Attribute error: json file processing .dt accessor with datetimelike values
Attribute error: json file processing .dt accessor with datetimelike values
我有一堆 .json 文件要访问。我需要根据种植和收获日期计算特定作物的生长季节。
问题：使用以下代码，我收到此错误：AttributeError：只能使用具有类似日期时间值的 .dt 访问器
代码：
import os
import copy
import json
import math
import numpy as np
import pandas as pd
import altair as alt
def get_data_single(exp_file_name):
# Read exp
with open(exp_file_name) as f:
data = json.load(f)
n = len(data['RotationComponents'])
out_vars = ['crop', 'plant_date', 'harv_date', 'CWAD_obs']
out = pd.DataFrame({'location':
[exp_file_name.split('-')[0]] * n, 'crop': [np.nan] * n, 'plant_date': [np.nan] * n,
'harv_date': [np.nan] * n, 'ppop': [np.nan] * n, 'rowsp': [np.nan] * n})
for i in range(n):
crop_id = data['RotationComponents'][i]['Planting']['Crop']['SpeciesID']
if crop_id == "CL":
harvest_data = data['RotationComponents'][i]['Harvest']
out.loc[i, 'crop'] = crop_id
out.loc[i, 'plant_date'] = pd.to_datetime(data['RotationComponents'][i]['Planting']['Date'],errors = 'coerce',format = '%Y-%m-%d')
out.loc[i, 'ppop'] = data['RotationComponents'][i]['Planting']['Ppop']
out.loc[i, 'rowsp'] = data['RotationComponents'][i]['Planting']['RowSpc']
out.loc[i, 'harv_date'] = pd.to_datetime(harvest_data['EventDate']['Date'],errors = 'coerce',format = '%Y-%m-%d')
return out
data_files = ['IA_1.json', 'IA_2.json', 'IA_3.json', 'IA_4.json']
> obs_df = pd.concat([get_data_single(j) for j in data_files]).dropna() obs_df['plant_date'] =
> pd.to_datetime(obs_df['plant_date']) obs_df['harv_date'] =
> pd.to_datetime(obs_df['harv_date']) obs_df['plant_year'] =
> obs_df['plant_date'].dt.strftime('%Y')
> obs_df['harv_year'] = obs_df['harv_date'].dt.strftime('%Y')
> obs_df['season'] = obs_df.apply(lambda x: x['plant_year'] + '_' + x['harv_year'], axis=1)
> obs_df
我正在尝试让 obs_df 根据以上代码给出以下内容：
location crop plant_date harv_date ppop rowsp plant_year harv_year season
回溯错误：
AttributeError Traceback (most recent call last)
/var/folders/ld/b6cy4j0d6pjb0t8d97rrgvbm0000gs/T/ipykernel_80477/757702288.py in <module>
1 data_files = ['IA_1.json', 'IA_2.json', 'IA_3.json', 'IA_4.json']
2 obs_df = pd.concat([get_data_single(j) for j in data_files]).dropna()
----> 3 obs_df['plant_year'] = obs_df['plant_date'].dt.strftime('%Y')
4 obs_df['harv_year'] = obs_df['harv_date'].dt.strftime('%Y')
5 obs_df['season'] = obs_df.apply(lambda x: x['plant_year'] + '_' + x['harv_year'], axis=1)
~/miniconda3/lib/python3.9/site-packages/pandas/core/generic.py in __getattr__(self, name)
5485 ):
5486 return self[name]
-> 5487 return object.__getattribute__(self, name)
5488
5489 def __setattr__(self, name: str, value) -> None:
~/miniconda3/lib/python3.9/site-packages/pandas/core/accessor.py in __get__(self, obj, cls)
179 # we're accessing the attribute of the class, i.e., Dataset.geo
180 return self._accessor
--> 181 accessor_obj = self._accessor(obj)
182 # Replace the property with the accessor object. Inspired by:
183 # https://www.pydanny.com/cached-property.html
~/miniconda3/lib/python3.9/site-packages/pandas/core/indexes/accessors.py in __new__(cls, data)
504 return PeriodProperties(data, orig)
505
--> 506 raise AttributeError("Can only use .dt accessor with datetimelike values")
AttributeError: Can only use .dt accessor with datetimelike values
示例json 文件
Blockquote
"SDate": "1999-05-26",
"NYrs": 22,
"SimControl": "N",
"RotationComponents": [
{
"Planting": {
"Ppop": 250.00886969940453,
"RowSpc": 25.0,
"SDepth": 4.0,
"Crop": {
"SpeciesID": "RY",
"CropParams": {
"Name": "Rye",
"RootC": 40.0,
"RootN": 4.0,
"RootP": 0.4,
"RootSloC": 30.0,
"RootIntC": 30.0,
"RootSloN": 10.0,
"VegC": 40.0,
"VegSloC": 30.0,
"VegIntC": 30.0,
"VegSloN": 10.0,
"KnDnFrac": 0.5,
"VegN": 4.0,
"VegP": 0.4,
"Code": null
},
"version": {
"id": "global/crops/RY",
"version": 1,
"updateTime": "2020-09-29T00:00:00Z",
"derivedFromId": null,
"derivedFromVersion": null,
"modelVersion": 1
},
"Name": null,
"cultivarId": null,
"CHeight": 1.0,
"PhotoSyn": {
"PhotSynID": "C3",
"Points": [
{
"CO2": 0.0,
"Multiplier": 0.0
},
{
"CO2": 220.0,
"Multiplier": 0.71
},
{
"CO2": 330.0,
"Multiplier": 1.0
},
{
"CO2": 440.0,
"Multiplier": 1.08
},
{
"CO2": 550.0,
"Multiplier": 1.17
},
{
"CO2": 660.0,
"Multiplier": 1.25
},
{
"CO2": 770.0,
"Multiplier": 1.32
},
{
"CO2": 880.0,
"Multiplier": 1.38
},
{
"CO2": 990.0,
"Multiplier": 1.43
},
{
"CO2": 9999.0,
"Multiplier": 1.5
}
]
},
"NitrogenFixing": null,
"relTT_P1": 0.35,
"relTT_P2": 0.62,
"relTT_Fl": null,
"relTT_Sn": 0.8,
"relLAI_P1": 0.02,
"relLAI_P2": 0.6,
"PlntN_Em": 0.03616,
"PlntN_Hf": 0.0288,
"PlntN_Mt": 0.014,
"GrnN_Mt": 0.023,
"PlntP_Em": 0.004,
"PlntP_Hf": 0.003,
"PlntP_Mt": 0.0024,
"GrnP_Mt": 0.0037,
"LAImax": 3.0,
"RUEmax": 1.5,
"SnParLAI": 0.61,
"SnParRUE": 1.0,
"TbaseDev": 0.0,
"ToptDev": 15.0,
"TTtoGerm": 20.0,
"TTtoMatr": 1200.0,
"EmgInter": 15.0,
"EmgSlope": 6.0,
"HrvIndex": 0.03,
"Kf2": null,
"MaturityGroup": null,
"Source": "ALMANAC (ABRVCROP.DAT) modified through calibration",
"LT50C": -28.0
},
"Date": "1999-11-23",
"VariableRateSeeding": false,
"Area": null
},
我成功了。这是更新的代码。在 pd.concat 之后，以下代码有所帮助：
obs_df['plant_date'] = pd.to_datetime(obs_df['plant_date'])
obs_df['harvest_date'] = pd.to_datetime(obs_df['harvest_date'])
>>> df
plant_date
0 NaN
1 2021-11-12
>>> df.loc[1, 'plant_date'] = pd.to_datetime(df.loc[1, 'plant_date'], errors='coerce', format='%Y-%m-%d')
>>> df
plant_date
0 NaN
1 2021-11-12 00:00:00
由于您创建数据框的方式 - 它预先填充了 np.nan 并将单独的“行”转换为日期时间 - 列的“类型”将为 object（因为 nan 是 float 类型 - 因此该列包含“混合类型”）
>>> df.dtypes
plant_date object
--------------^^^^^^
dtype: object
>>> df['plant_date'].dt
AttributeError: Can only use .dt accessor with datetimelike values
为了使用 .dt，您需要该列的类型为 datetime
>>> df
plant_date
0 NaN
1 2021-11-12
>>> df.dtypes
plant_date object
dtype: object
最简单的方法可能是立即在整个列上调用 to_datetime() - 在函数中的 out 上 - 或在创建后在 obs_df 上调用。
>>> df['plant_date'] = pd.to_datetime(df['plant_date'])
>>> df
plant_date
0 NaT
1 2021-11-12
>>> df.dtypes
plant_date datetime64[ns]
dtype: object
现在可以正常使用.dt
>>> df['plant_date'].dt
