Python 3.x 在列表的字典上循环并更新相应的列
我有一个Python 3.x 在列表的字典上循环并更新相应的列,python-3.x,pandas,dataframe,for-loop,if-statement,Python 3.x,Pandas,Dataframe,For Loop,If Statement,我有一个df和字典列表，如下所示 Date Tea_Good Tea_bad coffee_good coffee_bad 2020-02-01 3 1 10 7 2020-02-02 3 1 10 7 2020-02-03
df Date Tea_Good Tea_bad coffee_good coffee_bad
2020-02-01 3 1 10 7
2020-02-02 3 1 10 7
2020-02-03 3 1 10 7
2020-02-04 3 1 10 7
2020-02-05 6 1 10 7
2020-02-06 6 2 10 11
2020-02-07 6 2 5 11
2020-02-08 6 2 5 11
2020-02-09 9 2 5 11
2020-02-10 9 2 4 11
2020-02-11 9 2 4 11
2020-02-12 9 2 4 11
2020-02-13 9 2 4 11
2020-02-14 9 2 4 11
dictrf = {
"tea":
[
{
"type": "linear",
"from": "2020-02-01T20:00:00.000Z",
"to": "2020-02-03T20:00:00.000Z",
"days":3,
"coef":[0.1,0.1,0.1,0.1,0.1,0.1],
"case":"bad"
},
{
"type": "polynomial",
"from": "2020-02-08T20:00:00.000Z",
"to": "2020-02-10T20:00:00.000Z",
"days":3,
"coef":[0.1,0.1,0.1,0.1,0.1,0.1],
"case":"good"
}],
"coffee": [
{
"type": "quadratic",
"from": "2020-02-01T20:00:00.000Z",
"to": "2020-02-10T20:00:00.000Z",
"days": 10,
"coef": [0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
"case":"good"
},
{
"type": "constant",
"from": "2020-02-11T20:00:00.000Z",
"to": "2020-02-13T20:00:00.000Z",
"days": 5,
"coef": [0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
"case":"bad"
}]}
1. "tea"
2. "coffee"
df1. Which column?
If key == "tea" and "case" == "bad" update the Tea_bad column
2. When?
"from": "2020-02-01T20:00:00.000Z",
"to": "2020-02-03T20:00:00.000Z"
3. How?
if "type": "linear",
when "from": "2020-02-01T20:00:00.000Z"
t = 0,
a0 = coef[0]
a1 = coef[1]
a2 = coef[2]
a3 = coef[3]
a4 = coef[4]
a5 = coef[5]
df.loc[(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_bad'] = a0 + a1 * t.
1。哪个栏目？
如果键==“tea”和“case”==“bad”，则更新tea\U bad列
2.什么时候
“从”：“2020-02-01T20:00:00.000Z”，
“收件人”：“2020-02-03T20:00:00.000Z”
3.怎么用？
如果“类型”：“线性”，
当“开始”：“2020-02-01T20:00:00.000Z”
t=0，
a0=coef[0]
a1=系数[1]
a2=系数[2]
a3=系数[3]
a4=系数[4]
a5=系数[5]
df.loc[（df['Date']>=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date）]=开始日期）&（df['['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']=开始日期）&（df['Date']使用：
结果:
# rf_unser_input(df, rf)
Date Tea_Good Tea_bad coffee_good coffee_bad days
0 2020-02-01 3.0 1.0 10.0 7.0 1
1 2020-02-02 3.0 0.3 0.3 7.0 2
2 2020-02-03 3.0 0.4 0.4 7.0 3
3 2020-02-04 3.0 0.5 0.5 0.3 4
4 2020-02-05 12.0 1.0 3.1 0.4 5
5 2020-02-06 13.0 2.0 4.3 0.5 6
6 2020-02-07 6.0 2.0 5.7 0.6 7
7 2020-02-08 6.0 2.0 7.3 11.0 8
8 2020-02-09 6.3 2.0 9.1 11.0 9
9 2020-02-10 36.4 2.0 11.1 11.0 10
10 2020-02-11 136.5 2.0 13.3 11.0 11
11 2020-02-12 9.0 2.0 4.0 11.0 12
12 2020-02-13 9.0 2.0 4.0 11.0 13
13 2020-02-14 9.0 2.0 4.0 11.0 14
一种解决方案是循环字典并使用apply：
df.Date=pd.to_datetime（df.Date）
df=df.set_索引（'Date'，drop=True）
df['Period']=[（日期-df.index[0]）。df.index中日期的天数]
对于键，在rf.items（）中使用val：
对于val中的元素：
type_method=elem.get（'type'）
col_name=f'{key.capitalize（）}{elem.get（“case”）}'
date\u from=pd.to\u datetime（elem.get（'from'））
date_to=pd.to_datetime（elem.get（'to'））
a0、a1、a2、a3、a4、a5=要素获取（'coef'）
掩码日期=（df.index>=日期从）&（df.index
def rf_user_input(df, req_obj):
df = df.sort_values('Date')
df['days'] = (df['Date'] - df.at[0, 'Date']).dt.days + 1
cols, df.columns = df.columns, df.columns.str.lower()
for category in ("tea", "coffee"):
if category not in req_obj.keys():
continue
for params_obj in req_obj[category]:
case = params_obj['case']
kind = '{}_{}'.format(category, case)
start_date = pd.to_datetime(params_obj['from'], format='%Y-%m-%dT%H:%M:%S.%fZ')
end_date = pd.to_datetime(params_obj['to'], format='%Y-%m-%dT%H:%M:%S.%fZ')
label, coef, n_days = params_obj['type'], params_obj['coef'], params_obj['days']
# Additional n_days code - Start
first_date = df['date'].min()
period_days = (start_date - first_date).days
# Additional n_days code - End
# Checking 'start_date' , 'end_date' and 'n_days' conditions
# If the start_date and end_date is null return the calibration df as it is
if (start_date == 0) and (end_date == 0):
return df.set_axis(cols, axis=1)
if (start_date == 0) and (end_date != 0) and (n_days == 0):
return df.set_axis(cols, axis=1)
if (start_date != 0) and (end_date == 0) and (n_days == 0):
return df.set_axis(cols, axis=1)
# if start date, end date and n_days are non zero then consider start date and n_days
if (start_date != 0) and (end_date != 0) and (n_days != 0):
end_date = start_date + pd.Timedelta(days=n_days)
if (start_date != 0) and (end_date != 0) and (n_days == 0):
n_days = (end_date - start_date)
if (start_date != 0) and (end_date == 0) and (n_days != 0):
end_date = start_date + pd.Timedelta(days=n_days)
if (start_date == 0) and (end_date != 0) and (n_days != 0):
start_date = end_date - pd.Timedelta(days=n_days)
if (n_days != 0) and (start_date != 0):
end_date = start_date + pd.Timedelta(days=n_days)
# If the start_date and end_date is null return the calibration df as it is
if len(coef) == 6:
a0, a1, a2, a3, a4, a5 = coef
mask = df['date'].between(start_date, end_date)
if label == 'constant':
if kind in ('tea_good', 'tea_bad', 'coffee_good', 'coffee_bad'):
df.loc[mask, kind] = a0 + df['days'] - period_days
elif label == 'linear':
if kind in ('tea_good', 'tea_bad', 'coffee_good', 'coffee_bad'):
df.loc[mask, kind] = a0 + \
(a1 * ((df['days']) - period_days))
# Quadratic
elif label == 'quadratic':
if kind in ('tea_good', 'tea_bad', 'coffee_good', 'coffee_bad'):
df.loc[mask, kind] = a0 + (a1 * ((df['days']) - period_days)) + (
a2 * ((df['days']) - period_days) ** 2)
# Polynomial
elif label == 'polynomial':
if kind in ('tea_good', 'tea_bad', 'coffee_good', 'coffee_bad'):
df.loc[mask, kind] = a0 + (
a1 * ((df['days']) - period_days)) + (a2 * (
(df['days']) - period_days) ** 2) + (a3 * (
(df['days']) - period_days) ** 3) + (a4 * (
(df['days']) - period_days) ** 4) + (a5 * ((df['days']) - period_days) ** 5)
# Exponential
elif label == 'exponential':
if kind in ('tea_good', 'tea_bad', 'coffee_good', 'coffee_bad'):
df.loc[mask, kind] = np.exp(a0)
# Calibration File
elif label == 'calibration_file':
pass
else:
raise Exception(
'Coefficients index do not match. All values of coefficients should be passed')
return df.set_axis(cols, axis=1)
# rf_unser_input(df, rf)
Date Tea_Good Tea_bad coffee_good coffee_bad days
0 2020-02-01 3.0 1.0 10.0 7.0 1
1 2020-02-02 3.0 0.3 0.3 7.0 2
2 2020-02-03 3.0 0.4 0.4 7.0 3
3 2020-02-04 3.0 0.5 0.5 0.3 4
4 2020-02-05 12.0 1.0 3.1 0.4 5
5 2020-02-06 13.0 2.0 4.3 0.5 6
6 2020-02-07 6.0 2.0 5.7 0.6 7
7 2020-02-08 6.0 2.0 7.3 11.0 8
8 2020-02-09 6.3 2.0 9.1 11.0 9
9 2020-02-10 36.4 2.0 11.1 11.0 10
10 2020-02-11 136.5 2.0 13.3 11.0 11
11 2020-02-12 9.0 2.0 4.0 11.0 12
12 2020-02-13 9.0 2.0 4.0 11.0 13
13 2020-02-14 9.0 2.0 4.0 11.0 14
Tea_good Tea_bad Coffee_good Coffee_bad Period
Date
2020-02-01 3.0 1.0 10.0 7.0 0
2020-02-02 3.0 0.2 0.3 7.0 1
2020-02-03 3.0 0.3 0.7 7.0 2
2020-02-04 3.0 1.0 1.3 7.0 3
2020-02-05 6.0 1.0 2.1 7.0 4
2020-02-06 6.0 2.0 3.1 11.0 5
2020-02-07 6.0 2.0 4.3 11.0 6
2020-02-08 6.0 2.0 5.7 11.0 7
2020-02-09 3744.9 2.0 7.3 11.0 8
2020-02-10 6643.0 2.0 9.1 11.0 9
2020-02-11 9.0 2.0 4.0 11.0 10
2020-02-12 9.0 2.0 4.0 11.1 11
2020-02-13 9.0 2.0 4.0 12.1 12
2020-02-14 9.0 2.0 4.0 11.0 13