Python数据分析实例

Python数据分析

Python爬取网页数据

// An highlighted blockimport requestsif __name__=="__main__":     response= requests.get("https://book.douban.com/subject/26986954/")     content= response.content.decode("utf-8")print(content)

// An highlighted blockimport requests url="https://pro.jd.com/mall/active/4BNKTNkRMHJ48QQ5LrUf6AsydtZ6/index.html"try:     r=requests.get(url)     r.raise_for_status()     r.encoding=r.apparent_encodingprint(r.text[:100]) except:print("爬取失败")

Python生成柱状图

// An highlighted blockimport matplotlib.pyplotas plt      num_list=[1.5,0.6,7.8,6]   plt.bar(range(len(num_list)), num_list,color='rbgy')   plt.show()

Python生成堆状柱状图

// An highlighted blockimport matplotlib.pyplotas plt      name_list=['Monday','Tuesday','Friday','Sunday']   num_list=[1.5,0.6,7.8,6]   num_list1=[1,2,3,1]   plt.bar(range(len(num_list)), num_list, label='boy',fc='y')   plt.bar(range(len(num_list)), num_list1, bottom=num_list, label='girl',tick_label= name_list,fc='r')   plt.legend()   plt.show()

Python生成竖状柱状图

// An highlighted blockimport matplotlib.pyplotas plt      name_list=['Monday','Tuesday','Friday','Sunday']   num_list=[1.5,0.6,7.8,6]   num_list1=[1,2,3,1]   x=list(range(len(num_list)))   total_width, n=0.8,2   width= total_width/ n      plt.bar(x, num_list, width=width, label='boy',fc='y')for iinrange(len(x)):       x[i]= x[i]+ width   plt.bar(x, num_list1, width=width, label='girl',tick_label= name_list,fc='r')   plt.legend()   plt.show()

Python生成折线图

// An highlighted blockimport pandasas pdimport numpyas np   df= pd.DataFrame(np.random.rand(15,4), columns=['a','b','c','d']) df.plot.area()

Python生成柱状图

// An highlighted blockimport pandasas pdimport numpyas np   df= pd.DataFrame(3* np.random.rand(5), index=['a','b','c','d','e'], columns=['x']) df.plot.pie(subplots=True)

Python生成箱型图

// An highlighted block #首先导入基本的绘图包import matplotlib.pyplotas pltimport numpyas npimport pandasas pd  #添加成绩表 plt.style.use("ggplot") plt.rcParams['axes.unicode_minus']= False plt.rcParams['font.sans-serif']=['SimHei']   #新建一个空的DataFrame df=pd.DataFrame()

// An highlighted block df["英语"]=[76,90,97,71,70,93,86,83,78,85,81] df["经济数学"]=[65,95,51,74,78,63,91,82,75,71,55] df["西方经济学"]=[93,81,76,88,66,79,83,92,78,86,78] df["计算机应用基础"]=[85,78,81,95,70,67,82,72,80,81,77] df

// An highlighted block plt.boxplot(x=df.values,labels=df.columns,whis=1.5) plt.show()

// An highlighted block #用pandas自带的画图工具更快 df.boxplot() plt.show()

Python生成正态分布图

// An highlighted block #-*- coding:utf-8-*- # Python实现正态分布 # 绘制正态分布概率密度函数import numpyas npimport matplotlib.pyplotas pltimport math  u=0  # 均值μ u01=-2 sig= math.sqrt(0.2)  # 标准差δ  x= np.linspace(u-3* sig, u+3* sig,50) y_sig= np.exp(-(x- u)**2/(2* sig**2))/(math.sqrt(2* math.pi)* sig)print(x)print("="*20)print(y_sig) plt.plot(x, y_sig,"r-", linewidth=2) plt.grid(True) plt.show()

喜欢的小伙伴可以尝试一下