<pandas.core.indexes.accessors.DatetimeProperties object at 0x1210fe160>
harv_date 列应该有同样的问题。
我有一堆 .json 文件要访问。我需要根据种植和收获日期计算特定作物的生长季节。
问题：使用以下代码，我收到此错误：AttributeError：只能使用具有类似日期时间值的 .dt 访问器
代码：
import os
import copy
import json
import math
import numpy as np
import pandas as pd
import altair as alt
def get_data_single(exp_file_name):
# Read exp
with open(exp_file_name) as f:
data = json.load(f)
n = len(data['RotationComponents'])
out_vars = ['crop', 'plant_date', 'harv_date', 'CWAD_obs']
out = pd.DataFrame({'location':
[exp_file_name.split('-')[0]] * n, 'crop': [np.nan] * n, 'plant_date': [np.nan] * n,
'harv_date': [np.nan] * n, 'ppop': [np.nan] * n, 'rowsp': [np.nan] * n})
for i in range(n):
crop_id = data['RotationComponents'][i]['Planting']['Crop']['SpeciesID']
if crop_id == "CL":
harvest_data = data['RotationComponents'][i]['Harvest']
out.loc[i, 'crop'] = crop_id
out.loc[i, 'plant_date'] = pd.to_datetime(data['RotationComponents'][i]['Planting']['Date'],errors = 'coerce',format = '%Y-%m-%d')
out.loc[i, 'ppop'] = data['RotationComponents'][i]['Planting']['Ppop']
out.loc[i, 'rowsp'] = data['RotationComponents'][i]['Planting']['RowSpc']
out.loc[i, 'harv_date'] = pd.to_datetime(harvest_data['EventDate']['Date'],errors = 'coerce',format = '%Y-%m-%d')
return out
data_files = ['IA_1.json', 'IA_2.json', 'IA_3.json', 'IA_4.json']
> obs_df = pd.concat([get_data_single(j) for j in data_files]).dropna() obs_df['plant_date'] =
> pd.to_datetime(obs_df['plant_date']) obs_df['harv_date'] =
> pd.to_datetime(obs_df['harv_date']) obs_df['plant_year'] =
> obs_df['plant_date'].dt.strftime('%Y')
> obs_df['harv_year'] = obs_df['harv_date'].dt.strftime('%Y')
> obs_df['season'] = obs_df.apply(lambda x: x['plant_year'] + '_' + x['harv_year'], axis=1)
> obs_df
我正在尝试让 obs_df 根据以上代码给出以下内容：
location crop plant_date harv_date ppop rowsp plant_year harv_year season
回溯错误：
AttributeError Traceback (most recent call last)
/var/folders/ld/b6cy4j0d6pjb0t8d97rrgvbm0000gs/T/ipykernel_80477/757702288.py in <module>
1 data_files = ['IA_1.json', 'IA_2.json', 'IA_3.json', 'IA_4.json']
2 obs_df = pd.concat([get_data_single(j) for j in data_files]).dropna()
----> 3 obs_df['plant_year'] = obs_df['plant_date'].dt.strftime('%Y')
4 obs_df['harv_year'] = obs_df['harv_date'].dt.strftime('%Y')
5 obs_df['season'] = obs_df.apply(lambda x: x['plant_year'] + '_' + x['harv_year'], axis=1)
~/miniconda3/lib/python3.9/site-packages/pandas/core/generic.py in __getattr__(self, name)
5485 ):
5486 return self[name]
-> 5487 return object.__getattribute__(self, name)
5488
5489 def __setattr__(self, name: str, value) -> None:
~/miniconda3/lib/python3.9/site-packages/pandas/core/accessor.py in __get__(self, obj, cls)
179 # we're accessing the attribute of the class, i.e., Dataset.geo
180 return self._accessor
--> 181 accessor_obj = self._accessor(obj)
182 # Replace the property with the accessor object. Inspired by:
183 # https://www.pydanny.com/cached-property.html
~/miniconda3/lib/python3.9/site-packages/pandas/core/indexes/accessors.py in __new__(cls, data)
