2016.12.7 lesson 2 small edit

wingfish · wingfish · commit 8ca0c17d00ae · 2016-12-07T21:48:02.000+08:00
diff --git a/python_basic/python_basic_lesson_02.ipynb b/python_basic/python_basic_lesson_02.ipynb
@@ -28,7 +28,10 @@
     "    * list 用法\n",
     "    * dict 用法\n",
     "    * tuple 用法\n",
-    "* 随机数介绍"
+    "* 随机数介绍\n",
+    "* 举例\n",
+    "    * 中文分词介绍\n",
+    "    * 小程序联系"
    ]
   },
   {
@@ -1064,49 +1067,47 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 34,
    "metadata": {
     "collapsed": false
    },
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Building prefix dict from the default dictionary ...\n",
-      "Dumping model to file cache /var/folders/j8/7nj196c56plf7tg3rtjxjwhr0000gn/T/jieba.cache\n",
-      "Loading model cost 2.197 seconds.\n",
-      "Prefix dict has been built succesfully.\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Full Mode: 今天/ 上海/ 的/ 天气/ 怎么样\n",
+      "Full Mode: 今天/ 天上/ 上海/ 的/ 天气/ 怎么/ 怎么样\n",
       "Default Mode: 明天/ 纽约/ 下雨/ 么\n",
       "现在, 天气, 怎么样\n",
-      "2016, 年, 第一季度, 支付, 事业部, 交易量, 报表\n",
+      "小明, 硕士, 毕业, 于, 中国科学院, 计算所, ，, 后, 在, 日本京都大学, 深造\n",
       "小明, 硕士, 毕业, 于, 中国, 科学, 学院, 科学院, 中国科学院, 计算, 计算所, ，, 后, 在, 日本, 京都, 大学, 日本京都大学, 深造\n"
      ]
     }
    ],
    "source": [
     "import jieba\n",
     "\n",
-    "seg_list = jieba.cut(\"今天上海的天气怎么样\", cut_all=False)\n",
-    "print(\"Full Mode: \" + \"/ \".join(seg_list))  # 全模式\n",
+    "# 全模式\n",
+    "# 把句子中所有的可以称此的词语都扫描出来，速度非常快，但是不能解决歧义\n",
+    "seg_list = jieba.cut(\"今天上海的天气怎么样\", cut_all = True)\n",
+    "print(\"Full Mode: \" + \"/ \".join(seg_list))  \n",
     "\n",
-    "seg_list = jieba.cut(\"明天纽约下雨么\", cut_all=False)\n",
-    "print(\"Default Mode: \" + \"/ \".join(seg_list))  # 精确模式\n",
+    "# 精确模式\n",
+    "# 试图将句子最精确的切开，适合文本分析\n",
+    "seg_list = jieba.cut(\"明天纽约下雨么\", cut_all = False)\n",
+    "print(\"Default Mode: \" + \"/ \".join(seg_list))  \n",
     "\n",
-    "seg_list = jieba.cut(\"现在天气怎么样\")  # 默认是精确模式\n",
+    "# 默认是精确模式\n",
+    "seg_list = jieba.cut(\"现在天气怎么样\")  \n",
     "print(\", \".join(seg_list))\n",
     "\n",
-    "seg_list = jieba.cut(\"2016年第一季度支付事业部交易量报表\")  # 默认是精确模式\n",
+    "# 默认是精确模式\n",
+    "seg_list = jieba.cut(\"小明硕士毕业于中国科学院计算所，后在日本京都大学深造\")  \n",
     "print(\", \".join(seg_list))\n",
     "\n",
-    "seg_list = jieba.cut_for_search(\"小明硕士毕业于中国科学院计算所，后在日本京都大学深造\")  # 搜索引擎模式\n",
+    "# 搜索引擎模式\n",
+    "# 在精确模式的基础上，对长词再次切分，提高召回率，适合用于搜索引擎分词    \n",
+    "seg_list = jieba.cut_for_search(\"小明硕士毕业于中国科学院计算所，后在日本京都大学深造\") \n",
     "print(\", \".join(seg_list))"
    ]
   },
@@ -1248,7 +1249,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.1"
+   "version": "3.4.4"
   }
  },
  "nbformat": 4,
