读取并处理data文件

空空12345678

于 2023-03-30 13:16:22 发布

阅读量1.3k

点赞数 1

文章标签： python 机器学习

本文链接：https://blog.csdn.net/weixin_43259478/article/details/129854822

版权

导入data类型的数据集

使用pandas的read_table读取data数据

#读取data数据
	data=pd.read_table("./wdbc.data")

将data数据转化为csv文件，并读取csv文件

	data.to_csv('./machine.csv',sep=" ",index=False)
    #转化成csv文件
	csv=pd.read_csv("./machine.csv",header=None)

将文件将数据集分成feature和target

	#注意对于pandas的DataFrame类型，切片要调用iloc。如果是numpy的ndarray类型，就不需要写iloc
	X,Y=csv.iloc[:,2:],csv.iloc[:,1]

将target数据集中的非字符串转化成数字类型

	Y_class={"M":-1,"B":1}
    Y=Y.map(Y_class)

将pandas的DataFrame类型转为numpy的ndarray类型

	X,Y=X.to_numpy(),Y.to_numpy()
    # print(type(X),type(Y))

归一化

	std = StandardScaler()
    X_norm  = std.fit_transform(X)

划分数据集

	X_train = X_norm[:int(len(X_norm)*0.7)]
    X_test = X_norm[int(len(X_norm)*0.7):]
    y_train = Y[:int(len(X_norm)*0.7)]
    y_test = Y[int(len(X_norm)*0.7):]

总代码

from sklearn import datasets
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import pandas as pd
def datasets():
    # x, y = datasets.load_breast_cancer(return_X_y=True)
    #读取data数据
    data=pd.read_table("/home/ylkong/Text Summary/wdbc.data")
    data.to_csv('./machine.csv',sep=" ",index=False)
    #转化成csv文件
    csv=pd.read_csv("./machine.csv",header=None)
    #将数据集分成feature和target
    X,Y=csv.iloc[:,2:],csv.iloc[:,1]
    #将target数据集中的非字符串转化成数字类型
    Y_class={"M":-1,"B":1}
    Y=Y.map(Y_class)
    #将DataFrame转化成ndarray
    X,Y=X.to_numpy(),Y.to_numpy()
    # print(type(X),type(Y))
    # 归一化
    std = StandardScaler()
    X_norm  = std.fit_transform(X)
    #将数据集划分成train:test=7:3
    X_train = X_norm[:int(len(X_norm)*0.7)]
    X_test = X_norm[int(len(X_norm)*0.7):]
    y_train = Y[:int(len(X_norm)*0.7)]
    y_test = Y[int(len(X_norm)*0.7):]

    # y_train[y_train == 0] = -1
    # y_test[y_test == 0] = -1
    return X_train,y_train,X_test,y_test