def test_multi_dims_time_series_and_uni(self):
result = CSV(slicer.metrics.wins) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=False)[[fm('wins')]]
expected.index.names = ['Timestamp', 'State']
expected.columns = ['Wins']
self.assertEqual(expected.to_csv(), result)
def test_uni_dim(self):
result = CSV(slicer.metrics.wins) \
.transform(uni_dim_df, slicer, [slicer.dimensions.candidate], [])
expected = uni_dim_df.copy() \
.set_index(fd('candidate_display'), append=True) \
.reset_index(fd('candidate'), drop=True)[[fm('wins')]]
expected.index.names = ['Candidate']
expected.columns = ['Wins']
self.assertEqual(expected.to_csv(), result)
def test_uni_dim(self):
result = CSV(slicer.metrics.wins) \
.transform(uni_dim_df, slicer, [slicer.dimensions.candidate], [])
expected = uni_dim_df.copy() \
.set_index(fd('candidate_display'), append=True) \
.reset_index(fd('candidate'), drop=True)[[fm('wins')]]
expected.index.names = ['Candidate']
expected.columns = ['Wins']
self.assertEqual(expected.to_csv(), result)
def test_multi_dims_time_series_and_uni(self):
result = CSV(slicer.metrics.wins) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=False)[[fm('wins')]]
expected.index.names = ['Timestamp', 'State']
expected.columns = ['Wins']
self.assertEqual(expected.to_csv(), result)
def test_pivoted_multi_dims_time_series_and_uni(self):
result = CSV(slicer.metrics.votes, pivot=[slicer.dimensions.state]) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=True)[[fm('votes')]]
expected = expected.unstack(level=[1])
expected.index.names = ['Timestamp']
expected.columns = ['California', 'Texas']
self.assertEqual(expected.to_csv(), result)
def test_pivoted_multi_dims_time_series_and_uni(self):
result = CSV(slicer.metrics.votes, pivot=[slicer.dimensions.state]) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=True)[[fm('votes')]]
expected = expected.unstack(level=[1])
expected.index.names = ['Timestamp']
expected.columns = ['California', 'Texas']
self.assertEqual(expected.to_csv(), result)
def test_uni_dim(self):
result = Pandas(slicer.metrics.wins) \
.transform(uni_dim_df, slicer, [slicer.dimensions.candidate], [])
expected = uni_dim_df.copy() \
.set_index(fd('candidate_display'), append=True) \
.reset_index(fd('candidate'), drop=True) \
[[fm('wins')]]
expected.index.names = ['Candidate']
expected.columns = ['Wins']
expected.columns.name = 'Metrics'
pandas.testing.assert_frame_equal(expected, result)
def test_uni_dim(self):
result = Pandas(slicer.metrics.wins) \
.transform(uni_dim_df, slicer, [slicer.dimensions.candidate], [])
expected = uni_dim_df.copy() \
.set_index(fd('candidate_display'), append=True) \
.reset_index(fd('candidate'), drop=True) \
[[fm('wins')]]
expected.index.names = ['Candidate']
expected.columns = ['Wins']
expected.columns.name = 'Metrics'
pandas.testing.assert_frame_equal(expected, result)
def test_pivoted_multi_dims_time_series_and_uni_with_sort_index_desc(self):
result = Pandas(slicer.metrics.votes, pivot=[slicer.dimensions.state], sort=[0], ascending=[False]) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=True)[[fm('votes')]]
expected = expected.unstack(level=[1])
expected.index.names = ['Timestamp']
expected.columns = ['California', 'Texas']
expected.columns.names = ['State']
expected = expected.sort_index(ascending=False)
pandas.testing.assert_frame_equal(expected, result)
def test_pivoted_multi_dims_time_series_and_uni_with_sort_index_desc(self):
result = Pandas(slicer.metrics.votes, pivot=[slicer.dimensions.state], sort=[0], ascending=[False]) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=True)[[fm('votes')]]
expected = expected.unstack(level=[1])
expected.index.names = ['Timestamp']
expected.columns = ['California', 'Texas']
expected.columns.names = ['State']
expected = expected.sort_index(ascending=False)
pandas.testing.assert_frame_equal(expected, result)
def test_multi_dims_time_series_and_cat_sort_index_level_0_asc(self):
result = Pandas(slicer.metrics.wins, sort=[0]) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=False)[[fm('wins')]]
expected.index.names = ['Timestamp', 'State']
expected.columns = ['Wins']
expected.columns.name = 'Metrics'
expected = expected.reset_index()
expected = expected.sort_values(['Timestamp'])
expected = expected.set_index(['Timestamp', 'State'])
pandas.testing.assert_frame_equal(expected, result)
def test_pivoted_multi_dims_time_series_and_cat_sort_index_and_values(self):
result = Pandas(slicer.metrics.wins, sort=[0, 2], ascending=[False, True]) \
.transform(cont_uni_dim_df, slicer, [slicer.dimensions.timestamp, slicer.dimensions.state], [])
expected = cont_uni_dim_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=False)[[fm('wins')]]
expected.index.names = ['Timestamp', 'State']
expected.columns = ['Wins']
expected.columns.name = 'Metrics'
expected = expected.reset_index()
expected = expected.sort_values(['Timestamp', 'Wins'], ascending=[False, True])
expected = expected.set_index(['Timestamp', 'State'])
pandas.testing.assert_frame_equal(expected, result)
def test_uni_dim_no_display_definition(self):
import copy
candidate = copy.copy(slicer.dimensions.candidate)
uni_dim_df_copy = uni_dim_df.copy()
del uni_dim_df_copy[fd(slicer.dimensions.candidate.display.key)]
del candidate.display
result = ReactTable(slicer.metrics.wins) \
.transform(uni_dim_df_copy, slicer, [candidate], [])
self.assertEqual({
'columns': [{'Header': 'Candidate', 'accessor': '$d$candidate'},
{'Header': 'Wins', 'accessor': '$m$wins'}],
'data': [{'$d$candidate': {'raw': '1'}, '$m$wins': {'display': '2', 'raw': 2}},
{'$d$candidate': {'raw': '2'}, '$m$wins': {'display': '0', 'raw': 0}},
{'$d$candidate': {'raw': '3'}, '$m$wins': {'display': '0', 'raw': 0}},
{'$d$candidate': {'raw': '4'}, '$m$wins': {'display': '4', 'raw': 4}},
{'$d$candidate': {'raw': '5'}, '$m$wins': {'display': '0', 'raw': 0}},
{'$d$candidate': {'raw': '6'}, '$m$wins': {'display': '0', 'raw': 0}},
{'$d$candidate': {'raw': '7'}, '$m$wins': {'display': '4', 'raw': 4}},
{'$d$candidate': {'raw': '8'}, '$m$wins': {'display': '0', 'raw': 0}},
{'$d$candidate': {'raw': '9'}, '$m$wins': {'display': '0', 'raw': 0}},
{
'$d$candidate': {'raw': '10'},
'$m$wins': {'display': '2', 'raw': 2}
}, {
'$d$candidate': {'raw': '11'},
'$m$wins': {'display': '0', 'raw': 0}
}]
}, result)
def test_time_series_ref(self):
result = CSV(slicer.metrics.votes) \
.transform(cont_uni_dim_ref_df,
slicer,
[
slicer.dimensions.timestamp,
slicer.dimensions.state
], [
ElectionOverElection(slicer.dimensions.timestamp)
])
expected = cont_uni_dim_ref_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=True)[[fm('votes'), fm('votes_eoe')]]
expected.index.names = ['Timestamp', 'State']
expected.columns = ['Votes', 'Votes (EoE)']
self.assertEqual(expected.to_csv(), result)
def test_time_series_ref(self):
result = CSV(slicer.metrics.votes) \
.transform(cont_uni_dim_ref_df,
slicer,
[
slicer.dimensions.timestamp,
slicer.dimensions.state
], [
ElectionOverElection(slicer.dimensions.timestamp)
])
expected = cont_uni_dim_ref_df.copy() \
.set_index(fd('state_display'), append=True) \
.reset_index(fd('state'), drop=True)[[fm('votes'), fm('votes_eoe')]]
expected.index.names = ['Timestamp', 'State']
expected.columns = ['Votes', 'Votes (EoE)']
self.assertEqual(expected.to_csv(), result)
def test_uni_dim_no_display_definition(self):
import copy
candidate = copy.copy(slicer.dimensions.candidate)
uni_dim_df_copy = uni_dim_df.copy()
del uni_dim_df_copy[fd(slicer.dimensions.candidate.display.key)]
del candidate.display
result = DataTablesJS(slicer.metrics.wins) \
.transform(uni_dim_df_copy, slicer, [candidate], [])
self.assertEqual({
'columns': [{
'data': 'candidate',
'render': {'_': 'value'},
'title': 'Candidate'
}, {
'data': 'wins',
'render': {'_': 'value', 'display': 'display'},
'title': 'Wins'
}],
'data': [{
'candidate': {'value': 1},
'wins': {'display': '2', 'value': 2}
}, {
'candidate': {'value': 2},
'wins': {'display': '0', 'value': 0}
}, {
'candidate': {'value': 3},
'wins': {'display': '0', 'value': 0}
}, {
'candidate': {'value': 4},
'wins': {'display': '4', 'value': 4}
}, {
'candidate': {'value': 5},
'wins': {'display': '0', 'value': 0}
}, {
'candidate': {'value': 6},
'wins': {'display': '0', 'value': 0}
}, {
'candidate': {'value': 7},
'wins': {'display': '4', 'value': 4}
}, {
'candidate': {'value': 8},
'wins': {'display': '0', 'value': 0}
}, {
'candidate': {'value': 9},
'wins': {'display': '0', 'value': 0}
}, {
'candidate': {'value': 10},
'wins': {'display': '2', 'value': 2}
}, {
'candidate': {'value': 11},
'wins': {'display': '0', 'value': 0}
}],
}, result)
def test_uni_dim_no_display_definition(self):
import copy
candidate = copy.copy(slicer.dimensions.candidate)
uni_dim_df_copy = uni_dim_df.copy()
del uni_dim_df_copy[fd(slicer.dimensions.candidate.display.key)]
del candidate.display
result = CSV(slicer.metrics.wins) \
.transform(uni_dim_df_copy, slicer, [candidate], [])
expected = uni_dim_df_copy.copy()[[fm('wins')]]
expected.index.names = ['Candidate']
expected.columns = ['Wins']
self.assertEqual(expected.to_csv(), result)
def test_uni_dim_no_display_definition(self):
import copy
candidate = copy.copy(slicer.dimensions.candidate)
uni_dim_df_copy = uni_dim_df.copy()
del uni_dim_df_copy[fd(slicer.dimensions.candidate.display.key)]
del candidate.display
result = CSV(slicer.metrics.wins) \
.transform(uni_dim_df_copy, slicer, [candidate], [])
expected = uni_dim_df_copy.copy()[[fm('wins')]]
expected.index.names = ['Candidate']
expected.columns = ['Wins']
self.assertEqual(expected.to_csv(), result)
name=cat_dim_df.index.name)))
uni_dim_nans_df = uni_dim_df.append(
pd.DataFrame([[None, 300, 2]],
columns=uni_dim_df.columns,
index=pd.Index([None],
name=uni_dim_df.index.name)))
def add_nans(df):
return pd.DataFrame([[None, 300, 2]],
columns=df.columns,
index=pd.Index([None], name=df.index.names[1]))
cont_uni_dim_nans_df = cont_uni_dim_df \
.append(cont_uni_dim_df.groupby(level=fd('timestamp')).apply(add_nans)) \
.sort_index()
def totals(df):
return pd.DataFrame([[None] + list(df.sum())],
columns=df.columns,
index=pd.Index([None], name=df.index.names[1]))
cont_uni_dim_nans_totals_df = cont_uni_dim_nans_df \
.append(cont_uni_dim_nans_df.groupby(level=fd('timestamp')).apply(totals)) \
.sort_index() \
.sort_index(level=[0, 1], ascending=False) # This sorts the DF so that the first instance of NaN is the totals
(1, 1): True,
(1, 2): False,
(1, 3): False,
(2, 4): True,
(2, 5): False,
(3, 4): True,
(3, 6): False,
(4, 7): True,
(4, 8): False,
(5, 7): True,
(5, 9): False,
(6, 10): True,
(6, 11): False,
}
df_columns = [fd('timestamp'),
fd('candidate'), fd('candidate_display'),
fd('political_party'),
fd('election'), fd('election_display'),
fd('state'), fd('state_display'),
fd('winner'),
fm('votes'),
fm('wins')]
def PoliticsRow(timestamp, candidate, candidate_display, political_party, election, election_display, state,
state_display, winner, votes, wins):
return (
timestamp, candidate, candidate_display, political_party, election, election_display, state, state_display,
winner, votes, wins
)
(1, 2): False,
(1, 3): False,
(2, 4): True,
(2, 5): False,
(3, 4): True,
(3, 6): False,
(4, 7): True,
(4, 8): False,
(5, 7): True,
(5, 9): False,
(6, 10): True,
(6, 11): False,
}
df_columns = [
fd('timestamp'),
fd('candidate'),
fd('candidate_display'),
fd('political_party'),
fd('election'),
fd('election_display'),
fd('state'),
fd('state_display'),
fd('winner'),
fm('votes'),
fm('wins')
]
def PoliticsRow(timestamp, candidate, candidate_display, political_party,
election, election_display, state, state_display, winner,
columns=cat_dim_df.columns,
index=pd.Index([None], name=cat_dim_df.index.name)))
uni_dim_nans_df = uni_dim_df.append(
pd.DataFrame([[None, 300, 2]],
columns=uni_dim_df.columns,
index=pd.Index([None], name=uni_dim_df.index.name)))
def add_nans(df):
return pd.DataFrame([[None, 300, 2]],
columns=df.columns,
index=pd.Index([None], name=df.index.names[1]))
cont_uni_dim_nans_df = cont_uni_dim_df \
.append(cont_uni_dim_df.groupby(level=fd('timestamp')).apply(add_nans)) \
.sort_index()
def totals(df):
return pd.DataFrame([[None] + list(df.sum())],
columns=df.columns,
index=pd.Index([None], name=df.index.names[1]))
cont_uni_dim_nans_totals_df = cont_uni_dim_nans_df \
.append(cont_uni_dim_nans_df.groupby(level=fd('timestamp')).apply(totals)) \
.sort_index() \
.sort_index(level=[0, 1], ascending=False) # This sorts the DF so that the first instance of NaN is the totals
