Paris Remarkable Trees from 1700 to 2000¶

In [1]:

import pandas
from pandas.io.json import json_normalize
import json

local_file_path = '../files/arbres_remarquables_paris.json'
with open(local_file_path, 'r') as json_file:
    data_json = json.load(json_file)

df = pandas.DataFrame(json_normalize(data_json['records']))
df.head()

Out[1]:

	datasetid	recordid	record_timestamp	fields.geom_x_y	fields.libellefrancais	fields.objectid	fields.idemplacement	fields.arrondissement	fields.circonferenceencm	fields.hauteurenm	...	fields.stadedeveloppement	fields.remarquable	fields.idbase	fields.genre	fields.complementadresse	fields.typeemplacement	fields.dateplantation	geometry.type	geometry.coordinates	fields.varieteoucultivar
0	arbresremarquablesparis	a236960f295288698ca57fdccfd9825547ffb4d0	2019-10-04T10:00:41.063000+00:00	[48.8630096006, 2.2417737512]	Pin	49884	000901001	BOIS DE BOULOGNE	241.0	30.0	...	M	1	2002349.0	Pinus	16-08	Arbre	1882-01-01T00:09:21+00:00	Point	[2.2417737512, 48.8630096006]	NaN
1	arbresremarquablesparis	d7635937c3636051c99963676d3a97dd4d9dd8c9	2019-10-04T10:00:41.063000+00:00	[48.8731110898, 2.24886478886]	Hêtre	52761	000701004	BOIS DE BOULOGNE	231.0	16.0	...	M	1	2002354.0	Fagus	16-17	Arbre	1868-01-01T00:09:21+00:00	Point	[2.24886478886, 48.8731110898]	''Pendula''
2	arbresremarquablesparis	460e8eccd3ebc816f16317702223bf406e7d75e6	2019-10-04T10:00:41.063000+00:00	[48.8448875264, 2.35366916319]	Hêtre	62456	00000075	PARIS 5E ARRDT	85.0	3.0	...	M	1	132669.0	Fagus	NaN	Arbre	1905-01-01T00:09:21+00:00	Point	[2.35366916319, 48.8448875264]	''Tortuosa''
3	arbresremarquablesparis	b60b80e0f8327afba6d0c513b0b6b85639e516b6	2019-10-04T10:00:41.063000+00:00	[48.8787029872, 2.30647417371]	Erable	68801	00NO0144	PARIS 8E ARRDT	450.0	28.0	...	M	1	305507.0	Acer	08-01	Arbre	1700-01-01T00:09:21+00:00	Point	[2.30647417371, 48.8787029872]	NaN
4	arbresremarquablesparis	47e163d6f0536bc9e26ba2993447c6f50b14a6f6	2019-10-04T10:00:41.063000+00:00	[48.8671184424, 2.25294211329]	Platane	82341	001201001	BOIS DE BOULOGNE	534.0	45.0	...	M	1	2002389.0	Platanus	16-10	Arbre	1872-01-01T00:09:21+00:00	Point	[2.25294211329, 48.8671184424]	NaN

5 rows × 24 columns

In [2]:

df.columns = df.columns.str.replace(".", "_")
df[['lon','lat']] = pandas.DataFrame(df['geometry_coordinates'].values.tolist(), index=df.index)
df.loc[:, ['geometry_coordinates', 'lon', 'lat']]

Out[2]:

	geometry_coordinates	lon	lat
0	[2.2417737512, 48.8630096006]	2.241774	48.863010
1	[2.24886478886, 48.8731110898]	2.248865	48.873111
2	[2.35366916319, 48.8448875264]	2.353669	48.844888
3	[2.30647417371, 48.8787029872]	2.306474	48.878703
4	[2.25294211329, 48.8671184424]	2.252942	48.867118
...	...	...	...
177	[2.38368012582, 48.8814687366]	2.383680	48.881469
178	[2.35069308175, 48.8330296265]	2.350693	48.833030
179	[2.32633191622, 48.8940926568]	2.326332	48.894093
180	[2.43334109188, 48.8395251386]	2.433341	48.839525
181	[2.33940394029, 48.857749011]	2.339404	48.857749

182 rows × 3 columns

In [3]:

from geopandas import GeoDataFrame, points_from_xy

gdf = GeoDataFrame(df, geometry=points_from_xy(df['lon'], df['lat']))
gdf.head()

