Question

不知道问题是否与我分割数据集的方式有关，或者我做错了什么，但每次运行de程序时，我都会得到不同的准确度。有人可以帮我找出问题吗？谢谢这是我的代码：

import pandas as pd
import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier,     ExtraTreesClassifier, GradientBoostingClassifier
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC

# load the data
from sklearn.tree import DecisionTreeClassifier

# url = "data/lung-cancer.data"
url = "http://archive.ics.uci.edu/ml/machine-learning-databases/lung-        cancer/lung-cancer.data"
data_set = pd.read_csv(url)

def clean_data(data_set):
    # replace the ? with NaN
    data_set = data_set.convert_objects(convert_numeric=True)
    # replace the NaN with the average of the row
    data_set = data_set.fillna(data_set.mean(axis=0), axis=0)

    return data_set

data_set = clean_data(data_set)

def split_data(data_set):
    # split the data in two parts train(80%), test(20%)
    train, test = train_test_split(data_set.values, test_size=0.2)

    # first column of the data are labels
    labels_test = test[:, :1]
    labels_train = train[:, :1]

    # the rest of the columns are features
    features_test = test[:, 1:]
    features_train = train[:, 1:]

    return features_train, labels_train, features_test, labels_test

features_train, labels_train, features_test, labels_test = split_data(data_set)
"""
print(labels_train)
print(features_train)
print(features_test)
print(labels_test)
"""

# Modeling step Test different algorithms
random_state = 2
classifiers = [
    GaussianNB(),
    KNeighborsClassifier(n_neighbors=3),
    KNeighborsClassifier(n_neighbors=5),
    SVC(kernel="poly", C=0.4, probability=True),
    DecisionTreeClassifier(random_state=3),
    RandomForestClassifier(random_state=3),
    AdaBoostClassifier(random_state=3),
    ExtraTreesClassifier(random_state=3),
    GradientBoostingClassifier(random_state=3),
    MLPClassifier(random_state=random_state)
]

accuracy_res = []
algorithm_res = []
for clf in classifiers:
    clf.fit(features_train, labels_train)
    name = clf.__class__.__name__

    train_predictions = clf.predict(features_test)

    accuracy = accuracy_score(labels_test, train_predictions)
    print(name, "{:.4%}".format(accuracy))
    accuracy_res.append(accuracy)
    algorithm_res.append(name)
    print()

y_pos = np.arange(len(algorithm_res))
plt.barh(y_pos, accuracy_res, align='center', alpha=0.5)
plt.yticks(y_pos, algorithm_res)
plt.xlabel('Accuracy')
plt.title('Algorithms')
plt.show()

以下是我得到的结果：第一个结果

GaussianNB 28.5714%
KNeighborsClassifier 57.1429%
KNeighborsClassifier 71.4286%
SVC 57.1429%
DecisionTreeClassifier 57.1429%
RandomForestClassifier 42.8571%
AdaBoostClassifier 42.8571%
ExtraTreesClassifier 42.8571%
GradientBoostingClassifier 57.1429%
MLPClassifier 57.1429%

第二个结果

GaussianNB 28.5714%
KNeighborsClassifier 42.8571%
KNeighborsClassifier 28.5714%
SVC 57.1429%
DecisionTreeClassifier 28.5714%
RandomForestClassifier 57.1429%
AdaBoostClassifier 57.1429%
ExtraTreesClassifier 42.8571%
GradientBoostingClassifier 28.5714%
MLPClassifier 57.1429%

第三个结果

GaussianNB 71.4286%
KNeighborsClassifier 71.4286%
KNeighborsClassifier 71.4286%
SVC 28.5714%
DecisionTreeClassifier 28.5714%
RandomForestClassifier 57.1429%
AdaBoostClassifier 71.4286%
ExtraTreesClassifier 57.1429%
GradientBoostingClassifier 28.5714%
MLPClassifier 28.5714%

