问如何在scikit中创建自定义的评分函数--学习如何根据实例的各个属性对一组实例进行评分？

EN

# Invalid inputs
if y.ndim > 2 or (y.dtype == object and len(y) and
                  not isinstance(y.flat[0], string_types)):
    # return 'unknown'  # [[[1, 2]]] or [obj_1] and not ["label_1"]
    return 'binary' # Sneaky, modified to force binary classification.

import sklearn
import sklearn.model_selection
import sklearn.base
import sklearn.metrics
import numpy as np
import sklearn.tree
import sklearn.feature_selection
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.metrics.scorer import make_scorer


class PseudoInt(int):
    # Behaves like an integer, but is able to store instance variables
    pass


def grid_search(x, y_normal, x_amounts):
    # Change the label set to a np array containing pseudo ints with the costs associated with the instances
    y = np.empty(len(y_normal), dtype=PseudoInt)
    for index, value in y_normal.iteritems():
        new_int = PseudoInt(value)
        new_int.cost = x_amounts.loc[index]  # Here the cost is added to the label
        y[index] = new_int

    # Normal train test split
    x_train, x_test, y_train, y_test = sklearn.model_selection.train_test_split(x, y, test_size=0.2)

    # Classifier
    clf = sklearn.tree.DecisionTreeClassifier()

    # Custom scorer with the cost function below (lower cost is better)
    cost_scorer = make_scorer(cost_function, greater_is_better=False)  # Custom cost function (Lower cost is better)

    # Define pipeline
    pipe = Pipeline([('clf', clf)])

    # Grid search grid with any hyper parameters or other settings
    param_grid = [
        {'sfs__estimator__criterion': ['gini', 'entropy']}
    ]

    # Grid search and pass the custom scorer function
    gs = GridSearchCV(estimator=pipe,
                      param_grid=param_grid,
                      scoring=cost_scorer,
                      n_jobs=1,
                      cv=5,
                      refit=True)

    # run grid search and refit with best hyper parameters
    gs = gs.fit(x_train.as_matrix(), y_train)
    print("Best Parameters: " + str(gs.best_params_))
    print('Best Accuracy: ' + str(gs.best_score_))

    # Predict with retrained model (with best parameters)
    y_test_pred = gs.predict(x_test.as_matrix())

    # Get scores (also cost score)
    get_scores(y_test, y_test_pred)


def get_scores(y_test, y_test_pred):
    print("Getting scores")

    print("SCORES")
    precision = sklearn.metrics.precision_score(y_test, y_test_pred)
    recall = sklearn.metrics.recall_score(y_test, y_test_pred)
    f1_score = sklearn.metrics.f1_score(y_test, y_test_pred)
    accuracy = sklearn.metrics.accuracy_score(y_test, y_test_pred)
    print("Precision      " + str(precision))
    print("Recall         " + str(recall))
    print("Accuracy       " + str(accuracy))
    print("F1_Score       " + str(f1_score))

    print("COST")
    cost = cost_function(y_test, y_test_pred)
    print("Cost Savings   " + str(-cost))

    print("CONFUSION MATRIX")
    cnf_matrix = sklearn.metrics.confusion_matrix(y_test, y_test_pred)
    cnf_matrix = cnf_matrix.astype('float') / cnf_matrix.sum(axis=1)[:, np.newaxis]
    print(cnf_matrix)


def cost_function(y_test, y_test_pred):
    """
    Calculates total cost based on TP, FP, TN, FN and the cost of a certain instance
    :param y_test: Has to be an array of PseudoInts containing the cost of each instance
    :param y_test_pred: Any array of PseudoInts or ints
    :return: Returns total cost
    """
    cost = 0

    for index in range(len(y_test)):
        # print(index)
        y = y_test[index]
        y_pred = y_test_pred[index]
        x_amt = y.cost

        if y == 0 and y_pred == 0:
            cost -= x_amt # Reducing cot by x_amt
        elif y == 0 and y_pred == 1:
            cost += x_amt  # Wrong classification adds cost
        elif y == 1 and y_pred == 0:
            cost += x_amt + 5 # Wrong classification adds cost and fee
        elif y == 1 and y_pred == 1:
            cost += 0  # No cost
        else:
            raise ValueError("No cost could be assigned to the instance: " + str(index))

    # print("Cost: " + str(cost))
    return cost

import sklearn.utils.multiclass

def return_binary(y):
    return "binary"

sklearn.utils.multiclass.type_of_target = return_binary