תחילת העבודה עם Scikit-learn לסיווג בלמידת מכונה

pip install scikit-learn

from sklearn.datasets import load_wine X, y = load_wine(return_X_y=True)

from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.33, random_state=42
)

model_lr = LogisticRegression()
model_lr.fit(X_train, y_train)
y_pred_lr = model_lr.predict(X_test) print("Accuracy Score: ", accuracy_score(y_pred_lr, y_test))
print(classification_report(y_pred_lr, y_test))

Accuracy Score: 0.9830508474576272 precision recall f1-score support 0 1.00 0.95 0.98 21 1 0.96 1.00 0.98 23 2 1.00 1.00 1.00 15 accuracy 0.98 59 macro avg 0.99 0.98 0.98 59
weighted avg 0.98 0.98 0.98 59

model_knn = KNeighborsClassifier(n_neighbors=1)
model_knn.fit(X_train, y_train)
y_pred_knn = model_knn.predict(X_test) print("Accuracy Score:", accuracy_score(y_pred_knn, y_test))
print(classification_report(y_pred_knn, y_test))

Accuracy Score: 0.7796610169491526 precision recall f1-score support 0 0.90 0.78 0.84 23 1 0.75 0.82 0.78 22 2 0.67 0.71 0.69 14 accuracy 0.78 59 macro avg 0.77 0.77 0.77 59
weighted avg 0.79 0.78 0.78 59

Accuracy Score: 0.6949152542372882 precision recall f1-score support 0 0.90 0.72 0.80 25 1 0.75 0.69 0.72 26 2 0.33 0.62 0.43 8 accuracy 0.69 59 macro avg 0.66 0.68 0.65 59
weighted avg 0.76 0.69 0.72 59

from sklearn.naive_bayes import GaussianNB model_nb = GaussianNB()
model_nb.fit(X_train, y_train)
y_pred_nb = model_nb.predict(X_test) print("Accuracy Score:", accuracy_score(y_pred_nb, y_test))
print(classification_report(y_pred_nb, y_test))

Accuracy Score: 1.0 precision recall f1-score support 0 1.00 1.00 1.00 20 1 1.00 1.00 1.00 24 2 1.00 1.00 1.00 15 accuracy 1.00 59 macro avg 1.00 1.00 1.00 59
weighted avg 1.00 1.00 1.00 59

from sklearn.tree import DecisionTreeClassifier model_dtclassifier = DecisionTreeClassifier()
model_dtclassifier.fit(X_train, y_train)
y_pred_dtclassifier = model_dtclassifier.predict(X_test) print("Accuracy Score:", accuracy_score(y_pred_dtclassifier, y_test))
print(classification_report(y_pred_dtclassifier, y_test))

Accuracy Score: 0.9661016949152542 precision recall f1-score support 0 0.95 0.95 0.95 20 1 1.00 0.96 0.98 25 2 0.93 1.00 0.97 14 accuracy 0.97 59 macro avg 0.96 0.97 0.97 59
weighted avg 0.97 0.97 0.97 59

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import RandomizedSearchCV def get_best_parameters(): params = { "n_estimators": [10, 50, 100], "max_features": ["auto", "sqrt", "log2"], "max_depth": [5, 10, 20, 50], "min_samples_split": [2, 4, 6], "min_samples_leaf": [2, 4, 6], "bootstrap": [True, False], } model_rfclassifier = RandomForestClassifier(random_state=42) rf_randomsearch = RandomizedSearchCV( estimator=model_rfclassifier, param_distributions=params, n_iter=5, cv=3, verbose=2, random_state=42, ) rf_randomsearch.fit(X_train, y_train) best_parameters = rf_randomsearch.best_params_ print("Best Parameters:", best_parameters) return best_parameters parameters_rfclassifier = get_best_parameters() model_rfclassifier = RandomForestClassifier( **parameters_rfclassifier, random_state=42
) model_rfclassifier.fit(X_train, y_train) y_pred_rfclassifier = model_rfclassifier.predict(X_test) print("Accuracy Score:", accuracy_score(y_pred_rfclassifier, y_test))
print(classification_report(y_pred_rfclassifier, y_test))

Best Parameters: {'n_estimators': 100, 'min_samples_split': 6, 'min_samples_leaf': 4, 'max_features': 'log2', 'max_depth': 5, 'bootstrap': True}
Accuracy Score: 0.9830508474576272 precision recall f1-score support 0 1.00 0.95 0.98 21 1 0.96 1.00 0.98 23 2 1.00 1.00 1.00 15 accuracy 0.98 59 macro avg 0.99 0.98 0.98 59
weighted avg 0.98 0.98 0.98 59