Answer 1

由于您使用的是train_test_split，它会随机分割您的数据，这会导致每次运行上述代码时的准确性不同。

我建议多次查看输出，并从多个输出中找出准确度的平均值。你可以重定向输出，让python为你做。采用模型给出最高的平均精度。

当我运行你的代码时，在使用带有n_neighbors = 5的KNeighborsClassifier时，我获得了最佳的准确性。我也做了一些修改，所以没有警告。请在下面找到更新的代码。我已经更新了评论，只要有修改供参考。

import pandas as pd
import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import AdaBoostClassifier, RandomForestClassifier,     ExtraTreesClassifier, GradientBoostingClassifier
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC

# load the data
from sklearn.tree import DecisionTreeClassifier

# url = "data/lung-cancer.data"
url = "http://archive.ics.uci.edu/ml/machine-learning-databases/lung-cancer/lung-cancer.data"
data_set = pd.read_csv(url)

def clean_data(data_set):
    # replace the ? with NaN
    # data_set = data_set.convert_objects(convert_numeric=True)
    # convert objects is deprecated
    data_set = data_set.apply(pd.to_numeric, errors='coerce')
    # replace the NaN with the average of the row
    data_set = data_set.fillna(data_set.mean(axis=0), axis=0)

    return data_set

data_set = clean_data(data_set)

def split_data(data_set):
    # split the data in two parts train(80%), test(20%)
    train, test = train_test_split(data_set.values, test_size=0.2)

    # first column of the data are labels
    labels_test = test[:, :1]
    labels_train = train[:, :1]

    # the rest of the columns are features
    features_test = test[:, 1:]
    features_train = train[:, 1:]

    return features_train, labels_train, features_test, labels_test

features_train, labels_train, features_test, labels_test = split_data(data_set)
"""
print(labels_train)
print(features_train)
print(features_test)
print(labels_test)
"""

# Modeling step Test different algorithms
random_state = 2
classifiers = [
    GaussianNB(),
    KNeighborsClassifier(n_neighbors=3),
    KNeighborsClassifier(n_neighbors=5),
    SVC(kernel="poly", C=0.4, probability=True),
    DecisionTreeClassifier(random_state=3),
    RandomForestClassifier(random_state=3),
    AdaBoostClassifier(random_state=3),
    ExtraTreesClassifier(random_state=3),
    GradientBoostingClassifier(random_state=3),
    # MLPClassifier(random_state=random_state)
    # Set hidden_layer_sizes and max_iter parameters 
    # so that multilayer perceptron will converge
    MLPClassifier(solver='lbfgs', hidden_layer_sizes=[100], max_iter=2000, activation='logistic', random_state=random_state)
]

accuracy_res = []
algorithm_res = []
for clf in classifiers:
    # clf.fit(features_train, labels_train)
    # Added ravel to convert column vector to 1d array
    clf.fit(features_train, labels_train.ravel())
    name = clf.__class__.__name__

    train_predictions = clf.predict(features_test)

    accuracy = accuracy_score(labels_test, train_predictions)
    print(name, "{:.4%}".format(accuracy))
    accuracy_res.append(accuracy)
    algorithm_res.append(name)
    print()

y_pos = np.arange(len(algorithm_res))
plt.barh(y_pos, accuracy_res, align='center', alpha=0.5)
plt.yticks(y_pos, algorithm_res)
plt.xlabel('Accuracy')
plt.title('Algorithms')
plt.show()

Answer 2

{{1}}

您使用了sklearn的train_test_split，它将您的数据拆分为Train_set和Test_set 随机。因此，每次重新训练模型时，数据都与其他版本的数据不相似。

http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html

Answer 3

更改此行

train, test = train_test_split(data_set.values, test_size=0.2)

到

train, test = train_test_split(data_set.values, test_size=0.2,random_state=0)

random_state的值不必一定为0，它可以是1或2或42。只要每次分裂发生时它的值都相同即可。然后，不同的运行将为您提供一致的结果。

无需修改代码即可获得不同的准确度

3 个答案: