Question

我试图可视化训练集结果，但是每当我运行代码时，它就会给我：

ValueError：每个样本X具有2个功能；期望8。

我不知道要更改什么？

# 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))

plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), 
X2.ravel()]).T).reshape(X1.shape),
         alpha = 0.75, cmap = ListedColormap(('red', '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', 'green'))(i), label = j)

plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

Answer 1

好吧，我也从udemy做过同样的课程，如果是真的，那么您在准备特征矩阵x时可能做错了事

这是代码

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


# Importing the dataset
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2,3]].values
y = dataset.iloc[:, 4].values


#splitting into train 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,random_state=0)



#Very very important coz featurescaling is must for logit
from sklearn.preprocessing import StandardScaler
sc_X=StandardScaler();
X_train=sc_X.fit_transform(X_train);
X_test=sc_X.transform(X_test);


#building the logit model
from sklearn.linear_model import LogisticRegression
classifier=LogisticRegression(random_state=0)
classifier.fit(X_train,y_train)



#making a prediction
y_pred=classifier.predict(X_test)


#building confusion matrix to measure performance**
from sklearn.metrics import confusion_matrix
cm=confusion_matrix(y_test,y_pred) 


#plot to visualize training set result
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))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', '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', 'green'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

如何可视化训练集结果？

1 个答案: