使用支持向量机根据损坏数据对建筑物进行分类

Question

我有一项大学任务要完成。它是关于基于 damage 分类（1-5）的几个建筑物的分类（有 6 个参数）。我按照 SVM 的指导进行了编码，但不确定输出的准确性。你能告诉我如何改进我的结果以及算法的其他选择是什么。 ''' # 支持向量机（SVM）

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Ehsan Duzce.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 7].values

# Taking care of missing data
from sklearn.impute import SimpleImputer
# creating object for SimpleImputer class as "imputer"
imputer = SimpleImputer(missing_values = np.nan, strategy = "mean", verbose=0)
imputer = imputer.fit(X[:, 1:7]) #upper bound is not included, but lower bound
X[:, 1:7] = imputer.transform(X[:, 1:7])

# Avoiding the dummy Variable Trap
X = X[:, 1:] #To remove the first column from the dataset

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test) 

# Fitting SVM to the Training set
from sklearn.svm import SVC
classifier = SVC(kernel = 'poly', degree = 3)
classifier.fit(X_train, y_train)

# Predicting the Test set results
y_pred = classifier.predict(X_test)

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train

X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 
1, step = 0.01), np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, 
step = 0.01))
Xpred = np.array([X1.ravel(), X2.ravel()] + [np.repeat(0, X1.ravel().size) for _ in 
range(4)]).T
# Xpred now has a grid for x1 and x2 and average value (0) for x3 through x6
pred = classifier.predict(Xpred).reshape(X1.shape)   # is a matrix of 0's and 1's !
plt.contourf(X1, X2, pred, alpha = 1.0, cmap = ListedColormap(('green')))

plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
            c = ListedColormap(('red'))(I))
plt.title('SVM (Training set)')
plt.xlabel('Damage Scale')
plt.ylabel('Building Database')
plt.legend()
plt.show()

# Visualising the Test set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 
1, step = 0.01), np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, 
step = 0.01))
Xpred = np.array([X1.ravel(), X2.ravel()] + [np.repeat(0, X1.ravel().size) for _ in 
range(4)]).T
# Xpred now has a grid for x1 and x2 and average value (0) for x3 through x6
pred = classifier.predict(Xpred).reshape(X1.shape)   # is a matrix of 0's and 1's !
plt.contourf(X1, X2, pred, alpha = 1.0, cmap = ListedColormap(('green')))

plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
            c = ListedColormap(('red'))(I))

plt.title('SVM (Test set)')
plt.xlabel('Damage Scale')
plt.ylabel('Building Database')
plt.legend()
plt.show()

'''

Answer 1

)

首先，您应该熟悉您的训练数据。据我了解，您只是将数据提供给模型而不对数据进行任何类型的预处理，您不应该这样做。 我看到您正在输入带有平均值的缺失数据，也许尝试删除数据点并查看结果，删除可能“混淆”您的模型的异常值。 另外，您的图不是很友好，您告诉我们数据分类为 1-5，但在图 [-2,2] 中。 但是由于您的问题是特定于算法的，请尝试超参数调整。

你可以这样做：

from sklearn.model_selection import GridSearchCV

param_grid = {'C': [0.1,1, 10, 100], 'gamma': [1,0.1,0.01,0.001],'kernel': ['rbf', 'poly', 'sigmoid']}


grid = GridSearchCV(SVC(),param_grid,refit=True,verbose=2)
grid.fit(X_train,y_train)


print(grid.best_estimator_)

我建议阅读这篇文章，以了解 SVM 并调整您的参数]

https://towardsdatascience.com/svm-hyper-parameter-tuning-using-gridsearchcv-49c0bc55ce29