{"id":48,"date":"2018-02-26T14:26:45","date_gmt":"2018-02-26T14:26:45","guid":{"rendered":"http:\/\/www.lichzhang.net\/?p=48"},"modified":"2018-02-27T05:37:44","modified_gmt":"2018-02-27T05:37:44","slug":"%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e5%85%a5%e9%97%a8%e4%b9%8b%e6%9c%b4%e7%b4%a0%e8%b4%9d%e5%8f%b6%e6%96%af","status":"publish","type":"post","link":"https:\/\/www.lichzhang.net\/index.php\/2018\/02\/26\/%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0%e5%85%a5%e9%97%a8%e4%b9%8b%e6%9c%b4%e7%b4%a0%e8%b4%9d%e5%8f%b6%e6%96%af\/","title":{"rendered":"\u673a\u5668\u5b66\u4e60\u5165\u95e8\u4e4b\u6734\u7d20\u8d1d\u53f6\u65af"},"content":{"rendered":"<!--Dobby-Compress-html--><!--Dobby-Compress-html-no-compression--><p>[embeddoc url=\"http:\/\/www.lichzhang.net\/wp-content\/uploads\/2018\/02\/\u6734\u7d20\u8d1d\u53f6\u65af\u6cd5.pptx\" viewer=\"microsoft\"]<\/p>\n<h5>\u4f7f\u7528scikit-learn\u505a\u6e38\u620f\u6d41\u5931\u7528\u6237\u9884\u6d4b<\/h5>\n<p>\u5728scikit-learn\u4e2d\uff0c\u6734\u7d20\u8d1d\u53f6\u65af\u6709\u5982\u4e0b\u4e09\u79cd\u7c7b\u578b\uff1a<\/p>\n<ul>\n<li>\u9ad8\u65af\u6734\u7d20\u8d1d\u53f6\u65af<br \/>\n\u4e00\u822c\u7528\u4e8e\u8fde\u7eed\u578b\u7279\u5f81\u9884\u6d4b\u6a21\u578b<\/li>\n<li>\u591a\u9879\u5f0f\u6734\u7d20\u8d1d\u53f6\u65af<br \/>\n\u4e00\u822c\u7528\u4e8e\u79bb\u6563\u578b\u7279\u5f81\u9884\u6d4b\u6a21\u578b<\/li>\n<li>\u4f2f\u52aa\u5229\u6734\u7d20\u8d1d\u53f6\u65af<br \/>\n\u4e00\u822c\u7528\u4e8e\u4e8c\u9879\u5206\u5e03\u7684\u7279\u5f81\u9884\u6d4b\u6a21\u578b<\/li>\n<\/ul>\n<p>\u4ee5\u4e0b\u662f\u8fd9\u4e09\u79cd\u6a21\u578b\u7684\u7528\u6cd5<\/p>\n<pre class=\"line-numbers prism-highlight\" data-start=\"1\"><code class=\"language-python\">from sklearn.naive_bayes import GaussianNB\nfrom sklearn.naive_bayes import MultinomialNB\nfrom sklearn.naive_bayes import BernoulliNB\n\n# \u6784\u9020\u7279\u5f81\u503c x\n# \u6784\u9020\u6807\u6ce8\u6570\u636e y\nclfG = GaussianNB().fit(x, y)\nclfM = MultinomialNB().fit(x, y)\nclfB = BernoulliNB().fit(x, y)\n<\/code><\/pre>\n<p>\u4e0b\u9762\u4e3e\u4e00\u4e2a\u5177\u4f53\u7684\u4f7f\u7528\u6848\u4f8b\uff0c\u5229\u7528\u6734\u7d20\u8d1d\u53f6\u65af\u6765\u9884\u6d4b\u6e38\u620f\u7684\u6d41\u5931\u7528\u6237\u3002\u9996\u5148\u662f\u51c6\u5907\u7528\u6837\u672c\u6570\u636e\uff0c\u6839\u636e\u5bf9\u6e38\u620f\u7684\u7406\u89e3\uff0c\u9009\u53d6\u4e86\u5982\u4e0b\u7279\u5f81\uff1a<\/p>\n<pre class=\"line-numbers prism-highlight\" data-start=\"1\"><code class=\"language-python\">#\u6587\u4ef6\u8bf4\u660e\n# \u7edf\u8ba1\u65e5\u671f\n# appid\n# \u7528\u6237\u6807\u8bc6\n# \u6d41\u5931\u6807\u8bc6\n# \u524d\u4e24\u5468\u6d3b\u8dc3\u5929\u6570\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u767b\u9646\u6b21\u6570\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u6e38\u620f\u65f6\u957f\n# \u524d\u4e00\u5468\u6d3b\u8dc3\u5929\u6570\n# \u524d\u4e00\u5468\u7d2f\u8ba1\u767b\u9646\u6b21\u6570\n# \u524d\u4e00\u5468\u7d2f\u8ba1\u6e38\u620f\u65f6\u957f\n# \u6700\u540e\u767b\u5f55\u65e5\u671f\n# \u7528\u6237\u6e38\u620f\u751f\u547d\u5929\u6570\n# 