56 KiB
56 KiB
Preprocessing danych. Niektóre kolumny nie mają wpływu na predykcję i je usuwamy. Trzeba też uzyc one-hot-encodingu do kolumn będących kategoriami.
import pandas as pd
df = pd.read_csv('data/titanic.csv')
df.head()
df = df[['Survived', 'Age', 'Sex', 'Pclass']]
df = pd.get_dummies(df, columns=['Sex', 'Pclass'])
df.dropna(inplace=True)
df.head()Podzial danych na testowe i treningowe (80/20)
from sklearn.model_selection import train_test_split
X = df.drop('Survived', axis=1)
y = df['Survived']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)from sklearn.svm import SVC
model = SVC(kernel="rbf", probability=True, random_state=42)
model.fit(X_train, y_train)
print(f"RBF: {model.score(X_test, y_test)}")RBF: 0.6153846153846154
from sklearn.svm import SVC
model = SVC(kernel="linear", probability=True, random_state=42)
model.fit(X_train, y_train)
print(f"Linear: {model.score(X_test, y_test)}")Linear: 0.7832167832167832
from sklearn.svm import SVC
model = SVC(kernel="sigmoid", probability=True, random_state=42)
model.fit(X_train, y_train)
print(f"Sigmoid: {model.score(X_test, y_test)}")Sigmoid: 0.5594405594405595
Wyniki dla domyslnych parametrow dla roznych funkcji jadra nie sa powalajace (56-78%)
Spróbuję sprawdzić różne wariancje funkcji jądra oraz parametrów, które mówią o tym jak bardzo chcemy unikać misklasyfikacji oraz jak bardzo odległe przypadki mają wpływać na decyzję. Daje to sprawdzenie 300 roznych wariancji modelu.
from sklearn.model_selection import GridSearchCV
model = SVC(probability=True, random_state=42)
param_grid = {
'C': [0.5, 1, 10, 100],
'gamma': [1, 0.1, 0.01, 0.001, 0.0001],
'kernel': ['linear', 'rbf', 'sigmoid']
}
grid_search = GridSearchCV(estimator=model, param_grid=param_grid, cv=5, verbose=2)
grid_search.fit(X, y)
best_model = grid_search.best_estimator_Fitting 5 folds for each of 60 candidates, totalling 300 fits [CV] END ......................C=0.5, gamma=1, kernel=linear; total time= 0.1s [CV] END ......................C=0.5, gamma=1, kernel=linear; total time= 0.1s [CV] END ......................C=0.5, gamma=1, kernel=linear; total time= 0.1s [CV] END ......................C=0.5, gamma=1, kernel=linear; total time= 0.0s [CV] END ......................C=0.5, gamma=1, kernel=linear; total time= 0.1s [CV] END .........................C=0.5, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=0.5, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=0.5, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=0.5, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=0.5, gamma=1, kernel=rbf; total time= 0.1s [CV] END .....................C=0.5, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=0.5, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=0.5, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=0.5, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=0.5, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=0.5, gamma=0.1, kernel=linear; total time= 0.1s [CV] END ....................C=0.5, gamma=0.1, kernel=linear; total time= 0.1s [CV] END ....................C=0.5, gamma=0.1, kernel=linear; total time= 0.1s [CV] END ....................C=0.5, gamma=0.1, kernel=linear; total time= 0.0s [CV] END ....................C=0.5, gamma=0.1, kernel=linear; total time= 0.0s [CV] END .......................C=0.5, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .......................C=0.5, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .......................C=0.5, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .......................C=0.5, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .......................C=0.5, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END ...................C=0.5, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=0.5, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=0.5, gamma=0.1, kernel=sigmoid; total time= 0.1s [CV] END ...................C=0.5, gamma=0.1, kernel=sigmoid; total time= 0.1s [CV] END ...................C=0.5, gamma=0.1, kernel=sigmoid; total time= 0.1s [CV] END ...................C=0.5, gamma=0.01, kernel=linear; total time= 0.1s [CV] END ...................C=0.5, gamma=0.01, kernel=linear; total time= 0.1s [CV] END ...................C=0.5, gamma=0.01, kernel=linear; total time= 0.1s [CV] END ...................C=0.5, gamma=0.01, kernel=linear; total time= 0.0s [CV] END ...................C=0.5, gamma=0.01, kernel=linear; total time= 0.1s [CV] END ......................C=0.5, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ......................C=0.5, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ......................C=0.5, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ......................C=0.5, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ......................C=0.5, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ..................C=0.5, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ..................C=0.5, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ..................C=0.5, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ..................C=0.5, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ..................C=0.5, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ..................C=0.5, gamma=0.001, kernel=linear; total time= 0.1s [CV] END ..................C=0.5, gamma=0.001, kernel=linear; total time= 0.1s [CV] END ..................C=0.5, gamma=0.001, kernel=linear; total time= 0.1s [CV] END ..................C=0.5, gamma=0.001, kernel=linear; total time= 0.0s [CV] END ..................C=0.5, gamma=0.001, kernel=linear; total time= 0.0s [CV] END .....................C=0.5, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=0.5, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=0.5, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=0.5, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=0.5, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .................C=0.5, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=0.5, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=0.5, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=0.5, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=0.5, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=0.5, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END .................C=0.5, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END .................C=0.5, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END .................C=0.5, gamma=0.0001, kernel=linear; total time= 0.0s [CV] END .................C=0.5, gamma=0.0001, kernel=linear; total time= 0.0s [CV] END ....................C=0.5, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=0.5, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=0.5, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=0.5, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=0.5, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ................C=0.5, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=0.5, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=0.5, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=0.5, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=0.5, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ........................C=1, gamma=1, kernel=linear; total time= 0.1s [CV] END ........................C=1, gamma=1, kernel=linear; total time= 0.1s [CV] END ........................C=1, gamma=1, kernel=linear; total time= 0.1s [CV] END ........................C=1, gamma=1, kernel=linear; total time= 0.0s [CV] END ........................C=1, gamma=1, kernel=linear; total time= 0.1s [CV] END ...........................C=1, gamma=1, kernel=rbf; total time= 0.1s [CV] END ...........................C=1, gamma=1, kernel=rbf; total time= 0.1s [CV] END ...........................C=1, gamma=1, kernel=rbf; total time= 0.1s [CV] END ...........................C=1, gamma=1, kernel=rbf; total time= 0.1s [CV] END ...........................C=1, gamma=1, kernel=rbf; total time= 0.1s [CV] END .......................C=1, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .......................C=1, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .......................C=1, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .......................C=1, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .......................C=1, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ......................C=1, gamma=0.1, kernel=linear; total time= 0.1s [CV] END ......................C=1, gamma=0.1, kernel=linear; total time= 0.1s [CV] END ......................C=1, gamma=0.1, kernel=linear; total time= 0.1s [CV] END ......................C=1, gamma=0.1, kernel=linear; total time= 0.0s [CV] END ......................C=1, gamma=0.1, kernel=linear; total time= 0.1s [CV] END .........................C=1, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .........................C=1, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .........................C=1, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .........................C=1, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .........................C=1, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .....................C=1, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=1, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=1, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=1, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=1, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=1, gamma=0.01, kernel=linear; total time= 0.1s [CV] END .....................C=1, gamma=0.01, kernel=linear; total time= 0.1s [CV] END .....................C=1, gamma=0.01, kernel=linear; total time= 0.1s [CV] END .....................C=1, gamma=0.01, kernel=linear; total time= 0.0s [CV] END .....................C=1, gamma=0.01, kernel=linear; total time= 0.1s [CV] END ........................C=1, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ........................C=1, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ........................C=1, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ........................C=1, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ........................C=1, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ....................C=1, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ....................C=1, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ....................C=1, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ....................C=1, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ....................C=1, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ....................C=1, gamma=0.001, kernel=linear; total time= 0.1s [CV] END ....................C=1, gamma=0.001, kernel=linear; total time= 0.1s [CV] END ....................C=1, gamma=0.001, kernel=linear; total time= 0.1s [CV] END ....................C=1, gamma=0.001, kernel=linear; total time= 0.0s [CV] END ....................C=1, gamma=0.001, kernel=linear; total time= 0.1s [CV] END .......................C=1, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .......................C=1, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .......................C=1, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .......................C=1, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .......................C=1, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END ...................C=1, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ...................C=1, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ...................C=1, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ...................C=1, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ...................C=1, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ...................C=1, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END ...................C=1, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END ...................C=1, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END ...................C=1, gamma=0.0001, kernel=linear; total time= 0.0s [CV] END ...................C=1, gamma=0.0001, kernel=linear; total time= 0.1s [CV] END ......................C=1, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ......................C=1, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ......................C=1, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ......................C=1, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ......................C=1, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ..................C=1, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ..................C=1, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ..................C=1, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ..................C=1, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ..................C=1, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END .......................C=10, gamma=1, kernel=linear; total time= 0.6s [CV] END .......................C=10, gamma=1, kernel=linear; total time= 0.4s [CV] END .......................C=10, gamma=1, kernel=linear; total time= 0.3s [CV] END .......................C=10, gamma=1, kernel=linear; total time= 0.2s [CV] END .......................C=10, gamma=1, kernel=linear; total time= 0.3s [CV] END ..........................C=10, gamma=1, kernel=rbf; total time= 0.1s [CV] END ..........................C=10, gamma=1, kernel=rbf; total time= 0.1s [CV] END ..........................C=10, gamma=1, kernel=rbf; total time= 0.1s [CV] END ..........................C=10, gamma=1, kernel=rbf; total time= 0.1s [CV] END ..........................C=10, gamma=1, kernel=rbf; total time= 0.1s [CV] END ......................C=10, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ......................C=10, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ......................C=10, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ......................C=10, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ......................C=10, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=10, gamma=0.1, kernel=linear; total time= 0.5s [CV] END .....................C=10, gamma=0.1, kernel=linear; total time= 0.4s [CV] END .....................C=10, gamma=0.1, kernel=linear; total time= 0.3s [CV] END .....................C=10, gamma=0.1, kernel=linear; total time= 0.2s [CV] END .....................C=10, gamma=0.1, kernel=linear; total time= 0.3s [CV] END ........................C=10, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END ........................C=10, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END ........................C=10, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END ........................C=10, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END ........................C=10, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END ....................C=10, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=10, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=10, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=10, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=10, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=10, gamma=0.01, kernel=linear; total time= 0.6s [CV] END ....................C=10, gamma=0.01, kernel=linear; total time= 0.4s [CV] END ....................C=10, gamma=0.01, kernel=linear; total time= 0.3s [CV] END ....................C=10, gamma=0.01, kernel=linear; total time= 0.2s [CV] END ....................C=10, gamma=0.01, kernel=linear; total time= 0.3s [CV] END .......................C=10, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END .......................C=10, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END .......................C=10, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END .......................C=10, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END .......................C=10, gamma=0.01, kernel=rbf; total time= 0.1s [CV] END ...................C=10, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ...................C=10, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ...................C=10, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ...................C=10, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ...................C=10, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ...................C=10, gamma=0.001, kernel=linear; total time= 0.5s [CV] END ...................C=10, gamma=0.001, kernel=linear; total time= 0.4s [CV] END ...................C=10, gamma=0.001, kernel=linear; total time= 0.3s [CV] END ...................C=10, gamma=0.001, kernel=linear; total time= 0.2s [CV] END ...................C=10, gamma=0.001, kernel=linear; total time= 0.3s [CV] END ......................C=10, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END ......................C=10, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END ......................C=10, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END ......................C=10, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END ......................C=10, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END ..................C=10, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ..................C=10, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ..................C=10, gamma=0.001, kernel=sigmoid; total time= 0.1s [CV] END ..................C=10, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ..................C=10, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END ..................C=10, gamma=0.0001, kernel=linear; total time= 0.7s [CV] END ..................C=10, gamma=0.0001, kernel=linear; total time= 0.4s [CV] END ..................C=10, gamma=0.0001, kernel=linear; total time= 0.3s [CV] END ..................C=10, gamma=0.0001, kernel=linear; total time= 0.2s [CV] END ..................C=10, gamma=0.0001, kernel=linear; total time= 0.3s [CV] END .....................C=10, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END .....................C=10, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END .....................C=10, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END .....................C=10, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END .....................C=10, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END .................C=10, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END .................C=10, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END .................C=10, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END .................C=10, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END .................C=10, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ......................C=100, gamma=1, kernel=linear; total time= 9.8s [CV] END ......................C=100, gamma=1, kernel=linear; total time= 5.1s [CV] END ......................C=100, gamma=1, kernel=linear; total time= 10.0s [CV] END ......................C=100, gamma=1, kernel=linear; total time= 3.6s [CV] END ......................C=100, gamma=1, kernel=linear; total time= 5.2s [CV] END .........................C=100, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=100, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=100, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=100, gamma=1, kernel=rbf; total time= 0.1s [CV] END .........................C=100, gamma=1, kernel=rbf; total time= 0.1s [CV] END .....................C=100, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=100, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=100, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=100, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END .....................C=100, gamma=1, kernel=sigmoid; total time= 0.0s [CV] END ....................C=100, gamma=0.1, kernel=linear; total time= 11.1s [CV] END ....................C=100, gamma=0.1, kernel=linear; total time= 4.7s [CV] END ....................C=100, gamma=0.1, kernel=linear; total time= 8.4s [CV] END ....................C=100, gamma=0.1, kernel=linear; total time= 2.0s [CV] END ....................C=100, gamma=0.1, kernel=linear; total time= 3.8s [CV] END .......................C=100, gamma=0.1, kernel=rbf; total time= 0.2s [CV] END .......................C=100, gamma=0.1, kernel=rbf; total time= 0.1s [CV] END .......................C=100, gamma=0.1, kernel=rbf; total time= 0.2s [CV] END .......................C=100, gamma=0.1, kernel=rbf; total time= 0.3s [CV] END .......................C=100, gamma=0.1, kernel=rbf; total time= 0.2s [CV] END ...................C=100, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=100, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=100, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=100, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=100, gamma=0.1, kernel=sigmoid; total time= 0.0s [CV] END ...................C=100, gamma=0.01, kernel=linear; total time= 10.5s [CV] END ...................C=100, gamma=0.01, kernel=linear; total time= 4.6s [CV] END ...................C=100, gamma=0.01, kernel=linear; total time= 7.4s [CV] END ...................C=100, gamma=0.01, kernel=linear; total time= 1.8s [CV] END ...................C=100, gamma=0.01, kernel=linear; total time= 3.4s [CV] END ......................C=100, gamma=0.01, kernel=rbf; total time= 0.2s [CV] END ......................C=100, gamma=0.01, kernel=rbf; total time= 0.2s [CV] END ......................C=100, gamma=0.01, kernel=rbf; total time= 0.2s [CV] END ......................C=100, gamma=0.01, kernel=rbf; total time= 0.3s [CV] END ......................C=100, gamma=0.01, kernel=rbf; total time= 0.2s [CV] END ..................C=100, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ..................C=100, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ..................C=100, gamma=0.01, kernel=sigmoid; total time= 0.1s [CV] END ..................C=100, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ..................C=100, gamma=0.01, kernel=sigmoid; total time= 0.0s [CV] END ..................C=100, gamma=0.001, kernel=linear; total time= 10.6s [CV] END ..................C=100, gamma=0.001, kernel=linear; total time= 5.0s [CV] END ..................C=100, gamma=0.001, kernel=linear; total time= 9.5s [CV] END ..................C=100, gamma=0.001, kernel=linear; total time= 2.2s [CV] END ..................C=100, gamma=0.001, kernel=linear; total time= 4.1s [CV] END .....................C=100, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=100, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=100, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .....................C=100, gamma=0.001, kernel=rbf; total time= 0.2s [CV] END .....................C=100, gamma=0.001, kernel=rbf; total time= 0.1s [CV] END .................C=100, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=100, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=100, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=100, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=100, gamma=0.001, kernel=sigmoid; total time= 0.0s [CV] END .................C=100, gamma=0.0001, kernel=linear; total time= 10.9s [CV] END .................C=100, gamma=0.0001, kernel=linear; total time= 4.5s [CV] END .................C=100, gamma=0.0001, kernel=linear; total time= 7.5s [CV] END .................C=100, gamma=0.0001, kernel=linear; total time= 1.8s [CV] END .................C=100, gamma=0.0001, kernel=linear; total time= 3.4s [CV] END ....................C=100, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=100, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=100, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=100, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ....................C=100, gamma=0.0001, kernel=rbf; total time= 0.1s [CV] END ................C=100, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=100, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=100, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=100, gamma=0.0001, kernel=sigmoid; total time= 0.1s [CV] END ................C=100, gamma=0.0001, kernel=sigmoid; total time= 0.1s
print(grid_search.best_params_){'C': 1, 'gamma': 1, 'kernel': 'rbf'}
best_model.score(X_test, y_test)
0.8951048951048951
Najlepszy okazal sie model z funkcja jadra RBF oraz z C = 1 oraz gamma = 1. Skutecznosc wzrosla az do 89%. Mozna by pewnie zawężać jeszcze C oraz gamma aby uzyskac jeszcze wieksza dokladnosc.
from sklearn.metrics import plot_confusion_matrix
plot_confusion_matrix(best_model, X_test, y_test, display_labels=['Died', 'Survived'], cmap='Blues', xticks_rotation='vertical')/usr/local/lib/python3.9/site-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function plot_confusion_matrix is deprecated; Function `plot_confusion_matrix` is deprecated in 1.0 and will be removed in 1.2. Use one of the class methods: ConfusionMatrixDisplay.from_predictions or ConfusionMatrixDisplay.from_estimator. warnings.warn(msg, category=FutureWarning)
<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x1244ac610>
Confusion matrix pokazujący rozklad TP, TN, FP oraz FN. W zależności od tego czy bardziej chcemy unikac FN czy tez FP mozna doostosowac model, nawet kosztem ogolnej skutecznosci.