अपनी पहली पाइपलाइन बनाना: स्केलर और वर्गीकारक

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pipe = Pipeline([
    ('scaler', StandardScaler()),
    ('clf', LogisticRegression(C=1.0, max_iter=200))
])

print('Steps:', [name for name, _ in pipe.steps])
print('Named steps:', list(pipe.named_steps.keys()))

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

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

pipe = Pipeline([
    ('scaler', StandardScaler()),
    ('clf', LogisticRegression(max_iter=300))
])

pipe.fit(X_train, y_train)
print('Test accuracy:', pipe.score(X_test, y_test).round(4))

y_pred = pipe.predict(X_test)
print('Predictions[:5]:', y_pred[:5])

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
import numpy as np

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

pipe = Pipeline([('sc', StandardScaler()), ('lr', LogisticRegression(max_iter=300))])
pipe.fit(X_train, y_train)

# Scaler mean from pipeline vs computed from X_train
print('Pipeline scaler mean[0]:', pipe.named_steps['sc'].mean_[0].round(4))
print('Direct train mean[0]:   ', X_train[:, 0].mean().round(4))

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)

pipe = Pipeline([('sc', StandardScaler()), ('lr', LogisticRegression())])
pipe.fit(X, y)

# Get scaled output (all steps except the last)
X_scaled = pipe[:-1].transform(X)
print('After scaling — mean per feature:', X_scaled.mean(axis=0).round(4))
print('After scaling — std per feature:', X_scaled.std(axis=0).round(4))

from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import MinMaxScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import load_iris
from sklearn.model_selection import cross_val_score
import numpy as np

X, y = load_iris(return_X_y=True)

# Auto-names: 'minmaxscaler' and 'kneighborsclassifier'
pipe = make_pipeline(MinMaxScaler(), KNeighborsClassifier(n_neighbors=5))
print('Step names:', list(pipe.named_steps.keys()))
print('CV accuracy:', cross_val_score(pipe, X, y, cv=5).mean().round(4))

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

pipe = Pipeline([('sc', StandardScaler()), ('lr', LogisticRegression(max_iter=300))])
pipe.fit(X_train, y_train)

proba = pipe.predict_proba(X_test)[:, 1]
print('ROC-AUC:', roc_auc_score(y_test, proba).round(4))

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pipe = Pipeline([('sc', StandardScaler()), ('lr', LogisticRegression())])

# Change C and max_iter after construction
pipe.set_params(lr__C=10.0, lr__max_iter=500)
print('C after set_params:', pipe.named_steps['lr'].C)

import joblib
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)
pipe = Pipeline([('sc', StandardScaler()), ('lr', LogisticRegression())])
pipe.fit(X, y)

# Save and reload
joblib.dump(pipe, '/tmp/iris_pipeline.pkl')
loaded_pipe = joblib.load('/tmp/iris_pipeline.pkl')

print('Predictions match:', (pipe.predict(X) == loaded_pipe.predict(X)).all())

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

X, y = load_digits(return_X_y=True)

pipe = Pipeline([
    ('sc', StandardScaler()),
    ('svm', SVC(kernel='rbf', C=5.0, gamma='scale'))
])

scores = cross_val_score(pipe, X, y, cv=5, n_jobs=-1)
print(f'CV accuracy: {np.mean(scores):.4f} +/- {np.std(scores):.4f}')