geopandas

Getting Started with GeoPandas

References:

• https://geopandas.org/getting_started/introduction.html
• https://geopandas.org/docs/user_guide/io.html
• https://geogee.gishub.org
• https://geemap.org

Installation¶

conda create -n geo python=3.8
conda activate geo
conda install geopandas
conda install geogee matplotlib descartes -c conda-forge

Import libraries¶

In [1]:

import geogee
import geopandas as gpd

import geogee import geopandas as gpd

C:\Users\Sarath_Kin\miniconda3\envs\demo310\lib\site-packages\google\api_core\_python_version_support.py:266: FutureWarning: You are using a Python version (3.10.19) which Google will stop supporting in new releases of google.api_core once it reaches its end of life (2026-10-04). Please upgrade to the latest Python version, or at least Python 3.11, to continue receiving updates for google.api_core past that date.
  warnings.warn(message, FutureWarning)

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
ImportError: DLL load failed while importing _multiarray_umath: The specified module could not be found.

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
Cell In[1], line 2
      1 import geogee
----> 2 import geopandas as gpd

File ~\miniconda3\envs\demo310\lib\site-packages\geopandas\__init__.py:3
      1 from geopandas._config import options
----> 3 from geopandas.geoseries import GeoSeries
      4 from geopandas.geodataframe import GeoDataFrame
      5 from geopandas.array import points_from_xy

File ~\miniconda3\envs\demo310\lib\site-packages\geopandas\geoseries.py:8
      5 from typing import Any
      7 import numpy as np
----> 8 import pandas as pd
      9 from pandas import Series
     10 from pandas.core.internals import SingleBlockManager

File ~\miniconda3\envs\demo310\lib\site-packages\pandas\__init__.py:49
     46 # let init-time option registration happen
     47 import pandas.core.config_init  # pyright: ignore[reportUnusedImport] # noqa: F401
---> 49 from pandas.core.api import (
     50     # dtype
     51     ArrowDtype,
     52     Int8Dtype,
     53     Int16Dtype,
     54     Int32Dtype,
     55     Int64Dtype,
     56     UInt8Dtype,
     57     UInt16Dtype,
     58     UInt32Dtype,
     59     UInt64Dtype,
     60     Float32Dtype,
     61     Float64Dtype,
     62     CategoricalDtype,
     63     PeriodDtype,
     64     IntervalDtype,
     65     DatetimeTZDtype,
     66     StringDtype,
     67     BooleanDtype,
     68     # missing
     69     NA,
     70     isna,
     71     isnull,
     72     notna,
     73     notnull,
     74     # indexes
     75     Index,
     76     CategoricalIndex,
     77     RangeIndex,
     78     MultiIndex,
     79     IntervalIndex,
     80     TimedeltaIndex,
     81     DatetimeIndex,
     82     PeriodIndex,
     83     IndexSlice,
     84     # tseries
     85     NaT,
     86     Period,
     87     period_range,
     88     Timedelta,
     89     timedelta_range,
     90     Timestamp,
     91     date_range,
     92     bdate_range,
     93     Interval,
     94     interval_range,
     95     DateOffset,
     96     # conversion
     97     to_numeric,
     98     to_datetime,
     99     to_timedelta,
    100     # misc
    101     Flags,
    102     Grouper,
    103     factorize,
    104     unique,
    105     value_counts,
    106     NamedAgg,
    107     array,
    108     Categorical,
    109     set_eng_float_format,
    110     Series,
    111     DataFrame,
    112 )
    114 from pandas.core.dtypes.dtypes import SparseDtype
    116 from pandas.tseries.api import infer_freq

File ~\miniconda3\envs\demo310\lib\site-packages\pandas\core\api.py:1
----> 1 from pandas._libs import (
      2     NaT,
      3     Period,
      4     Timedelta,
      5     Timestamp,
      6 )
      7 from pandas._libs.missing import NA
      9 from pandas.core.dtypes.dtypes import (
     10     ArrowDtype,
     11     CategoricalDtype,
   (...)
     14     PeriodDtype,
     15 )