Out[3]:

	datasetid	recordid	record_timestamp	fields_geom_x_y	fields_libellefrancais	fields_objectid	fields_idemplacement	fields_arrondissement	fields_circonferenceencm	fields_hauteurenm	...	fields_genre	fields_complementadresse	fields_typeemplacement	fields_dateplantation	geometry_type	geometry_coordinates	fields_varieteoucultivar	lon	lat	geometry
0	arbresremarquablesparis	a236960f295288698ca57fdccfd9825547ffb4d0	2019-10-04T10:00:41.063000+00:00	[48.8630096006, 2.2417737512]	Pin	49884	000901001	BOIS DE BOULOGNE	241.0	30.0	...	Pinus	16-08	Arbre	1882-01-01T00:09:21+00:00	Point	[2.2417737512, 48.8630096006]	NaN	2.241774	48.863010	POINT (2.24177 48.86301)
1	arbresremarquablesparis	d7635937c3636051c99963676d3a97dd4d9dd8c9	2019-10-04T10:00:41.063000+00:00	[48.8731110898, 2.24886478886]	Hêtre	52761	000701004	BOIS DE BOULOGNE	231.0	16.0	...	Fagus	16-17	Arbre	1868-01-01T00:09:21+00:00	Point	[2.24886478886, 48.8731110898]	''Pendula''	2.248865	48.873111	POINT (2.24886 48.87311)
2	arbresremarquablesparis	460e8eccd3ebc816f16317702223bf406e7d75e6	2019-10-04T10:00:41.063000+00:00	[48.8448875264, 2.35366916319]	Hêtre	62456	00000075	PARIS 5E ARRDT	85.0	3.0	...	Fagus	NaN	Arbre	1905-01-01T00:09:21+00:00	Point	[2.35366916319, 48.8448875264]	''Tortuosa''	2.353669	48.844888	POINT (2.35367 48.84489)
3	arbresremarquablesparis	b60b80e0f8327afba6d0c513b0b6b85639e516b6	2019-10-04T10:00:41.063000+00:00	[48.8787029872, 2.30647417371]	Erable	68801	00NO0144	PARIS 8E ARRDT	450.0	28.0	...	Acer	08-01	Arbre	1700-01-01T00:09:21+00:00	Point	[2.30647417371, 48.8787029872]	NaN	2.306474	48.878703	POINT (2.30647 48.87870)
4	arbresremarquablesparis	47e163d6f0536bc9e26ba2993447c6f50b14a6f6	2019-10-04T10:00:41.063000+00:00	[48.8671184424, 2.25294211329]	Platane	82341	001201001	BOIS DE BOULOGNE	534.0	45.0	...	Platanus	16-10	Arbre	1872-01-01T00:09:21+00:00	Point	[2.25294211329, 48.8671184424]	NaN	2.252942	48.867118	POINT (2.25294 48.86712)

5 rows × 27 columns

In [4]:

from cartoframes.viz import Layer

Layer(gdf)

Out[4]:

In [5]:

gdf['plantation_date'] = pandas.to_datetime(gdf['fields_dateplantation'], errors='coerce')
gdf = gdf[gdf['plantation_date'].notnull()]
gdf['plantation_year'] = pandas.to_numeric(gdf['plantation_date'].dt.strftime('%Y'))

gdf.loc[:, ['plantation_date', 'plantation_year']]

Out[5]:

	plantation_date	plantation_year
0	1882-01-01 00:09:21+00:00	1882
1	1868-01-01 00:09:21+00:00	1868
2	1905-01-01 00:09:21+00:00	1905
3	1700-01-01 00:09:21+00:00	1700
4	1872-01-01 00:09:21+00:00	1872
...	...	...
177	1700-01-01 00:09:21+00:00	1700
178	1894-01-01 00:09:21+00:00	1894
179	1700-01-01 00:09:21+00:00	1700
180	1918-01-01 00:00:00+00:00	1918
181	1700-01-01 00:09:21+00:00	1700

181 rows × 2 columns

In [7]:

from cartoframes.viz import Layer, color_bins_style

Layer(gdf, color_bins_style('plantation_year', breaks=[1700, 1800, 1900, 2000], palette='Mint'))

Out[7]: