grid = [ FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
{'C': [0.1, 1, 10, 100],
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
'solver': ['liblinear', 'lbfgs']}
warnings.warn(
] /usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
# Initialize the Logistic Regression classifier
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
log_regwarnings.warn(
= LogisticRegression(max_iter=1000, random_state=42)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
# Initialize the GridSearchCV
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
log_reg_grid_search = GridSearchCV(log_reg, param_grid, cv=10, FutureWarning: The RandomOverSampler or classes from whi
warnings.warn( scoring='f1_macro', return_train_score=True)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
# Perform the grid search on the training set
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
log_reg_grid_search.fit(Xtrain,
warnings.warn( ytrain)
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
i (
 warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: UserWarning:
FutureWarning: The least populated
The RandomOverSampler class
or classes in y
from h
whi
warnings.warn(
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
▸ GridSearchCV FutureWarning: The RandomOverSampler or classes from whi
warnings.warn( i ?
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
▸warnings.warn(
best_estimator_:
LogisticRegression
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
▸ LogisticRegression ?
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
# training and validation RMSE
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
print_cv_results(log_reg_grid_search, col_width=100)
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn( params mean_train_score mean_test_score diff, %
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
5 warnings.warn(
{'C': 10, 'solver': 'lbfgs'} -0.453283 -0.398510 12.083681
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
3 {'C': 1, 'solver': 'lbfgs'} -0.343640 -0.394325 -14.749376
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
7 {'C': 100, 'solver': 'lbfgs'} -0.513432 -0.390429 23.957006 FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
1 {'C': 0.1, 'solver': 'lbfgs'} -0.283365 -0.346313 -22.214245 FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
6 {'C': 100, 'solver': 'liblinear'} -0.184973 FutureWarning: `BaseEstimator._check_n_features` is deprecated
-0.213747 -15.555387
warnings.warn(
4 {'C': 10, 'solver': 'liblinear'} -0.181816
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: -0.207062 -13.885188
FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
2 {'C': 1, 'solver': 'liblinear'} -0.166541 -0.206610 -24.059198
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
0 {'C': 0.1, 'solver': 'liblinear'} -0.160519 -0.199989 -24.588969
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
# Perform cross-validation predictions on the training data
warnings.warn(
yhat /usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
= cross_val_predict(log_reg_grid_search.best_estimator_, Xtrain, ytrain, cv=10)
FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
# Plot the confusion matrix
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
ConfusionMatrixDisplay.from_predictions(ytrain, yhat,
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
labels=log_reg_grid_search.best_estimator_.classes_,
warnings.warn( normalize="true",
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
cmap=plt.cm.Blues) FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
plt.show()
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805: UserWarning: The least populated class in y h
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
4.4 Random forest
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
unbalanced data:
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
from sklearn.model_selection import GridSearchCV
from /usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
timeit import default_timer as timer # Import the timer function FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
 /usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
start =warnings.warn(
timer()
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn( import RandomForestClassifier
from sklearn.ensemble
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
# ... rest of your code
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
from sklearn.model_selection import GridSearchCV
warnings.warn(
from timeit import default_timer as timer # Import the timer function
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
from datetime import timedelta # Import timedelta
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
start =warnings.warn(
timer()
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn( import RandomForestClassifier
from sklearn.ensemble
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
rf = RandomForestClassifier(random_state=7, max_depth=40, min_samples_split=5)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
hp_grid = {
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
'n_estimators': [100, 200, 500],
warnings.warn(
'max_features': ["sqrt", 0.5],
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
'max_samples': [None, 0.5],
warnings.warn(
} /usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
# we'll use 5-fold cross-validation
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
grid_search = GridSearchCV(rf, hp_grid, cv=5,
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
scoring='f1_macro', FutureWarning: The RandomOverSampler or classes from whi
warnings.warn( return_train_score=True, verbose=2)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
grid_search.fit(Xtrain, ytrain)
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
print("Execution time HH:MM:SS:", timedelta(seconds=timer() - start))
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: # Use timedelta
FutureWarning: to format execution time
`BaseEstimator._check_feature_names` is deprecat
warnings.warn(
Fitting 5 folds for each of 12 candidates, totalling 60 fits
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805:
warnings.warn( UserWarning: The least populated class in y h
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
[CV] END max_features=sqrt, max_samples=None, n_estimators=100; total time=
warnings.warn( 4.7s
[CV] END max_features=sqrt, max_samples=None, n_estimators=100; total
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 3.6s The RandomOverSampler or classes from whi
FutureWarning:
[CV] END max_features=sqrt, max_samples=None, n_estimators=100; total time=
warnings.warn( 3.6s
[CV] END max_features=sqrt, max_samples=None, n_estimators=100;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: total time= `BaseEstimator._check_n_features`
FutureWarning: 4.6s is deprecated
[CV] END max_features=sqrt, max_samples=None, n_estimators=100; total time=
warnings.warn( 3.5s
[CV] END max_features=sqrt, max_samples=None, n_estimators=200;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: total time= `BaseEstimator._check_feature_names`
FutureWarning: 9.0s is deprecat
[CV] END max_features=sqrt, max_samples=None, n_estimators=200; total time=
warnings.warn( 7.1s
[CV] END max_features=sqrt, max_samples=None, n_estimators=200; total
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 8.1s The RandomOverSampler or classes from whi
FutureWarning:
[CV] END max_features=sqrt, max_samples=None, n_estimators=200; total time=
warnings.warn( 7.3s
[CV] END max_features=sqrt, max_samples=None, n_estimators=200; total
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 7.8s The RandomOverSampler or classes from whi
FutureWarning:
[CV] END max_features=sqrt, max_samples=None, n_estimators=500; total time= 19.4s
warnings.warn(
[CV] END max_features=sqrt, max_samples=None, n_estimators=500; total
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 18.8s The RandomOverSampler or classes from whi
FutureWarning:
[CV] END max_features=sqrt, max_samples=None, n_estimators=500; total time= 19.4s
warnings.warn(
[CV] END max_features=sqrt, max_samples=None, n_estimators=500;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: total time= `BaseEstimator._check_n_features`
FutureWarning: 18.8s is deprecated
[CV] END max_features=sqrt, max_samples=None, n_estimators=500; total time= 19.7s
warnings.warn(
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=100;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: total time= `BaseEstimator._check_feature_names`
FutureWarning: 2.3s is deprecat
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=100; total time=
warnings.warn( 2.3s
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=100; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 2.3s The RandomOverSampler or classes from whi
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=100; total time=
warnings.warn( 2.8s
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=100; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 2.8s The RandomOverSampler or classes from whi
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=200; total time=
warnings.warn( 4.7s
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=200; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 5.0s The RandomOverSampler or classes from whi
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=200; total time=
warnings.warn( 5.0s
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=200;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: total time= `BaseEstimator._check_n_features`
FutureWarning: 4.6s is deprecated
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=200; total time=
warnings.warn( 5.6s
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=500;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: total time= `BaseEstimator._check_feature_names`
FutureWarning: 12.6s is deprecat
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=500; total time= 12.8s
warnings.warn(
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=500; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 12.5s The RandomOverSampler or classes from whi
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=500; total time= 12.5s
warnings.warn(
[CV] END max_features=sqrt, max_samples=0.5, n_estimators=500; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 12.5s The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=None, n_estimators=100; total time=
warnings.warn( 7.2s
[CV] END max_features=0.5, max_samples=None, n_estimators=100; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 8.1s The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=None, n_estimators=100; total time=
warnings.warn( 7.9s
[CV] END max_features=0.5, max_samples=None, n_estimators=100;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: total time= `BaseEstimator._check_n_features`
FutureWarning: 7.2s is deprecated
[CV] END max_features=0.5,
warnings.warn( max_samples=None, n_estimators=100; total time= 8.1s
