Question

我目前正在应用一些机器学习代码来使用python中的以下代码来分析来自enron数据集的电子邮件：

import os
import numpy as np
from collections import Counter
from sklearn.naive_bayes import MultinomialNB, GaussianNB, BernoulliNB
from sklearn.svm import SVC, NuSVC, LinearSVC

def make_dictionary(train_dir):
    emails = [os.path.join(train_dir,f) for f in os.listdir(train_dir)]    
    all_words = []       
    for mail in emails:    
        with open(mail) as m:
            for i,line in enumerate(m):
                if i == 2:
                    words = line.split()
                    all_words += words
    dictionary = Counter(all_words)
    return dictionary
list_to_remove = dictionary.keys()
for item in list_to_remove:
    if item.isalpha() == False:
        del dictionary[item]
    elif len(item) == 1:
        del dictionary[item]
    dictionary = dictionary.most_common(3000)
train_dir = 'train-mails'
dictionary = make_Dictionary(train_dir)


def extract_features(mail_dir):
    files = [os.path.join(mail_dir,fi) for fi in os.listdir(mail_dir)]
    features_matrix = np.zeros((len(files),3000))
    docID = 0;
    for fil in files:
        with open(fil) as fi:
            for i,line in enumerate(fi):
                if i == 2:
                    words = line.split()
                for word in words:
                  wordID = 0
                  for i,d in enumerate(dictionary):
                    if d[0] == word:
                      wordID = i
                      features_matrix[docID,wordID] = words.count(word)
            docID = docID + 1
        return features_matrix

train_labels = np.zeros(702)
train_labels[351:701] = 1
train_matrix = extract_features(train_dir)

model1 = MultinomialNB()
model2 = LinearSVC()
model1.fit(train_matrix,train_labels)
model2.fit(train_matrix,train_labels)

test_dir = 'test-mails'
test_matrix = extract_features(test_dir)
test_labels = np.zeros(260)
test_labels[130:260] = 1
result1 = model1.predict(test_matrix)
result2 = model2.predict(test_matrix)
print confusion_matrix(test_labels,result1)
print confusion_matrix(test_labels,result2)

然而，每次我运行它时都会说字典没有定义，我无法弄清楚为什么它不想工作。我缩进了需要它的区域，我已经导入了正确的模块，但它仍然无效。关于如何解决这个问题的任何想法都会有所帮助。

Answer 1

dictionary = make_Dictionary(train_dir)
应为dictionary = make_dictionary(train_dir)

python区分大小写。 D应为d。

为什么python说字典没有定义？

1 个答案: