头歌Python数据框、序列定义及数据处理应用实验闯关

粘贴答案不是目的

把Python学会这才叫做意义

童年的纸飞机

现在终于飞回我手里~~

这是网站给的答案，不过运行报错，其他关卡应该没问题。

def return_values():
    import pandas as pd
    L1 = [1,-2,2.3,'hq']
    L2 = ['kl','ht','as','km']
    T1 = (1,8,8,9)
    T2 = (2,4,7,'hp')
    data = {'a':L1,'b':L2,'c':T1,'d':T2}
    A= pd.DataFrame(data)
    t1 = pd.Series(L1,index = ['a','b','c','d'])
    t2 = pd.Series(L2,index = ['a','b','c','d'])
    t3 = pd.Series(T1,index = ['a','b','c','d'])
    t4 = pd.Series(T2,index = ['a','b','c','d'])
    t = {'L1':t1,'L2':t2,'T1':t3,'T2':t4}
    B = pd.DataFrame(t)
    return(A,B)

def return_values():
    import pandas as pd
    df1 = pd.read_excel('一、车次上车人数统计表.xlsx')
    df2 = pd.read_table('txt1.txt',header=None)
    reader = pd.read_csv('data.csv',chunksize=20000)
    k=0;
    names = locals()
    for i in reader:
        k=k+1
        names['A%s'%k]=pd.DataFrame(i)
        print('第'+str(k)+'次读取数据规模为： ',len(i))
        print(i.shape)

def return_values():
    import pandas as pd
    A=pd.read_excel('Data.xlsx')
    code=list(A['站点编号'].unique())
    B=A.groupby(['站点编号','日期'])['进站人数','出站人数'].sum()
    c=list(B.index)
    A1=[]
    A2=[]
    for i in range(len(c)):
        r=c[i]
        A1.append(r[0])
        A2.append(r[1])
    sat_num=pd.DataFrame({'A1_站点编号':A1,'A2_日期':A2,'A3_进站人数':B['进站人数'].values,
                        'A4_出站人数':B['出站人数'].values})
    D=sat_num.iloc[sat_num['A2_日期'].values'2015-10-07',:]
    D1=D.groupby(['A1_站点编号'])['A3_进站人数','A4_出站人数'].sum()
    sat_num2=pd.DataFrame({'A1_站点编号':list(D1.index),
                        'A2_进站人数':D1['A3_进站人数'].values,'A3_出站人数':D1['A4_出站人数'].values})
    return(code,sat_num,sat_num2)

def return_values():

    import pandas as pd

    dict1={'code':['A01','A01','A01','A02','A02','A02','A03','A03'],
           'month':['01','02','03','01','02','03','01','02'],
           'price':[10,12,13,15,17,20,10,9]}
    dict2={'code':['A01','A01','A01','A02','A02','A02'],
           'month':['01','02','03','01','02','03'],
           'vol':[10000,10110,20000,10002,12000,21000]}

    dict1 = pd.DataFrame(dict1)
    dict2 = pd.DataFrame(dict2)

    df_inner=pd.merge(dict1,dict2,how='inner',on=['code','month'])
    df_left=pd.merge(dict1,dict2,how='left',on=['code','month'])
    df_right=pd.merge(dict1,dict2,how='right',on=['code','month'])
    return(df_inner,df_left,df_right)

def return_values():
    import pandas as pd
    import numpy as np

    dict1={'a':[2,2,'kt',6],'b':[4,6,7,8],'c':[6,5,np.nan,6]}
    dict2={'d':[8,9,10,11],'e':['p',16,10,8]}
    dict3={'a':[1,2],'b':[2,3],'c':[3,4],'d':[4,5],'e':[5,6]}

    df1 = pd.DataFrame(dict1)
    df2 = pd.DataFrame(dict2)
    df3 = pd.DataFrame(dict3)

    df4 = pd.concat([df1,df2],axis=1)

    df5 = pd.concat([df3,df4],axis=0)
    return(df4,df5)

def return_values():

    import pandas as pd

    L=[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]

    S = pd.Series(L)

    Sum  =  S.rolling(10).sum()
    mean = S.rolling(10).mean()
    max1 = S.rolling(10).max()
    min1 = S.rolling(10).min()
    return(L,S,Sum)

def return_values():
    import pandas as pd

    read = pd.read_excel('Data.xlsx')
    zhandian = read.iloc[read['站点编号'].values==135,:]
    riqi = zhandian.iloc[zhandian['日期'].values<'2015-10-03',:]
    shike = riqi.iloc[riqi['时刻'].values>=9,:]
    shike1 = shike.iloc[shike['时刻'].values11,:]
    A1 = read['站点编号'].values==135
    A2 = read['日期'].values<'2015-10-03'
    A3 = read['时刻'].values>=9
    A4 = read['时刻'].values11
    A = read.iloc[A1&A2&A3&A4,[0,1,2,3]]
    read = pd.read_excel('Data.xlsx')
    zhandian = read.loc[read['站点编号'].values==135,:]
    riqi = zhandian.loc[zhandian['日期'].values<'2015-10-03',:]
    shike = riqi.loc[riqi['时刻'].values>=9,:]
    shike1 = shike.loc[shike['时刻'].values11,:]
    A1 = read['站点编号'].values==135
    A2 = read['日期'].values<'2015-10-03'
    A3 = read['时刻'].values>=9
    A4 = read['时刻'].values11
    B = read.loc[A1&A2&A3&A4,:]
    return(A,B)

def return_values():
    import pandas as pd
    read = pd.read_excel('data.xlsx')
    data = read.iloc[read['代码'].values=='600000.SH',:].sort_values('交易日期',axis=0)
    da2 = read.sort_values(['代码','交易日期'])
    return(data,da2)

def return_values():
    import pandas as pd
    import numpy as np

    df = pd.read_excel('Data.xlsx')
    df=df.iloc[df['日期'].values>='2015-10-08',:]
    station = df.iloc[:,0].unique()
    time = df.iloc[:,2].unique()
    A1 =[]
    A2 =[]
    A3 =[]
    A4 =[]
    for i in range(len(station)):
        d1=df.iloc[df['站点编号'].values==station[i],:]
        for j in range(len(time)):
            sk = d1['时刻'].unique()
            if time[j] in sk:
                jz_sum = d1.iloc[d1['时刻'].values==time[j],3].sum()
                cz_sum = d1.iloc[d1['时刻'].values==time[j],4].sum()
                A1.append(station[i])
                A2.append(time[j])
                A3.append(jz_sum)
                A4.append(cz_sum)
    df0=pd.DataFrame({'A1_站点编号':A1,'A2_时刻':A2,'A3_总进站客流':A3,'A4_总出站客流':A4})
    df0.to_excel('各站点各时刻进出站客流数据.xlsx')
    return(df0)

def return_values():
    import random
    import pandas as pd
    code=list(range(1,31))
    A=random.sample(code,30)
    s=pd.Series(A,index=code)
    return s

def return_values():

    import random
    import pandas as pd
    t1=[]
    t2=[]
    t3=[]
    t4=[]
    t5=[]
    for i in range(40):
        t1.append(random.randint(1,70))
        t2.append(random.randint(1,80))
        t3.append(random.randint(1,50))
        t4.append(random.randint(1,30))
        t5.append(random.randint(1,20))
    A=pd.DataFrame({'t1':t1,'t2':t2,'t3':t3,'t4':t4,'t5':t5})
    return A

Original: https://blog.csdn.net/weixin_46322367/article/details/123986568
Author: 数据攻城小狮子
Title: 头歌Python数据框、序列定义及数据处理应用实验闯关