def test_gdeltrange_sequence_v1_2005(self):
date_sequence = ['2001 Feb 01', '2005 Feb 05']
ranger_output = _dateRanger(date_sequence)
gdeltstring_test = np.sort(
np.array(_gdeltRangeString(ranger_output, version=1)))
exp = np.sort(np.array(['2001', '2002', '2003', '2004', '2005']))
np.testing.assert_array_equal(exp, gdeltstring_test)
def test_urlbuilder_v4(self):
date_sequence = '2001 Mar 01'
ranger_output = _dateRanger(date_sequence)
gdeltstring_output = _gdeltRangeString(ranger_output, version=1)
urlbuilder_test = _urlBuilder(gdeltstring_output, version=1)
exp = 'http://data.gdeltproject.org/events/2001.zip'
return self.assertEqual(exp, urlbuilder_test, "Version 1 Url works.")
def test_urlbuilder_v2(self):
date_sequence = '2016 10 01'
ranger_output = _dateRanger(date_sequence)
gdeltstring_output = _gdeltRangeString(ranger_output, version=2)
urlbuilder_test = _urlBuilder(gdeltstring_output, version=2)
exp = 'http://data.gdeltproject.org/gdeltv2/20161001234500.export.CSV.zip'
return self.assertEqual(exp, urlbuilder_test, "Version 2 Url works.")
def test_gdeltrange_sequence_v2_single_tester(self):
date_sequence = ['2016 10 01', '2016 Dec 31']
ranger_output = _dateRanger(date_sequence)
gdeltstring_test = _gdeltRangeString(ranger_output,
coverage=True,
version=2)
return self.assertIsInstance(gdeltstring_test, np.ndarray)
def test_urlbuilder_graph2_pass(self):
date_sequence = '2015 Apr 01'
ranger_output = _dateRanger(date_sequence)
gdeltstring_output = _gdeltRangeString(ranger_output, version=2)
urlbuilder_test = _urlBuilder(gdeltstring_output,
table='gkg',
version=2)
exp = 'http://data.gdeltproject.org/gdeltv2/20150401234500.gkg.csv.zip'
return self.assertEqual(exp, urlbuilder_test, "Version 2 Url works.")
def test_urlbuilder_v5(self):
date_sequence = '2013 Apr 01'
ranger_output = _dateRanger(date_sequence)
gdeltstring_output = _gdeltRangeString(ranger_output, version=1)
urlbuilder_test = _urlBuilder(gdeltstring_output,
table='gkg',
version=1)
exp = 'http://data.gdeltproject.org/gkg/20130401.gkg.csv.zip'
return self.assertEqual(exp, urlbuilder_test, "Version 1 Url works.")
def test_gdeltrange_nearest_single(self):
date_string = _dateRanger([str((datetime.datetime.now()).date())])
ranger_test = _gdeltRangeString(date_string, coverage=False, version=2)
# build time range including 30 minutes before and 30 after current
r = pd.date_range(
datetime.datetime.now() - datetime.timedelta(minutes=30),
datetime.datetime.now() + datetime.timedelta(minutes=30),
freq='15min')
return self.assertTrue(r[0] < parse(ranger_test) < r[-1])
def test_separate_rangestring_24hours(self):
"""Tests more than 3 dates"""
date_array = np.array(datetime.datetime(2017, 8, 6, 0, 0),
dtype=object)
bottom_number = (datetime.datetime.now().time().hour) * 4
ranger_test = _gdeltRangeString(date_array, coverage=True)
return self.assertGreaterEqual((ranger_test).shape[0], bottom_number)
def test_gdeltrange_sequence_v2(self):
date_sequence = ['2016 10 01', '2016 10 05']
ranger_output = _dateRanger(date_sequence)
gdeltstring_test = np.sort(
np.array(_gdeltRangeString(ranger_output, version=2)))
exp = np.sort(
np.array([
'20161001234500', '20161002234500', '20161003234500',
'20161004234500', '20161005234500'
]))
np.testing.assert_array_equal(exp, gdeltstring_test)
def test_urlbuilder_events1_passlist(self):
date_sequence = ['2015 Apr 01', '2015 Apr 02']
ranger_output = _dateRanger(date_sequence)
gdeltstring_output = _gdeltRangeString(ranger_output, version=1)
urlbuilder_test = _urlBuilder(gdeltstring_output,
table='events',
version=1)
exp = np.sort(
np.array([
'http://data.gdeltproject.org/events/20150401.export.CSV.zip',