504 return PeriodProperties(data, orig)
505
--> 506 raise AttributeError("Can only use .dt accessor with datetimelike values")
AttributeError: Can only use .dt accessor with datetimelike values
示例json 文件
Blockquote
"SDate": "1999-05-26",
"NYrs": 22,
"SimControl": "N",
"RotationComponents": [
{
"Planting": {
"Ppop": 250.00886969940453,
"RowSpc": 25.0,
"SDepth": 4.0,
"Crop": {
"SpeciesID": "RY",
"CropParams": {
"Name": "Rye",
"RootC": 40.0,
"RootN": 4.0,
"RootP": 0.4,
"RootSloC": 30.0,
"RootIntC": 30.0,
"RootSloN": 10.0,
"VegC": 40.0,
"VegSloC": 30.0,
"VegIntC": 30.0,
"VegSloN": 10.0,
"KnDnFrac": 0.5,
"VegN": 4.0,
"VegP": 0.4,
"Code": null
},
"version": {
"id": "global/crops/RY",
"version": 1,
"updateTime": "2020-09-29T00:00:00Z",
"derivedFromId": null,
"derivedFromVersion": null,
"modelVersion": 1
},
"Name": null,
"cultivarId": null,
"CHeight": 1.0,
"PhotoSyn": {
"PhotSynID": "C3",
"Points": [
{
"CO2": 0.0,
"Multiplier": 0.0
},
{
"CO2": 220.0,
"Multiplier": 0.71
},
{
"CO2": 330.0,
"Multiplier": 1.0
},
{
"CO2": 440.0,
"Multiplier": 1.08
},
{
"CO2": 550.0,
"Multiplier": 1.17
},
{
"CO2": 660.0,
"Multiplier": 1.25
},
{
"CO2": 770.0,
"Multiplier": 1.32
},
{
"CO2": 880.0,
"Multiplier": 1.38
},
{
"CO2": 990.0,
"Multiplier": 1.43
},
{
"CO2": 9999.0,
"Multiplier": 1.5
}
]
},
"NitrogenFixing": null,
"relTT_P1": 0.35,
"relTT_P2": 0.62,
"relTT_Fl": null,
"relTT_Sn": 0.8,
"relLAI_P1": 0.02,
"relLAI_P2": 0.6,
"PlntN_Em": 0.03616,
"PlntN_Hf": 0.0288,
"PlntN_Mt": 0.014,
"GrnN_Mt": 0.023,
"PlntP_Em": 0.004,
"PlntP_Hf": 0.003,
"PlntP_Mt": 0.0024,
"GrnP_Mt": 0.0037,
"LAImax": 3.0,
"RUEmax": 1.5,
"SnParLAI": 0.61,
"SnParRUE": 1.0,
"TbaseDev": 0.0,
"ToptDev": 15.0,
"TTtoGerm": 20.0,
"TTtoMatr": 1200.0,
"EmgInter": 15.0,
"EmgSlope": 6.0,
"HrvIndex": 0.03,
"Kf2": null,
"MaturityGroup": null,
"Source": "ALMANAC (ABRVCROP.DAT) modified through calibration",
"LT50C": -28.0
},
"Date": "1999-11-23",
"VariableRateSeeding": false,
"Area": null
},
我成功了。这是更新的代码。在 pd.concat 之后，以下代码有所帮助：
obs_df['plant_date'] = pd.to_datetime(obs_df['plant_date'])
obs_df['harvest_date'] = pd.to_datetime(obs_df['harvest_date'])
>>> df
plant_date
0 NaN
1 2021-11-12
>>> df.loc[1, 'plant_date'] = pd.to_datetime(df.loc[1, 'plant_date'], errors='coerce', format='%Y-%m-%d')
>>> df
plant_date
0 NaN
1 2021-11-12 00:00:00
由于您创建数据框的方式 - 它预先填充了 np.nan 并将单独的“行”转换为日期时间 - 列的“类型”将为 object（因为 nan 是 float 类型 - 因此该列包含“混合类型”）
>>> df.dtypes
plant_date object
--------------^^^^^^
dtype: object
>>> df['plant_date'].dt
AttributeError: Can only use .dt accessor with datetimelike values
为了使用 .dt，您需要该列的类型为 datetime
>>> df
plant_date
0 NaN
1 2021-11-12
>>> df.dtypes
plant_date object
dtype: object
最简单的方法可能是立即在整个列上调用 to_datetime() - 在函数中的 out 上 - 或在创建后在 obs_df 上调用。
>>> df['plant_date'] = pd.to_datetime(df['plant_date'])
>>> df
plant_date
0 NaT
1 2021-11-12
>>> df.dtypes
plant_date datetime64[ns]
dtype: object
现在可以正常使用.dt
>>> df['plant_date'].dt
<pandas.core.indexes.accessors.DatetimeProperties object at 0x1210fe160>
harv_date 列应该有同样的问题。