使用“压缩重复代码”；至于；使用字符串的语句-Python

我对Python中的“for”语句非常陌生，我无法得到我认为应该简单易用的东西。我的代码是：

import pandas as pd

df1 = pd.DataFrame({'Column1' : pd.Series([1,2,3,4,5,6])})
df2 = pd.DataFrame({'Column1' : pd.Series([1,2,3,4,5,6])})
df3 = pd.DataFrame({'Column1' : pd.Series([1,2,3,4,5,6])})

DF1 = pd.DataFrame({'Column1' : pd.Series([1,2,3,4,5,6])})
DF2 = pd.DataFrame({'Column1' : pd.Series([1,2,3,4,5,6])})
DF3 = pd.DataFrame({'Column1' : pd.Series([1,2,3,4,5,6])})

然后：

A1=len（df1.loc[df1['Column1']=df1['Column1'].iloc[3]]
A2=len（df2.loc[df2['Column1']=df2['Column1'].iloc[3]]
A3=len（df3.loc[df3['Column1']=df3['Column1'].iloc[3]]

正如您所看到的，这是大量重复代码，只是识别号不同。因此，我第一次尝试使用“for”语句是：

Numbers = [1,2,3]

for i in Numbers:
    "A" + str(i) = len("df" + str(i).loc["df" + str(i)['Column1'] <= "DF" + str(i)['Column1'].iloc[2]])
    "Z" + str(i) = len("df" + str(i).loc["df" + str(i)['Column1'] >= "DF" + str(i)['Column1'].iloc[3]])

number=[1,2,3]
以数字表示的i：
“A”+str（i）=len（“df”+str（i）.loc[“df”+str（i）[Column1']=“df”+str（i）[Column1'].iloc[3]]）

这产生了SyntaxError：“无法分配给运算符”。所以我试着：

Numbers = [1,2,3]

for i in Numbers:
    A = "A" + str(i)
    Z = "Z" + str(i)
    A = len("df" + str(i).loc["df" + str(i)['Column1'] <= "DF" + str(i)['Column1'].iloc[2]])
    Z = len("df" + str(i).loc["df" + str(i)['Column1'] >= "DF" + str(i)['Column1'].iloc[3]])

number=[1,2,3]
以数字表示的i：
A=“A”+str（一）
Z=“Z”+str（一）
A=len（“df”+str（i）.loc[“df”+str（i）[Column1']=“df”+str（i）[Column1'].iloc[3]]

这产生了AttributeError:“str”对象没有属性“loc”。我尝试了其他一些方法，如：

Numbers = [1,2,3]

for i in Numbers:
    A = "A" + str(i)
    Z = "Z" + str(i)
    df = "df" + str(i)
    DF = "DF" + str(i)
    A = len(df.loc[df['Column1'] <= DF['Column1'].iloc[2]])
    Z = len(df.loc[df['Column1'] <= DF['Column1'].iloc[3]])

number=[1,2,3]
以数字表示的i：
A=“A”+str（一）
Z=“Z”+str（一）
df=“df”+str（一）
DF=“DF”+str（一）
A=len（df.loc[df['Column1']在for循环中生成变量是“受限的”（您可以这样做，但最好避免。请参阅其他帖子：，）

相反，使用此代码来实现您的目标，而无需根据需要生成尽可能多的变量（实际上只生成for循环中的值）：

#数据帧列表
Hanimals=[H26，H45，H46，H47，H51，H58，H64，H65]
Ianimals=[I26，I45，I46，I47，I51，I58，I64，I65]
#在上面的列表中使用for循环生成序列
BPM=pd.DataFrame（{'BPM_Base'：pd.Series（[i_a for i_a in[len（i_h.loc[i_h['EKG-evt']=\
i_i[0].iloc[-1]]/30表示i_h，i_i在zip中（Hanimals，Ianimals）]}）

更新

更有效的方法（仅在“动物”列表上迭代一次）：

#数据帧列表
Hanimals=[H26，H45，H46，H47，H51，H58，H64，H65]
Ianimals=[I26，I45，I46，I47，I51，I58，I64，I65]
#您不需要使用pd.Series（），
#只需创建一个元组列表：[（A26，Z26），（A45，Z45）…]并对其进行迭代
BPM=pd.DataFrame（{'BPM_Base'：i[0]，'BPM_Test'：i[1]}用于中的i\
[（len（i_h.loc[i_h['EKG-evt']=i_i[0].iloc[-1]]）/30）\
对于i_h，i_i in zip（Hanimals，Ianimals）]）
找到了一种更好的方法来满足我的需要。这主要是为了让我能够找到我的方法

# Change/Add animals and conditions here, make sure they match up directly

Animal = ['26','45','46','47','51','58','64','65', '69','72','84']
Cond = ['Stomach','Intestine','Stomach','Stomach','Intestine','Intestine','Intestine','Stomach','Cut','Cut','Cut']    

d = []

def CuSO4():
    for i in Animal:

