python - 在管道中的分类器之后使用度量

Question

我继续调查管道。我的目标是仅使用管道执行机器学习的每个步骤。将我的管道与其他用例相适应会更加灵活和容易。所以我做什么:

• 第 1 步:填充 NaN 值
• 第 2 步:将分类值转换为数字
• 第 3 步:分类器
• 第 4 步:网格搜索
• 第 5 步:添加指标(失败)

这是我的代码:

import pandas as pd
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.feature_selection import SelectKBest
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.metrics import f1_score


class FillNa(BaseEstimator, TransformerMixin):

    def transform(self, x, y=None):
            non_numerics_columns = x.columns.difference(
                x._get_numeric_data().columns)
            for column in x.columns:
                if column in non_numerics_columns:
                    x.loc[:, column] = x.loc[:, column].fillna(
                        df[column].value_counts().idxmax())
                else:
                    x.loc[:, column] = x.loc[:, column].fillna(
                        x.loc[:, column].mean())
            return x

    def fit(self, x, y=None):
        return self


class CategoricalToNumerical(BaseEstimator, TransformerMixin):

    def transform(self, x, y=None):
        non_numerics_columns = x.columns.difference(
            x._get_numeric_data().columns)
        le = LabelEncoder()
        for column in non_numerics_columns:
            x.loc[:, column] = x.loc[:, column].fillna(
                x.loc[:, column].value_counts().idxmax())
            le.fit(x.loc[:, column])
            x.loc[:, column] = le.transform(x.loc[:, column]).astype(int)
        return x

    def fit(self, x, y=None):
        return self


class Perf(BaseEstimator, TransformerMixin):

    def fit(self, clf, x, y, perf="all"):
        """Only for classifier model.

        Return AUC, ROC, Confusion Matrix and F1 score from a classifier and df
        You can put a list of eval instead a string for eval paramater.
        Example: eval=['all', 'auc', 'roc', 'cm', 'f1'] will return these 4
        evals.
        """
        evals = {}
        y_pred_proba = clf.predict_proba(x)[:, 1]
        y_pred = clf.predict(x)
        perf_list = perf.split(',')
        if ("all" or "roc") in perf.split(','):
            fpr, tpr, _ = roc_curve(y, y_pred_proba)
            roc_auc = round(auc(fpr, tpr), 3)
            plt.style.use('bmh')
            plt.figure(figsize=(12, 9))
            plt.title('ROC Curve')
            plt.plot(fpr, tpr, 'b',
                     label='AUC = {}'.format(roc_auc))
            plt.legend(loc='lower right', borderpad=1, labelspacing=1,
                       prop={"size": 12}, facecolor='white')
            plt.plot([0, 1], [0, 1], 'r--')
            plt.xlim([-0.1, 1.])
            plt.ylim([-0.1, 1.])
            plt.ylabel('True Positive Rate')
            plt.xlabel('False Positive Rate')
            plt.show()

        if "all" in perf_list or "auc" in perf_list:
            fpr, tpr, _ = roc_curve(y, y_pred_proba)
            evals['auc'] = auc(fpr, tpr)

        if "all" in perf_list or "cm" in perf_list:
            evals['cm'] = confusion_matrix(y, y_pred)

        if "all" in perf_list or "f1" in perf_list:
            evals['f1'] = f1_score(y, y_pred)

        return evals


path = '~/proj/akd-doc/notebooks/data/'
df = pd.read_csv(path + 'titanic_tuto.csv', sep=';')
y = df.pop('Survival-Status').replace(to_replace=['dead', 'alive'],
                                      value=[0., 1.])
X = df.copy()
X_train, X_test, y_train, y_test = train_test_split(
    X.copy(), y.copy(), test_size=0.2, random_state=42)

percent = 0.50
nb_features = round(percent * df.shape[1]) + 1
clf = RandomForestClassifier()
pipeline = Pipeline([('fillna', FillNa()),
                     ('categorical_to_numerical', CategoricalToNumerical()),
                     ('features_selection', SelectKBest(k=nb_features)),
                     ('random_forest', clf),
                     ('perf', Perf())])

params = dict(random_forest__max_depth=list(range(8, 12)),
              random_forest__n_estimators=list(range(30, 110, 10)))
cv = GridSearchCV(pipeline, param_grid=params)
cv.fit(X_train, y_train)

我知道打印 roc 曲线并不理想，但现在这不是问题。

所以，当我执行这段代码时，我有:

TypeError: If no scoring is specified, the estimator passed should have a 'score' method. The estimator Pipeline(steps=[('fillna', FillNa()), ('categorical_to_numerical', CategoricalToNumerical()), ('features_selection', SelectKBest(k=10, score_func=<function f_classif at 0x7f4ed4c3eae8>)), ('random_forest', RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None,...=1, oob_score=False, random_state=None,
            verbose=0, warm_start=False)), ('perf', Perf())]) does not.

我对所有的想法都感兴趣......

Answer 1

如错误所述，您需要在 GridSearchCV 中指定评分参数。

使用

GridSearchCV(pipeline, param_grid=params, scoring = 'accuracy')

编辑(根据评论中的问题):

如果您需要整个 X_train 和 y_train(而不是 GridSearchCV 的所有拆分)的 roc、auc 曲线和 f1，最好将 Perf 类排除在管道之外。

pipeline = Pipeline([('fillna', FillNa()),
                     ('categorical_to_numerical', CategoricalToNumerical()),
                     ('features_selection', SelectKBest(k=nb_features)),
                     ('random_forest', clf)])

#Fit the data in the pipeline
pipeline.fit(X_train, y_train)

performance_meas = Perf()
performance_meas.fit(pipeline, X_train, y_train)