Kaggle Masterに学ぶ機械学習実践アプローチ 写経 08

# %%
import numpy as np
import pandas as pd

from functools import partial

from sklearn import ensemble, metrics, model_selection

from skopt import gp_minimize, space

def optimize(params, param_names, x, y):
    params = dict(zip(param_names, params))
    model = ensemble.RandomForestClassifier(**params)
    kf = model_selection.StratifiedKFold(n_splits=5)

    accuracies = []
    for train_idx, test_idx in kf.split(X=x, y=y):
        x_train = x.iloc[train_idx].values
        y_train = y.iloc[train_idx].values
        x_test = x.iloc[test_idx].values
        y_test = y.iloc[test_idx].values

        model.fit(x_train, y_train)
        preds = model.predict(x_test)

        fold_accuracy = metrics.accuracy_score(y_test, preds)
        accuracies.append(fold_accuracy)

    return -1 * np.mean(accuracies)

if __name__ == "__main__":
    df = pd.read_csv("../input/train.csv")
    # 目的変数を削除
    X = df.drop("price_range", axis=1)
    y = df.price_range

    param_space = [
        # max_depthは1から10の範囲で整数
        space.Integer(3, 15, name="max_depth"),
        # n_estimatorsは100から1000の範囲で整数
        space.Integer(100, 1500, name="n_estimators"),
        # criterionはカテゴリ型のリスト
        space.Categorical(["gini", "entropy"], name="criterion"),
        # 分布を指定したreal型も扱える
        space.Real(0.01, 1, prior="uniform", name="max_features")
    ]

    param_names = ["max_depth", "n_estimators", "criterion", "max_features"]
    optimization_function = partial(optimize, param_names=param_names, x=X, y=y)
    result = gp_minimize(optimization_function, dimensions = param_space, n_calls=15, n_random_starts=10, verbose=10)
    best_params = dict(zip(param_names, result.x))

    print(best_params)


# %%
import matplotlib.pyplot as plt

# %%
from skopt.plots import plot_convergence

plot_convergence(result)

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn import model_selection


if __name__ == "__main__":
    df = pd.read_csv("../input/train.csv")
    
    X = df.drop("price_range", axis=1)

    y = df.price_range.values

    classifier = RandomForestClassifier(n_jobs=-1)

    param_grid = {
        "n_estimators": [100, 200, 300, 400, 500],
        "max_depth": [1,2,5,7,11,15],
        "criterion": ["gini", "entropy"]
    }

    model = model_selection.GridSearchCV(
        estimator=classifier,
        param_grid=param_grid,
        scoring="accuracy",
        verbose=10,
        cv=5,
        n_jobs=-1
    )

    model.fit(X, y)
    print(f"Best score: {model.best_score_}")
    print("best parameters set")

    best_parameters = model.best_estimator_.get_params()
    for param_name in sorted(best_parameters.keys()):
        print(f"{param_name}: {best_parameters[param_name]}")

    print("")

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn import model_selection


if __name__ == "__main__":
    df = pd.read_csv("../input/train.csv")
    
    X = df.drop("price_range", axis=1)

    y = df.price_range.values

    classifier = RandomForestClassifier(n_jobs=-1)

    param_grid = {
        "n_estimators": [100, 200, 300, 400, 500],
        "max_depth": [1,2,5,7,11,15],
        "criterion": ["gini", "entropy"]
    }

    model = model_selection.RandomizedSearchCV(
        estimator=classifier,
        param_distributions=param_grid,
        scoring="accuracy",
        verbose=10,
        cv=5,
        n_jobs=-1,
        n_iter=20
    )

    model.fit(X, y)
    print(f"Best score: {model.best_score_}")
    print("best parameters set")

    best_parameters = model.best_estimator_.get_params()
    for param_name in sorted(best_parameters.keys()):
        print(f"{param_name}: {best_parameters[param_name]}")

    print("")

# %%
import numpy as np
import pandas as pd

from functools import partial

from sklearn import ensemble, metrics, model_selection

from hyperopt import hp, fmin, tpe, Trials
from hyperopt.pyll.base import scope

def optimize(params, x, y):

    model = ensemble.RandomForestClassifier(**params)
    kf = model_selection.StratifiedKFold(n_splits=5)

    accuracies = []
    for train_idx, test_idx in kf.split(X=x, y=y):
        x_train = x.iloc[train_idx].values
        y_train = y.iloc[train_idx].values
        x_test = x.iloc[test_idx].values
        y_test = y.iloc[test_idx].values

        model.fit(x_train, y_train)
        preds = model.predict(x_test)

        fold_accuracy = metrics.accuracy_score(y_test, preds)
        accuracies.append(fold_accuracy)

    return -1 * np.mean(accuracies)

if __name__ == "__main__":
    df = pd.read_csv("../input/train.csv")
    # 目的変数を削除
    X = df.drop("price_range", axis=1)
    y = df.price_range

    param_space = {
        "max_depth": scope.int(hp.quniform('max_depth', 3, 15, 1)),
        "n_estimators": scope.int(hp.quniform('n_estimators', 100, 1500, 1)),
        "criterion": hp.choice("criterion", ["gini", "entropy"]),
        "max_features": hp.uniform("max_features", 0.01, 1)
    }

    optimization_function = partial(optimize, x=X, y=y)
    trials = Trials()
    hopt = fmin(fn=optimization_function, space=param_space, algo=tpe.suggest, max_evals=15, trials=trials)

    print(hopt)