标签:分析 False 数据 frame DataFrame 查询 pd 18 True
数据的更新
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame['height']=frame['height']+0.01
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame.loc[1,'name']='赵仪伊'
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
data1={'ID':['08'],
'name':['方文吾'],
'gender':[False],
'age':[21],
'height':[1.75]}
frame1=pd.DataFrame(data1)
print(frame.append(frame1))
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
data1={'ID':['08'],
'name':['方文吾'],
'gender':[False],
'age':[21],
'height':[1.75]}
frame1=pd.DataFrame(data1)
print(frame.append(frame1,ignore_index=True)) #忽略索引号
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame['class']=['C1','C2','A1','B2','C1','C1','C2']
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame.insert(0,'class',['C1','C2','A1','B2','C1','C1','C2'])
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.drop(1) #以索引号删除
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.drop(columns='name')
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.drop('name',axis=1) #删除列
frame=frame.drop(1,axis=0) #删除行
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.drop(index=(frame.loc[(frame['gender']==True)].index))
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.append(frame.loc[frame['age']>17])
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.reindex([6,5,4,3,2,1,0])
print(frame)
数据的排序
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame.sort_values(by=['height'])) #默认为升序
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame.sort_values(by=['age','height'],ascending=[True,False])) #定义排序方式
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
frame=frame.sort_values(by=['height'],ascending=False)
print(frame)
frame=frame.reset_index(drop=True) #索引号重置
print(frame)
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame[['name','height','ID','age','gender']]) #改变每一列的位置
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'col1':[4,2,1,3,5],
'col2':[6,4,2,6,1],
'col3':[4,2,7,6,0],
'col4':[4,3,1,5,2]}
frame=pd.DataFrame(data)
print(frame)
print(frame.sort_values(by=[3],axis=1))
数据的分组与聚合
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
groups=frame.groupby(frame['gender'])
print(groups.count())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
groups=frame.groupby(frame['gender'])
print(groups['gender'].count())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
groups=frame[['gender']].groupby(frame['gender'])
print(groups.count())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
groups=frame[['gender']].groupby(frame['gender'])
print(groups.count().rename(columns={'gender':'gendercount'}))
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame['gender'].value_counts())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame['age'].groupby(frame['age']).count().sort_values(ascending=False))
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame[['ID']].groupby([frame['gender'],frame['age']]).count())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame[['height']].groupby(frame['age']).mean())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame['name'].groupby(frame['name'].apply(len)).count())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame['name'].groupby(frame['height'].apply(round,args=[1])).count())
# coding:utf-8
import pandas as pd
from pandas import DataFrame
def peak_to_peak(arr):
return arr.max()-arr.min()
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame['height'].groupby(frame['gender']).apply(peak_to_peak))
# coding:utf-8
import pandas as pd
from pandas import DataFrame
data={'ID':['01','02','03','04','05','06','07'],
'name':['黎明','赵伊','萧晓','李思思','姚希溪','徐晗','卢昭'],
'gender':[True,False,True,False,False,False,True],
'age':[16,20,18,18,17,18,16],
'height':[1.88,1.65,1.78,1.6,1.58,1.66,1.80]}
frame=pd.DataFrame(data)
print(frame['height'].groupby(frame['gender']).apply(lambda arr:arr.max()-arr.min()))
标签:分析,False,数据,frame,DataFrame,查询,pd,18,True 来源: https://blog.csdn.net/m0_48420123/article/details/112768343
本站声明: 1. iCode9 技术分享网(下文简称本站)提供的所有内容,仅供技术学习、探讨和分享; 2. 关于本站的所有留言、评论、转载及引用,纯属内容发起人的个人观点,与本站观点和立场无关; 3. 关于本站的所有言论和文字,纯属内容发起人的个人观点,与本站观点和立场无关; 4. 本站文章均是网友提供,不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属;如您发现该文章侵犯了您的权益,可联系我们第一时间进行删除; 5. 本站为非盈利性的个人网站,所有内容不会用来进行牟利,也不会利用任何形式的广告来间接获益,纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。