https://colab.research.google.com/assets/colab-badge.svg

EarthRanger IO#

Setup#

Ecoscope#

[ ]:

%pip install \
    'ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@v1.8.16' &> /dev/null

[ ]:

import getpass
import os
import sys

import pandas as pd

import ecoscope

ecoscope.init()

Google Drive Setup#

[ ]:

output_dir = "Ecoscope-Outputs"

if "google.colab" in sys.modules:
    from google.colab import drive

    drive.mount("/content/drive/", force_remount=True)
    output_dir = os.path.join("/content/drive/MyDrive/", output_dir)

os.makedirs(output_dir, exist_ok=True)

Connect to EarthRanger#

[ ]:

ER_SERVER = os.getenv("ER_SERVER", "https://mep-dev.pamdas.org")
ER_USERNAME = os.getenv("ER_USERNAME", "username")  # replace with your username

ER_PASSWORD = os.getenv("ER_PASSWORD", "")

if not ER_PASSWORD:
    ER_PASSWORD = getpass.getpass("Please enter your ER password: ")

er_io = ecoscope.io.EarthRangerIO(
    server=ER_SERVER,
    username=ER_USERNAME,
    password=ER_PASSWORD,
    tcp_limit=5,
    sub_page_size=4000,
)

GET Event#

By event_ids#

Use this approach to download an individual Event if you know its id. Downloading from multiple ids at once is not currently supported in ER.

[ ]:

er_io.get_events(
    event_ids="76e76c8c-0936-4ef4-9298-0cbd4f516a9c",  # Distance count event
)

By event_type#

Use this approach if you want to download events of a given event type (using the EventType ID from ER)

[ ]:

df_event_types = pd.DataFrame(er_io.get_event_types())
mepdev_distance_count_id = df_event_types[df_event_types["value"] == "mepdev_distance_count"]["id"].values[0]
mepdev_distance_count_id

[ ]:

er_io.get_events(
    event_type=[mepdev_distance_count_id],  # MEP Distance Count
    since=pd.Timestamp("2023-01-01").isoformat(),
    until=pd.Timestamp("2024-01-01").isoformat(),
).reset_index()

Unpack event_details column of JSON data into individual columns#

[ ]:

df_event_types = pd.DataFrame(er_io.get_event_types())
mepdev_distance_survey_id = df_event_types[df_event_types["value"] == "mepdev_distance_count"]["id"].values[0]
mepdev_distance_survey_id

[ ]:

events_df = er_io.get_events(event_type=[mepdev_distance_survey_id])  # MEP Distance Survey Count
events_df.event_details

[ ]:

ecoscope.io.earthranger_utils.normalize_column(events_df, "event_details")
events_df

GET Subjects#

by id#

[ ]:

df_subjects = er_io.get_subjects()
habiba_id = df_subjects[df_subjects["name"] == "Habiba"]["id"].values[0]
habiba_id

[ ]:

er_io.get_subjects(id=habiba_id)  # Habiba

By SubjectGroup subject_group_name#

[ ]:

er_io.get_subjects(subject_group_name="Elephants")

GET Observations#

The output is an Ecoscope Relocations dataframe that has a core set of columns: groupby_col, fixtime, junk_status.

All other columns are prepended by extra__. The groupby_col will be the subject_id and the index of the dataframe is the observation indices.

Classic ER Observation format can be returned by passing in parameter relocations=False.

Filter observation by setting filter to one of: None, 0, 1, 2 or 3

  • None returns everything

  • 0 filters out everything but observations with exclusion flag 0 (Pass back clean data)

  • 1 filters out everything but observations with exclusion flag 1 (Pass back manually filtered data)

  • 2 filters out everything but observations with exclusion flag 2 (Ppass back automatically filtered data)

  • 3 filters out everything but observations with exclusion flag 2 or 1 (Pass back both manual and automatic filtered data)

By SubjectGroup subject_group_name:#

[ ]:

since = pd.Timestamp("2008-01-01").isoformat()
until = pd.Timestamp("2020-01-01").isoformat()

[ ]:

relocs = er_io.get_subjectgroup_observations(
    subject_group_name="Elephants",
    filter=0,
    since=since,
    until=until,
    include_details=True,
    include_inactive=True,
    include_source_details=True,
    include_subject_details=True,
    include_subjectsource_details=True,
)
relocs

By subject_id#

[ ]:

df_subjects = er_io.get_subjects()
habiba_id = df_subjects[df_subjects["name"] == "Habiba"]["id"].values[0]
salif_keita_id = df_subjects[df_subjects["name"] == "Salif Keita"]["id"].values[0]
habiba_id, salif_keita_id

[ ]:

relocs = er_io.get_subject_observations(
    subject_ids=[
        habiba_id,  # Habiba
        salif_keita_id,  # Salif Keita
    ],
    since=since,
    until=until,
    filter=0,
    include_details=True,
    include_subject_details=True,
    include_source_details=True,
    include_subjectsource_details=True,
)
relocs

By source_id#

[ ]:

df_sources = er_io.get_sources()
habiba_source_id = df_sources[df_sources["manufacturer_id"] == "ST-Habiba"]["id"].values[0]
salif_keita_source_id = df_sources[df_sources["manufacturer_id"] == "ST-SalifKeita"]["id"].values[0]
habiba_source_id, salif_keita_source_id

[ ]:

df_sources = er_io.get_sources()

relocs = er_io.get_source_observations(
    source_ids=[
        habiba_source_id,  # Habiba's Source
        salif_keita_source_id,  # Salif Keita's Source
    ],
    since=since,
    until=until,
    filter=0,
    include_details=True,
    include_source_details=True,
)
relocs

GET Patrols#

[ ]:

df_patrol_types = er_io.get_patrol_types().reset_index()
mep_distance_id = df_patrol_types[df_patrol_types["value"] == "MEP_Distance_Survey_Patrol"]["id"].values[0]
mep_distance_id

[ ]:

er_io.get_patrols(patrol_type=[mep_distance_id])  # MEP Distance Count Survey

GET Observations for a Patrol#

[ ]:

patrol_df = er_io.get_patrols(
    since=pd.Timestamp("2017-01-01").isoformat(),
    until=pd.Timestamp("2017-04-01").isoformat(),
)


relocs = er_io.get_patrol_observations(
    patrol_df,
    include_patrol_details=True,
    include_source_details=True,
    include_subject_details=True,
    include_subjectsource_details=True,
)
relocs

GET SPATIAL FEATURES#

GET SPATIAL FEATURE from spatial_feature_id#

[ ]:

spatial_feature = er_io.get_spatial_feature(spatial_feature_id="8868718f-0154-45bf-a74d-a66706ef958f")
spatial_feature

GET SPATIAL FEATURES from spatial_features_group_id#

[ ]:

spatial_features = er_io.get_spatial_features_group(spatial_features_group_id="15698426-7e0f-41df-9bc3-495d87e2e097")
spatial_features

GET Users#

[ ]:

df = pd.DataFrame(er_io.get_users())
df

Export to File#

Create test data#

Skip this cell if you would like to provide your own data

[ ]:

relocs = er_io.get_subjectgroup_observations(
    subject_group_name="Elephants",
    filter=0,
    since=since,
    until=until,
    include_details=True,
    include_inactive=True,
    include_source_details=True,
    include_subject_details=True,
    include_subjectsource_details=True,
)
relocs

GeoPackage (.gpkg)#

(GeoPackage does not support columns with type list so we drop them.)

[ ]:

relocs = relocs.select_dtypes(exclude=[list])

relocs.to_file(os.path.join(output_dir, "observations.gpkg"), layer="observations")

CSV#

[ ]:

relocs.to_csv(os.path.join(output_dir, "observations.csv"))

Python Pickle (.pkl)#

[ ]:

relocs.to_pickle(os.path.join(output_dir, "observations.pkl"))

Apache Feather (.feather)#

[ ]:

relocs.to_feather(os.path.join(output_dir, "observations.feather"))