File ~\miniconda3\envs\demo310\lib\site-packages\pandas\_libs\__init__.py:17
     13 # Below imports needs to happen first to ensure pandas top level
     14 # module gets monkeypatched with the pandas_datetime_CAPI
     15 # see pandas_datetime_exec in pd_datetime.c
     16 import pandas._libs.pandas_parser  # isort: skip # type: ignore[reportUnusedImport]
---> 17 import pandas._libs.pandas_datetime  # noqa: F401 # isort: skip # type: ignore[reportUnusedImport]
     18 from pandas._libs.interval import Interval
     19 from pandas._libs.tslibs import (
     20     NaT,
     21     NaTType,
   (...)
     26     iNaT,
     27 )

ImportError: numpy._core.multiarray failed to import

Reading files¶

In [2]:

url = "https://raw.githubusercontent.com/giswqs/geogee/master/examples/data/nyc_neighborhoods.geojson"

url = "https://raw.githubusercontent.com/giswqs/geogee/master/examples/data/nyc_neighborhoods.geojson"

In [3]:

gdf = gpd.read_file(url)

gdf = gpd.read_file(url)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[3], line 1
----> 1 gdf = gpd.read_file(url)

NameError: name 'gpd' is not defined

In [4]:

gdf

gdf

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 1
----> 1 gdf

NameError: name 'gdf' is not defined

In [5]:

gdf.crs

gdf.crs

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 1
----> 1 gdf.crs

NameError: name 'gdf' is not defined

Writing files¶

In [6]:

gdf.to_file("data/nyc_streets.geojson", driver="GeoJSON")

gdf.to_file("data/nyc_streets.geojson", driver="GeoJSON")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[6], line 1
----> 1 gdf.to_file("data/nyc_streets.geojson", driver="GeoJSON")

NameError: name 'gdf' is not defined

Measuring area¶

In [7]:

gdf = gdf.set_index("NAME")

gdf = gdf.set_index("NAME")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[7], line 1
----> 1 gdf = gdf.set_index("NAME")

NameError: name 'gdf' is not defined

In [8]:

gdf["area"] = gdf.area
gdf["area"]

gdf["area"] = gdf.area gdf["area"]

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[8], line 1
----> 1 gdf["area"] = gdf.area
      2 gdf["area"]

NameError: name 'gdf' is not defined

Getting polygon bounary¶

In [9]:

gdf['boundary'] = gdf.boundary
gdf['boundary']

gdf['boundary'] = gdf.boundary gdf['boundary']

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[9], line 1
----> 1 gdf['boundary'] = gdf.boundary
      2 gdf['boundary']

NameError: name 'gdf' is not defined

Getting polygon centroid¶

In [10]:

gdf['centroid'] = gdf.centroid
gdf['centroid']

gdf['centroid'] = gdf.centroid gdf['centroid']

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[10], line 1
----> 1 gdf['centroid'] = gdf.centroid
      2 gdf['centroid']

NameError: name 'gdf' is not defined

Making maps¶

In [11]:

gdf.plot()

gdf.plot()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[11], line 1
----> 1 gdf.plot()

NameError: name 'gdf' is not defined

In [12]:

gdf.plot("area", legend=True, figsize=(10, 8))

gdf.plot("area", legend=True, figsize=(10, 8))

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[12], line 1
----> 1 gdf.plot("area", legend=True, figsize=(10, 8))

NameError: name 'gdf' is not defined

In [13]:

gdf = gdf.set_geometry("centroid")
gdf.plot("area", legend=True,figsize=(10, 8))

gdf = gdf.set_geometry("centroid") gdf.plot("area", legend=True,figsize=(10, 8))

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[13], line 1
----> 1 gdf = gdf.set_geometry("centroid")
      2 gdf.plot("area", legend=True,figsize=(10, 8))

