def test_frame_target_object_set(self):
df = pd.DataFrame({datetime.datetime(2014, 1, 1): [1, 2, 3],
datetime.datetime(2015, 1, 1): [4, 5, 6],
datetime.datetime(2016, 1, 1): [7, 8, 9]},
index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df)
mdf.target = pd.Series(['A', 'B', 'C'], index=['a', 'b', 'c'], name=5)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
expected = pd.Index([5, datetime.datetime(2014, 1, 1),
datetime.datetime(2015, 1, 1), datetime.datetime(2016, 1, 1)])
tm.assert_index_equal(mdf.columns, expected)
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series(['A', 'B', 'C'], index=['a', 'b', 'c'], name=5)
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, 5)
# name will be ignored if ModelFrame already has a target
mdf.target = pd.Series([10, 11, 12], index=['a', 'b', 'c'], name='X')
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
expected = pd.Index([5,
datetime.datetime(2014, 1, 1),
datetime.datetime(2015, 1, 1),
datetime.datetime(2016, 1, 1)])
tm.assert_index_equal(mdf.columns, expected)
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series([10, 11, 12], index=['a', 'b', 'c'], name=5)
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, 5)
def test_patsy_matrices(self):
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([10, 11, 12], index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=s)
result = mdf.transform('A ~ B + C')
self.assertIsInstance(result, pdml.ModelFrame)
self.assertEqual(result.shape, (3, 4))
tm.assert_index_equal(result.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(result.columns, pd.Index(['A', 'Intercept', 'B', 'C']))
expected = pd.DataFrame({'A': [1, 2, 3],
'Intercept': [1, 1, 1],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'Intercept', 'B', 'C'],
dtype=float)
tm.assert_frame_equal(result, expected)
expected = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='A', dtype=float)
tm.assert_series_equal(result.target, expected)
self.assertEqual(result.target.name, 'A')
self.assertEqual(result.target_name, 'A')
def test_inverse_transform(self):
iris = datasets.load_iris()
df = pdml.ModelFrame(iris)
models = ['PCA']
for model in models:
mod1 = getattr(df.decomposition, model)()
mod2 = getattr(decomposition, model)()
df.fit(mod1)
mod2.fit(iris.data, iris.target)
result = df.transform(mod1)
expected = mod2.transform(iris.data)
self.assertIsInstance(result, pdml.ModelFrame)
tm.assert_series_equal(df.target, result.target)
self.assert_numpy_array_almost_equal(result.data.values, expected)
result = df.inverse_transform(mod1)
expected = mod2.inverse_transform(iris.data)
self.assertIsInstance(result, pdml.ModelFrame)
tm.assert_series_equal(df.target, result.target)
self.assert_numpy_array_almost_equal(result.data.values, expected)
tm.assert_index_equal(result.columns, df.columns)
def test_frame_init_df_series(self):
# initialization by dataframe and no-named series
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
s = pd.Series([1, 2, 3])
with self.assertRaisesRegexp(ValueError, 'data and target must have equal index'):
mdf = pdml.ModelFrame(df, target=s)
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='XXX')
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['XXX', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, 'XXX')
self.assertEqual(mdf.target_name, 'XXX')
def test_frame_init_df_df(self):
# initialization by dataframe and dataframe
df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
target = pd.DataFrame({
't1': [10, 11, 12],
't2': [13, 14, 15]
},
index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=target)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 5))
expected = pd.DataFrame(
{
't1': [10, 11, 12],
't2': [13, 14, 15],
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['t1', 't2', 'A', 'B', 'C'])
tm.assert_frame_equal(mdf, expected)
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns,
pd.Index(['t1', 't2', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_frame_equal(mdf.target, target)
tm.assert_index_equal(mdf.target.columns, pd.Index(['t1', 't2']))
tm.assert_index_equal(mdf.target_name, pd.Index(['t1', 't2']))
self.assertTrue(mdf.has_multi_targets())
target = pd.DataFrame({'t1': [10, 11, 12], 't2': [13, 14, 15]})
msg = 'data and target must have equal index'
with pytest.raises(ValueError, match=msg):
mdf = pdml.ModelFrame(df, target=target)
# single column DataFrame will results in single target column
target = pd.DataFrame({'t1': [10, 11, 12]}, index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=target)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['t1', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
target = pd.Series([10, 11, 12], name='t1', index=['a', 'b', 'c'])
tm.assert_series_equal(mdf.target, target)
self.assertEqual(mdf.target_name, 't1')
def test_series_groupby(self):
s = pdml.ModelSeries([1, 2, 1, 2], name='X')
self.assertIsInstance(s, pdml.ModelSeries)
grouped = s.groupby([1, 1, 1, 2])
self.assertIsInstance(grouped, pdml.core.groupby.ModelSeriesGroupBy)
gs = grouped.get_group(1)
self.assertIsInstance(gs, pdml.ModelSeries)
expected = pd.Series([1, 2, 1], index=[0, 1, 2], name='X')
tm.assert_series_equal(gs, expected)
self.assertEqual(gs.name, 'X')
def test_fit_transform_PCA(self):
iris = datasets.load_iris()
df = pdml.ModelFrame(iris)
mod1 = df.decomposition.PCA()
mod2 = decomposition.PCA()
result = df.fit_transform(mod1)
expected = mod2.fit_transform(iris.data, iris.target)
self.assertIsInstance(result, pdml.ModelFrame)
tm.assert_series_equal(df.target, result.target)
self.assert_numpy_array_almost_equal(result.data.values, expected)
def test_fit_transform_KernelPCA(self):
iris = datasets.load_iris()
df = pdml.ModelFrame(iris)
mod1 = df.decomposition.KernelPCA()
mod2 = decomposition.KernelPCA()
result = df.fit_transform(mod1)
expected = mod2.fit_transform(iris.data, iris.target)
self.assertIsInstance(result, pdml.ModelFrame)
tm.assert_series_equal(df.target, result.target)
self.assert_numpy_array_almost_equal(result.data.values[:, :40],
expected[:, :40])
def test_frame_init_dict_list_series_index(self):
# initialization by dataframe and list
df = {'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]}
target = pd.Series([9, 8, 7], name='X', index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=target)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['X', 'A', 'B', 'C']))
expected = pd.DataFrame(df, index=['a', 'b', 'c'])
tm.assert_frame_equal(mdf.data, expected)
tm.assert_series_equal(mdf.target, target)
self.assertEqual(mdf.target.name, 'X')
self.assertEqual(mdf.target_name, 'X')
def test_frame_init_dict_list_series_index(self):
# initialization by dataframe and list
df = {'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]}
target = pd.Series([9, 8, 7], name='X', index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=target)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['X', 'A', 'B', 'C']))
expected = pd.DataFrame(df, index=['a', 'b', 'c'])
tm.assert_frame_equal(mdf.data, expected)
tm.assert_series_equal(mdf.target, target)
self.assertEqual(mdf.target.name, 'X')
self.assertEqual(mdf.target_name, 'X')
def test_frame_init_df_df(self):
# initialization by dataframe and dataframe
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
target = pd.DataFrame({'t1': [10, 11, 12],
't2': [13, 14, 15]},
index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=target)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 5))
expected = pd.DataFrame({'t1': [10, 11, 12],
't2': [13, 14, 15],
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['t1', 't2', 'A', 'B', 'C'])
tm.assert_frame_equal(mdf, expected)
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns,
pd.Index(['t1', 't2', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_frame_equal(mdf.target, target)
tm.assert_index_equal(mdf.target.columns, pd.Index(['t1', 't2']))
tm.assert_index_equal(mdf.target_name, pd.Index(['t1', 't2']))
self.assertTrue(mdf.has_multi_targets())
target = pd.DataFrame({'t1': [10, 11, 12], 't2': [13, 14, 15]})
msg = 'data and target must have equal index'
with self.assertRaisesRegexp(ValueError, msg):
mdf = pdml.ModelFrame(df, target=target)
# single column DataFrame will results in single target column
target = pd.DataFrame({'t1': [10, 11, 12]}, index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=target)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['t1', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
target = pd.Series([10, 11, 12], name='t1', index=['a', 'b', 'c'])
tm.assert_series_equal(mdf.target, target)
self.assertEqual(mdf.target_name, 't1')
def _assert_fit_transform(self, df, exp_data, model1, model2):
result = df.fit_transform(model1)
expected = model2.fit_transform(exp_data)
self.assertIsInstance(result, pdml.ModelFrame)
# target is unchanged
if df.has_target():
# target is unchanged
tm.assert_series_equal(df.target, result.target)
else:
self.assertIsNone(result.target)
self.assert_numpy_array_almost_equal(result.data.values, expected)
# index and columns are kept
tm.assert_index_equal(result.index, df.index)
tm.assert_index_equal(result.columns, df.columns)
def _assert_fit_transform(self, df, exp_data, model1, model2):
result = df.fit_transform(model1)
expected = model2.fit_transform(exp_data)
self.assertIsInstance(result, pdml.ModelFrame)
# target is unchanged
if df.has_target():
# target is unchanged
tm.assert_series_equal(df.target, result.target)
else:
self.assertIsNone(result.target)
self.assert_numpy_array_almost_equal(result.data.values, expected)
# index and columns are kept
tm.assert_index_equal(result.index, df.index)
tm.assert_index_equal(result.columns, df.columns)
def test_frame_target_object(self):
df = pd.DataFrame({datetime.datetime(2014, 1, 1): [1, 2, 3],
datetime.datetime(2015, 1, 1): [4, 5, 6],
datetime.datetime(2016, 1, 1): [7, 8, 9]},
index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=datetime.datetime(2016, 1, 1))
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
expected = pd.DatetimeIndex(['2014-01-01', '2015-01-01', '2016-01-01'])
tm.assert_index_equal(mdf.columns, expected)
tm.assert_frame_equal(mdf.data, df.iloc[:, :2])
expected = pd.Series([7, 8, 9], index=['a', 'b', 'c'],
name=pd.Timestamp('2016-01-01'))
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, datetime.datetime(2016, 1, 1))
self.assertEqual(mdf.target_name, datetime.datetime(2016, 1, 1))
def test_frame_init_df_array_series(self):
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(np.array([[1, 2, 3], [4, 5, 6],
[7, 8, 9]]), target=s,
index=['a', 'b', 'c'], columns=['A', 'B', 'C'])
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
expected = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6],
[7, 8, 9]]),
index=['a', 'b', 'c'], columns=['A', 'B', 'C'])
tm.assert_frame_equal(mdf.data, expected)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
def test_frame_target_object_set(self):
df = pd.DataFrame(
{
datetime.datetime(2014, 1, 1): [1, 2, 3],
datetime.datetime(2015, 1, 1): [4, 5, 6],
datetime.datetime(2016, 1, 1): [7, 8, 9]
},
index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df)
mdf.target = pd.Series(['A', 'B', 'C'], index=['a', 'b', 'c'], name=5)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
expected = pd.Index([
5,
datetime.datetime(2014, 1, 1),
datetime.datetime(2015, 1, 1),
datetime.datetime(2016, 1, 1)
])
tm.assert_index_equal(mdf.columns, expected)
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series(['A', 'B', 'C'], index=['a', 'b', 'c'], name=5)
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, 5)
# name will be ignored if ModelFrame already has a target
mdf.target = pd.Series([10, 11, 12], index=['a', 'b', 'c'], name='X')
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
expected = pd.Index([
5,
datetime.datetime(2014, 1, 1),
datetime.datetime(2015, 1, 1),
datetime.datetime(2016, 1, 1)
])
tm.assert_index_equal(mdf.columns, expected)
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series([10, 11, 12], index=['a', 'b', 'c'], name=5)
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, 5)
def test_frame_init_df_array_series(self):
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]),
target=s,
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B',
'C']))
expected = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]),
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
tm.assert_frame_equal(mdf.data, expected)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
def test_frame_init_df_str(self):
# initialization by dataframe and str
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
mdf = pdml.ModelFrame(df, target='A')
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df[['B', 'C']])
tm.assert_series_equal(mdf.target, df['A'])
self.assertEqual(mdf.target.name, 'A')
self.assertEqual(mdf.target_name, 'A')
msg = "Specified target 'X' is not included in data"
with self.assertRaisesRegexp(ValueError, msg):
mdf = pdml.ModelFrame(df, target='X')
def test_frame_data_none(self):
msg = "ModelFrame must have either data or target"
with self.assertRaisesRegexp(ValueError, msg):
mdf = pdml.ModelFrame(None)
msg = "target must be list-like when data is None"
with self.assertRaisesRegexp(ValueError, msg):
mdf = pdml.ModelFrame(None, target='X')
# initialization without data
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(None, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 1))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target']))
self.assertTrue(mdf.data is None)
self.assertFalse(mdf.has_data())
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
def test_frame_data_none(self):
msg = "ModelFrame must have either data or target"
with pytest.raises(ValueError, match=msg):
mdf = pdml.ModelFrame(None)
msg = "target must be list-like when data is None"
with pytest.raises(ValueError, match=msg):
mdf = pdml.ModelFrame(None, target='X')
# initialization without data
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(None, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 1))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target']))
self.assertTrue(mdf.data is None)
self.assertFalse(mdf.has_data())
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
def test_frame_target_object(self):
df = pd.DataFrame(
{
datetime.datetime(2014, 1, 1): [1, 2, 3],
datetime.datetime(2015, 1, 1): [4, 5, 6],
datetime.datetime(2016, 1, 1): [7, 8, 9]
},
index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=datetime.datetime(2016, 1, 1))
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
expected = pd.DatetimeIndex(['2014-01-01', '2015-01-01', '2016-01-01'])
tm.assert_index_equal(mdf.columns, expected)
tm.assert_frame_equal(mdf.data, df.iloc[:, :2])
expected = pd.Series([7, 8, 9],
index=['a', 'b', 'c'],
name=pd.Timestamp('2016-01-01'))
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, datetime.datetime(2016, 1, 1))
self.assertEqual(mdf.target_name, datetime.datetime(2016, 1, 1))
def test_frame_groupby(self):
df = pd.DataFrame(
{
'A': [1, 2, 1, 2],
'B': [4, 5, 6, 7],
'C': [7, 8, 9, 10]
},
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3, 4])
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
grouped = mdf.groupby('A')
self.assertIsInstance(grouped, pdml.core.groupby.ModelFrameGroupBy)
df = grouped.get_group(1)
self.assertIsInstance(df, pdml.ModelFrame)
expected = pd.Series([1, 3], index=[0, 2], name='.target')
tm.assert_series_equal(df.target, expected)
self.assertIsInstance(df.target, pdml.ModelSeries)
def test_LabelEncoder_series(self):
arr = np.array(['X', 'Y', 'Z', 'X'])
s = pdml.ModelSeries(arr, index=['a', 'b', 'c', 'd'])
mod1 = s.pp.LabelEncoder()
s.fit(mod1)
result = s.transform(mod1)
expected = np.array([0, 1, 2, 0])
self.assertIsInstance(result, pdml.ModelSeries)
self.assert_numpy_array_almost_equal(result.values, expected)
tm.assert_index_equal(result.index, s.index)
mod1 = s.pp.LabelEncoder()
result = s.fit_transform(mod1)
self.assertIsInstance(result, pdml.ModelSeries)
self.assert_numpy_array_almost_equal(result.values, expected)
inversed = result.inverse_transform(mod1)
self.assertIsInstance(inversed, pdml.ModelSeries)
tm.assert_series_equal(inversed, s)
def test_frame_init_df_str(self):
# initialization by dataframe and str
df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
mdf = pdml.ModelFrame(df, target='A')
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df[['B', 'C']])
tm.assert_series_equal(mdf.target, df['A'])
self.assertEqual(mdf.target.name, 'A')
self.assertEqual(mdf.target_name, 'A')
msg = "Specified target 'X' is not included in data"
with pytest.raises(ValueError, match=msg):
mdf = pdml.ModelFrame(df, target='X')
def test_LabelEncoder_series(self):
arr = np.array(['X', 'Y', 'Z', 'X'])
s = pdml.ModelSeries(arr, index=['a', 'b', 'c', 'd'])
mod1 = s.pp.LabelEncoder()
s.fit(mod1)
result = s.transform(mod1)
expected = np.array([0, 1, 2, 0])
self.assertIsInstance(result, pdml.ModelSeries)
self.assert_numpy_array_almost_equal(result.values, expected)
tm.assert_index_equal(result.index, s.index)
mod1 = s.pp.LabelEncoder()
result = s.fit_transform(mod1)
self.assertIsInstance(result, pdml.ModelSeries)
self.assert_numpy_array_almost_equal(result.values, expected)
inversed = result.inverse_transform(mod1)
self.assertIsInstance(inversed, pdml.ModelSeries)
tm.assert_series_equal(inversed, s)
def test_frame_init_dict_list(self):
# initialization by dataframe and list
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = [1, 2, 3]
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
df = {'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]}
