本期内容为大家带来Python数据分析可视化综合实例
给定素如下：
sex=["男","女"] df1=pd.DataFrame({ "names":["student"+str(i) for i in range(1,32) ], "sex":[sex[np.random.randint(2)] for i in range(31) ], "python":np.random.randint(60,101,31), "spark":np.random.randint(60,90,31), "linux":np.random.randint(60,98,31) })
折线图
1.用折线图呈现python,spark,linux的前5名
import numpy as np import pandas as pd import matplotlib.pyplot as plt plt.rcParams['font.sans-serif'] = ['SimHei'] plt.rcParams['axes.unicode_minus'] = False df1 = pd.DataFrame({ 'names': [f'student{i}' for i in range(1, 48)], 'sex': np.random.choice(['男', '女'], 47), 'python': np.random.randint(50, 101, 47), 'spark': np.random.randint(50, 90, 47), 'linux': np.random.randint(50, 95, 47), }) print(df1) # 用折线图分别呈现Python，spark，Linux的前五名 score1 = df1['python'].sort_values(ascending=False).head(5) score2 = df1['spark'].sort_values(ascending=False).head(5) score3 = df1['linux'].sort_values(ascending=False).head(5) nums = [1, 2, 3, 4, 5] labels = [f'第{i}名' for i in range(1, 6)] # 绘制Python、spark、Linux折线 plt.plot(nums, score1, color='red', marker='o', linestyle=':') plt.plot(nums, score2, color='blue', marker='p', linestyle=':') plt.plot(nums, score3, color='green', marker='x', linestyle=':') plt.xticks(nums, labels) # 设置x轴刻度及标签 plt.ylabel('成绩') # y轴标签 plt.xlabel('名次') # x轴标签 plt.title('学生成绩分析') # 标题 plt.legend(['python', 'spark', 'linux']) # 图例 plt.show()
效果：
并列柱状图
2.用并列柱状图呈现总分前5名的各科成绩，横轴显示学生的姓名，纵轴显示分数，共3个图例。
df1['total'] = df1['python'] + df1['spark'] + df1['linux'] result1 = df1.sort_values('total', ascending=False).head(5) width = 0.2 nums = np.arange(5) plt.bar(nums, result1['python'], color='blue', width=width) plt.bar(nums + width, result1['spark'], color='red', width=width) plt.bar(nums + width * 2, result1['linux'], color='green', width=width) plt.xticks(nums, result1['names']) plt.ylim(0, 120) for x, y in zip(nums, result1['python']): plt.text(x, y, y, ha='center') for x, y in zip(nums + width, result1['spark']): plt.text(x, y, y, ha='center') for x, y in zip(nums + width * 2, result1['python']): plt.text(x, y, y, ha='center') plt.xlabel('学生') plt.ylabel('成绩') plt.title('学生总分top5') plt.legend(['python', 'spark', 'linux']) plt.show()
效果：
4.用并列柱状图分别呈现男生和女孩的python，spark,linux的平均分
result1 = df1.groupby('sex')['python', 'spark', 'linux'].mean() print(result1) w = 0.2 nums = np.arange(2) plt.bar(nums, result1['python'], color='red', width=w) plt.bar(nums + w, result1['spark'], color='blue', width=w) plt.bar(nums + w * 2, result1['linux'], color='green', width=w) plt.xticks(nums, result1.index) plt.ylim(0, 120) for x, y in zip(nums, result1['python']): plt.text(x, y, f'{round(y, 1)}分', ha='center') for x, y in zip(nums, result1['spark']): plt.text(x + w, y, f'{round(y, 1)}分', ha='center') for x, y in zip(nums + w, result1['spark']): plt.text(x + w, y, f'{round(y, 1)}分', ha='center') plt.legend(['python', 'spark', 'linux']) plt.title('男女生各科成绩平均分') plt.show()
效果
- 显示前5个电影三天的总票房及票房趋势 (三天票房的并列柱状图，并做单日票房的数据标注).
