def test_intersection_of_index(self):
df1 = pd.DataFrame({}, index=[1, 2, 3, 4])
df2 = pd.DataFrame({}, index=[2, 3, 4])
df3 = pd.DataFrame({}, index=[1, 3, 4])
index = intersection_of_index(df1, df2, df3)
self.assertListEqual([3, 4], index.tolist())
def test_intersection_of_tuples(self):
df1 = pd.DataFrame({}, index=[1, 2, 3, 4])
df2 = pd.DataFrame({}, index=[2, 3, 4])
df3 = pd.DataFrame({}, index=[1, 3, 4])
index1 = intersection_of_index(df1,
MultiFrameDecorator([df2, df3], True))
index2 = intersection_of_index(MultiFrameDecorator([df1, df2], True),
df3)
self.assertListEqual([3, 4], index1.tolist())
self.assertListEqual([3, 4], index2.tolist())
def test_similar_columns_multi_index(self):
df1 = pd.DataFrame({},
index=[1, 2, 3, 4],
columns=pd.MultiIndex.from_product([["a", "b"],
range(3)]))
df2 = pd.DataFrame({},
index=[1, 2, 3, 4],
columns=pd.MultiIndex.from_tuples([
("a", 1), ("a", 2), ("b", 1), ("b", 3)
]))
self.assertTrue(same_columns_after_level(df1))
self.assertFalse(same_columns_after_level(df2))
def trails(self):
"""
In case of hyper parameter optimization a trails object as used by `Hyperopt <https://github.com/hyperopt/hyperopt/wiki/FMin>`_
is available.
:return: Trails object
"""
if self._trails is not None:
return pd.DataFrame(self._trails.results)\
.drop("parameter", axis=1)\
.join(pd.DataFrame([r['parameter'] for r in self._trails.results]))
else:
return None
def map_prediction_to_target(df, prediction, targets):
def _round(val, d):
return round(val, d) if isinstance(val, float) else val
dfp = get_pandas_object(df, prediction)
p = dfp._.values.reshape((len(df), -1))
dft = get_pandas_object(df, targets)
t = dft._.values.reshape((len(df), -1))
if p.shape[1] == t.shape[1]:
# 1:1 mapping
index = [(date, _round(target, 2)) for date in df.index for target in dft.loc[date].values]
elif p.shape[1] == t.shape[1] - 1:
# we need to build ranges
def build_tuples(l):
return [(_round(l[i - 1], 2), _round(l[i], 2)) for i in range(1, len(l))]
index = [(date, f"{target}") for date in df.index for target in
build_tuples(dft.loc[date].tolist())]
elif p.shape[1] == t.shape[1] + 1:
# mapping of the left and right extremes using +/- inf
def build_tuples(l):
l = [-np.inf, *l, np.inf]
return [(_round(l[i - 1], 2), _round(l[i], 2)) for i in range(1, len(l))]
index = [(date, target) for date in df.index for target in
build_tuples(dft.loc[date]._.values.tolist())]
else:
raise ValueError(f"unable to match {p.shape[1]} predictions to {t.shape[1]} +/-1 targets")
return pd.DataFrame({"prediction": p.reshape((-1,))},
index=pd.MultiIndex.from_tuples(index))
def test_call_if_not_none(self):
df1 = pd.DataFrame({"a": [np.nan]})
df2 = None
self.assertIsNone(call_if_not_none(df2, 'dropna'))
self.assertEqual(0, len(call_if_not_none(df1, 'dropna')))
self.assertEqual(1, len(df1))
def test_get_pandas_obj(self):
df = pd.DataFrame({"hallo": [1, 2, 3]})
dfmi = df.copy()
dfmi.columns = pd.MultiIndex.from_product([["a"], dfmi.columns])
self.assertIsNone(get_pandas_object(df, None))
self.assertListEqual([1, 2, 3],
get_pandas_object(df, "hallo").to_list())
self.assertListEqual([9, 9, 9],
get_pandas_object(df, Constant(9)).to_list())
self.assertListEqual(
[2., 4., 6.],
get_pandas_object(
df, 2.0, {
float: lambda df, item, **kwargs: df["hallo"] * item
}).to_list())
self.assertListEqual([2, 4, 6],
get_pandas_object(df, df["hallo"] * 2).to_list())
self.assertListEqual([2, 4, 6],
get_pandas_object(
df, lambda df: df["hallo"] * 2).to_list())
self.assertEqual((3, 0), get_pandas_object(df, "allo").shape)
self.assertListEqual([1, 2, 3],
get_pandas_object(dfmi,
"hallo").iloc[:, 0].to_list())
self.assertListEqual([1, 2, 3],