s = [1, 2, 3]
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index([0, 1, 2]))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
expected = pd.DataFrame(df)
tm.assert_frame_equal(mdf.data, expected)
expected = pd.Series([1, 2, 3], index=[0, 1, 2], name='.target')
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
mdf = pdml.ModelFrame(df, target='A')
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index([0, 1, 2]))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
expected = pd.DataFrame(df)
tm.assert_frame_equal(mdf.data, expected[['B', 'C']])
tm.assert_series_equal(mdf.target, expected['A'])
self.assertEqual(mdf.target.name, 'A')
self.assertEqual(mdf.target_name, 'A')
mdf = pdml.ModelFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, mdf)
self.assertEqual(mdf.target_name, '.target')
def test_frame_init_df_series(self):
# initialization by dataframe and no-named series
df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B',
'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
s = pd.Series([1, 2, 3])
with pytest.raises(ValueError,
match='data and target must have equal index'):
mdf = pdml.ModelFrame(df, target=s)
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='XXX')
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['XXX', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, 'XXX')
self.assertEqual(mdf.target_name, 'XXX')
def test_frame_data_proparty(self):
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
new = pd.DataFrame({'X': [1, 2, 3],
'Y': [4, 5, 6]},
index=['a', 'b', 'c'],
columns=['X', 'Y'])
# set data property
mdf.data = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'X', 'Y']))
tm.assert_frame_equal(mdf.data, new)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
new = pdml.ModelFrame({'M': [1, 2, 3],
'N': [4, 5, 6]},
index=['a', 'b', 'c'],
columns=['M', 'N'])
# set data property
mdf.data = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'M', 'N']))
tm.assert_frame_equal(mdf.data, new)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
new = pd.DataFrame({'.target': [1, 2, 3],
'K': [4, 5, 6]},
index=['a', 'b', 'c'])
# unable to set data if passed value has the same column as the target
msg = "Passed data has the same column name as the target '.target'"
with self.assertRaisesRegexp(ValueError, msg):
mdf.data = new
# unable to set ModelFrame with target attribute
msg = "Cannot update with ModelFrame which has target attribute"
with self.assertRaisesRegexp(ValueError, msg):
mdf.data = mdf
# set delete property
del mdf.data
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 1))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target']))
self.assertTrue(mdf.data is None)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
def test_frame_init_dict_list(self):
# initialization by dataframe and list
df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = [1, 2, 3]
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B',
'C']))
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
df = {'A': [1, 2, 3], 'B': [4, 5, 6], 'C': [7, 8, 9]}
s = [1, 2, 3]
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index([0, 1, 2]))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B',
'C']))
expected = pd.DataFrame(df)
tm.assert_frame_equal(mdf.data, expected)
expected = pd.Series([1, 2, 3], index=[0, 1, 2], name='.target')
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
mdf = pdml.ModelFrame(df, target='A')
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index([0, 1, 2]))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
expected = pd.DataFrame(df)
tm.assert_frame_equal(mdf.data, expected[['B', 'C']])
tm.assert_series_equal(mdf.target, expected['A'])
self.assertEqual(mdf.target.name, 'A')
self.assertEqual(mdf.target_name, 'A')
mdf = pdml.ModelFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, mdf)
self.assertEqual(mdf.target_name, '.target')
def test_frame_target_proparty(self):
df = pd.DataFrame({'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=s)
new = pd.Series([4, 5, 6], index=['a', 'b', 'c'], name='.target')
# set target property
mdf.target = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_series_equal(mdf.target, new)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
with tm.assert_produces_warning(UserWarning):
new = pd.Series([4, 5, 6], index=['a', 'b', 'c'], name='xxx')
# set target property
mdf.target = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
exp_target = pd.Series(new, name='.target')
tm.assert_series_equal(mdf.target, exp_target)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
new = pd.Series([4, 5, 6], name='.target')
with self.assertRaisesRegexp(ValueError, 'data and target must have equal index'):
mdf.target = new
# set target property
mdf.target = [7, 8, 9]
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series([7, 8, 9], index=['a', 'b', 'c'], name='.target')
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
with self.assertRaisesRegexp(ValueError, 'Wrong number of items passed 2, placement implies 3'):
mdf.target = [1, 2]
# set target property
mdf.target = None
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
self.assertEqual(mdf.target_name, '.target')
def test_frame_target_proparty(self):
df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'])
mdf = pdml.ModelFrame(df, target=s)
new = pd.Series([4, 5, 6], index=['a', 'b', 'c'], name='.target')
# set target property
mdf.target = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B',
'C']))
tm.assert_frame_equal(mdf.data, df)
tm.assert_series_equal(mdf.target, new)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
with tm.assert_produces_warning(UserWarning):
new = pd.Series([4, 5, 6], index=['a', 'b', 'c'], name='xxx')
# set target property
mdf.target = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns,
pd.Index(['.target', 'A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
exp_target = pd.Series(new, name='.target')
tm.assert_series_equal(mdf.target, exp_target)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
new = pd.Series([4, 5, 6], name='.target')
with pytest.raises(ValueError,
match='data and target must have equal index'):
mdf.target = new
# set target property
mdf.target = [7, 8, 9]
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 4))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'A', 'B',
'C']))
tm.assert_frame_equal(mdf.data, df)
expected = pd.Series([7, 8, 9], index=['a', 'b', 'c'], name='.target')
tm.assert_series_equal(mdf.target, expected)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
if pdml.compat._PANDAS_ge_023:
msg = 'Length of passed values is 2, index implies 3'
else:
msg = 'Wrong number of items passed 2, placement implies 3'
with pytest.raises(ValueError, match=msg):
mdf.target = [1, 2]
# set target property
mdf.target = None
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['A', 'B', 'C']))
tm.assert_frame_equal(mdf.data, df)
self.assertEqual(mdf.target_name, '.target')
def test_frame_data_proparty(self):
df = pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6],
'C': [7, 8, 9]
},
index=['a', 'b', 'c'],
columns=['A', 'B', 'C'])
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'], name='.target')
mdf = pdml.ModelFrame(df, target=s)
self.assertIsInstance(mdf, pdml.ModelFrame)
new = pd.DataFrame({
'X': [1, 2, 3],
'Y': [4, 5, 6]
},
index=['a', 'b', 'c'],
columns=['X', 'Y'])
# set data property
mdf.data = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'X', 'Y']))
tm.assert_frame_equal(mdf.data, new)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
new = pdml.ModelFrame({
'M': [1, 2, 3],
'N': [4, 5, 6]
},
index=['a', 'b', 'c'],
columns=['M', 'N'])
# set data property
mdf.data = new
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 3))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target', 'M', 'N']))
tm.assert_frame_equal(mdf.data, new)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
new = pd.DataFrame({
'.target': [1, 2, 3],
'K': [4, 5, 6]
},
index=['a', 'b', 'c'])
# unable to set data if passed value has the same column as the target
msg = "Passed data has the same column name as the target '.target'"
with pytest.raises(ValueError, match=msg):
mdf.data = new
# unable to set ModelFrame with target attribute
msg = "Cannot update with ModelFrame which has target attribute"
with pytest.raises(ValueError, match=msg):
mdf.data = mdf
# set delete property
del mdf.data
self.assertIsInstance(mdf, pdml.ModelFrame)
self.assertEqual(mdf.shape, (3, 1))
tm.assert_index_equal(mdf.index, pd.Index(['a', 'b', 'c']))
tm.assert_index_equal(mdf.columns, pd.Index(['.target']))
self.assertTrue(mdf.data is None)
tm.assert_series_equal(mdf.target, s)
self.assertEqual(mdf.target.name, '.target')
self.assertEqual(mdf.target_name, '.target')
