Python数据分析--Pandas知识点(三)

            1
            import
             pandas as pd

            2
            import
             matplotlib.pyplot as plt

            3
            #
            第一步读取数据: 使用read_csv()函数读取csv文件中的数据
            4 df = pd.read_csv(r"D:\Data\percent-bachelors-degrees-women-usa.csv")
5#第二步利用pandas的plot方法绘制折线图6 df.plot(x = "Year", y = "Agriculture")
7#第三步: 通过plt的show()方法展示所绘制图形8 plt.show()

            1
            import
             pandas as pd

            2
            import
             matplotlib.pyplot as plt

            3 df = pd.read_csv(r"D:\Data\percent-bachelors-degrees-women-usa.csv")
4#添加指定的style参数5 df.plot(x = "Year", y = "Agriculture", style = "--")
6 plt.show()

             1
            import
             pandas as pd

             2
            import
             matplotlib.pyplot as plt

             3 df = pd.read_csv(r"D:\Data\percent-bachelors-degrees-women-usa.csv")
 4 df.plot(x = "Year", y = "Agriculture", style = "--")
 5#添加横坐标轴标签 6 plt.xlabel("Year")
 7#添加纵坐标轴标签 8 plt.ylabel("Percent")
 9#添加标题10 plt.title("Percent of American women earn Agriculture‘s degree")
11 plt.show()

             1
            import
             pandas as pd

             2
            import
             matplotlib.pyplot as plt

             3
            #
            第一步: 读取数据
             4 df = pd.read_csv(r"D:\Data\percent-bachelors-degrees-women-usa.csv")
 5#第二步: 将所需数据赋值给对应的变量 6 df_year, df_Agriculture = df["Year"], df["Agriculture"]
 7#第三步: 用matplotlib中绘图框架的plot()方法绘制红色的折线图 8 plt.plot(df_year, df_Agriculture,"-", color = "r",linewidth = 10)
 9#添加横坐标轴标签10 plt.xlabel("Year")
11#添加纵坐标轴标签12 plt.ylabel("Percent")
13#添加标题14 plt.title("Percent of American women earn Agriculture‘s degree")
15 plt.show()

             1
            import
             pandas as pd

             2
            import
             matplotlib.pyplot as plt

             3
            #
            读取数据
             4 df = pd.read_csv(r"D:\Data\Iris.csv")
 5#原始数据中没有给出字段名, 在这里指定 6 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 7#指定x轴与y轴数据并绘制散点图 8 df.plot(x = "sepal_len", y = "sepal_wid", kind = "scatter" )
 9#添加横坐标轴标签10 plt.xlabel("sepal length")
11#添加纵坐标轴标签12 plt.ylabel("sepal width")
13#添加标题14 plt.title("Iris sepal length and width analysis")
15 plt.show()

             1
            import
             pandas as pd

             2
            import
             matplotlib.pyplot as plt

             3 df = pd.read_csv(r"D:\Data\Iris.csv")
 4 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 5#用绘图框架的plot()方法绘图, 样式为".", 颜色为红色 6 plt.plot(df["sepal_len"], df["sepal_wid"],".", color = "r")
 7 plt.xlabel("sepal length")
 8 plt.ylabel("sepal width")
 9 plt.title("Iris sepal length and width analysis")
10 plt.show()

            1
            import
             pandas as pd

            2 df = pd.read_csv(r"D:\Data\Iris.csv")
3 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
4#查看数据总体信息5 df.describe()

            1
            import
             pandas as pd

            2 df = pd.read_csv(r"D:\Data\Iris.csv")
3 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
4#对species列进行分类并对sepal_len列进行计数5 df_gbsp = df.groupby("species")["sepal_len"].agg(["count"])
6 df_gbsp

            1
            import
             pandas as pd

            2
            import
             matplotlib.pyplot as plt

            3 df = pd.read_csv(r"D:\Data\Iris.csv")
4 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
5#对species列进行分类并对sepal_len列进行计数6 df_gbsp = df.groupby("species")["sepal_len"].agg(["count"])
7#绘制图形样式为饼图, 百分比保留两位小数, 字体大小为20, 图片大小为6x6, subplots为True表示将数据每列绘制为一个子图,legend为True表示隐藏图例8 df_gbsp.plot(kind = "pie", autopct=‘%.2f%%‘, fontsize=20, figsize=(6, 6), subplots = True, legend = False)
9 plt.show()

            1
            import
             pandas as pd

            2
            import
             matplotlib.pyplot as plt

            3 df = pd.read_csv(r"D:\Data\Iris.csv")
4 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
5 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
6 df_gbsp = df.groupby("species",as_index = False)["sepal_len"].agg({"counts": "count"})
7#对counts列的数据绘制饼状图.8 plt.pie(df_gbsp["counts"],labels = df_gbsp["species"], autopct = "%.2f%%" )
9 plt.show()

             1
            import
             pandas as pd

             2
            import
             matplotlib.pyplot as plt

             3 df = pd.read_csv(r"D:\Data\Iris.csv")
 4 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 5 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
 6#对species分组求均值 7 df_gbsp = df.groupby("species", as_index = False).mean()
 8#绘制柱形图 9 df_gbsp.plot(kind = "bar")
10#修改横坐标轴刻度值11 plt.xticks(df_gbsp.index,df_gbsp["species"],rotation=360)
12 plt.show()

             1
            import
             pandas as pd

             2
            import
             matplotlib.pyplot as plt

             3 df = pd.read_csv(r"D:\Data\Iris.csv")
 4 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 5 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
 6 df_gbsp = df.groupby("species", as_index = False).mean()
 7#将bar改为barh即可绘制横向柱形图 8 df_gbsp.plot(kind = "barh")
 9 plt.yticks(df_gbsp.index,df_gbsp["species"],rotation=360)
10 plt.show()

            #
            修改stacked参数为True即可
df_gbsp.plot(kind = "barh", stacked = True)

            1
            import
             pandas as pd

            2
            import
             matplotlib.pyplot as plt

            3 df = pd.read_csv(r"D:\Data\Iris.csv")
4 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
5 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
6 df_gbsp = df.groupby("species").mean()
7#绘制"sepal_len"列柱形图8 plt.bar(df_gbsp.index,df_gbsp["sepal_len"], width= 0.5 , color = "g")
9 plt.show()

             1
            import
             numpy as np

             2
            import
             pandas as pd

             3
            import
             matplotlib.pyplot as plt

             4 df = pd.read_csv(r"D:\Data\Iris.csv")
 5 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 6 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
 7 df_gbsp = df.groupby("species").mean()
 8#计算有多少个列 9 len_spe = len(df_gbsp.count())
10#计算有多少行, 并生成一个步进为1的数组11 index = np.arange(len(df_gbsp.index))
12#设置每组总宽度13 total_width= 1.4
14#求出每组每列宽度15 width = total_width/len_spe
16#对每个字段进行遍历17for i in range(len_spe):
18#得出每个字段的名称19     het = df_gbsp.columns[i]
20#求出每个字段所包含的数组, 也就是对应的高度21     y_values = df_gbsp[het]
22#设置x轴标签23     x_tables = index * 1.5 + i*width
24#绘制柱形图25     plt.bar(x_tables, y_values, width =width)
26#通过zip接收(x_tables,y_values),返回一个可迭代对象, 每一个元素都是由(x_tables,y_values)组成的元组.27for x, y in zip(x_tables, y_values):
28#通过text()方法设置数据标签, 位于柱形中心, 最顶部, 字体大小为10.529         plt.text(x, y ,‘%.2f‘% y ,ha=‘center‘, va=‘bottom‘, fontsize=10.5)
30#设置x轴刻度标签位置31 index1 = index * 1.5 + 1/2
32#通过xticks设置x轴标签为df_gbsp的索引33plt.xticks(index1 , df_gbsp.index)
34#添加图例35plt.legend(df_gbsp.columns)
36 plt.show()

             1
            import
             numpy as np

             2
            import
             pandas as pd

             3
            import
             matplotlib.pyplot as plt

             4 df = pd.read_csv(r"D:\Data\Iris.csv")
 5 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 6 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
 7 df_gbsp = df.groupby("species").mean()
 8 len_spe = len(df_gbsp.count())
 9 index = np.arange(len(df_gbsp.index))
10 total_width= 1
11 width = total_width/len_spe
12 ysum = 0
13for i in range(len_spe):
14     het = df_gbsp.columns[i]
15     y_values = df_gbsp[het]
16#将x轴标签改为index/2, 之后在设置bottom为ysum.17     plt.bar(index/2, y_values, width =width, bottom = ysum)
18     ysum, ysum1= ysum+ y_values, ysum
19#计算堆积后每个区域中心对应的高度20     zsum = ysum1 + (ysum - ysum1)/2
21for x, y , z in zip(index/2, y_values, zsum):
22         plt.text(x, z ,‘%.2f‘% y ,ha=‘center‘, va=‘center‘, fontsize=10.5)
23 plt.xticks(index/2 , df_gbsp.index)
24plt.legend(df_gbsp.columns)
25 plt.show()

             1
            import
             numpy as np

             2
            import
             pandas as pd

             3
            import
             matplotlib.pyplot as plt

             4 df = pd.read_csv(r"D:\Data\Iris.csv")
 5 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
 6 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
 7 df_gbsp = df["sepal_len"]
 8#绘制直方图 9 df_gbsp.plot(kind = "hist")
10 plt.show()

            #
            可修改cumulative=True实现累加直方图, 以及通过bins参数修改分组数
df_gbsp.plot(kind = "hist", cumulative=‘True‘, bins = 20)

            1
            import
             numpy as np

            2
            import
             pandas as pd

            3
            import
             matplotlib.pyplot as plt

            4 df = pd.read_csv(r"D:\Data\Iris.csv")
5 df.columns = [‘sepal_len‘, ‘sepal_wid‘, ‘petal_len‘, ‘petal_wid‘,‘species‘]
6 df["species"] = df["species"].apply(lambda x: x.replace("Iris-",""))
7#hist()方法绘制直方图8 plt.hist(df["sepal_wid"], bins =20, color = "k")
9 plt.show()

#修改为累加直方图, 透明度为0.7
plt.hist(df["sepal_wid"], bins =20, color = "K", cumulative=True, alpha = 0.7)