[CV] END max_features=0.5, max_samples=None, n_estimators=200;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: total time= `BaseEstimator._check_feature_names`
FutureWarning: 15.3s is deprecat
[CV] END max_features=0.5, max_samples=None, n_estimators=200; total time= 15.4s
warnings.warn(
[CV] END max_features=0.5, max_samples=None, n_estimators=200; total time= 15.2s
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=None, n_estimators=200; total time= 15.6s
warnings.warn(
[CV] END max_features=0.5, max_samples=None, n_estimators=200; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 15.7s The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=None, n_estimators=500; total time= 38.5s
warnings.warn(
[CV] END max_features=0.5, max_samples=None, n_estimators=500; totalFutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: time= 38.2s The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=None, n_estimators=500; total time= 37.6s
warnings.warn(
[CV] END max_features=0.5, max_samples=None, n_estimators=500;
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: total time= 38.2s
FutureWarning: `BaseEstimator._check_n_features` is deprecated
[CV] END max_features=0.5, max_samples=None, n_estimators=500; total time= 38.5s
warnings.warn(
[CV]
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: 5.2s
END max_features=0.5, max_samples=0.5, n_estimators=100; total time= `BaseEstimator. check feature names` is deprecat
 / / / /py / p g / / py g _ _ _ p
[CV] END max_features=0.5, max_samples=0.5, n_estimators=100; total time=
warnings.warn( 4.5s
[CV] END max_features=0.5, max_samples=0.5, n_estimators=100; total time=
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: 5.2s
FutureWarning: The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=0.5, n_estimators=100; total time=
warnings.warn( 4.7s
[CV] END max_features=0.5, max_samples=0.5, n_estimators=100; total time=
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: 4.4s
FutureWarning: The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=0.5, n_estimators=200; total time=
warnings.warn( 9.9s
[CV] END max_features=0.5, max_samples=0.5, n_estimators=200; total time=
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: 9.9s
FutureWarning: The RandomOverSampler or classes from whi
[CV] END max_features=0.5, max_samples=0.5, n_estimators=200; total time=
warnings.warn( 9.3s
[CV] END max_features=0.5, max_samples=0.5, n_estimators=200;FutureWarning:
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: total time= 9.2s
`BaseEstimator._check_n_features` is deprecated
[CV] END max_features=0.5, max_samples=0.5, n_estimators=200; total time=
warnings.warn( 9.9s
[ ]
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
cv_results = pd.DataFrame(grid_search.cv_results_)[['params', 'mean_train_score', 'mean_test_score']]
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
cv_results["diff, %"] = 100*(cv_results["mean_train_score"]-cv_results["mean_test_score"] FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
)/cv_results["mean_train_score"]
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
pd.set_option('display.max_colwidth', 100)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
cv_results.sort_values('mean_test_score',
warnings.warn( ascending=False)
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn( params mean_train_score mean_test_score diff, %
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
8warnings.warn(
{'max_features': 0.5, 'max_samples': None, 'n_estimators': 500} 0.997563 0.493076 50.571978
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
7warnings.warn(
{'max_features': 0.5, 'max_samples': None, 'n_estimators': 200} 0.995720 0.492912 50.496893
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
6warnings.warn(
{'max_features': 0.5, 'max_samples': None, 'n_estimators': 100} 0.994789 0.492418 50.500210
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
2 {'max_features': 'sqrt', 'max_samples': None, 'n_estimators': 500} 0.995538 0.479189 51.866392
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
0 {'max_features': 'sqrt', 'max_samples': None, 'n_estimators': 100} FutureWarning:
0.990357 `BaseEstimator._check_n_features`
0.478270 51.707338 is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
... ... FutureWarning:
... `BaseEstimator._check_feature_names`
... ... is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
9 {'max_features': 0.5, 'max_samples': 0.5, 'n_estimators': 100} FutureWarning:
0.659287 The RandomOverSampler
0.472108 28.391082 or classes from whi
warnings.warn(
11 {'max_features': 0.5, 'max_samples': 0.5, 'n_estimators': 500} 0.663103 0.469791 29.152683
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
3 {'max_features': 'sqrt', 'max_samples': 0.5, 'n_estimators': 100} 0.669981 0.465184 30.567638
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
5warnings.warn(
{'max_features': 'sqrt', 'max_samples': 0.5, 'n_estimators': 500} 0.663344 0.463179 30.175101
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
4warnings.warn(
{'max_features': 'sqrt', 'max_samples': 0.5, 'n_estimators': 200} 0.705286 0.451862 35.932176
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
12 warnings.warn(
rows × 4 columns
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
# cross-validation confusion matrix on the training data FutureWarning: The RandomOverSampler or classes from whi
yhat = warnings.warn(
cross_val_predict(grid_search.best_estimator_, Xtrain, ytrain, cv=10)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
ConfusionMatrixDisplay.from_predictions(ytrain, yhat,
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
labels=grid_search.best_estimator_.classes_,
warnings.warn(
normalize="true",
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn( cmap=plt.cm.Blues);
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_split.py:805:
warnings.warn( UserWarning: The least populated class in y h
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
5. Evaluate model
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings warn(
 warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
5.1 Unbalanced linear SVC
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
# Unbalanced linear SVC FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
evaluate_model(lsvc_grid_search.best_estimator_, ytest, Xtest)
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn( precision recall f1-score support
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
1 0.00 0.00 0.00 0
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
4 0.00 0.00 0.00 6 FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
5 0.00 0.00 0.00 38
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
6 0.48 0.04 0.08 391 FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
7 0.62 0.89 0.73 1842
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493:
8 0.52 0.53 0.52 1220 FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
9 0.34 0.24 0.28 513
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
10 0.23 0.07 0.11 213 FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
11 0.25 0.01 0.02 80
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
12 1.00 0.06 0.11 18 FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
13 0.00 0.00 0.00 2
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
accuracy 0.56 4323
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
macro avg 0.31 0.17 0.17 4323 FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
weighted avg 0.52 0.56 0.51 4323
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
Macro RMSE 1.77
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354:
Macro MAE 1.47 FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
5.2 Linear SVC - Random over sampler
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
# /usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
linear SVC - Random over sampler FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
evaluate_model(cb_grid_search.best_estimator_, ytest, Xtest)
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
precision recall f1-score support
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
1 0.00 0.00 0.00 0
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
4 0.03 0.50 0.06 6
warnings.warn(
5 0.07 0.45 0.12 38
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
6 0.24 0.59 0.34 391
warnings.warn(
7 0.62 0.36 0.46 1842
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
8 0.49 0.35 0.41 1220
warnings.warn(
9 0.34 0.31 0.32 513
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
10 0.14 0.10 0.12 213
warnings.warn(
11 0.09 0.28 0.13 80
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
12 0.08 0.94 0.15 18
warnings.warn(
13 0.00 0.00 0.00 2
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
accuracy 0.36 4323
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
macro avg 0.19 0.35 0.19 4323
warnings.warn(
weighted avg 0.47 0.36 0.39 4323
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
warnings.warn(
Macro RMSE 1.17
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
Macro MAE 0.821
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
5.3 Logistic regression grid search
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
# Logistic regression grid search
warnings.warn(
evaluate_model(log_reg_grid_search.best_estimator_, ytest, Xtest) FutureWarning: `BaseEstimator._check_n_features` is deprecated
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484:
warnings.warn(
precision recall f1-score support
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
warnings.warn(
1 0.00 0.00 0.00 0
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
4
warnings.warn( 0.33 0.17 0.22 6
5 0.25 0.08 0.12 38
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
6
warnings.warn( 0.60 0.48 0.53 391
7 0.72 0.80 0.76 1842
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
8
warnings.warn( 0.61 0.61 0.61 1220
9 0.54 0.48 0.50 513
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
10
warnings.warn( 0.48 0.46 0.47 213
11 0.52 0.41 0.46 80
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: `BaseEstimator._check_feature_names` is deprecat
12
warnings.warn( 0.31 0.28 0.29 18
13 0.00 0.00 0.00 2
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
accuracy 0.64 4323
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
macro avg
warnings.warn( 0.40 0.34 0.36 4323
weighted avg 0.63 0.64 0.64 4323
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(
Macro RMSE 1.0
/usr/local/lib/python3.10/dist-packages/sklearn/base.py:484: FutureWarning: `BaseEstimator._check_n_features` is deprecated
Macro MAE
warnings.warn( 0.752
/usr/local/lib/python3 10/dist packages/sklearn/base py:493: FutureWarning: `BaseEstimator check feature names` is deprecat
 /usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: FutureWarning: BaseEstimator._check_feature_names is deprecat
warnings.warn(
5.4 Random forest
/usr/local/lib/python3.10/dist-packages/sklearn/utils/_tags.py:354: FutureWarning: The RandomOverSampler or classes from whi
warnings.warn(