df = pd.read_excel(r'分区.xlsx',dtype=object,usecols=['区域','语言','国家'])ValueError: '语言' is not in list

这个错误提示意味着你读取的 Excel 文件中没有名为 `语言` 的列。你可以检查一下文件中的列名是否正确。

另外，`usecols` 参数指定了你要读取的列，如果文件中没有该列，也会报出这个错误。你可以检查一下该参数是否正确设置了。如果不需要限制列，可以省略该参数，例如：

df = pd.read_excel(r'分区.xlsx')

这样会读取该 Excel 文件中的所有列。如果你需要限制列，可以像这样指定：

df = pd.read_excel(r'分区.xlsx', usecols=['区域', '国家'])

这样就只会读取 `区域` 和 `国家` 两列。如果文件中没有这些列，也会报错，需要检查一下文件中的列名是否正确。

相关问题

python中 train_df = pd.read_excel(os.path.join(raw_data_dir,"train.xlsx")) answer_df = pd.read_excel(os.path.join(raw_data_dir,"answer.xlsx")) val_df = pd.read_excel(os.path.join(raw_data_dir,"val.xlsx"))这三行代码什么意思

这三行代码是在Python中使用pandas库读取Excel文件的数据。其中，train_df、answer_df和val_df是DataFrame类型的变量，分别对应train.xlsx、answer.xlsx和val.xlsx文件中的数据。os.path.join(raw_data_dir,"train.xlsx")、os.path.join(raw_data_dir,"answer.xlsx")和os.path.join(raw_data_dir,"val.xlsx")是用来将文件路径名连接起来的函数，其中raw_data_dir是存储原始数据的文件夹路径。

import numpy as np import pylab as pl import pandas as pd from sklearn.linear_model import Ridge from sklearn.metrics import mean_squared_error from sklearn.model_selection import train_test_split X2=[] X3=[] X4=[] X5=[] X6=[] X7=[] df=pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx',header=0,usecols=(3,)) X2=df.values.tolist() x2=[] for i in X2: if X2.index(i)<=2927: #两个单元楼的分隔数 x2.append(i) df=pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx',header=0,usecols=(4,)) X3=df.values.tolist() x3=[] for i in X3: if X3.index(i)<=2927: x3.append(i) df=pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx',header=0,usecols=(5,)) X4=df.values.tolist() x4=[] for i in X4: if X4.index(i)<=2927: x4.append(i) df=pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx',header=0,usecols=(6,)) X5=df.values.tolist() x5=[] for i in X5: if X5.index(i)<=2927: x5.append(i) df=pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx',header=0,usecols=(7,)) X6=df.values.tolist() x6=[] for i in X6: if X6.index(i)<=2927: x6.append(i) df=pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx',header=0,usecols=(8,)) X7=df.values.tolist() x7=[] for i in X7: if X7.index(i)<=2927: x7.append(i) np.random.seed(42) q=np.array(X2[:2922]) w=np.array(x3[:2922]) e=np.array(x4[:2922]) r=np.array(x5[:2922]) t=np.array(x6[:2922]) p=np.array(x7[:2922]) eps=np.random.normal(0,0.05,152) X=np.c_[q,w,e,r,t,p] beta=[0.1,0.15,0.2,0.5,0.33,0.45] y=np.dot(X,beta)X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) alpha = 0.1 # 设置岭回归的惩罚参数 ridge = Ridge(alpha=alpha) ridge.fit(X_train, y_train) y_pred = ridge.predict(X_test) mse = mean_squared_error(y_test, y_pred) print('MSE:', mse) coef = ridge.coef_ # 计算岭回归的系数 intercept = ridge.intercept_ # 计算岭回归的截距 print('Coefficients:', coef) print('Intercept:', intercept)修改这个代码，要求增加时间序列x1参与建模

import numpy as np
import pandas as pd
from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split

df = pd.read_excel('C:/Users/86147/OneDrive/文档/777.xlsx', header=0, usecols=(1, 3, 4, 5, 6, 7, 8))
X1 = df.iloc[:, 0].values.reshape(-1, 1)
X2 = df.iloc[:, 1].values.reshape(-1, 1)
X3 = df.iloc[:, 2].values.reshape(-1, 1)
X4 = df.iloc[:, 3].values.reshape(-1, 1)
X5 = df.iloc[:, 4].values.reshape(-1, 1)
X6 = df.iloc[:, 5].values.reshape(-1, 1)
X7 = df.iloc[:, 6].values.reshape(-1, 1)

np.random.seed(42)
q = np.array(X1[:2922])
w = np.array(X2[:2922])
e = np.array(X3[:2922])
r = np.array(X4[:2922])
t = np.array(X5[:2922])
p = np.array(X6[:2922])
o = np.array(X7[:2922])

eps = np.random.normal(0, 0.05, 152)
X = np.concatenate((q, w, e, r, t, p, o), axis=1)
beta = [0.1, 0.15, 0.2, 0.5, 0.33, 0.45, 0.25]
y = np.dot(X, beta)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

alpha = 0.1
ridge = Ridge(alpha=alpha)
ridge.fit(X_train, y_train)
y_pred = ridge.predict(X_test)
mse = mean_squared_error(y_test, y_pred)

print('MSE:', mse)
coef = ridge.coef_
intercept = ridge.intercept_
print('Coefficients:', coef)
print('Intercept:', intercept)