'http://data.gdeltproject.org/events/20150402.export.CSV.zip'
]))
return np.testing.assert_array_equal(
np.sort(np.array(exp)), np.sort(np.array(urlbuilder_test)))
def test_gdeltrange_nearest_full(self):
date_string = _dateRanger([str((datetime.datetime.now()).date())])
ranger_test = _gdeltRangeString(date_string, coverage=True, version=2)
# convert result to array of python datetimes
vect = np.vectorize(parse)
comp = vect(ranger_test)
# build time range of all day up to latest 15 minute interval
# convert to pydatetime array
exp = (pd.date_range(start=str(datetime.datetime.now().date()),
periods=len(ranger_test), freq='15 min')).\
to_pydatetime()
# compare arrays
return np.testing.assert_array_equal(comp, exp, 'Not equal')
def test_gdeltrange_sequence_v2_with_coverage(self):
date_sequence = ['2016 10 01']
ranger_output = _dateRanger(date_sequence)
gdeltstring_test = np.sort(
np.array(_gdeltRangeString(ranger_output, coverage=True,
version=2)))
exp = np.sort(
np.array([
'20161001000000', '20161001001500', '20161001003000',
'20161001004500', '20161001010000', '20161001011500',
'20161001013000', '20161001014500', '20161001020000',
'20161001021500', '20161001023000', '20161001024500',
'20161001030000', '20161001031500', '20161001033000',
'20161001034500', '20161001040000', '20161001041500',
'20161001043000', '20161001044500', '20161001050000',
'20161001051500', '20161001053000', '20161001054500',
'20161001060000', '20161001061500', '20161001063000',
'20161001064500', '20161001070000', '20161001071500',
'20161001073000', '20161001074500', '20161001080000',
'20161001081500', '20161001083000', '20161001084500',
'20161001090000', '20161001091500', '20161001093000',
'20161001094500', '20161001100000', '20161001101500',
'20161001103000', '20161001104500', '20161001110000',
'20161001111500', '20161001113000', '20161001114500',
'20161001120000', '20161001121500', '20161001123000',
'20161001124500', '20161001130000', '20161001131500',
'20161001133000', '20161001134500', '20161001140000',
'20161001141500', '20161001143000', '20161001144500',
'20161001150000', '20161001151500', '20161001153000',
'20161001154500', '20161001160000', '20161001161500',
'20161001163000', '20161001164500', '20161001170000',
'20161001171500', '20161001173000', '20161001174500',
'20161001180000', '20161001181500', '20161001183000',
'20161001184500', '20161001190000', '20161001191500',
'20161001193000', '20161001194500', '20161001200000',
'20161001201500', '20161001203000', '20161001204500',
'20161001210000', '20161001211500', '20161001213000',
'20161001214500', '20161001220000', '20161001221500',
'20161001223000', '20161001224500', '20161001230000',
'20161001231500', '20161001233000', '20161001234500'
],
dtype='<U14'))
np.testing.assert_array_equal(exp, gdeltstring_test)
def Search(self,
date,
table='events',
coverage=False,
translation=False,
output=None,
queryTime=datetime.datetime.now().strftime('%m-%d-%Y %H:%M:%S'),
normcols=False):
"""Core searcher method to set parameters for GDELT data searches
Keyword arguments
----------
date : str, required
The string representation of a datetime (single) or date
range (list of strings) that is (are) the targeted timelines to
pull GDELT data.
table : string,{'events','gkg','mentions'}
Select from the table formats offered by the GDELT service:
* events (1.0 and 2.0)
The biggest difference between 1.0 and 2.0 are the
update frequencies. 1.0 data is disseminated daily,
and the most recent data will be published at 6AM
Eastern Standard time of the next day. So, 21 August 2016
results would be available 22 August 2016 at 6AM EST. 2.0
data updates every 15 minutes of the current day.
Version 1.0 runs from January 1, 1979 through March 31,
2013 contains 57 fields for each record. The Daily
Updates collection, which begins April 1, 2013 and runs
through present, contains an additional field at the end
of each record, for a total of 58 fields for each
record. The format is dyadic CAMEO format, capturing two
actors and the action performed by Actor1 upon Actor2.
Version 2.0 only covers February 19, 2015 onwards,
and is stored in an expanded version of the dyadic CAMEO
format . See
http://data.gdeltproject.org/documentation/GDELT-Event_
Codebook-V2.0.pdf for more information.
* gkg (1.0 and 2.0)
**Warning** These tables and queries can be extremely
large and consume a lot of RAM. Consider running a
single days worth of gkg pulls, store to disc,
flush RAM, then proceed to the next day.
Table that represents all of the latent dimensions,
geography, and network structure of the global news. It
applies an array of highly sophisticated natural language
processing algorithms to each document to compute a range
of codified metadata encoding key latent and contextual
dimensions of the document. Version 2.0 includes Global
Content Analysis Measures (GCAM) which reportedly
provides 24 emotional measurement packages that assess
more than 2,300 emotions and themes from every article
in realtime, multilingual dimensions natively assessing
the emotions of 15 languages (Arabic, Basque, Catalan,
Chinese, French, Galician, German, Hindi, Indonesian,
Korean, Pashto, Portuguese, Russian, Spanish,
and Urdu).See documentation about GKG
1.0 at http://data.gdeltproject.org/documentation/GDELT-
Global_Knowledge_Graph_Codebook.pdf, and GKG 2.0 at http://
data.gdeltproject.org/documentation/GDELT-Global_Knowledge_
Graph_Codebook-V2.1.pdf.
* mentions (2.0 only)
Mentions table records every mention
of an event over time, along with the timestamp the
article was published. This allows the progression of
an event through the global media to be tracked,
identifying outlets that tend to break certain kinds
of events the earliest or which may break stories
later but are more accurate in their reporting on
those events. Combined with the 15 minute update
resolution and GCAM, this also allows the emotional
reaction and resonance of an event to be assessed as
it sweeps through the world’s media.
coverage : bool, default: False
When set to 'True' and the GDELT version parameter is set to 2,
gdeltPyR will pull back every 15 minute interval in the day (
full results) or, if pulling for the current day, pull all 15
minute intervals up to the most recent 15 minute interval of the
current our. For example, if the current date is 22 August,
2016 and the current time is 0828 HRs Eastern, our pull would
get pull every 15 minute interval in the day up to 0815HRs.
When coverate is set to true and a date range is entered,
we pull every 15 minute interval for historical days and up to
the most recent 15 minute interval for the current day, if that
day is included.
translation : bool, default: False
Whether or not to pull the translation database available from
version 2 of GDELT. If translation is True, the translated set
is downloaded, if set to False the english set is downloaded.
queryTime : datetime object, system generated
This records the system time when gdeltPyR's query was executed,
which can be used for logging purposes.
output : string, {None,'df','gpd','shp','shapefile', 'json', 'geojson'
'r','geodataframe'}
Select the output format for the returned GDELT data
Options
-------
json - Javascript Object Notation output; returns list of
dictionaries in Python or a list of json objects
r - writes the cross language dataframe to the current directory.
This uses the Feather library found at https://github.com/wesm/
feather. This option returns a pandas dataframe but write the R
dataframe to the current working directory. The filename
includes all the parameters used to launch the query: version,
coverage, table name, query dates, and query time.
csv- Outputs a CSV format; all dates and columns are joined
shp- Writes an ESRI shapefile to current directory or path; output
is filtered to exclude rows with no latitude or longitude
geojson-
geodataframe- Returns a geodataframe; output is filtered to exclude
rows with no latitude or longitude. This output can be manipulated
for geoprocessing/geospatial operations such as reprojecting the
coordinates, creating a thematic map (choropleth map), merging with
other geospatial objects, etc. See http://geopandas.org/ for info.
normcols : bool
Applies a generic lambda function to normalize GDELT columns
for compatibility with SQL or Shapefile outputs.
Examples
--------
>>> from gdelt
>>> gd = gdelt.gdelt(version=1)
>>> results = gd.Search(['2016 10 19'],table='events',coverage=True)
>>> print(len(results))
244767
>>> gd = gdelt.gdelt(version=2)
>>> results = gd.Search(['2016 Oct 10'], table='gkg')
>>> print(len(results))
2398
>>> print(results.V2Persons.ix[2])
Juanita Broaddrick,1202;Monica Lewinsky,1612;Donald Trump,12;Donald
Trump,244;Wolf Blitzer,1728;Lucianne Goldberg,3712;Linda Tripp,3692;
Bill Clinton,47;Bill Clinton,382;Bill Clinton,563;Bill Clinton,657;Bill
Clinton,730;Bill Clinton,1280;Bill Clinton,2896;Bill Clinton,3259;Bill
Clinton,4142;Bill Clinton,4176;Bill Clinton,4342;Ken Starr,2352;Ken
Starr,2621;Howard Stern,626;Howard Stern,4286;Robin Quivers,4622;
Paula Jones,3187;Paula Jones,3808;Gennifer Flowers,1594;Neil Cavuto,
3362;Alicia Machado,1700;Hillary Clinton,294;Hillary Clinton,538;
Hillary Clinton,808;Hillary Clinton,1802;Hillary Clinton,2303;Hillary
Clinton,4226
>>> results = gd.Search(['2016 Oct 10'], table='gkg',output='r')
Notes
------
Read more about GDELT data at http://gdeltproject.org/data.html
gdeltPyR retrieves Global Database of Events, Language, and Tone
(GDELT) data (version 1.0 or version 2.0) via parallel HTTP GET
requests and is an alternative to accessing GDELT
data via Google BigQuery.
Performance will vary based on the number of available cores
(i.e. CPUs), internet connection speed, and available RAM. For
systems with limited RAM, Later iterations of gdeltPyR will include
an option to store the output directly to disc.
"""
# check for valid table names; fail early
valid = ['events', 'gkg', 'vgkg', 'iatv', 'mentions']
if table not in valid:
raise ValueError(
'You entered "{}"; this is not a valid table name.'
' Choose from "events", "mentions", or "gkg".'.format(table))
_date_input_check(date, self.version)
self.coverage = coverage
self.date = date
version = self.version
baseUrl = self.baseUrl
self.queryTime = queryTime
self.table = table
self.translation = translation
self.datesString = _gdeltRangeString(_dateRanger(self.date),
version=version,
coverage=self.coverage)
#################################
# R dataframe check; fail early
#################################
if output == 'r': # pragma: no cover
try:
import feather
except ImportError:
raise ImportError(('You need to install `feather` in order '
'to output data as an R dataframe. Keep '
'in mind the function will return a '
'pandas dataframe but write the R '
'dataframe to your current working '
'directory as a `.feather` file. Install '
'by running\npip install feather\nor if '
'you have Anaconda (preferred)\nconda '
'install feather-format -c conda-forge\nTo '
'learn more about the library visit https:/'
'/github.com/wesm/feather'))
##################################
# Partial Functions
#################################
v1RangerCoverage = partial(_gdeltRangeString, version=1, coverage=True)
v2RangerCoverage = partial(_gdeltRangeString, version=2, coverage=True)
v1RangerNoCoverage = partial(_gdeltRangeString,
version=1,
coverage=False)
v2RangerNoCoverage = partial(_gdeltRangeString,
version=2,
coverage=False)
urlsv1gkg = partial(_urlBuilder, version=1, table='gkg')
urlsv2mentions = partial(_urlBuilder,
version=2,
table='mentions',
translation=self.translation)
urlsv2events = partial(_urlBuilder,
version=2,
table='events',
translation=self.translation)
urlsv1events = partial(_urlBuilder, version=1, table='events')
urlsv2gkg = partial(_urlBuilder,
version=2,
table='gkg',
translation=self.translation)
eventWork = partial(_mp_worker, table='events', proxies=self.proxies)
codeCams = partial(_cameos, codes=codes)
#####################################
# GDELT Version 2.0 Headers
#####################################
if int(self.version) == 2:
###################################
# Download 2.0 Headers
###################################
if self.table == 'events':
try:
self.events_columns = \
pd.read_csv(os.path.join(BASE_DIR, "data", 'events2.csv'))[
'name'].values.tolist()
except: # pragma: no cover
self.events_columns = _events2Heads()
elif self.table == 'mentions':
try:
self.mentions_columns = \
pd.read_csv(
os.path.join(BASE_DIR, "data", 'mentions.csv'))[
'name'].values.tolist()
except: # pragma: no cover
self.mentions_columns = _mentionsHeads()
else:
try:
self.gkg_columns = \
pd.read_csv(
os.path.join(BASE_DIR, "data", 'gkg2.csv'))[
'name'].values.tolist()
except: # pragma: no cover
self.gkg_columns = _gkgHeads()
#####################################
# GDELT Version 1.0 Analytics, Header, Downloads
#####################################
if int(self.version) == 1:
if self.table is "mentions":
raise ValueError('GDELT 1.0 does not have the "mentions"'
' table. Specify the "events" or "gkg"'
'table.')
if self.translation:
raise ValueError('GDELT 1.0 does not have an option to'
' return translated table data. Switch to '
'version 2 by reinstantiating the gdelt '
'object with <gd = gdelt.gdelt(version=2)>')
else:
pass
try:
self.events_columns = \
pd.read_csv(os.path.join(BASE_DIR, "data", 'events1.csv'))[
'name'].values.tolist()
except: # pragma: no cover
self.events_columns = _events1Heads()
columns = self.events_columns
if self.table == 'gkg':
self.download_list = (urlsv1gkg(
v1RangerCoverage(_dateRanger(self.date))))
elif self.table == 'events' or self.table == '':
if self.coverage is True: # pragma: no cover
self.download_list = (urlsv1events(
v1RangerCoverage(_dateRanger(self.date))))
else:
# print("I'm here at line 125")
self.download_list = (urlsv1events(
v1RangerNoCoverage(_dateRanger(self.date))))
else: # pragma: no cover
raise Exception('You entered an incorrect table type for '
'GDELT 1.0.')
#####################################
# GDELT Version 2.0 Analytics and Download
#####################################
elif self.version == 2:
if self.table == 'events' or self.table == '':
columns = self.events_columns
if self.coverage is True: # pragma: no cover
self.download_list = (urlsv2events(
v2RangerCoverage(_dateRanger(self.date))))
else:
self.download_list = (urlsv2events(
v2RangerNoCoverage(_dateRanger(self.date))))
if self.table == 'gkg':
columns = self.gkg_columns
if self.coverage is True: # pragma: no cover
self.download_list = (urlsv2gkg(
v2RangerCoverage(_dateRanger(self.date))))
else:
self.download_list = (urlsv2gkg(
v2RangerNoCoverage(_dateRanger(self.date))))
# print ("2 gkg", urlsv2gkg(self.datesString))
if self.table == 'mentions':
columns = self.mentions_columns
if self.coverage is True: # pragma: no cover
self.download_list = (urlsv2mentions(
v2RangerCoverage(_dateRanger(self.date))))
else:
self.download_list = (urlsv2mentions(
v2RangerNoCoverage(_dateRanger(self.date))))
#########################
# DEBUG Print Section
#########################
# if isinstance(self.datesString,str):
# if parse(self.datesString) < datetime.datetime.now():
# self.datesString = (self.datesString[:8]+"234500")
# elif isinstance(self.datesString,list):
# print("it's a list")
# elif isinstance(self.datesString,np.ndarray):
# print("it's an array")
# else:
# print("don't know what it is")
# print (self.version,self.download_list,self.date, self.table, self.coverage, self.datesString)
#
# print (self.download_list)
# if self.coverage:
# coverage = 'True'
# else:
# coverage = 'False'
# if isinstance(self.date, list):
#
# formattedDates = ["".join(re.split(' |-|;|:', l)) for l in
# self.date]
# path = formattedDates
# print("gdeltVersion_" + str(self.version) +
# "_coverage_" + coverage + "_" +
# "_table_" + self.table + '_queryDates_' +
# "_".join(path) +
# "_queryTime_" +
# datetime.datetime.now().strftime('%m-%d-%YT%H%M%S'))
# else:
# print("gdeltVersion_" + str(self.version) +
# "_coverage_" + coverage + "_" +
# "_table_" + self.table + '_queryDates_' +
# "".join(re.split(' |-|;|:', self.date)) +
# "_queryTime_" +
# datetime.datetime.now().strftime('%m-%d-%YT%H%M%S'))
#########################
# Download section
#########################
# print(self.download_list,type(self.download_list))
# from gdelt.extractors import normalpull
# e=ProcessPoolExecutor()
# if isinstance(self.download_list,list) and len(self.download_list)==1:
# from gdelt.extractors import normalpull
#
# results=normalpull(self.download_list[0],table=self.table)
# elif isinstance(self.download_list,list):
# print(table)
# multilist = list(e.map(normalpull,self.download_list))
# results = pd.concat(multilist)
# print(results.head())
if isinstance(self.datesString, str):