给定素材为:豆瓣电影数据1.csv,其中r1,r2,r3分别表示前3天的票房
df1 = pd.read_csv('data/豆瓣电影数据1.csv') result1 = df1.head(5) print(result1.index) width = 0.2 nums = np.arange(result1.shape[0]) plt.bar(nums, result1['r1'], color='blue', width=width) plt.bar(nums + width, result1['r2'], color='red', width=width) plt.bar(nums + width * 2, result1['r3'], color='green', width=width) plt.xticks(nums, result1['name']) for x, y in zip(nums, result1['r1']): plt.text(x, y, y, ha='center') for x, y in zip(nums + width, result1['r2']): plt.text(x, y, y, ha='center') for x, y in zip(nums + width * 2, result1['r3']): plt.text(x, y, y, ha='center') plt.xlabel('学生') plt.ylabel('成绩') plt.title('学生总分top5') plt.legend(['第一天', '第二天', '第三天']) plt.show()
效果
堆积折线图
显示各个手机各个月份的总销量和销量趋势,使用堆积折线图
df1 = pd.read_csv('data/手机年销量.txt') print(df1) plt.xlabel('品牌') plt.ylabel('销量') plt.ylim(0, 1500) plt.title('手机总销量趋势图') plt.stackplot(df1['品牌'], df1['6月'], df1['7月'], df1['8月'], df1['9月']) plt.legend(['6月', '7月', '8月', '9月']) plt.show()
效果
饼图
使用饼图显示每个城市的学生的人数
import numpy as np import pandas as pd import matplotlib.pyplot as plt plt.rcParams['font.sans-serif'] = 'SimHei' # 设置字体 plt.rcParams["font.size"] = 10 # 设置字号 plt.rcParams["axes.unicode_minus"] = False # 正常显示负号 sex = ["男", "女"] address = ["北京", "上海", "襄阳"] df1 = pd.DataFrame({ "names": ["student" + str(i) for i in range(1, 32)], "sex": [sex[np.random.randint(2)] for i in range(31)], "address": [address[np.random.randint(3)] for i in range(31)], "python": np.random.randint(60, 101, 31), "spark": np.random.randint(60, 90, 31), "linux": np.random.randint(60, 98, 31) }) # 使用饼图显示每个城市的学生的人数 data1 = df1.groupby('address')['sex'].count() plt.pie(data1.values, labels=data1.index, explode=[0, 0.1, 0], autopct='%.2f%%') plt.legend(data1.index) plt.title('各城市学生人数占比') plt.show()
散点图
随机生成大数据专业200名学生的性别,姓名,身高,体重,绘制身高和体重分布的散点图,女生数据用红色绘制,男生数据用蓝色绘制
size = 200 df1 = pd.DataFrame({ 'name': [f'student{i}' for i in range(1, size + 1)], 'sex': np.random.choice(['男', '女'], size), 'height': np.random.randint(150, 200, size), 'width': np.random.randint(40, 100, size) }) print(df1.head()) men = df1[df1['sex'] == '男'] women = df1[df1['sex'] == '女'] plt.scatter(men['height'], men['width'], color='red') plt.scatter(women['height'], women['width'], color='blue', cmap='viridis') plt.xlabel('身高（单位：CM）') plt.ylabel('体重：(单位：KG）') plt.title('男女生身高体重分布图') plt.legend(['男', '女']) plt.show()
雷达图
使用雷达图绘制小明各科成绩
import numpy as np import matplotlib.pyplot as plt from matplotlib.font_manager import FontProperties # 加载中文字体 font = FontProperties(fname="./data/SimHei.ttf", size=14) # 数据准备 labels=np.array(["英语","数学","语文","化学","物理","体育"]) stats=[90, 80, 76, 70, 75, 88] # 画图数据准备，角度、状态值 angles=np.linspace(0, 2*np.pi, len(labels), endpoint=False) stats=np.concatenate((stats,[stats[0]])) angles=np.concatenate((angles,[angles[0]])) # 画蜘蛛图 fig = plt.figure(figsize = (10,6)) ax = fig.add_subplot(111, polar=True) ax.plot(angles, stats, 'o-', linewidth=2) ax.fill(angles, stats, alpha=0.25) # 设置中文标题和维度名称 ax.set_thetagrids(angles * 180/np.pi, labels, FontProperties=font) ax.set_title("小明各科成绩",FontProperties = font, size = 20) plt.show()
热力图
使用热力图绘制学生各科成绩
import matplotlib.pyplot as plt import seaborn as sns plt.rcParams['font.family'] = ['sans-serif'] plt.rcParams['font.size'] = '20' plt.rcParams['font.sans-serif'] = ['SimHei'] labels=np.array(["英语","数学","语文","化学","物理","体育"]) names = ["李雷","韩梅梅","汤姆","安"] scores=np.array([[90, 80, 76, 70, 75, 88],[70, 60, 73, 80, 95, 55], [70, 60, 56, 30, 65, 95],[50, 40, 66, 75, 74, 98]]) fig = plt.figure(0,figsize = (10,6)) plt.matshow(scores,fignum = 0) plt.xticks(ticks = range(len(labels)),labels = labels) plt.yticks(ticks = range(len(names)),labels = names) # 绘制⽂本 for i in range(len(names)): for j in range(len(labels)): plt.text(j, i, round(scores[i, j],1), ha="center", va="center", color='r') plt.colorbar() plt.show()
