import numpy as np
import pandas as pd
import matplotlib.pyplot as pt
data1 = pd.read_csv('stage1_labels.csv')
X = data1.iloc[:, :-1].values
y = data1.iloc[:, 1].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
label_X = LabelEncoder()
X[:,0] = label_X.fit_transform(X[:,0])
encoder = OneHotEncoder(categorical_features = [0])
X = encoder.fit_transform(X).toarray()
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train,y_test = train_test_split(X, y, test_size = 0.4, random_state = 0)
#fitting Simple Regression to training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
#predecting the test set results
y_pred = regressor.predict(X_test)
#Visualization of the training set results
pt.scatter(X_train, y_train, color = 'red')
pt.plot(X_train, regressor.predict(X_train), color = 'green')
pt.title('salary vs yearExp (Training set)')
pt.xlabel('years of experience')
pt.ylabel('salary')
pt.show()
我需要帮助理解执行上述代码时的错误。以下是错误信息:
"raise ValueError("x and y must be the same size")"
我有一个包含1398行和2列的.csv文件。如上所示,我将40%的数据作为y_test集。