- 博客(16)
- 收藏
- 关注
RSS订阅原创 计算复杂列
import pandas as pd import numpy as np def get_circumcircle_area(l, h): r = np.sqrt(l ** 2 + h ** 2) / 2 return r ** 2 * np.pi def wrapper(row): return get_circumcircle_area(row['Length'], row['Height']) rects = pd.read_excel('D:/Code/.vs
2021-04-13 22:46:15
121
1
原创 列操作汇总
import pandas as pd import numpy as np page_001=pd.read_excel('D:/Code/.vscode/Students.xlsx',sheet_name='Page_001') page_002=pd.read_excel('D:/Code/.vscode/Students.xlsx',sheet_name='Page_002') students = pd.concat([page_001,page_002],axis=1)#并排放在一起 pri
2021-04-12 23:01:39
117
原创 行操作汇总-增加/修改/删除/筛选删除行数据
import pandas as pd from pandas._libs import missing page_001 = pd.read_excel("",sheet_name="") page_002 = pd.read_excel("",sheet_name="") students = page_001.append(page_002).reset_index(drop=True) print(students) #可以将两张表上下拼接起来,reset 放弃原来的index stu = p
2021-04-08 23:40:13
220
原创 拟合线性方程分析预测
import pandas as pd import matplotlib.pyplot as plt sales = pd.read_excel('D:/Code/.vscode/Sales.xlsx',dtype={'Month':str}) print(sales) plt.bar(sales.index,sales.Revenue) plt.title('Sales') plt.xticks(sales.index,sales.Month,rotation=90) plt.tight_layou
2021-04-01 23:56:53
317
1
原创 数据透视表/分组/聚合
import pandas as pd import numpy as np pd.options.display.max_columns = 999 orders = pd.read_excel('D:/Code/.vscode/Orders.xlsx') orders['Year'] = pd.DatetimeIndex(orders.Date).year groups = orders.groupby(['Category','Year']) s = groups['Total'].sum() c
2021-03-31 22:04:09
281
原创 导入CSV等文件
import pandas as pd students1 = pd.read_csv('D:/Code/.vscode/Students.csv',index_col='ID') print(students1) students2 = pd.read_csv('D:/Code/.vscode/Students.tsv',sep='\t',index_col='ID') print(students2) # students3 = pd.read_csv('D:/Code/.vscode/Studen
2021-03-31 20:41:13
344
原创 duplicate去除并且找出所有重复项
import pandas as pd students = pd.read_excel('D:/Code/.vscode/Students_Duplicates.xlsx') dupe = students.duplicated(subset='Name') dupe = dupe[dupe==True] print(students.iloc[dupe.index]) #找出打印重复项 # students.drop_duplicates(subset='Name',inplace=True,k
2021-03-29 22:37:59
634
1
原创 函数调用之SUM/mean
import pandas as pd students = pd.read_excel('D:/Code/.vscode/Students.xlsx',index_col='ID') temp = students[['Test_1','Test_2','Test_3']] row_sum = temp.sum(axis=1) row_mean = temp.mean(axis=1) students['Total'] = row_sum students['Average'] =row_mean co
2021-03-24 23:01:13
203
原创 split-数据分离
import pandas as pd employees = pd.read_excel('D:/Code/.vscode/Employees.xlsx',index_col='ID') df = employees['Full Name'].str.split(expand=True) employees['First Name'] = df[0] employees['Last Name'] = df[1].str.upper() # print(df) print(employees) df
2021-03-24 22:01:35
113
原创 数据验证-之ASSER-语法错误
import pandas as pd def score_valication(row): # try: # assert 0 <= row.Score <= 100 if not 0<row.Score<=100 # except: print(f'#{row.ID}\tstudent {row.Name} has an invalid score {row.Score}.') studen
2021-03-23 22:54:26
79
原创 多表联合-JOIN MERGE
```python import pandas as pd # students = pd.read_excel('C:/Temp/Student_score.xlsx', sheet_name='Students') # scores = pd.read_excel('C:/Temp/Student_score.xlsx', sheet_name='Scores') # table = students.merge(scores, how='left', on='ID').fillna(0) # ta.
2021-03-22 22:44:25
130
原创 Matplotlib 可视化之图形美化
import pandas as pd import matplotlib.pyplot as plt students = pd.read_excel('D:/Code/.vscode/Students.xlsx') students.sort_values(by = '2017',inplace = True, ascending=False) print(students) students.plot.bar(x='From',y=['2016','2017'],color=['orange','
2021-03-20 23:28:36
258
原创 Matplotlib 数据可视化
import pandas as pd import matplotlib.pyplot as plt students = pd.read_excel('D:/Code/.vscode/Students.xlsx') students.sort_values(by='Number',inplace=True,ascending=False) print(students) # students.plot.bar(x='Field',y='Number',color='orange',title= 'i
2021-03-18 23:59:25
114
原创 VBA之批量导出图片
`Sub Rename() Application.ScreenUpdating = False On Error Resume Next MkDir ThisWorkbook.Path & “\图片” For Each pic In ActiveSheet.Shapes If pic.Type = msoPicture Then RN = pic.TopLeftCell.Offset(0, -1).Value '重命名图片 pic.Copy With ActiveShee
2021-03-18 17:00:37
1267
原创 定义函数\排序\筛选
import pandas as pd books = pd.read_excel('D:/Code/.vscode/Books.xlsx',index_col='ID') # books['price'] = books['ListPrice'] * books['Discount'] # for i in range(5,16): # books['Price'].at[i] = books['ListPrice'].at[i] * books['Discount'].at[i]
2021-03-17 23:44:20
120
1
原创 自动填充序列文字日期-pandas
import pandas as pd from datetime import date,timedelta # books = pd.read_excel('D:\Code\.vscode\Books.xlsx') # print(books) def add_month(d,md): yd = md // 12 m = d.month + md % 12 if m != 12: yd += m// 12 m = m % 12 retur
2021-03-16 00:32:26
197
1
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人