摘要：
1importpandasaspd2importnumpyasnp34#加载数据5detail=pd.read_excel("../day05/meal_order_detail.xlsx")6#print("detail：",detail)7print("detail的列索引：",detail.columns)89#将dishes_name转化为数值型数据10#哑变量矩阵转化11res=pd.g
1 importpandas as pd 2 importnumpy as np 3 4 #加载数据 5 detail = pd.read_excel("../day05/meal_order_detail.xlsx") 6 #print("detail ：", detail) 7 print("detail 的列索引：", detail.columns) 8 9 #将dishes_name 转化为数值型数据 10 #哑变量矩阵转化 11 res =pd.get_dummies( 12 data=detail.loc[:,"dishes_name"], 13 prefix_sep="_", 14 prefix="菜品" 15 ) 16 print("转化之后的结果res: ",res) 17 #res.to_csv("./hh.csv") 18 19 20 #身高 150 - 190 每位同学 都是一个具体的身高---连续的小数 21 #将连续型数据转化为类别数据 ----离散化 22 #分组 23 print("菜品单价的最大值与最小值：", detail.loc[:, "amounts"].max(), detail.loc[:, "amounts"].min()) 24 #将detail 里面的amounts 数据进行离散化 25 #detail.loc[:, "amounts"] = pd.cut(detail.loc[:, "amounts"], bins=5) 26 27 #自定义分组 28 ## 等宽分组 29 ## 1、指定分组个数 30 group_num = 5 31 ## # 2、计算最大值与最小值的极差 32 ptp = detail.loc[:, "amounts"].max() - detail.loc[:, "amounts"].min() 33 ## # 3、确定步长 34 step = int(np.ceil(ptp /group_num)) 35 ## # 4、确定分组的区间的节点 36 bins = np.arange(detail.loc[:, "amounts"].min(), detail.loc[:, "amounts"].max() +step, step) 37 print(bins) 38 ## 5、指定自定义分组 39 ## include_lowest ---指定包含最小值 40 detail.loc[:, "amounts"] = pd.cut(detail.loc[:, "amounts"], bins=bins, include_lowest=True) 41 42 #等频分组 43 #1、计算分位数 44 #bins = detail.loc[:, "amounts"].quantile(q=np.arange(0, 1 + 1 / 5, 1 / 5)) 45 #print(bins) 46 ## include_lowest ---指定包含最小值 47 #detail.loc[:, "amounts"] = pd.cut(detail.loc[:, "amounts"], bins=bins, include_lowest=True) 48 # 49 #print(detail.loc[:, "amounts"]) 50 ## 51 ## 统计每一个组内的个数 52 #res_counts = pd.value_counts(detail.loc[:, "amounts"]) 53 #print("res_counts: ", res_counts)