python - 在 Pandas 数据框中保存网格搜索中的最佳参数

Question

我需要将所有参数组合和相应的准确度保存在一种 pandas 数据框中。

我希望，我很清楚，请指出，如果我做错了。

示例代码是:

from sklearn.grid_search import GridSearchCV
import sklearn
from sklearn.ensemble import RandomForestClassifier


X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(iris.data, iris.target, test_size=0.3, random_state=0)

rfc = RandomForestClassifier(n_jobs=-1,max_features= 'sqrt' ,n_estimators=50, oob_score = True) 

param_grid = {
    'n_estimators': [200, 700],
    'max_features': ['auto', 'sqrt', 'log2'],
    'criterion' : ['gini', 'entropy']
}

CV_rfc = GridSearchCV(estimator=rfc, param_grid=param_grid, cv= 5)
CV_rfc.fit(X_train, y_train)
CV_rfc.grid_scores_

我在 sklearn 中使用 Grid Search CV，以获得最佳参数。但是，我担心的是，有什么办法可以将所有不同的参数组合和相应的精度存储在 pandas 数据框中，我可以将其保存在 CSV 文件中以备后用。

[mean: 0.94286, std: 0.05344, params: {'criterion': 'gini', 'max_features': 'auto', 'n_estimators': 200},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'gini', 'max_features': 'auto', 'n_estimators': 700},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 200},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'gini', 'max_features': 'sqrt', 'n_estimators': 700},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'gini', 'max_features': 'log2', 'n_estimators': 200},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'gini', 'max_features': 'log2', 'n_estimators': 700},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'entropy', 'max_features': 'auto', 'n_estimators': 200},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'entropy', 'max_features': 'auto', 'n_estimators': 700},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 200},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'entropy', 'max_features': 'sqrt', 'n_estimators': 700},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'entropy', 'max_features': 'log2', 'n_estimators': 200},
 mean: 0.94286, std: 0.05344, params: {'criterion': 'entropy', 'max_features': 'log2', 'n_estimators': 700}]

所以，我有这些值的列表，我想要它的数据框，以保存在 csv 文件中。

len(CV_rfc.grid_scores_)
12

Answer 1

我在网上找到它，代码是针对 python 2 的，但我将其修复为在 python 3 上运行。

这是我在那里找到的。

import pandas as pd
from sklearn.grid_search import GridSearchCV
import numpy as np

class EstimatorSelectionHelper:
    def __init__(self, models, params):
        if not set(models.keys()).issubset(set(params.keys())):
            missing_params = list(set(models.keys()) - set(params.keys()))
            raise ValueError("Some estimators are missing parameters: %s" % missing_params)
        self.models = models
        self.params = params
        self.keys = models.keys()
        self.grid_searches = {}

    def fit(self, X, y, cv=3, n_jobs=1, verbose=1, scoring=None, refit=False):
        for key in self.keys:
            print("Running GridSearchCV for %s." % key)
            model = self.models[key]
            params = self.params[key]
            gs = GridSearchCV(model, params, cv=cv, n_jobs=n_jobs, 
                              verbose=verbose, scoring=scoring, refit=refit)
            gs.fit(X,y)
            self.grid_searches[key] = gs    

    def score_summary(self, sort_by='mean_score'):
        def row(key, scores, params):
            d = {
                 'estimator': key,
                 'min_score': min(scores),
                 'max_score': max(scores),
                 'mean_score': np.mean(scores),
                 'std_score': np.std(scores),
            }
            return pd.Series({**params,**d})

        rows = [row(k, gsc.cv_validation_scores, gsc.parameters) 
                     for k in self.keys
                     for gsc in self.grid_searches[k].grid_scores_]
        df = pd.concat(rows, axis=1).T.sort_values([sort_by], ascending=False)

        columns = ['estimator', 'min_score', 'mean_score', 'max_score', 'std_score']
        columns = columns + [c for c in df.columns if c not in columns]

        return df[columns]

from sklearn import datasets

iris = datasets.load_iris()
X_iris = iris.data
y_iris = iris.target

from sklearn.ensemble import (ExtraTreesClassifier, RandomForestClassifier, 
                              AdaBoostClassifier, GradientBoostingClassifier)
from sklearn.svm import SVC

models = {'RandomForestClassifier': RandomForestClassifier()}

params = {'RandomForestClassifier': { 'n_estimators': [16, 32],
                                      'max_features': ['auto', 'sqrt', 'log2'],
                                      'criterion' : ['gini', 'entropy'] }}

helper = EstimatorSelectionHelper(models, params)
helper.fit(X_iris, y_iris)

helper.score_summary()

输出:

Running GridSearchCV for RandomForestClassifier.
Fitting 3 folds for each of 12 candidates, totalling 36 fits
[Parallel(n_jobs=1)]: Done  36 out of  36 | elapsed:    1.7s finished
Out[31]:
estimator   min_score   mean_score  max_score   std_score   criterion   max_features    n_estimators
1   RandomForestClassifier  0.921569    0.96732 1   0.0333269   gini    auto    32
6   RandomForestClassifier  0.921569    0.96732 1   0.0333269   entropy auto    16
10  RandomForestClassifier  0.941176    0.966912    0.980392    0.0182045   entropy log2    16
2   RandomForestClassifier  0.901961    0.960784    1   0.0423578   gini    sqrt    16
4   RandomForestClassifier  0.921569    0.960376    0.980392    0.0274454   gini    log2    16
7   RandomForestClassifier  0.921569    0.960376    0.980392    0.0274454   entropy auto    32
8   RandomForestClassifier  0.921569    0.960376    0.980392    0.0274454   entropy sqrt    16
9   RandomForestClassifier  0.921569    0.960376    0.980392    0.0274454   entropy sqrt    32
3   RandomForestClassifier  0.941176    0.959967    0.980392    0.0160514   gini    sqrt    32
0   RandomForestClassifier  0.901961    0.95384 0.980392    0.0366875   gini    auto    16
11  RandomForestClassifier  0.901961    0.95384 0.980392    0.0366875   entropy log2    32
5   RandomForestClassifier  0.921569    0.953431    0.980392    0.0242635   gini    log2    32