In [1]:
import pandas as pd
import pg8000 as pg
from sqlalchemy import create_engine
import matplotlib.pyplot as plt
%matplotlib inline
from datetime import datetime, timedelta
In [4]:
engine = create_engine('postgresql+pg8000://dot_student:qgis@training.c1erymiua9dx.us-east-1.rds.amazonaws.com:5432/training')
In [5]:
con=engine.raw_connection()
In [6]:
df=pd.read_sql_query('select * from noise_311', con=con)
In [7]:
df.head()
Out[7]:
b'unique_key'
b'created_date'
b'closed_date'
b'agency'
b'agency_name'
b'complaint_type'
b'descriptor'
b'location_type'
b'incident_zip'
b'incident_address'
...
b'bridge_highway_name'
b'bridge_highway_direction'
b'road_ramp'
b'bridge_highway_segment'
b'garage_lot_name'
b'ferry_direction'
b'ferry_terminal_name'
b'latitude'
b'longitude'
b'location'
0
28792167
2014-08-31 23:59:00
2014-09-01 03:52:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
11222
200 KINGSLAND AVENUE
...
None
None
None
None
None
None
None
40.723888
-73.941349
(40.723888303549415, -73.94134888943505)
1
28789088
2014-08-31 23:56:00
2014-09-01 06:17:00
NYPD
New York City Police Department
Noise - Vehicle
Car/Truck Music
Street/Sidewalk
11234
FLATLANDS AVENUE
...
None
None
None
None
None
None
None
40.619489
-73.938051
(40.61948901090983, -73.93805104516916)
2
28791854
2014-08-31 23:54:00
2014-09-01 01:29:00
NYPD
New York City Police Department
Noise - Commercial
Loud Music/Party
Club/Bar/Restaurant
10002
161 LUDLOW STREET
...
None
None
None
None
None
None
None
40.721410
-73.987694
(40.72141034382407, -73.98769444021134)
3
28789936
2014-08-31 23:52:00
2014-09-01 02:53:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
10033
624 WEST 182 STREET
...
None
None
None
None
None
None
None
40.850167
-73.933972
(40.85016671877659, -73.93397220795968)
4
28789931
2014-08-31 23:47:00
2014-09-01 01:06:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
11217
525 DEAN STREET
...
None
None
None
None
None
None
None
40.681208
-73.972775
(40.68120794066068, -73.97277535440028)
5 rows × 53 columns
In [8]:
for bytes_name in df.columns:
df.rename(columns = {bytes_name:bytes_name.decode('utf-8')}, inplace = True)
In [9]:
df.head()
Out[9]:
unique_key
created_date
closed_date
agency
agency_name
complaint_type
descriptor
location_type
incident_zip
incident_address
...
bridge_highway_name
bridge_highway_direction
road_ramp
bridge_highway_segment
garage_lot_name
ferry_direction
ferry_terminal_name
latitude
longitude
location
0
28792167
2014-08-31 23:59:00
2014-09-01 03:52:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
11222
200 KINGSLAND AVENUE
...
None
None
None
None
None
None
None
40.723888
-73.941349
(40.723888303549415, -73.94134888943505)
1
28789088
2014-08-31 23:56:00
2014-09-01 06:17:00
NYPD
New York City Police Department
Noise - Vehicle
Car/Truck Music
Street/Sidewalk
11234
FLATLANDS AVENUE
...
None
None
None
None
None
None
None
40.619489
-73.938051
(40.61948901090983, -73.93805104516916)
2
28791854
2014-08-31 23:54:00
2014-09-01 01:29:00
NYPD
New York City Police Department
Noise - Commercial
Loud Music/Party
Club/Bar/Restaurant
10002
161 LUDLOW STREET
...
None
None
None
None
None
None
None
40.721410
-73.987694
(40.72141034382407, -73.98769444021134)
3
28789936
2014-08-31 23:52:00
2014-09-01 02:53:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
10033
624 WEST 182 STREET
...
None
None
None
None
None
None
None
40.850167
-73.933972
(40.85016671877659, -73.93397220795968)
4
28789931
2014-08-31 23:47:00
2014-09-01 01:06:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
11217
525 DEAN STREET
...
None
None
None
None
None
None
None
40.681208
-73.972775
(40.68120794066068, -73.97277535440028)
5 rows × 53 columns
In [10]:
len(df)
Out[10]:
37615
In [13]:
df['open_duration']=df['closed_date']-df['created_date']
In [15]:
df['open_duration'].head(5)
Out[15]:
0 03:53:00
1 06:21:00
2 01:35:00
3 03:01:00
4 01:19:00
Name: open_duration, dtype: timedelta64[ns]
In [19]:
df.groupby(by='agency').mean()
Out[19]:
unique_key
x_coordinate
y_coordinate
latitude
longitude
agency
DEP
28479030
1.002513e+06
204514.087172
40.727968
-73.934065
DSNY
28441464
1.005781e+06
205684.000000
40.731180
-73.922281
EDC
28463637
9.949129e+05
208390.951768
40.738636
-73.961490
NYPD
28480302
1.002381e+06
213668.653246
40.753113
-73.934536
In [20]:
df.index=df['created_date']
In [21]:
df.head(5)
Out[21]:
unique_key
created_date
closed_date
agency
agency_name
complaint_type
descriptor
location_type
incident_zip
incident_address
...
bridge_highway_direction
road_ramp
bridge_highway_segment
garage_lot_name
ferry_direction
ferry_terminal_name
latitude
longitude
location
open_duration
created_date
2014-08-31 23:59:00
28792167
2014-08-31 23:59:00
2014-09-01 03:52:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
11222
200 KINGSLAND AVENUE
...
None
None
None
None
None
None
40.723888
-73.941349
(40.723888303549415, -73.94134888943505)
03:53:00
2014-08-31 23:56:00
28789088
2014-08-31 23:56:00
2014-09-01 06:17:00
NYPD
New York City Police Department
Noise - Vehicle
Car/Truck Music
Street/Sidewalk
11234
FLATLANDS AVENUE
...
None
None
None
None
None
None
40.619489
-73.938051
(40.61948901090983, -73.93805104516916)
06:21:00
2014-08-31 23:54:00
28791854
2014-08-31 23:54:00
2014-09-01 01:29:00
NYPD
New York City Police Department
Noise - Commercial
Loud Music/Party
Club/Bar/Restaurant
10002
161 LUDLOW STREET
...
None
None
None
None
None
None
40.721410
-73.987694
(40.72141034382407, -73.98769444021134)
01:35:00
2014-08-31 23:52:00
28789936
2014-08-31 23:52:00
2014-09-01 02:53:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
10033
624 WEST 182 STREET
...
None
None
None
None
None
None
40.850167
-73.933972
(40.85016671877659, -73.93397220795968)
03:01:00
2014-08-31 23:47:00
28789931
2014-08-31 23:47:00
2014-09-01 01:06:00
NYPD
New York City Police Department
Noise - Street/Sidewalk
Loud Music/Party
Street/Sidewalk
11217
525 DEAN STREET
...
None
None
None
None
None
None
40.681208
-73.972775
(40.68120794066068, -73.97277535440028)
01:19:00
5 rows × 54 columns
In [36]:
df['open_duration_sec']=.total_seconds()
Out[36]:
13980.0
In [ ]:
lambda
Content source: ledeprogram/algorithms
Similar notebooks: