修改逻辑回归文件读取：这里如果就一个空的元素，则跳过本次循环

Author: jiangzhonglian

src/py2.x/ML/5.Logistic/logistic.py

@@ -31,6 +31,8 @@ def loadDataSet(file_name):
     fr = open(file_name)
     for line in fr.readlines():
         lineArr = line.strip().split()
+        if len(lineArr) == 1:
+            continue    # 这里如果就一个空的元素，则跳过本次循环
         # 为了方便计算，我们将 X0 的值设为 1.0 ，也就是在每一行的开头添加一个 1.0 作为 X0
         dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
         labelMat.append(int(lineArr[2]))

src/py3.x/ML/5.Logistic/logistic.py

@@ -202,6 +202,8 @@ def colic_test():
     # trainingSet 中存储训练数据集的特征，trainingLabels 存储训练数据集的样本对应的分类标签
     for line in f_train.readlines():
         curr_line = line.strip().split('\t')
+        if len(curr_line) == 1:
+            continue    # 这里如果就一个空的元素，则跳过本次循环
         line_arr = [float(curr_line[i]) for i in range(21)]
         training_set.append(line_arr)
         training_labels.append(float(curr_line[21]))
@@ -213,6 +215,8 @@ def colic_test():
     for line in f_test.readlines():
         num_test_vec += 1
         curr_line = line.strip().split('\t')
+        if len(curr_line) == 1: 
+            continue    # 这里如果就一个空的元素，则跳过本次循环
         line_arr = [float(curr_line[i]) for i in range(21)]
         if int(classify_vector(np.array(line_arr), train_weights)) != int(curr_line[21]):
             error_count += 1

src/py3.x/NLP/1.语言处理与Python/test.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+"""
+Created on 2018-05-09
+Updated on 2017-05-09
+Author: /片刻
+GitHub: https://github.com/apachecn/MachineLearning
+"""
+
+
+"""
+the first example for nltk book
+"""
+from nltk.book import *
+
+
+# 查找特定词语上下文
+text1.concordance("monstrous")
+
+# 相关词查找
+text1.similar("monstrous")
+
+# 查找多个词语的共同上下文
+text2.common_contexts(["monstrous", "very"])
+
+# 画出词语的离散图
+text4.dispersion_plot(["citizens", "democracy", "freedom", "duties", "America"])
+
+# 产生随机文本
+text3.generate()
+Traceback (most recent call last):
+  File "E:/nlp/eg1.py", line 25, in <module>
+    text3.generate()
+TypeError: generate() missing 1 required positional argument: 'words'
+
+# 单词数量 标识符总数
+print(len(text3))
+
+# 词汇的种类及数量 用集合set显示
+print(sorted(set(text3)))
+print(len(set(text3)))
+
+# 测量平均每类词语被使用的次数
+from __future__ import division #本命令必须放在文件的开始之初
+print(len(text3)/len(set(text3)))
+
+# 统计特定单词在文本中出现的次数，并计算其占比
+print(text3.count("smote"))
+print(100*text4.count('a')/len(text4))
+
+# # 词的频率分布
+fdist1 = FreqDist(text1)
+# # 输出总的词数
+print(fdist1)
+# In Python 3 dict.keys() returns an iteratable but not indexable object.
+vac1 = list(fdist1.keys())
+# # 输出词数最多的前五十个词
+print(vac1[:50])
+# # 输出whale的次数
+print(fdist1["whale"])
+# # 输出前五十个词的累积频率图
+
+fdist1.plot(50)
+
+# 查找长度超过15个字符的词
+V = set(text1)
+long_words = [w for w in V if len(w)>15]
+print(sorted(long_words))
+
+# 查找长度超过7的词且频率超过7
+fdist5 = FreqDist(text5)
+print(sorted([ w for w in set(text5) if len(w)>7 and fdist5[w]>7]))
+
+# 双连词的使用
+from nltk import bigrams
+# # 查了一下nltk官网上的函数说明，要加list()函数，结果才是书上的情况
+print(list(bigrams(['more', 'is', 'said', 'than', 'done'])))
+
+# 文本中常用的连接词
+print(text4.collocations())
+
+print([len(w) for w in text1])
+fdist = FreqDist([len(w) for w in text1])
+print(fdist)
+print(fdist.keys())
+print(fdist.items())
+print(fdist.max())
+print(fdist[3])
+print(fdist.freq(3))
+
+print(sorted([w for w in set(text1) if w.endswith('ableness')]))
+
+print(babelize_shell())