初识数据
from sklearn.datasets import load_iris
if __name__ == '__main__':
iris_dataset = load_iris()
print("数据集的键为:\n{}".format(iris_dataset.keys()))
print(iris_dataset['DESCR'][:193])
print("目标名字:{}".format(iris_dataset['target_names']))
print("特征的说明:{}".format(iris_dataset['feature_names']))
print("数据为:{}".format(iris_dataset['data']))
print("数据为:{}".format(iris_dataset['data'].shape))
print("品种为:{}".format(iris_dataset['target']))
print("品种为:{}".format(iris_dataset['target'].shape))
训练数据与测试数据
train_test_split解释
from sklearn.model_selection import train_test_split
if __name__ == '__main__':
X_train,X_test,Y_train,Y_test = train_test_split(iris_dataset['data'],
iris_dataset['target'],random_state=0)
print("X训练数据:{}".format(X_train.shape))
print("Y训练数据:{}".format(Y_train.shape))
print("X测试数据:{}".format(X_test.shape))
print("Y测试数据:{}".format(Y_test.shape))
观察数据
import pandas as pd
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
if __name__ == '__main__':
iris_dataframe = pd.DataFrame(X_train,columns=iris_dataset.feature_names)
cm3 = ListedColormap(['#0000aa', '#ff2020', '#50ff50'])
pd.plotting.scatter_matrix(iris_dataframe, c=Y_train, figsize=(15, 15),
marker='o', hist_kwds={'bins': 20}, s=60,
alpha=.8, cmap=cm3)
plt.show()
![在这里插入图片描述](https://i-blog.csdnimg.cn/blog_migrate/a69e2f80cb6bd602482a8463e715249e.png)
k邻近算法
from sklearn.neighbors import KNeighborsClassifier
if __name__ == '__main__':
knn = KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train,Y_train)
预测数据
if __name__ == '__main__':
X_new = np.array([[5, 2.9, 1, 0.2]])
prediction =knn.predict(X_new)
print("预测结果为:{}".format(prediction))
print("预测结果的种类为:{}".format(iris_dataset['target_names'][prediction]))
评估模型
if __name__ == '__main__':
y_pred = knn.predict(X_test)
print("预测结果:{}".format(y_pred))
print("精度:{:.2f}".format(knn.score(X_test,Y_test)))