У меня есть df и список словарей, как показано ниже.
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
Dictionary:
rf = {
"tea":
[
{
"type": "df",
"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"
},
{
"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": "constant",
"from": "2020-02-04T20:00:00.000Z",
"to": "2020-02-05T20:00:00.000Z",
"days":2,
"coef":[10,10,10,10,10,10],
"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": "df",
"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"
},
{
"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":"good"
},
{
"type": "linear",
"from": "2020-02-03T20:00:00.000Z",
"to": "2020-02-06T20:00:00.000Z",
"days": 4,
"coef": [0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
"case":"bad"
}
]
}
Где мне нужно обновить столбцы на основе словарного значения. Значение по умолчанию end_date, start_date, n_days = 0, но для этого нам нужно как минимум 2. как ненулевое.
Если все не равны нулю, рассмотрите start_date и end_date и вычислите n_days, как показано ниже. n_days = end_date - start_date и обновить df.
Если любые два равны нулю, верните df, как и для этого условия.
Ниже приведены все условия, связанные с end_date, start_date и n_days
if (start_date == 0) & (end_date == 0):
return df
if (start_date == 0) & (end_date != 0) & (n_days == 0):
return df
if (start_date != 0) & (end_date == 0) & (n_days == 0):
return df
# if start date, end date and n_days are non zero then consider start date and n_days
if (start_date != 0) & (end_date != 0) & (n_days != 0):
#n_days = (end_date - start_date).days
#n_days = (end_date - start_date).days
end_date = start_date + DT.timedelta(days=n_days)
if (start_date != 0) & (end_date != 0) & (n_days == 0) :
n_days = (end_date - start_date)
print(f" n day = {n_days}")
end_date = end_date
if (start_date != 0) & (end_date == 0) & (n_days != 0) :
#n_days = (end_date - start_date)
#print(f" n day = {n_days}")
end_date = start_date + DT.timedelta(days=n_days)
if (start_date == 0) & (end_date != 0) & (n_days != 0) :
start_date = end_date - DT.timedelta(days=n_days)
if (n_days != 0) & (start_date != 0):
end_date = start_date + DT.timedelta(days=n_days)
Я пробовал код ниже.
def rf_user_input(df, REQUEST_OBJ):
'''
This functions returns the tea_coffee dataframe with the user input functions for tea, coffee
params: data : tea_coffee dataframe uploaded from user
request_object_api: The api should contain the below params
start_date: start date of the user function for rf
end_date : end date of the user function for the rf
label : {'constant', 'linear', 'quadratic', 'polynomial', 'exponential', 'df'}
coef : list with 6 indexes [a0,a1,a2,a3,a4,a5]
return: rf computed with user inputs
'''
# df.days.iloc[(df[df.Date==start_date].index[0])]
df = df.sort_values(by='Date')
df['days'] = (df['Date'] - df.at[0, 'Date']).dt.days + 1
REQUIRED_KEYS = ["tea", "coffee"]
for teacoffee_category in REQUIRED_KEYS:
print(f" teacoffee_category - {teacoffee_category}")
if teacoffee_category in REQUEST_OBJ.keys():
param_obj_list = REQUEST_OBJ[teacoffee_category]
for params_obj in param_obj_list:
# Do the data processing
goodbad_catgeory = params_obj['case']
kind = teacoffee_category + '_' + goodbad_catgeory
start_date, end_date, label, coef, n_days = params_obj['from'], params_obj['to'], params_obj['type'], \
params_obj['coef'], params_obj['days']
start_date = DT.datetime.strptime(start_date, "%Y-%m-%dT%H:%M:%S.%fZ")
end_date = DT.datetime.strptime(end_date, "%Y-%m-%dT%H:%M:%S.%fZ")
print(f" start date - {start_date}")
print(f" end date - {end_date}")
# Additional n_days code - Start
first_date = df['Date'].min()
period_days = (start_date - first_date)
print(f" period day - {period_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) & (end_date == 0):
return df
if (start_date == 0) & (end_date != 0) & (n_days == 0):
return df
if (start_date != 0) & (end_date == 0) & (n_days == 0):
return df
# if start date, end date and n_days are non zero then consider start date and n_days
if (start_date != 0) & (end_date != 0) & (n_days != 0):
#n_days = (end_date - start_date).days
#n_days = (end_date - start_date).days
end_date = start_date + DT.timedelta(days=n_days)
if (start_date != 0) & (end_date != 0) & (n_days == 0) :
n_days = (end_date - start_date)
print(f" n day = {n_days}")
end_date = end_date
if (start_date != 0) & (end_date == 0) & (n_days != 0) :
#n_days = (end_date - start_date)
#print(f" n day = {n_days}")
end_date = start_date + DT.timedelta(days=n_days)
if (start_date == 0) & (end_date != 0) & (n_days != 0) :
start_date = end_date - DT.timedelta(days=n_days)
if (n_days != 0) & (start_date != 0):
end_date = start_date + DT.timedelta(days=n_days)
# If the start_date and end_date is null return the calibration df as it is
if len(coef) == 6:
