测量KNN分类器的准确性

Question

我写了以下代码来实现KNN。

from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors=5)
classifier.fit(x,y)
classifier.score(x,y)
y_predict_classifier=classifier.predict(x_test)

问题是，当我试图使用准确度分数来计算准确度时，它给了我以下错误。

ValueError                                Traceback (most recent call last)
<ipython-input-128-358130e4f0a2> in <module>
----> 1 print("Accuracy:",metrics.accuracy_score(y_test, y_predict_classifier))

~\Anaconda3\lib\site-packages\sklearn\metrics\_classification.py in accuracy_score(y_true, y_pred, normalize, sample_weight)
    183 
    184     # Compute accuracy for each possible representation
--> 185     y_type, y_true, y_pred = _check_targets(y_true, y_pred)
    186     check_consistent_length(y_true, y_pred, sample_weight)
    187     if y_type.startswith('multilabel'):

~\Anaconda3\lib\site-packages\sklearn\metrics\_classification.py in _check_targets(y_true, y_pred)
     78     y_pred : array or indicator matrix
     79     """
---> 80     check_consistent_length(y_true, y_pred)
     81     type_true = type_of_target(y_true)
     82     type_pred = type_of_target(y_pred)

~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_consistent_length(*arrays)
    210     if len(uniques) > 1:
    211         raise ValueError("Found input variables with inconsistent numbers of"
--> 212                          " samples: %r" % [int(l) for l in lengths])
    213 
    214 

ValueError: Found input variables with inconsistent numbers of samples: [176701, 1]

我打印了y和y_predict_classifier的形状，我得到的结果分别是(176701,)和(1,)。

谁能告诉我如何解决这个错误？

Answer 1

这个怎么样？

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd


url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"

# Assign colum names to the dataset
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'Class']

# Read dataset to pandas dataframe
dataset = pd.read_csv(url, names=names)


dataset.head()


X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 4].values


from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20)


from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
scaler.fit(X_train)

X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)


from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors=5, metric='minkowski')
classifier.fit(X_train, y_train)


y_pred = classifier.predict(X_test)


from sklearn.metrics import classification_report, confusion_matrix
print(confusion_matrix(y_test, y_pred))
print(classification_report(y_test, y_pred))

结果:

                 precision    recall  f1-score   support

    Iris-setosa       1.00      1.00      1.00        13
Iris-versicolor       1.00      0.89      0.94         9
 Iris-virginica       0.89      1.00      0.94         8

       accuracy                           0.97        30
      macro avg       0.96      0.96      0.96        30
   weighted avg       0.97      0.97      0.97        30

继续...

error = []
# Calculating error for K values between 1 and 40
for i in range(1, 40):
    knn = KNeighborsClassifier(n_neighbors=i)
    knn.fit(X_train, y_train)
    pred_i = knn.predict(X_test)
    error.append(np.mean(pred_i != y_test))

plt.figure(figsize=(12, 6))
plt.plot(range(1, 40), error, color='red', linestyle='dashed', marker='o',
         markerfacecolor='blue', markersize=10)
plt.title('Error Rate K Value')
plt.xlabel('K Value')
plt.ylabel('Mean Error')