sklearn pandas matplot

pandas 读取问题

import pandas as pd
# 读取 
path = 'xxx'
data = pd.read_csv(path, header=None, names=['label','title','text'])

#分比例
from sklearn.model_selection import train_test_split
 
x= data.iloc[:,:] # 选取 data 所有行、所有列数据
y = data.iloc[:,0] # 选取 data 所有行、第一列数据
 
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.4, random_state=0

#保存：
X_train.to_csv('X_train.csv', index=False)
X_test.to_csv('X_test.csv', index=False)
y_train.to_csv('y_train.csv', index=False)
y_test.to_csv('y_test.csv', index=False)

import numpy as np 

from sklearn import linear model, svm, neighbors, datasets, preprocessing
from sklearn.model selection import train test split
from sklearn.metrics import accuracy score, classification report, confusion matrix, f1 score
from sklearn.model selection import cross val scor
from matplotlib import pyplot as plt
from sklearn.metrics import roc curve,precision_recall_curve


import warnings
warnings.filterwarnings("ignore")
np.random.RandomState(0)
#加载数据cancer = datasets.load breast cancer()
x,y= cancer.data, cancer.target

print(accuracy_score(y test, y_pred))
print(fl score(y_test, y_pred, average='micro'))
print(classification report(y test, y_pred))
#混淆矩阵
brint(confusion matrix(y test, y pred))
fpr, tpr, thresholds = roc_curve(y_pred, y_test)
plt.plot(fpr.tpr.'b')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')plt.title('Roc curve')

https://chat18.aichatos.xyz/#/chat/1714305686355

在问 | 让知识无界，智能触手可及