# Coefficients Index Initializations
a0 = coef[0]
a1 = coef[1]
a2 = coef[2]
a3 = coef[3]
a4 = coef[4]
a5 = coef[5]
# Constant
if label == 'constant':
if kind == 'tea_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_Good'] = a0 + (df['days']) - period_days
elif kind == 'tea_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_bad'] = a0 + df['days'] - period_days
elif kind == 'coffee_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_good'] = a0 + df['days'] - period_days
elif kind == 'coffee_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_bad'] = a0 + df['days'] - period_days
# Linear
if label == 'linear':
if kind == 'tea_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_Good'] = a0 + (
a1 * ((df['days']) - period_days))
elif kind == 'tea_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_bad'] = a0 + (
a1 * ((df['days']) - period_days))
elif kind == 'coffee_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_good'] = a0 + (
a1 * ((df['days']) - period_days))
elif kind == 'coffee_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_bad'] = a0 + (
a1 * ((df['days']) - period_days))
# Quadratic
if label == 'quadratic':
if kind == 'tea_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_Good'] = a0 + (
a1 * ((df['days']) - period_days)) + (a2 * ((df['days']) - period_days) ** 2)
elif kind == 'tea_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_bad'] = a0 + (
a1 * ((df['days']) - period_days)) + (a2 * ((df['days']) - period_days) ** 2)
elif kind == 'coffee_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_good'] = a0 + (
a1 * ((df['days']) - period_days)) + (a2 * ((df['days']) - period_days) ** 2)
elif kind == 'coffee_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_bad'] = a0 + (
a1 * ((df['days']) - period_days)) + (a2 * ((df['days']) - period_days) ** 2)
# Polynomial
if label == 'polynomial':
if kind == 'tea_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_Good'] = 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)
elif kind == 'tea_bad':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_bad'] = 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)
elif kind == 'coffee_good':
df.loc[
(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_good'] = 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)
elif kind == 'coffee_bad':
df.loc[(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_bad'] = 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
if label == 'exponential':
if kind == 'tea_good':
df.loc[(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_Good'] = np.exp(a0)
elif kind == 'tea_bad':
df.loc[(df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_bad'] = np.exp(a0)
elif kind == 'coffee_good':
df.loc[(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_good'] = np.exp(a0)
elif kind == 'coffee_bad':
df.loc[(df['Date'] >= start_date) & (df['Date'] <= end_date), 'coffee_bad'] = np.exp(a0)
# Calibration File
if label == 'calibration_file':
pass
# return df
else:
raise Exception('Coefficients index do not match. All values of coefficients should be passed')
else:
return df
return df
И я столкнулся с ошибкой ниже после выполнения ниже.
df1 = rf_user_input(df, rf)
Я столкнулся с ошибкой ниже
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-146-338f614b0d56> in <module>
----> 1 df1 = rf_user_input(df, rf)
<ipython-input-144-86019ba60ca3> in rf_user_input(df, REQUEST_OBJ)
109 df.loc[
110 (df['Date'] >= start_date) & (df['Date'] <= end_date), 'Tea_Good'] = a0 + (
--> 111 a1 * ((df['days']) - period_days))
112 elif kind == 'tea_bad':
113 df.loc[
~/admvenv/lib/python3.7/site-packages/pandas/core/ops/common.py in new_method(self, other)
62 other = item_from_zerodim(other)
63
---> 64 return method(self, other)
65
66 return new_method
~/admvenv/lib/python3.7/site-packages/pandas/core/ops/__init__.py in wrapper(left, right)
501 lvalues = extract_array(left, extract_numpy=True)
502 rvalues = extract_array(right, extract_numpy=True)
--> 503 result = arithmetic_op(lvalues, rvalues, op, str_rep)
504
505 return _construct_result(left, result, index=left.index, name=res_name)
~/admvenv/lib/python3.7/site-packages/pandas/core/ops/array_ops.py in arithmetic_op(left, right, op, str_rep)
191 # by dispatch_to_extension_op.
192 # Timedelta is included because numexpr will fail on it, see GH#31457
--> 193 res_values = dispatch_to_extension_op(op, lvalues, rvalues)
194
195 else:
~/admvenv/lib/python3.7/site-packages/pandas/core/ops/dispatch.py in dispatch_to_extension_op(op, left, right)
123 # The op calls will raise TypeError if the op is not defined
124 # on the ExtensionArray
--> 125 res_values = op(left, right)
126 return res_values
TypeError: unsupported operand type(s) for -: 'numpy.ndarray' and 'Timedelta'