        # load in Spike data
        A = pd.read_csv('TXT/INJ/' + i + '.txt',delimiter=r"\s+", skiprows = 15, header = None, usecols = range(1))
        B = pd.read_csv('TXT/EKG/' + i + '.txt', skiprows = 3)
        C = pd.read_csv('TXT/ESO/' + i + '.txt', skiprows = 3) 
        D = pd.read_csv('TXT/TRACH/' + i + '.txt', skiprows = 3)
        E = pd.read_csv('TXT/BP/' + i + '.txt', delimiter=r"\s+").rename(columns={"4 BP": "BP"})


        # Count number of beats before/after injection, divide by 10/30 minutes for average BPM.
        F = len(B.loc[B['EKG-evt'] <= A[0].iloc[0]])/10   
        G = len(B.loc[B['EKG-evt'] >= A[0].iloc[-1]])/30


        # Count number of esophogeal events before/after injection
        H = len(C.loc[C['Eso-evt'] <= A[0].iloc[0]])
        I = len(C.loc[C['Eso-evt'] >= A[0].iloc[-1]])

        # Find Trach events after injection
        J = D.loc[D['Trach-evt'] >= A[0].iloc[-1]]

        # Count number of breaths before/after injection, divide by 10/30 min for average breaths/min
        K = len(D.loc[D['Trach-evt'] <= A[0].iloc[0]])/10
        L = len(J)/30

        # Use Trach events from J to find the number of EE
        M = pd.DataFrame(pybursts.kleinberg(J['Trach-evt'], s=4, gamma=0.1))
        N = M.last_valid_index()

        # Use N and M to determine the latency, set value to MaxTime (1800s)if EE = 0
        O = 1800 if N == 0 else M.iloc[1][1] - A[0].iloc[-1]

        # Find BP value before/after injection, then determine the mean value
        P = E.loc[E['Time'] <= A[0].iloc[0]]
        Q = E.loc[E['Time'] >= A[0].iloc[-1]]
        R = P["BP"].mean()
        S = Q["BP"].mean()

        # Combine all factors into one DF
        d.append({'EE' : N, 'EE-lat' : O,
          'BPM_Base' : F, 'BPM_Test' : G,
          'Eso_Base' : H, 'Eso_Test' : I,
          'Trach_Base' : K, 'Trach_Test' : L,
          'BP_Base' : R, 'BP_Test' : S})

CuSO4()

# Create shell DF with animal numbers and their conditions.

DF = pd.DataFrame({'Animal' : pd.Series(Animal), 'Cond' : pd.Series(Cond)})

# Pull appended DF from CuSO4 and make it a pd.DF
Df = pd.DataFrame(d)

# Combine the two DF's
df = pd.concat([DF, Df], axis=1)
df

#在此处更改/添加动物和条件，确保它们直接匹配
动物=['26'、'45'、'46'、'47'、'51'、'58'、'64'、'65'、'69'、'72'、'84']
Cond=[‘胃’、‘肠’、‘胃’、‘肠’、‘肠’、‘肠’、‘胃’、‘切’、‘切’、‘切’]
d=[]
def CuSO4（）：
对于动物中的i：
#加载峰值数据
A=pd.read_csv（'TXT/INJ/'+i+'.TXT'，分隔符=r“\s+”，skiprows=15，header=None，usecols=range（1））
B=pd.read_csv（'TXT/EKG/'+i+'.TXT'，skiprows=3）
C=pd.read_csv（'TXT/ESO/'+i+'.TXT'，skiprows=3）
D=pd.read_csv（'TXT/TRACH/'+i+'.TXT'，skiprows=3）
E=pd.read_csv（'TXT/BP/'+i+'.TXT'，分隔符=r“\s+”）。重命名（列={“4 BP”：“BP”}）
#计算注射前/后的心跳次数，除以10/30分钟获得平均BPM。
F=len（B.loc[B['EKG-evt']=A[0].iloc[-1]]）/30
#统计注射前后的食管事件数
H=len（C.loc[C['Eso-evt']=A[0].iloc[-1]]
#注射后查找Trach事件
J=D.loc[D['Trach-evt']>=A[0].iloc[-1]]
#计算注射前/后的呼吸次数，除以10/30分钟获得平均每分钟呼吸次数
K=len（D.loc[D['Trach-evt']可能是@ukaszRogalski的复制品这是如何工作的，我会将“x”定义为等于[26,45,46,47,51,58,64,65]，然后键入“Ax=len（Hx.loc[Hx['EKG-evt']如果您将列一起提供给dataframe，这将是更好的代码，而不是为每个列指定一个列的命名变量。您的要求要求是对看起来像变量名的字符串使用
eval
或
exec
。所有这些努力都只是为了引用已经很好地表示的内容ED在另一个数据框里，你没有分享。我不会浪费我的时间去解决这个混乱。但是，如果你用原始数据问了一个类似的问题，我会考虑它。@ PrimaRead我简化了它，并做了一个原始数据示例。这是一个更有效的解决方案（只有2个
用于
循环，而不是4个）
Numbers = [1,2,3]

for i in Numbers:
     Ai = len(dfi.loc[dfi['Column1'] <= DFi['Column1'].iloc[2]])
     Zi = len(dfi.loc[dfi['Column1'] <= DFi['Column1'].iloc[3]])

