Python 根据数据帧中的多个列和行的某些条件构造新列
我有一个如下所示的数据帧：Python 根据数据帧中的多个列和行的某些条件构造新列,python,pandas,numpy,dataframe,Python,Pandas,Numpy,Dataframe,我有一个如下所示的数据帧： leid run_seq cp_id products currency amount 101 1 201 A YEN 345 102 2 201 B INR 223 101 2 202 A USD
leid run_seq cp_id products currency amount
101 1 201 A YEN 345
102 2 201 B INR 223
101 2 202 A USD 845
102 3 201 C USD 345
102 3 203 A INR 747
leid run_seq current History
101 1 {201:{A:{YEN:345}}} {}
102 2 {201:{B:{INR:223}}} {}
101 2 {202:{A:{USD:845}}} {201:{A:{YEN:345}}}
102 3 {201:{C:{USD:773}},203:{A:{INR:747 } {201:{B:{INR:223}}}
我已经尝试了所有的方法，但是没有一个完整的代码。更重要的是，我想不出从哪里开始？我利用了Pandas的应用功能和定制的Pandas的groupby功能 定制熊猫团购积分： 我还稍微修改了您的输入，以显示一些可能的结果 代码如下所示
# defined the table copied from your question
table = """
leid run_seq cp_id products currency amount
101 1 201 A YEN 345
102 1 201 A IDR 900
102 2 201 B INR 223
101 2 202 A USD 845
102 3 201 C USD 345
"""
import pandas as pd
import numpy as np
with open("stackoverflow.csv", "w") as f:
f.write(table)
df = pd.read_csv("stackoverflow.csv", delim_whitespace=True)
df = df.sort_values(by = ["leid", "run_seq"]).reset_index(drop = True)
# assigned using pandas apply in axis = 1
df["current"] = df.apply(lambda x: {x["cp_id"]: {x["products"]: {x["currency"]: x["amount"]}}}, axis = 1)
# defining a function to merge dictionaries
def Merge(dict1, dict2):
res = {**dict1, **dict2}
return res
# defining a customised cumulative function dictionary
def cumsumdict(data):
current_dict = [{}]
for i in range(1, data.shape[0]):
cp_id = list(data["current"].iloc[i-1])[0]
product = list(data["current"].iloc[i-1][cp_id])[0]
currency = list(data["current"].iloc[i-1][cp_id][product])[0]
if cp_id in current_dict[-1]:
# merge cp_id using dictionary merge if exist in previous trx
cp_merger = Merge(current_dict[-1][cp_id], data["current"].iloc[i-1][cp_id])
appender = current_dict[-1]
appender[cp_id] = cp_merger
if product in current_dict[-1][cp_id]:
# merge products using dictionary merge if exist in previous trx
product_merger = Merge(current_dict[-1][cp_id][product], data["current"].iloc[i-1][cp_id][product])
appender = current_dict[-1]
appender[cp_id][product] = product_merger
if currency in current_dict[-1][cp_id][product]:
# sum the currency value
currency_merger = current_dict[-1][cp_id][product][currency] + data["current"].iloc[i-1][cp_id][product][currency]
appender = current_dict[-1]
appender[cp_id][product][currency] = currency_merger
else:
appender = Merge(current_dict[-1], data["current"].iloc[i-1])
current_dict.append(appender)
data["history"] = current_dict
return data
df = df.groupby(["leid"]).apply(cumsumdict)
df = df[["leid", "run_seq", "current", "history"]]
print(df)
leid run_seq current \
0 101 1 {201: {'A': {'YEN': 345}}}
3 101 2 {202: {'A': {'USD': 845}}}
1 102 1 {201: {'A': {'IDR': 900}}}
2 102 2 {201: {'B': {'INR': 223}}}
4 102 3 {201: {'C': {'USD': 345}}}
history
0 {}
3 {201: {'A': {'YEN': 345}}}
