KNN Python实现

Question

当我尝试运行我的代码时，如下所示：

FutureWarning:与其他还原函数(例如skew、kurtosis)不同，mode的默认行为通常保持它所遵循的轴。在SciPy 1.11.0中，此行为将发生变化：keepdims的默认值将变为False，统计数据所经过的axis将被消除，而None值将不再被接受。将keepdims设置为True或False以避免此警告。lab =模式(标签)

这是我的Python代码，我发现在寻找合适的解决方案时遇到了一些困难：

# Importing the required modules
import numpy as np
from scipy.stats import mode


# Euclidean Distance
def eucledian(p1, p2):
    dist = np.sqrt(np.sum((p1 - p2) ** 2))
    return dist


# Function to calculate KNN
def predict(x_train, y, x_input, k):
    op_labels = []

    # Loop through the Datapoints to be classified
    for item in x_input:

        # Array to store distances
        point_dist = []

        # Loop through each training Data
        for j in range(len(x_train)):
            distances = eucledian(np.array(x_train[j, :]), item)
            # Calculating the distance
            point_dist.append(distances)
        point_dist = np.array(point_dist)

        # Sorting the array while preserving the index
        # Keeping the first K datapoints
        dist = np.argsort(point_dist)[:k]

        # Labels of the K datapoints from above
        labels = y[dist]

       ** # Majority voting
        lab = mode(labels)
        lab = lab.mode[0]
        op_labels.append(lab)**

    return op_labels

# Importing the required modules
# Importing required modules
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_iris
from numpy.random import randint

# Loading the Data

iris= load_iris()

# Store features matrix in X

X= iris.data

# Store target vector in

y = iris.target

# Creating the training Data

train_idx = xxx = randint(0, 150, 100)

X_train = X[train_idx]

y_train = y[train_idx]

# Creating the testing Data

test_idx = xxx = randint(0, 150, 50)  # taking 50 random samples
X_test = X[test_idx]
y_test = y[test_idx]

# Applying our function
y_pred = predict(X_train, y_train, X_test, 7)

# Checking the accuracy
accuracy_score(y_test, y_pred)

我期待一个预测/准确的提示。

Answer 1

KNN可以这样做。

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))

# Result:
                 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


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')

​

​