if self.table == 'events':
results = eventWork(self.download_list)
else:
# if self.table =='gkg':
# results = eventWork(self.download_list)
#
# else:
results = _mp_worker(self.download_list, proxies=self.proxies)
else:
if self.table == 'events':
pool = Pool(processes=cpu_count())
downloaded_dfs = list(
pool.imap_unordered(eventWork, self.download_list))
else:
pool = NoDaemonProcessPool(processes=cpu_count())
downloaded_dfs = list(
pool.imap_unordered(
_mp_worker,
self.download_list,
))
pool.close()
pool.terminate()
pool.join()
# print(downloaded_dfs)
results = pd.concat(downloaded_dfs)
del downloaded_dfs
results.reset_index(drop=True, inplace=True)
if self.table == 'gkg' and self.version == 1:
results.columns = results.ix[0].values.tolist()
results.drop([0], inplace=True)
columns = results.columns
# check for empty dataframe
if results is not None:
if len(results.columns) == 57: # pragma: no cover
results.columns = columns[:-1]
else:
results.columns = columns
# if dataframe is empty, raise error
elif results is None or len(results) == 0: # pragma: no cover
raise ValueError("This GDELT query returned no data. Check "
"query parameters and "
"retry")
# Add column of human readable codes; need updated CAMEO
if self.table == 'events':
cameoDescripts = results.EventCode.apply(codeCams)
results.insert(27,
'CAMEOCodeDescription',
value=cameoDescripts.values)
###############################################
# Setting the output options
###############################################
# dataframe output
if output == 'df':
self.final = results
# json output
elif output == 'json':
self.final = results.to_json(orient='records')
# csv output
elif output == 'csv':
self.final = results.to_csv(encoding='utf-8')
# geopandas dataframe output
elif output == 'gpd' or output == 'geodataframe' or output == 'geoframe':
self.final = _geofilter(results)
self.final = self.final[self.final.geometry.notnull()]
# r dataframe output
elif output == 'r': # pragma: no cover
if self.coverage:
coverage = 'True'
else:
coverage = 'False'
if isinstance(self.date, list):
formattedDates = [
"".join(re.split(' |-|;|:', l)) for l in self.date
]
path = formattedDates
outPath = (
"gdeltVersion_" + str(self.version) + "_coverage_" +
coverage + "_" + "_table_" + self.table + '_queryDates_' +
"_".join(path) + "_queryTime_" +
datetime.datetime.now().strftime('%m-%d-%YT%H%M%S') +
".feather")
else:
outPath = (
"gdeltVersion_" + str(self.version) + "_coverage_" +
coverage + "_" + "_table_" + self.table + '_queryDates_' +
"".join(re.split(' |-|;|:', self.date)) + "_queryTime_" +
datetime.datetime.now().strftime('%m-%d-%YT%H%M%S') +
".feather")
if normcols:
results.columns = list(
map(lambda x: (x.replace('_', "")).lower(),
results.columns))
feather.api.write_dataframe(results, outPath)
return results
else:
self.final = results
#########################
# Return the result
#########################
# normalized columns
if normcols:
self.final.columns = list(
map(lambda x: (x.replace('_', "")).lower(),
self.final.columns))
return self.final
def test_gdeltrange_sequence_v2_single_string(self):
date_sequence = '2016 10 01'
ranger_output = _dateRanger(date_sequence)
gdeltstring_test = _gdeltRangeString(ranger_output, version=2)
exp = '20161001234500'
return self.assertEqual(exp, gdeltstring_test)
