Question

我在csv文件中有这样的数据：

F1,1,1,1,1,0,1,1,0,0,1
F2,1,0,0,0,0,0,1,0,1,1
F3,1,0,0,0,0,0,1,1,1,1
F4,1,0,0,0,0,0,1,1,1,0
F5,14,24,22,22,22,16,18,19,26,22
F6,8.0625,6.2,6.2609,6.6818,6.2174,6.3333,7.85,6.0833,6.9655,6.9167
F7,0,0,0,0,0,0,1,0,1,0
F8,1,0,2,0,0,0,2,0,0,0
F9,1,0,0,0,1,1,0,0,0,0
F10,8,4,3,3,3,6,8,5,8,4
F11,0,0,1,0,0,1,0,0,0,0
F12,1,0,0,0,1,0,1,1,1,1

我只想求数字而不是字符串和我的代码如下：

import csv
import math
import copy

class Pearsons:

def __init__(self,fiturs,docs):
    self.fiturs = fiturs
    self.docs = docs

def x_value(self):
    sumx = []
    for fitur in self.fiturs:
        x = sum(([float(x)]) for x in fitur[1:])
        sumx.append(x)
    print sumx

def x_pow(self):
    sumxp = []
    for fitur in self.fiturs:
        xval_pow = sum([float(x)**2 for x in fitur[1:]])
        sumxp.append(xval_pow)
    return sumxp

def y_value(self):
    sumy = []
    for dokumen in self.docs:
        if dokumen[2] == "POSITIF":
            sumy.append(1)
        else:
            sumy.append(0)
    sigma_y = sum(sumy)
    return sigma_y

def y_pow(self):
    sumy = []
    for dokumen in self.docs:
        if dokumen[2] == 'POSITIF':
            sumy.append(1)
        else:
            sumy.append(0)
    ypow = []
    for x in sumy:
        ypow.append(x ** 2)
    sigmapow = sum(ypow)
    return sigmapow

def xy_val(self):
    list_y = []
    for dokumen in self.docs:
        if dokumen[2] == 'POSITIF':
            list_y.append(1)
        else:
            list_y.append(0)
    # print list_y
    sigmaxy = []
    for xyfitur in self.fiturs:
        xy = []
        for i, x in enumerate(list_y):
            xy.append(float(xyfitur[i]) * list_y[i])
        sigmaxy.append(sum(xy))
    return sigmaxy

def pearsons(self):
    list_y = []
    for dokumen in self.docs:
        if dokumen[2] == 'POSITIF':
            list_y.append(1)
        else:
            list_y.append(0)
    # Assume len(x) == len(y)
    n = len(list_y)
    sigmax = self.x_value()
    sigmay = self.y_value()
    sigmaxpow = self.x_pow()
    sigmaypow = self.y_pow()
    sigmaxy = self.xy_val()

    rpxy_list = []
    for i, v in enumerate(sigmax):
        rpxy_top = (n * sigmaxy[i]) - (sigmax[i] * sigmay)
        rpxy_bot = math.sqrt((n * sigmaxpow[i]) - (sigmax[i] ** 2)) * math.sqrt((n * sigmaypow) - (sigmay ** 2))
        if rpxy_bot == 0:
            rpxy_list.append(0)
        else:
            rpxy_list.append(abs(rpxy_top / rpxy_bot))
    #print rpxy_list
    return rpxy_list

fiturs = []
docs = []
with open("features2.csv", "rb") as f:
    fiturcsv = csv.reader(f, None)
    fiturs = [x for x in fiturcsv]
    fiturs.insert(0, fiturs[0])

with open("datalatih.csv", "rb") as f:
    docscsv = csv.reader(f)
    docs = [x for x in docscsv]

p = Pearsons(fiturs, docs)
# nb.BernoulliNaiveBayes()
p.x_value()
#p.xy_val()

导致以下错误：

C：/Users/USER/PycharmProjects/Skripsi/coba.py Traceback（最近期）   最后调用）：文件“C：/Users/USER/PycharmProjects/Skripsi/coba.py”，   第117行       p.x_value（）文件“C：/Users/USER/PycharmProjects/Skripsi/coba.py”，第14行，x_value       x = sum（[float（x）]）for fitur [1：]中的类型TypeError：+：'int'和'list'的不支持的操作数类型

使用退出代码1完成处理

Answer 1

你在代码

中有额外的]

应该是

def x_value(self):
    sumx = []
    for fitur in self.fiturs:

        x = sum([float(x) for x in fitur[1:]])
        sumx.append(x)
    print sumx

改变了我

[7.0, 7.0, 4.0, 5.0, 4.0, 205.0, 67.5714, 2.0, 5.0, 3.0, 52.0, 2.0, 6.0]

+：'int'和'list'不支持的操作数类型 - python

1 个答案: