def simple_df(request):
_df = FULL_FEATURE_DF.copy()
if request.param == 'datetime':
_df.rename(DTS_MAPPING, axis="columns", inplace=True)
yield IamDataFrame(model='model_a', scenario='scen_a', data=_df)
def test_init_df_with_index(test_pd_df):
df = IamDataFrame(test_pd_df.set_index(META_IDX))
pd.testing.assert_frame_equal(df.timeseries().reset_index(), test_pd_df)
def test_init_df_from_timeseries(test_df):
df = IamDataFrame(test_df.timeseries())
pd.testing.assert_frame_equal(df.timeseries(), test_df.timeseries())
def plot_stack_plot_df():
df = IamDataFrame(TEST_STACKPLOT_DF)
yield df
def test_init(data):
IamDataFrame(data)
def test_init_df_with_duplicates_raises(test_df):
_df = test_df.timeseries()
_df = _df.append(_df.iloc[0]).reset_index()
match = '3 model_a scen_a World Primary Energy EJ/yr'
with pytest.raises(ValueError, match=match):
IamDataFrame(_df)
def reg_df():
df = IamDataFrame(data=REG_DF)
yield df
def test_load_meta_empty(test_pd_df):
"""Initializing from xlsx where 'meta' has no rows and non-empty invisible header"""
obs = IamDataFrame(TEST_DATA_DIR / "empty_meta_sheet.xlsx")
exp = IamDataFrame(test_pd_df)
assert_iamframe_equal(obs, exp)
def test_load_rcp_database_downloaded_file(test_pd_df):
exp = IamDataFrame(test_pd_df).filter(**FILTER_ARGS).as_pandas()
file = TEST_DATA_DIR / "test_RCP_database_raw_download.xlsx"
obs_df = IamDataFrame(file)
pd.testing.assert_frame_equal(obs_df.as_pandas(), exp)
import pandas as pd
from pyam import IamDataFrame
from nomenclature import swap_time_for_subannual
TEST_DF = pd.DataFrame([
['model_a', 'scen_a', 'Europe', 'Primary Energy', 'EJ/yr', 1, 6.],
],
columns=[
'model', 'scenario', 'region', 'variable', 'unit',
'2005-06-17T00:00+0100', '2010-07-21T12:00+0100'
])
df = IamDataFrame(TEST_DF)
def test_swap_time_for_subannual():
# test transforming of IamDataFrame in datetime domain to year + subannual
obs = swap_time_for_subannual(df).data
obs_year = list(obs['year'].values)
obs_subannual = list(obs['subannual'].values)
assert obs_year == [2005, 2010] and \
obs_subannual == ['06-17 00:00+01:00', '07-21 12:00+01:00']
def test_data_none():
# initializing with 'data=None' raises an error
match = "IamDataFrame constructor not properly called!"
with pytest.raises(ValueError, match=match):
IamDataFrame(None)
def test_load_rcp_database_downloaded_file(test_df_year):
exp = test_df_year.filter(**FILTER_ARGS).as_pandas()
obs_df = IamDataFrame(
os.path.join(TEST_DATA_DIR, 'test_RCP_database_raw_download.xlsx'))
pd.testing.assert_frame_equal(obs_df.as_pandas(), exp)
import copy
import pytest
import numpy as np
import pandas as pd
from numpy import testing as npt
from pyam import IamDataFrame, META_IDX, IAMC_IDX, compare
from conftest import TEST_DTS, META_COLS
RENAME_DF = IamDataFrame(
pd.DataFrame(
[
["model", "scen", "region_a", "test_1", "unit", 1, 5],
["model", "scen", "region_a", "test_2", "unit", 2, 6],
["model", "scen", "region_a", "test_3", "unit", 3, 7],
["model", "scen", "region_b", "test_3", "unit", 4, 8],
],
columns=IAMC_IDX + [2005, 2010],
))
# expected output
EXP_RENAME_DF = (IamDataFrame(
pd.DataFrame(
[
["model", "scen", "region_c", "test", "unit", 4, 12],
["model", "scen", "region_a", "test_2", "unit", 2, 6],
["model", "scen", "region_b", "test_3", "unit", 4, 8],
],
columns=IAMC_IDX + [2005, 2010],
)).data.sort_values(by="region").reset_index(drop=True))
import copy
import pytest
import numpy as np
import pandas as pd
from numpy import testing as npt
from pyam import IamDataFrame, META_IDX, IAMC_IDX, compare
from conftest import TEST_DTS, META_COLS
RENAME_DF = IamDataFrame(
pd.DataFrame(
[
['model', 'scen', 'region_a', 'test_1', 'unit', 1, 5],
['model', 'scen', 'region_a', 'test_2', 'unit', 2, 6],
['model', 'scen', 'region_a', 'test_3', 'unit', 3, 7],
['model', 'scen', 'region_b', 'test_3', 'unit', 4, 8],
],
columns=IAMC_IDX + [2005, 2010],
))
# expected output
EXP_RENAME_DF = IamDataFrame(
pd.DataFrame(
[
['model', 'scen', 'region_c', 'test', 'unit', 4, 12],
['model', 'scen', 'region_a', 'test_2', 'unit', 2, 6],
['model', 'scen', 'region_b', 'test_3', 'unit', 4, 8],
],
columns=IAMC_IDX + [2005, 2010],
)).data.sort_values(by='region').reset_index(drop=True)
def test_filter_empty_df():
# test for issue seen in #254
df = IamDataFrame(data=df_empty)
obs = df.filter(variable='foo')
assert len(obs) == 0
def test_unknown_type():
# initializing with unsupported argument type raises an error
match = "IamDataFrame constructor not properly called!"