1 {}
2 {201: {'A': {'IDR': 900}, 'B': {'INR': 446}}}
4 {201: {'A': {'IDR': 900}, 'B': {'INR': 446}}}
这是我的解决方案，但是“历史”包含了dict列表，而不仅仅是dict
import pandas as pd, numpy as np
import io
# My test data:
text="""leid run_seq cp_id products currency amount
0 101.0 1.0 201.0 A YEN 345.0
1 102.0 2.0 201.0 B INR 223.0
2 101.0 2.0 202.0 A USD 845.0
3 102.0 3.0 201.0 C USD 345.0
4 101.0 1.0 201.0 A YEN 100.0
5 101.0 1.0 203.0 B EURO 200.0
6 101.0 1.0 203.0 C AUD 300.0"""
df= pd.read_csv(io.StringIO(text),sep=r"\s+",engine="python").sort_values(["leid","run_seq"])
G= df.groupby(["leid","run_seq"],sort=False)
def mkdict(grp):
# Out: {201:{A:{YEN:345}}}
d_cpid={}
for r in grp.itertuples():
d_prod= d_cpid.setdefault(r.cp_id, {} ) # {201:{}
d_curr= d_prod.setdefault(r.products,{}) # {201:{A:{}
d_curr[r.currency]= d_curr.get(r.currency,0)+r.amount # {201:{A:{YEN:
return d_cpid
rslt= G.apply(lambda grp: mkdict(grp))
rslt= rslt.reset_index().rename(columns={0:"current"})
L=[]
G1= rslt.groupby("leid")
for key,grp in G1:
L.append([])
lv= grp["current"].values
for i in range(1,len(lv)):
L.append(lv[:i])
rslt["history"]= L
是否可以将更多示例从例如段落添加到数据帧？它给出以下错误-KeyError:“金额”，“发生在索引0处”@AkashDubey在pandas apply中，您需要添加axis=1，其中df.applylambda x:。。。x[金额]…，轴=1是。我只是复制粘贴了你的代码。它抛出相同的错误。对不起。是我的错。现在工作。列名不同。非常感谢。不管怎样，这些清单还是字典。这对我来说是最重要的。而且，代码没有按它应该的方式工作。特定leid、run_seq对的历史记录是该特定leid的所有当前DICT在所有前一次run_seq中的合并字典。因此，对于'leid=102'，运行leid=102的历史记录。运行顺序=4将是当前的运行顺序=1+当前的运行顺序=2+当前的运行顺序=3，leid=101当前列工作正常，但历史列都搞乱了。@AkashDubey查看上面编辑的代码。第一步不是创建字典，而是创建元组列表，然后将这些元组转换为dict。这将列表定位到dict部分。但仍然不能使历史部分正确。历史完全是一团糟。
import pandas as pd, numpy as np
import io
# My test data
text="""leid run_seq cp_id products currency amount
0 101.0 1.0 201.0 A YEN 345.0
1 102.0 2.0 201.0 B INR 223.0
2 101.0 2.0 202.0 A USD 845.0
3 102.0 3.0 201.0 C USD 345.0
4 101.0 1.0 201.0 A YEN 100.0
5 101.0 1.0 203.0 B EUR 200.0
6 101.0 1.0 203.0 C AUD 300.0
7 101.0 3.0 204.0 D INR 400.0
8 101.0 2.0 203.0 B EUR 155.0
"""
df= pd.read_csv(io.StringIO(text),sep=r"\s+",engine="python").sort_values(["leid","run_seq"])
G= df.groupby(["leid","run_seq"],sort=False)
# This function works on a groupby object, and returns list of tuples:
def mklist(grp):
return [ (r.cp_id,r.products,r.currency,r.amount) for r in grp.itertuples()]
# It makes dictionary from a list of tuples:
def mkdict(lt):
# Out: { {201:{A:{YEN:345}}}, ... }
d_cpid={}
for cpid,prod,curr,amnt in lt:
d_prod= d_cpid.setdefault(cpid, {}) # {201:{}
d_curr= d_prod.setdefault(prod,{}) # {201:{A:{}
d_curr[curr]= d_curr.get(curr,0)+amnt # {201:{A:{YEN:
return d_cpid
rslt= G.apply(lambda grp: mklist(grp) )
rslt= rslt.reset_index().rename(columns={0:"current"})
L=[]
G1= rslt.groupby("leid")
for key,grp in G1:
L.append([])
lv= grp["current"].values
for i in range(1,len(lv)):
L.append( [t for l in lv[:i] for t in l] )
rslt["history"]= [ mkdict(l) for l in L ]
rslt["current"]= [ mkdict(l) for l in rslt.current.values ]