habush / sklearn-genetic-opt Goto Github PK

from sklearn_genetic import GASearchCV
from sklearn_genetic.space import Continuous, Categorical, Integer
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split, StratifiedKFold
from sklearn.datasets import load_digits
from sklearn.metrics import accuracy_score

data = load_digits()
n_samples = len(data.images)
X = data.images.reshape((n_samples, -1))
y = data['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)

clf = RandomForestClassifier()

param_grid = {'min_weight_fraction_leaf': Continuous(0.01, 0.5, distribution='log-uniform'),
              'bootstrap': Categorical([True, False]),
              'max_depth': Integer(2, 30),
              'max_leaf_nodes': Integer(2, 35),
              'n_estimators': Integer(100, 300)}

cv = StratifiedKFold(n_splits=3, shuffle=True)

evolved_estimator = GASearchCV(estimator=clf,
                               cv=cv,
                               scoring='accuracy',
                               population_size=10,
                               generations=35,
                               param_grid=param_grid,
                               n_jobs=-1,
                               verbose=True,
                               keep_top_k=4)

# Train and optimize the estimator
evolved_estimator.fit(X_train, y_train)
# Best parameters found
print(evolved_estimator.best_params_)
# Use the model fitted with the best parameters
y_predict_ga = evolved_estimator.predict(X_test)
print(accuracy_score(y_test, y_predict_ga))

# Saved metadata for further analysis
print("Stats achieved in each generation: ", evolved_estimator.history)
print("Best k solutions: ", evolved_estimator.hof)

import matplotlib.pyplot as plt
from sklearn_genetic import GAFeatureSelectionCV
from sklearn.model_selection import train_test_split, StratifiedKFold
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score
import numpy as np

data = load_iris()
X, y = data["data"], data["target"]

# Add random non-important features
noise = np.random.uniform(0, 10, size=(X.shape[0], 5))
X = np.hstack((X, noise))

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=0)

clf = SVC(gamma='auto')

evolved_estimator = GAFeatureSelectionCV(
    estimator=clf,
    scoring="accuracy",
    population_size=30,
    generations=20,
    n_jobs=-1)

# Train and select the features
evolved_estimator.fit(X_train, y_train)

# Features selected by the algorithm
features = evolved_estimator.best_features_
print(features)

# Predict only with the subset of selected features
y_predict_ga = evolved_estimator.predict(X_test[:, features])
print(accuracy_score(y_test, y_predict_ga))