with pytest.raises(ValueError, match=match):
IamDataFrame(True)
def test_init_from_iamdf_raises(test_df_year):
# casting an IamDataFrame instance again with extra args fails
args = dict(model='foo')
match = f'Invalid arguments `{args}` for initializing an IamDataFrame'
with pytest.raises(ValueError, match=match):
IamDataFrame(test_df_year, **args)
def test_not_a_file():
# initializing with a file-like that's not a file raises an error
match = "File foo.csv does not exist"
with pytest.raises(FileNotFoundError, match=match):
IamDataFrame("foo.csv")
def test_df_year():
df = IamDataFrame(data=TEST_DF)
for i in META_COLS:
df.set_meta(META_DF[i])
yield df
def test_io_list():
# initializing with a list raises an error
match = r"Initializing from list is not supported,*."
with pytest.raises(ValueError, match=match):
IamDataFrame([1, 2])
def plot_df():
df = IamDataFrame(data=os.path.join(TEST_DATA_DIR, 'plot_data.csv'))
yield df
import pandas as pd
from pyam import IamDataFrame, IAMC_IDX
from pyam.testing import assert_iamframe_equal
import pytest
TEST_DF = IamDataFrame(
pd.DataFrame(
[
["model_a", "scen_a", "World", "Cap", "GW", 1, 2],
["model_a", "scen_a", "World", "Cost", "US$2010/kW", 1, 0.5],
["model_a", "scen_b", "World", "Cap", "GW", 0.1, 0.2],
["model_a", "scen_b", "World", "Cost", "US$2010/kW", 1, 0.5],
["model_a", "scen_c", "World", "Cap", "GW", 10, 20],
["model_a", "scen_c", "World", "Cost", "US$2010/kW", 1, 0.5],
["model_a", "scen_d", "World", "Cap", "GW", 1, 2],
["model_a", "scen_d", "World", "Cost", "US$2010/kW", 1, 0.75],
["model_a", "scen_e", "World", "Cap", "GW", 1, 2],
["model_a", "scen_e", "World", "Cost", "US$2010/kW", 1, 0.25],
],
columns=IAMC_IDX + [2005, 2010],
))
EXP_DF = IamDataFrame(
pd.DataFrame(
[
["model_a", "scen_a", "World", "Learning Rate", "", 0.5],
["model_a", "scen_b", "World", "Learning Rate", "", 0.5],
["model_a", "scen_c", "World", "Learning Rate", "", 0.5],
["model_a", "scen_d", "World", "Learning Rate", "", 0.25],
["model_a", "scen_e", "World", "Learning Rate", "", 0.75],
],
import math
import pandas as pd
import pandas.testing as pdt
from pyam import IamDataFrame, IAMC_IDX
from pyam.testing import assert_iamframe_equal
from pyam.timeseries import growth_rate
import pytest
from conftest import META_DF
EXP_DF = IamDataFrame(
pd.DataFrame(
[
["model_a", "scen_a", "World", "Growth Rate", "", 0.430969],
["model_a", "scen_b", "World", "Growth Rate", "", 0.284735],
],
columns=IAMC_IDX + [2005],
),
meta=META_DF,
)
@pytest.mark.parametrize("append", (False, True))
def test_growth_rate(test_df_year, append):
"""Check computing the growth rate from an IamDataFrame"""
if append:
obs = test_df_year.copy()
obs.compute.growth_rate({"Primary Energy": "Growth Rate"}, append=True)
assert_iamframe_equal(test_df_year.append(EXP_DF), obs)
else:
def test_init_empty_message(caplog):
IamDataFrame(data=df_empty)
drop_message = ("Formatted data is empty!")
message_idx = caplog.messages.index(drop_message)
assert caplog.records[message_idx].levelno == logging.WARNING
def test_read_pandas():
df = IamDataFrame(os.path.join(TEST_DATA_DIR, 'testing_data_2.csv'))
assert list(df.variables()) == ['Primary Energy']
def test_equals_raises(test_pd_df):
df = IamDataFrame(test_pd_df)
pytest.raises(ValueError, df.equals, test_pd_df)
def test_init_df_with_float_cols(test_pd_df):
_test_df = test_pd_df.rename(columns={2005: 2005., 2010: 2010.})
obs = IamDataFrame(_test_df).timeseries().reset_index()
pd.testing.assert_series_equal(obs[2005], test_pd_df[2005])
def test_index_attributes_extra_col(test_pd_df):
test_pd_df['subannual'] = ['summer', 'summer', 'winter']
df = IamDataFrame(test_pd_df)
assert df.subannual == ['summer', 'winter']
def test_load_SSP_database_downloaded_file(test_df):
obs_df = IamDataFrame(
os.path.join(TEST_DATA_DIR, 'test_SSP_database_raw_download.xlsx'))
pd.testing.assert_frame_equal(obs_df.as_pandas(), test_df.as_pandas())
def test_df_year():
df = IamDataFrame(data=TEST_DF)
yield df
