为json数据分配自定义类别

Question

将标签分配给原始数据，而不是从get\ dummies获取新的指示符列。我想要这样的东西：

json\u输入：

[{id:100，车辆类型：“Car”，时间：“2017-04-06 01:39:43”，区域=“A”，类型：“Checked”}， {id:101，车辆类型：“Truck”，时间：“2017-04-06 02:35:45”，区域=“B”，类型：“Unchecked”}， {id:102，车辆类型：“Truck”，时间：“2017-04-05 03:20:12”，区域=“A”，类型：“Checked”}， {id:103，车辆类型：“Car”，时间：“2017-04-04 10:05:04”，区域=“C”，类型：“Unchecked”} ]你知道吗

结果：

• id、车辆类型、时间范围、区域、类型
• 100，0，1，1，1
• 101，1，1，2，0
• 102，1，2，1，1
• 103，0，3，3，0

时间戳-TS 列->；车辆类型，类型为二进制，时间范围（1->；（TS1-TS2），2->；（TS3-TS4），3->；（TS5-TS6）），区域->；分类（1、2或3）。 我想在将扁平的json提供给pandas中的dataframe时自动分配这些标签。这可能吗？（我不想从熊猫中的get\u dummies中得到区域\u 1、类型\u 1、车辆\u类型\u 3指示列）。如果无法使用pandas，请建议使用python lib实现此自动化。你知道吗

Answer 1

这是我能想到的。我不知道你在找什么时间范围

import datetime
import io
import pandas as pd
import numpy as np
df_string='[{"id":100,"vehicle_type":"Car","time":"2017-04-06 01:39:43","zone":"A","type":"Checked"},{"id":101,"vehicle_type":"Truck","time":"2017-04-06 02:35:45","zone":"B","type":"Unchecked"},{"id":102,"vehicle_type":"Truck","time":"2017-04-05 03:20:12","zone":"A","type":"Checked"},{"id":103,"vehicle_type":"Car","time":"2017-04-04 10:05:04","zone":"C","type":"Unchecked"}]'
df = pd.read_json(io.StringIO(df_string))
df['zone'] = pd.Categorical(df.zone)
df['vehicle_type'] = pd.Categorical(df.vehicle_type)
df['type'] = pd.Categorical(df.type)
df['zone_int'] = df.zone.cat.codes
df['vehicle_type_int'] = df.vehicle_type.cat.codes
df['type_int'] = df.type.cat.codes
df.head()

编辑 这是我能想到的

import datetime
import io
import math
import pandas as pd
#Taken from http://stackoverflow.com/questions/13071384/python-ceil-a-datetime-to-next-quarter-of-an-hour
def ceil_dt(dt, num_seconds=900):
    nsecs = dt.minute*60 + dt.second + dt.microsecond*1e-6  
    delta = math.ceil(nsecs / num_seconds) * num_seconds - nsecs
    return dt + datetime.timedelta(seconds=delta)

df_string='[{"id":100,"vehicle_type":"Car","time":"2017-04-06 01:39:43","zone":"A","type":"Checked"},{"id":101,"vehicle_type":"Truck","time":"2017-04-06 02:35:45","zone":"B","type":"Unchecked"},{"id":102,"vehicle_type":"Truck","time":"2017-04-05 03:20:12","zone":"A","type":"Checked"},{"id":103,"vehicle_type":"Car","time":"2017-04-04 10:05:04","zone":"C","type":"Unchecked"}]'
df = pd.read_json(io.StringIO(df_string))
df['zone'] = pd.Categorical(df.zone)
df['vehicle_type'] = pd.Categorical(df.vehicle_type)
df['type'] = pd.Categorical(df.type)
df['zone_int'] = df.zone.cat.codes
df['vehicle_type_int'] = df.vehicle_type.cat.codes
df['type_int'] = df.type.cat.codes
df['time'] = pd.to_datetime(df.time)
df['dayofweek'] = df.time.dt.dayofweek
df['month_int'] = df.time.dt.month
df['year_int'] = df.time.dt.year
df['day'] = df.time.dt.day
df['date'] = df.time.apply(lambda x: x.date())
df['month'] = df.date.apply(lambda x: datetime.date(x.year, x.month, 1))
df['year'] = df.date.apply(lambda x: datetime.date(x.year, 1, 1))
df['hour'] = df.time.dt.hour
df['mins']  = df.time.dt.minute
df['seconds'] = df.time.dt.second
df['time_interval_3hour'] = df.hour.apply(lambda x : math.floor(x/3)+1)
df['time_interval_6hour'] = df.hour.apply(lambda x : math.floor(x/6)+1)
df['time_interval_12hour'] = df.hour.apply(lambda x : math.floor(x/12)+1)
df['weekend']  = df.dayofweek.apply(lambda x:  x>4)

df['ceil_quarter_an_hour'] =df.time.apply(lambda x : ceil_dt(x))
df['ceil_half_an_hour'] =df.time.apply(lambda x : ceil_dt(x, num_seconds=1800))
df.head()