{
   "question_id": 7461537,
   "question_title": "线性回归",
   "question_content": "<p>把以下数据制作成csv数据文件,并命名为LR_data_exam.csv。 <br />\n对该文件内的数据进行线性回归<br />\n画出数据的散点图<br />\n建立线性回归模型并拟合<br />\n打印拟合结果(参数) <br />\n画出数据和拟合直线的图<br />\n用model.predict预测x为10,20,30时的结果<br />\n用拟合参数预测x为40,50,60时的结果<br />\n   battery,KM<br />\n   2,12<br />\n   5,31<br />\n   8,45<br />\n   8,52<br />\n   13,79<br />\n   15,85<br />\n   17,115<br />\n   19,119<br />\n   21,135<br />\n   24,145</p>",
   "difficulty": "简单",
   "answer_id": 53446955,
   "answer_content": "<pre>\n<code class=\"language-python\">import numpy as np\nimport csv\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.linear_model import LinearRegression\nimport matplotlib\nmatplotlib.rcParams[&#39;font.sans-serif&#39;] &#61; [&#39;SimHei&#39;]\nmatplotlib.rcParams[&#39;font.family&#39;]&#61;[&#39;sans-serif&#39;]\n\ndata &#61; &#39;&#39;&#39;battery,KM\n   2,12\n   5,31\n   8,45\n   8,52\n   13,79\n   15,85\n   17,115\n   19,119\n   21,135\n   24,145&#39;&#39;&#39;.split(&#39;\\n&#39;)\nfor i,j in enumerate(data):\n    data[i] &#61; j.replace(&#39; &#39;, &#39;&#39;).split(&#39;,&#39;)\n\nwith  open(&#39;LR_data_exam.csv&#39;,&#39;w&#39;) as csvFile: #一行一行地写入到csv文件中\n    writer &#61; csv.writer(csvFile)\n    #先写columns_name\n    writer.writerow(data[0])\n    #写入多行用writerows\n    writer.writerows(data[1:])</code></pre>\n\n<p> LR_data_exam.csv&#xff1a;</p>\n\n<p><img alt=\"\" height=\"310\" src=\"https://img-ask.csdnimg.cn/upload/1624861372289.png\" width=\"402\" /></p>\n\n<pre>\n<code class=\"language-python\">dataframe &#61; pd.read_csv(&#34;LR_data_exam.csv&#34;, sep&#61;&#34;,&#34;)\nx &#61; dataframe[&#39;battery&#39;].tolist()\ny &#61; dataframe[&#39;KM&#39;].tolist()\n\n# 画出数据的散点图\nfig &#61; plt.figure()\nfig.set_size_inches(10, 4)   # 整个绘图区域的宽度10和高度4\nax &#61; fig.add_subplot(1, 2, 1)  # 整个绘图区分成一行两列&#xff0c;当前图是第一个。\n# 画出原始数据的散点图。\nax.set_title(&#34;散点图&#34;)\nax.set_xlabel(&#34;battery&#34;)\nax.set_ylabel(&#34;KM&#34;)\nax.scatter(x, y)\nplt.show()</code></pre>\n\n<p><img alt=\"\" height=\"269\" src=\"https://img-ask.csdnimg.cn/upload/1624861411134.png\" width=\"309\" /></p>\n\n<pre>\n<code class=\"language-python\">regressor &#61; LinearRegression()\nregressor &#61; regressor.fit(np.reshape(x,(-1, 1)),np.reshape(y,(-1, 1)))\nprint(regressor.coef_, regressor.intercept_)  # 打印拟合结果(参数)</code></pre>\n\n<pre>\n[[6.28763667]] [-1.19680404]</pre>\n\n<pre>\n<code class=\"language-python\"># 画出数据和拟合直线的图\nplt.scatter(x, y)\nplt.plot(np.reshape(x,(-1,1)), regressor.predict(np.reshape(x,(-1,1))))\nplt.xlabel(&#34;battery&#34;) \nplt.ylabel(&#34;KM&#34;) \nplt.title(&#34;拟合结果&#34;)\nplt.show()</code></pre>\n\n<p><img alt=\"\" height=\"275\" src=\"https://img-ask.csdnimg.cn/upload/1624861449046.png\" width=\"399\" /></p>\n\n<pre>\n<code class=\"language-python\">print(regressor.predict([[10], [20], [30]]))  # model.predict预测x为10,20,30时的结果\nfor i in [40,50,60]:\n    print(regressor.coef_*i &#43; regressor.intercept_)   #用拟合参数预测x为40,50,60时的结果</code></pre>\n\n<pre>\n[[ 61.67956266]\n [124.55592935]\n [187.43229605]]\n[[250.30866274]]\n[[313.18502944]]\n[[376.06139613]]</pre>\n",
   "tag_name": "python",
   "python": "import numpy as np\nimport csv\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.linear_model import LinearRegression\nimport matplotlib\nmatplotlib.rcParams['font.sans-serif'] = ['SimHei']\nmatplotlib.rcParams['font.family']=['sans-serif']\ndata = '''battery,KM\n   2,12\n   5,31\n   8,45\n   8,52\n   13,79\n   15,85\n   17,115\n   19,119\n   21,135\n   24,145'''.split('\\n')\nfor i,j in enumerate(data):\n    data[i] = j.replace(' ', '').split(',')\nwith  open('LR_data_exam.csv','w') as csvFile: \n    writer = csv.writer(csvFile)\n    writer.writerow(data[0])\n    writer.writerows(data[1:])\n",
   "topic_link": "https://bbs.csdn.net/topics/600470502",
   "status": 0,
   "keywords": "图算法,算法高阶,图的表示,基本的图算法",
   "license": "csdn.net",
   "notebook": {
      "python": "https://codechina.csdn.net/csdn/csdn-daily-code/-/jupyter/master/data/notebook/answer/ipynb/python/26.ipynb?type=file"
   }
}