A1 = len(df1.loc[df1['Column1'] <= DF1['Column1'].iloc[2]])  
Z1 = len(df1.loc[df1['Column1'] >= DF1['Column1'].iloc[3]])

A2 = len(df2.loc[df1['Column1'] <= DF2['Column1'].iloc[2]])  
Z2 = len(df2.loc[df1['Column1'] >= DF2['Column1'].iloc[3]])

A3 = len(df3.loc[df3['Column1'] <= DF3['Column1'].iloc[2]])  
Z3 = len(df3.loc[df3['Column1'] >= DF3['Column1'].iloc[3]])

# Lists of your dataframes
Hanimals = [H26, H45, H46, H47, H51, H58, H64, H65]
Ianimals = [I26, I45, I46, I47, I51, I58, I64, I65]

# Generate your series using for loops iterating through your lists above
BPM = pd.DataFrame({'BPM_Base':pd.Series([i_a for i_a in [len(i_h.loc[i_h['EKG-evt'] <=\
     i_i[0].iloc[0]]) / 10 for i_h, i_i in zip(Hanimals, Ianimals)]]),
    'BPM_Test':pd.Series([i_z for i_z in [len(i_h.loc[i_h['EKG-evt'] >=\
     i_i[0].iloc[-1]]) / 30 for i_h, i_i in zip(Hanimals, Ianimals)]])})

# Lists of your dataframes
Hanimals = [H26, H45, H46, H47, H51, H58, H64, H65]
Ianimals = [I26, I45, I46, I47, I51, I58, I64, I65]

# You don't need using pd.Series(),
# just create a list of tuples: [(A26, Z26), (A45, Z45)...] and iterate over it
BPM = pd.DataFrame({'BPM_Base':i[0], 'BPM_Test':i[1]} for i in \
    [(len(i_h.loc[i_h['EKG-evt'] <= i_i[0].iloc[0]]) / 10,
    len(i_h.loc[i_h['EKG-evt'] >= i_i[0].iloc[-1]]) / 30) \
    for i_h, i_i in zip(Hanimals, Ianimals)])

# Change/Add animals and conditions here, make sure they match up directly

Animal = ['26','45','46','47','51','58','64','65', '69','72','84']
Cond = ['Stomach','Intestine','Stomach','Stomach','Intestine','Intestine','Intestine','Stomach','Cut','Cut','Cut']    

d = []

def CuSO4():
    for i in Animal:

        # load in Spike data
        A = pd.read_csv('TXT/INJ/' + i + '.txt',delimiter=r"\s+", skiprows = 15, header = None, usecols = range(1))
        B = pd.read_csv('TXT/EKG/' + i + '.txt', skiprows = 3)
        C = pd.read_csv('TXT/ESO/' + i + '.txt', skiprows = 3) 
        D = pd.read_csv('TXT/TRACH/' + i + '.txt', skiprows = 3)
        E = pd.read_csv('TXT/BP/' + i + '.txt', delimiter=r"\s+").rename(columns={"4 BP": "BP"})


        # Count number of beats before/after injection, divide by 10/30 minutes for average BPM.
        F = len(B.loc[B['EKG-evt'] <= A[0].iloc[0]])/10   
        G = len(B.loc[B['EKG-evt'] >= A[0].iloc[-1]])/30


        # Count number of esophogeal events before/after injection
        H = len(C.loc[C['Eso-evt'] <= A[0].iloc[0]])
        I = len(C.loc[C['Eso-evt'] >= A[0].iloc[-1]])

        # Find Trach events after injection
        J = D.loc[D['Trach-evt'] >= A[0].iloc[-1]]

        # Count number of breaths before/after injection, divide by 10/30 min for average breaths/min
        K = len(D.loc[D['Trach-evt'] <= A[0].iloc[0]])/10
        L = len(J)/30

        # Use Trach events from J to find the number of EE
        M = pd.DataFrame(pybursts.kleinberg(J['Trach-evt'], s=4, gamma=0.1))
        N = M.last_valid_index()

        # Use N and M to determine the latency, set value to MaxTime (1800s)if EE = 0
        O = 1800 if N == 0 else M.iloc[1][1] - A[0].iloc[-1]

        # Find BP value before/after injection, then determine the mean value
        P = E.loc[E['Time'] <= A[0].iloc[0]]
        Q = E.loc[E['Time'] >= A[0].iloc[-1]]
        R = P["BP"].mean()
        S = Q["BP"].mean()

        # Combine all factors into one DF
        d.append({'EE' : N, 'EE-lat' : O,
          'BPM_Base' : F, 'BPM_Test' : G,
          'Eso_Base' : H, 'Eso_Test' : I,
          'Trach_Base' : K, 'Trach_Test' : L,
          'BP_Base' : R, 'BP_Test' : S})

CuSO4()

# Create shell DF with animal numbers and their conditions.

DF = pd.DataFrame({'Animal' : pd.Series(Animal), 'Cond' : pd.Series(Cond)})

# Pull appended DF from CuSO4 and make it a pd.DF
Df = pd.DataFrame(d)

# Combine the two DF's
df = pd.concat([DF, Df], axis=1)
df