NameError: name 'gdf' is not defined

In [14]:

ax = gdf["geometry"].plot(figsize=(10, 8))
gdf["centroid"].plot(ax=ax, color="black")

ax = gdf["geometry"].plot(figsize=(10, 8)) gdf["centroid"].plot(ax=ax, color="black")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[14], line 1
----> 1 ax = gdf["geometry"].plot(figsize=(10, 8))
      2 gdf["centroid"].plot(ax=ax, color="black")

NameError: name 'gdf' is not defined

In [15]:

gdf = gdf.set_geometry("geometry")

gdf = gdf.set_geometry("geometry")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[15], line 1
----> 1 gdf = gdf.set_geometry("geometry")

NameError: name 'gdf' is not defined

Reprojecting data¶

In [16]:

url = "https://raw.githubusercontent.com/giswqs/geogee/master/examples/data/nyc_neighborhoods.geojson"

url = "https://raw.githubusercontent.com/giswqs/geogee/master/examples/data/nyc_neighborhoods.geojson"

In [17]:

gdf = gpd.read_file(url)

gdf = gpd.read_file(url)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[17], line 1
----> 1 gdf = gpd.read_file(url)

NameError: name 'gpd' is not defined

In [18]:

gdf_crs = gdf.to_crs(epsg="4326")

gdf_crs = gdf.to_crs(epsg="4326")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[18], line 1
----> 1 gdf_crs = gdf.to_crs(epsg="4326")

NameError: name 'gdf' is not defined

In [19]:

gdf_crs

gdf_crs

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[19], line 1
----> 1 gdf_crs

NameError: name 'gdf_crs' is not defined

In [20]:

geojson = gdf_crs.__geo_interface__

geojson = gdf_crs.__geo_interface__

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[20], line 1
----> 1 geojson = gdf_crs.__geo_interface__

NameError: name 'gdf_crs' is not defined

Displaying data on an interative map¶

In [21]:

m = geogee.Map(center=[40.7341, -73.9113], zoom=10)
m

m = geogee.Map(center=[40.7341, -73.9113], zoom=10) m

Out[21]:

In [22]:

style = {
    "stroke": True,
    "color": "#000000",
    "weight": 2,
    "opacity": 1,
    "fill": True,
    "fillColor": "#0000ff",
    "fillOpacity": 0.4,
}

style = { "stroke": True, "color": "#000000", "weight": 2, "opacity": 1, "fill": True, "fillColor": "#0000ff", "fillOpacity": 0.4, }

In [23]:

m.add_geojson(geojson, style=style, layer_name="nyc neighborhoods")

m.add_geojson(geojson, style=style, layer_name="nyc neighborhoods")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[23], line 1
----> 1 m.add_geojson(geojson, style=style, layer_name="nyc neighborhoods")

NameError: name 'geojson' is not defined

In [24]:

url2 = "https://github.com/giswqs/geogee/raw/master/examples/data/nyc_subway_stations.zip"

url2 = "https://github.com/giswqs/geogee/raw/master/examples/data/nyc_subway_stations.zip"

In [25]:

gdf_subway = gpd.read_file(url2)

gdf_subway = gpd.read_file(url2)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[25], line 1
----> 1 gdf_subway = gpd.read_file(url2)

NameError: name 'gpd' is not defined

In [26]:

gdf_subway_crs = gdf_subway.to_crs(epsg="4326")

gdf_subway_crs = gdf_subway.to_crs(epsg="4326")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[26], line 1
----> 1 gdf_subway_crs = gdf_subway.to_crs(epsg="4326")

NameError: name 'gdf_subway' is not defined

In [27]:

subway_geojson = gdf_subway_crs.__geo_interface__

subway_geojson = gdf_subway_crs.__geo_interface__

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[27], line 1
----> 1 subway_geojson = gdf_subway_crs.__geo_interface__

NameError: name 'gdf_subway_crs' is not defined

In [28]:

m.add_geojson(subway_geojson, layer_name="nyc subway stations")

m.add_geojson(subway_geojson, layer_name="nyc subway stations")

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[28], line 1
----> 1 m.add_geojson(subway_geojson, layer_name="nyc subway stations")

NameError: name 'subway_geojson' is not defined