8 * \u524d\u4e00\u5468\u7d2f\u8ba1\u767b\u9646\u5929\u6570\/\u7528\u6237\u6e38\u620f\u751f\u547d\u5929\u6570\n# \u6d3b\u8dc3\u5929\u6570\u8d8b\u52bf\n# \u767b\u9646\u6b21\u6570\u5468\u8d8b\u52bf\n# \u6e38\u620f\u65f6\u957f\u5468\u8d8b\u52bf\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u5929\u6570\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u6b21\u6570\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u5929\u6570\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\n# \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u6b21\u6570\n# \u4ed8\u8d39\u5929\u6570\u5468\u8d8b\u52bf\n# \u4ed8\u8d39\u91d1\u989d\u5468\u8d8b\u52bf\n<\/code><\/pre>\n<p>\u4e0b\u9762\u5f00\u59cb\u8bfb\u5165\u6570\u636e<\/p>\n<pre class=\"line-numbers prism-highlight\" data-start=\"1\"><code class=\"language-python\">import pandas as pd\nfrom matplotlib import pyplot as plt\n%matplotlib inline\n\ndf=pd.read_table(\"lost_user_sample\", header = None)\n<\/code><\/pre>\n<p>\u6784\u9020\u6837\u672c\u6570\u636e<\/p>\n<pre class=\"line-numbers prism-highlight\" data-start=\"1\"><code class=\"language-python\">y=df[3]\nprint y.values\nx=df[[4,7,  5,8,  6,9,  18,21,  19,22,  20,23,  15,16,17,  24,25]]\nprint x.values\n<\/code><\/pre>\n<p>\u5206\u522b\u4f7f\u7528\u9ad8\u65af\u6734\u7d20\u8d1d\u53f6\u65af\u3001\u591a\u9879\u5f0f\u6734\u7d20\u8d1d\u53f6\u65af\u6765\u505a\u9884\u6d4b<\/p>\n<pre class=\"line-numbers prism-highlight\" data-start=\"1\"><code class=\"language-python\">from sklearn.naive_bayes import GaussianNB\nfrom sklearn.naive_bayes import MultinomialNB\nfrom sklearn.cross_validation import train_test_split \nfrom sklearn import metrics\n\nprint \"\u603b\u6837\u672c\u6570\uff1a\",len(y)\nx_data_train,x_data_test,y_data_train,y_data_test = train_test_split(x, y, test_size=0.2, random_state=1)\ntrain_count = len(y_data_train)\nprint \"\u8bad\u7ec3\u6837\u672c\u6570\uff1a\", train_count\n\n\n#--------------------------------------------------------\nprint \"\\n\\nGaussianNB:\"\nclf = GaussianNB().fit(x_data_train, y_data_train)\nacc_test = clf.score(x_data_test,y_data_test)\nacc_all = clf.score(x,y)\n\nprint \"\u6d4b\u8bd5\u96c6\u7cbe\u5ea6:\" , acc_test\nprint \"\u603b\u7cbe\u5ea6:\" , acc_all\n\ny_pred = clf.predict(x_data_test)\nprint metrics.accuracy_score(y_data_test, y_pred)\nprint metrics.confusion_matrix(y_data_test, y_pred)\nprint metrics.recall_score(y_data_test, y_pred)\n\n#--------------------------------------------------------\nprint \"\\n\\nMultinomialNB:\"\nclf_MNB = MultinomialNB().fit(x_data_train,y_data_train)\nacc_test = clf_MNB.score(x_data_test,y_data_test)\nacc_all = clf_MNB.score(x,y)\n\nprint \"\u6d4b\u8bd5\u96c6\u7cbe\u5ea6:\" , acc_test\nprint \"\u603b\u7cbe\u5ea6:\" , acc_all\n\n\ny_pred = clf_MNB.predict(x_data_test)\nprint metrics.accuracy_score(y_data_test, y_pred)\nprint metrics.confusion_matrix(y_data_test, y_pred)\nprint metrics.recall_score(y_data_test, y_pred)\n<\/code><\/pre>\n<!--Dobby-Compress-html-no-compression--><!--Dobby-Compress-html-->","protected":false},"excerpt":{"rendered":"<p>[embeddoc url=&#8221;http:\/\/www.lichzhang.net\/wp-content\/uploads\/2018\/02\/\u6734\u7d20\u8d1d\u53f6\u65af\u6cd5.pptx&#8221; viewer=&#8221;microsoft&#8221;] \u4f7f\u7528scikit-learn\u505a\u6e38\u620f\u6d41\u5931\u7528\u6237\u9884\u6d4b \u5728scikit-learn\u4e2d\uff0c\u6734\u7d20\u8d1d\u53f6\u65af\u6709\u5982\u4e0b\u4e09\u79cd\u7c7b\u578b\uff1a \u9ad8\u65af\u6734\u7d20\u8d1d\u53f6\u65af \u4e00\u822c\u7528\u4e8e\u8fde\u7eed\u578b\u7279\u5f81\u9884\u6d4b\u6a21\u578b \u591a\u9879\u5f0f\u6734\u7d20\u8d1d\u53f6\u65af \u4e00\u822c\u7528\u4e8e\u79bb\u6563\u578b\u7279\u5f81\u9884\u6d4b\u6a21\u578b \u4f2f\u52aa\u5229\u6734\u7d20\u8d1d\u53f6\u65af \u4e00\u822c\u7528\u4e8e\u4e8c\u9879\u5206\u5e03\u7684\u7279\u5f81\u9884\u6d4b\u6a21\u578b \u4ee5\u4e0b\u662f\u8fd9\u4e09\u79cd\u6a21\u578b\u7684\u7528\u6cd5 from sklearn.naive_bayes import GaussianNB from sklearn.naive_bayes import MultinomialNB from sklearn.naive_bayes import BernoulliNB # \u6784\u9020\u7279\u5f81\u503c x # \u6784\u9020\u6807\u6ce8\u6570\u636e y clfG = GaussianNB().fit(x, y) clfM = MultinomialNB().fit(x, y) clfB = BernoulliNB().fit(x, y) \u4e0b\u9762\u4e3e\u4e00\u4e2a\u5177\u4f53\u7684\u4f7f\u7528\u6848\u4f8b\uff0c\u5229\u7528\u6734\u7d20\u8d1d\u53f6\u65af\u6765\u9884\u6d4b\u6e38\u620f\u7684\u6d41\u5931\u7528\u6237\u3002\u9996\u5148\u662f\u51c6\u5907\u7528\u6837\u672c\u6570\u636e\uff0c\u6839\u636e\u5bf9\u6e38\u620f\u7684\u7406\u89e3\uff0c\u9009\u53d6\u4e86\u5982\u4e0b\u7279\u5f81\uff1a #\u6587\u4ef6\u8bf4\u660e # \u7edf\u8ba1\u65e5\u671f # appid # \u7528\u6237\u6807\u8bc6 # \u6d41\u5931\u6807\u8bc6 # \u524d\u4e24\u5468\u6d3b\u8dc3\u5929\u6570 # \u524d\u4e24\u5468\u7d2f\u8ba1\u767b\u9646\u6b21\u6570 # \u524d\u4e24\u5468\u7d2f\u8ba1\u6e38\u620f\u65f6\u957f # \u524d\u4e00\u5468\u6d3b\u8dc3\u5929\u6570 # \u524d\u4e00\u5468\u7d2f\u8ba1\u767b\u9646\u6b21\u6570 # \u524d\u4e00\u5468\u7d2f\u8ba1\u6e38\u620f\u65f6\u957f # \u6700\u540e\u767b\u5f55\u65e5\u671f # \u7528\u6237\u6e38\u620f\u751f\u547d\u5929\u6570 # 8 * \u524d\u4e00\u5468\u7d2f\u8ba1\u767b\u9646\u5929\u6570\/\u7528\u6237\u6e38\u620f\u751f\u547d\u5929\u6570 # \u6d3b\u8dc3\u5929\u6570\u8d8b\u52bf # \u767b\u9646\u6b21\u6570\u5468\u8d8b\u52bf # \u6e38\u620f\u65f6\u957f\u5468\u8d8b\u52bf # \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u5929\u6570 # \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39 # \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u6b21\u6570 # \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u5929\u6570 # \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39 # \u524d\u4e24\u5468\u7d2f\u8ba1\u4ed8\u8d39\u6b21\u6570 # \u4ed8\u8d39\u5929\u6570\u5468\u8d8b\u52bf # \u4ed8\u8d39\u91d1\u989d\u5468\u8d8b\u52bf \u4e0b\u9762\u5f00\u59cb\u8bfb\u5165\u6570\u636e import pandas as pd from matplotlib import pyplot as plt %matplotlib inline df=pd.read_table(&#8220;lost_user_sample&#8221;, header = None) \u6784\u9020\u6837\u672c\u6570\u636e y=df[3] print y.values x=df[[4,7, 5,8, 6,9, 18,21, 19,22, 20,23, 15,16,17, 24,25]] print x.values \u5206\u522b\u4f7f\u7528\u9ad8\u65af\u6734\u7d20\u8d1d\u53f6\u65af\u3001\u591a\u9879\u5f0f\u6734\u7d20\u8d1d\u53f6\u65af\u6765\u505a\u9884\u6d4b from sklearn.naive_bayes import GaussianNB from sklearn.naive_bayes import MultinomialNB from sklearn.cross_validation import train_test_split from sklearn import metrics print &#8220;\u603b\u6837\u672c\u6570\uff1a&#8221;,len(y) x_data_train,x_data_test,y_data_train,y_data_test = train_test_split(x, y, test_size=0.2, random_state=1) train_count = len(y_data_train) print &#8220;\u8bad\u7ec3\u6837\u672c\u6570\uff1a&#8221;, train_count #&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211; print &#8220;\\n\\nGaussianNB:&#8221; clf = GaussianNB().fit(x_data_train, y_data_train) acc_test = clf.score(x_data_test,y_data_test) acc_all = clf.score(x,y) print &#8220;\u6d4b\u8bd5\u96c6\u7cbe\u5ea6:&#8221; , acc_test print &#8220;\u603b\u7cbe\u5ea6:&#8221; , acc_all y_pred = clf.predict(x_data_test) print metrics.accuracy_score(y_data_test, y_pred) print metrics.confusion_matrix(y_data_test, y_pred) print metrics.recall_score(y_data_test, y_pred) #&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8212;&#8211; print &#8220;\\n\\nMultinomialNB:&#8221; clf_MNB = MultinomialNB().fit(x_data_train,y_data_train) acc_test = clf_MNB.score(x_data_test,y_data_test) acc_all =\u2026<\/p>\n","protected":false},"author":1,"featured_media":61,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[15],"tags":[17,19,18,16],"_links":{"self":[{"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/posts\/48"}],"collection":[{"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/comments?post=48"}],"version-history":[{"count":13,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/posts\/48\/revisions"}],"predecessor-version":[{"id":68,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/posts\/48\/revisions\/68"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/media\/61"}],"wp:attachment":[{"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/media?parent=48"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/categories?post=48"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lichzhang.net\/index.php\/wp-json\/wp\/v2\/tags?post=48"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}