python - 文本分析-无法将Python程序的输出写入csv或xls文件

Question

嗨，我正在尝试使用 python 2.x 中的朴素贝叶斯分类器进行情感分析。它使用 txt 文件读取情绪，然后根据样本 txt 文件情绪给出积极或消极的输出。我希望输出与输入的形式相同，例如我有一个包含 1000 个原始情绪的文本文件，我希望输出显示每种情绪的积极或消极。请帮忙。下面是我正在使用的代码

import math
import string

def Naive_Bayes_Classifier(positive, negative, total_negative, total_positive, test_string):
    y_values = [0,1]
    prob_values = [None, None]

    for y_value in y_values:
        posterior_prob = 1.0

        for word in test_string.split():
            word = word.lower().translate(None,string.punctuation).strip()
            if y_value == 0:
                if word not in negative:
                    posterior_prob *= 0.0
                else:
                    posterior_prob *= negative[word]
            else:
                if word not in positive:
                    posterior_prob *= 0.0
                else:
                    posterior_prob *= positive[word]

        if y_value == 0:
            prob_values[y_value] = posterior_prob * float(total_negative) / (total_negative + total_positive)
        else:
            prob_values[y_value] = posterior_prob * float(total_positive) / (total_negative + total_positive)

    total_prob_values = 0
    for i in prob_values:
        total_prob_values += i

    for i in range(0,len(prob_values)):
        prob_values[i] = float(prob_values[i]) / total_prob_values

    print prob_values

    if prob_values[0] > prob_values[1]:
        return 0
    else:
        return 1


if __name__ == '__main__':
    sentiment = open(r'C:/Users/documents/sample.txt')

    #Preprocessing of training set
    vocabulary = {}
    positive = {}
    negative = {}
    training_set = []
    TOTAL_WORDS = 0
    total_negative = 0
    total_positive = 0

    for line in sentiment:
        words = line.split()
        y = words[-1].strip()
        y = int(y)

        if y == 0:
            total_negative += 1
        else:
            total_positive += 1

        for word in words:
            word = word.lower().translate(None,string.punctuation).strip()
            if word not in vocabulary and word.isdigit() is False:
                vocabulary[word] = 1
                TOTAL_WORDS += 1
            elif word in vocabulary:
                vocabulary[word] += 1
                TOTAL_WORDS += 1

            #Training
            if y == 0:
                if word not in negative:
                    negative[word] = 1
                else:
                    negative[word] += 1
            else:
                if word not in positive:
                    positive[word] = 1
                else:
                    positive[word] += 1

    for word in vocabulary.keys():
        vocabulary[word] = float(vocabulary[word])/TOTAL_WORDS

    for word in positive.keys():
        positive[word] = float(positive[word])/total_positive

    for word in negative.keys():
        negative[word] = float(negative[word])/total_negative

    test_string = raw_input("Enter the review: \n")

    classifier = Naive_Bayes_Classifier(positive, negative, total_negative, total_positive, test_string)
    if classifier == 0:
        print "Negative review"
    else:
        print "Positive review"

Answer 1

我已经检查了您在评论中发布的 github 存储库。我尝试运行该项目，但出现一些错误。

无论如何，我已经检查了项目结构和用于训练朴素贝叶斯算法的文件，我认为以下代码可用于将结果数据写入 Excel 文件(即 .xls)

with open("test11.txt") as f:
    for line in f:
        classifier = naive_bayes_classifier(positive, negative, total_negative, total_positive, line)
        result = 'Positive' if classifier == 0 else 'Negative'
        data_to_be_written += ([line, result],)

# Create a workbook and add a worksheet.
workbook = xlsxwriter.Workbook('test.xls')
worksheet = workbook.add_worksheet()

# Start from the first cell. Rows and columns are zero indexed.
row = 0
col = 0

# Iterate over the data and write it out row by row.
for item, cost in data_to_be_written:
   worksheet.write(row, col,     item)
worksheet.write(row, col + 1, cost)
row += 1

workbook.close()

接下来，对于包含要测试的句子的文件的每一行，我调用分类器并准备一个将写入 csv 文件中的结构。
然后循环结构体并写入xls文件。
为此，我使用了一个名为 xlsxwriter 的 Python 站点包。

正如我之前告诉过你的，我在运行该项目时遇到了一些问题，因此这段代码也没有经过测试。它应该运作良好，但是无论如何，如果您遇到麻烦，请告诉我。

问候