पूरी पाइपलाइन का क्रॉस-वैलिडेशन और ग्रिड सर्च

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_wine
import numpy as np

X, y = load_wine(return_X_y=True)

pipe = Pipeline([
    ('sc', StandardScaler()),
    ('lr', LogisticRegression(C=1.0, max_iter=300))
])

scores = cross_val_score(pipe, X, y, cv=5, scoring='accuracy')
print(f'CV accuracy: {np.mean(scores):.4f} +/- {np.std(scores):.4f}')

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

pipe = Pipeline([('sc', StandardScaler()), ('svm', SVC())])

# Print all tunable parameters
params = pipe.get_params()
for k, v in params.items():
    print(f'  {k}: {v}')

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import load_wine

X, y = load_wine(return_X_y=True)

pipe = Pipeline([('sc', StandardScaler()), ('svm', SVC())])

param_grid = {
    'svm__C': [0.1, 1.0, 10.0, 100.0],
    'svm__kernel': ['rbf', 'linear'],
    'svm__gamma': ['scale', 'auto']
}

grid = GridSearchCV(pipe, param_grid, cv=5, n_jobs=-1, scoring='accuracy')
grid.fit(X, y)
print('Best params:', grid.best_params_)
print('Best CV score:', grid.best_score_.round(4))

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import load_digits

X, y = load_digits(return_X_y=True)

pipe = Pipeline([
    ('sc', StandardScaler()),
    ('pca', PCA()),
    ('lr', LogisticRegression(max_iter=500))
])

param_grid = {
    'pca__n_components': [10, 20, 30, 40],
    'lr__C': [0.1, 1.0, 10.0]
}

grid = GridSearchCV(pipe, param_grid, cv=5, n_jobs=-1)
grid.fit(X, y)
print('Best:', grid.best_params_)
print('Score:', grid.best_score_.round(4))

import pandas as pd

results = pd.DataFrame(grid.cv_results_)
results_sorted = results.sort_values('rank_test_score')
print(results_sorted[['param_pca__n_components', 'param_lr__C',
                       'mean_test_score', 'std_test_score']].head(6).to_string())

from sklearn.model_selection import RandomizedSearchCV
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.datasets import load_wine
from scipy.stats import loguniform, uniform

X, y = load_wine(return_X_y=True)

pipe = Pipeline([('sc', StandardScaler()), ('svm', SVC())])

param_dist = {
    'svm__C': loguniform(0.01, 100),
    'svm__gamma': loguniform(1e-4, 1),
    'svm__kernel': ['rbf', 'linear']
}

rs = RandomizedSearchCV(pipe, param_dist, n_iter=30, cv=5, random_state=42, n_jobs=-1)
rs.fit(X, y)
print('Best params:', rs.best_params_)
print('Best score:', rs.best_score_.round(4))

from sklearn.model_selection import GridSearchCV, cross_val_score
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.datasets import load_iris
import numpy as np

X, y = load_iris(return_X_y=True)

pipe = Pipeline([('sc', StandardScaler()), ('svm', SVC())])
param_grid = {'svm__C': [0.1, 1.0, 10.0], 'svm__gamma': ['scale', 'auto']}

inner_cv = GridSearchCV(pipe, param_grid, cv=5, n_jobs=-1)
# Outer CV evaluates the tuning procedure itself
outer_scores = cross_val_score(inner_cv, X, y, cv=5)
print(f'Nested CV score: {np.mean(outer_scores):.4f} +/- {np.std(outer_scores):.4f}')

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.datasets import load_wine

X, y = load_wine(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

pipe = Pipeline([('sc', StandardScaler()), ('svm', SVC())])
param_grid = {'svm__C': [0.1, 1.0, 10.0], 'svm__kernel': ['rbf', 'linear']}

grid = GridSearchCV(pipe, param_grid, cv=5, n_jobs=-1)
grid.fit(X_train, y_train)

best = grid.best_estimator_
print('Test accuracy:', best.score(X_test, y_test).round(4))

from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_breast_cancer

X, y = load_breast_cancer(return_X_y=True)

pipe = Pipeline([('sc', StandardScaler()), ('lr', LogisticRegression(max_iter=300))])
param_grid = {'lr__C': [0.01, 0.1, 1.0, 10.0]}

grid = GridSearchCV(pipe, param_grid, cv=5, scoring='roc_auc', n_jobs=-1)
grid.fit(X, y)
print('Best C:', grid.best_params_)
print('Best ROC-AUC:', grid.best_score_.round(4))

import joblib

# Save the best estimator
joblib.dump(grid.best_estimator_, '/tmp/best_pipeline.pkl')

# Load and verify
loaded = joblib.load('/tmp/best_pipeline.pkl')
print('Loaded pipeline test score:', loaded.score(X_test, y_test).round(4))