0

好的，所以我想在我的数据集上运行具有 X 个特征的递归特征提取，并在每次迭代中删除排名最低的特征，而不是重新运行 RFE，直到我只剩下 5 个特征。但是，我不知道如何编码。

运行 RFE 的第一部分很好，但我不想坐下来手动重新运行 RFE 并一次删除一个功能，这将花费很长时间。有人可以帮我编码吗？

import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_score
from sklearn.metrics import accuracy_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import RFE
from sklearn.datasets import make_friedman1

X, y = make_friedman1(n_samples=2000, n_features=85, random_state=42)


# split data into train and test split
from sklearn.model_selection import train_test_split
# if we need train test split
X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.3,random_state=42)

estimator = RandomForestClassifier(n_estimators=500, min_samples_leaf=5,
                             min_samples_split=8, max_features='auto',
                             max_depth=90, bootstrap=True)
selector = RFE(estimator, 83, step=1)
selector = selector.fit(X_train, y_train)


# predict and get rankings and optimal number of features
selector.fit(X_test, y_test)
selector.predict(X_test)
ranking = selector.ranking_
y_hats = selector.predict(X_test)
predictions = [round(value) for value in y_hats]
accuracy = accuracy_score(y_test, predictions)
print("Test Accuracy: %.2f%%" % (accuracy*100.0))


# index rankings
header = X_test.columns
frame = pd.DataFrame(ranking, index=header)
frame = frame.rename(columns = {frame.columns[0]: 'rankings'}, inplace = False)
frame = frame.sort_values(by = 'rankings', ascending=True)

# save table
from pandas.tools.plotting import table
ax = plt.subplot(111, frame_on=True) # no visible frame
ax.xaxis.set_visible(False)  # hide the x axis
ax.yaxis.set_visible(False)  # hide the y axis

table(ax, frame)  # where df is your data frame
4

2 回答 2

0

通过非常简单地这样做自己解决了这个问题：

iters = list(range(1, 235))
iters = iters[::-1]

for i in iters:


    estimator = RandomForestClassifier(n_estimators=500, min_samples_leaf=5,
                             min_samples_split=8, max_features='auto',
                             max_depth=90, bootstrap=True)
    selector = RFE(estimator, i, step=1)
    selector = selector.fit(X_train, y_train)
于 2019-02-10T18:49:21.050 回答
0 
features = [1, 28, 9, 17, 0, 16, 9]

def recursive(features, max_features=5, max_iterations=100):
    feature_length = len(features)
    long_enough = (feature_length <= max_features)
    tried_too_many_times = (max_iterations < 1)
    if long_enough or tried_too_many_times:
        raise GeneratorExit(
            {
                'features': features,
                'iterations': max_iterations,
            }
        )
    _features = sorted(features, reverse=True)
    lowest = _features.pop()
    print('Removing', lowest)
    max_iterations -= 1
    yield from recursive(_features, max_features=max_features, max_iterations=max_iterations)


s = recursive(features)

try:
    list(s)
except GeneratorExit as e:
    context = e.args[0]

# Removing 0
# Removing 1

context
# {'features': [28, 17, 16, 9, 9], 'iterations': 98}
于 2019-02-09T21:36:40.947 回答