get_pandas_object(dfmi, "a").iloc[:, 0].to_list())
self.assertListEqual([1, 2, 3],
get_pandas_object(dfmi,
".*ll.*").iloc[:, 0].to_list())
self.assertEqual((3, 0), get_pandas_object(dfmi, "allo").shape)
def test_partial_fit_classification(self):
data = make_classification(100, 2, 1, 0, n_clusters_per_class=1)
df = pd.DataFrame(data[0])
df["label"] = data[1]
with df.model() as m:
fit_partial = m.fit(
SkModel(
MLPClassifier(max_iter=1, random_state=42),
FeaturesAndLabels(features=[0, 1], labels=['label']),
classes=np.unique(data[1])
),
FittingParameter(
stratified_random_splitter(0.3),
batch_size=10,
fold_epochs=10,
)
)
with df.model() as m:
fit = m.fit(
SkModel(
MLPClassifier(max_iter=10, random_state=42),
FeaturesAndLabels(features=[0, 1], labels=['label'])
),
FittingParameter(stratified_random_splitter(0.3))
)
self.assertAlmostEqual(df.model.predict(fit.model).iloc[0,-1], df.model.predict(fit_partial.model).iloc[0,-1], 4)
def test_multindex_row_multi_samples(self):
"""given some toy regression data while we provide a multiindex for the rows"""
df = pd.DataFrame(
{
"a":
[-1.0, 0.0, 1.0, 2.0, 3.0, 4.0, -1.0, 0.0, 1.0, 2.0, 3.0, 4.0],
"b": [
-2.0, 1.0, 4.0, 7.0, 10.0, 13.0, -2.0, 1.0, 4.0, 7.0, 10.0,
13.0
]
},
index=pd.MultiIndex.from_product([["A", "B"], range(6)]))
"""and a model"""
model = self.provide_regression_model(
FeaturesAndLabels(features=["a"], labels=["b"]))
"""when we fit the model"""
batch_size, epochs = self.provide_batch_size_and_epoch()
with df.model() as m:
fit = m.fit(model,
FittingParameter(splitter=random_splitter(
0.3, partition_row_multi_index=True),
batch_size=batch_size,
epochs=epochs),
verbose=0)
self.assertEqual(8, len(fit.training_summary.df))
self.assertEqual(4, len(fit.test_summary.df))
prediction = df.model.predict(fit.model, samples=2)
self.assertEqual(2, len(prediction.iloc[:, 0]._.values))
self.assertEqual((6, 2), prediction.loc["A"].iloc[:, 0]._.values.shape)
self.assertEqual((6, 2), prediction.loc["B"].iloc[:, 0]._.values.shape)
def test__item_multi_index(self):
df = pd.DataFrame({},
columns=pd.MultiIndex.from_product([[a_x, b_x, c_x],
[a_y, b_y,
c_y]]))
# pandas_ml_common_test ordinary access single
for col in df.columns.tolist():
self.assertEqual(col, df._[col].name)
# pandas_ml_common_test ordinary access multi
cols = []
for col in df.columns.tolist():
cols.append(col)
self.assertEqual(cols, df._[cols].columns.tolist())
# pandas_ml_common_test 1st level
self.assertListEqual([a_y, b_y, c_y], df._[a_x].columns.tolist())
# pandas_ml_common_test 2nd level
self.assertListEqual([(b_y, a_x), (b_y, b_x), (b_y, c_x)],
df._[b_y].columns.tolist())
# pandas_ml_common_test regex
self.assertListEqual([(a_x, a_y), (a_x, b_y), (a_x, c_y), (b_x, a_y),
(c_x, a_y)], df._["a_."].columns.tolist())
def test_regressor(self):
"""given some toy regression data"""
df = pd.DataFrame({
"a": [-1.0, 0.0, 1.0, 2.0, 3.0, 4.0],
"b": [-2.0, 1.0, 4.0, 7.0, 10.0, 13.0]
})
"""and a model"""
model = self.provide_regression_model(
FeaturesAndLabels(features=["a"], labels=["b"]))
"""when we fit the model"""
fit = df.model.fit(model, RandomSplits(0.3), verbose=0, epochs=500)
print(fit.training_summary.df)
"""then we can predict"""
prediction = df.model.predict(fit.model)
np.testing.assert_array_almost_equal(prediction.iloc[:, 0].values,
df["b"].values, 1)
"""and save and load the model"""
temp = os.path.join(tempfile.gettempdir(), str(uuid.uuid4()))
try:
fit.model.save(temp)
copy = Model.load(temp)
pd.testing.assert_frame_equal(df.model.predict(fit.model),
df.model.predict(copy),
check_less_precise=True)
finally:
os.remove(temp)
def test_custom_objects(self):
df = pd.DataFrame({
"a": [-1.0, 0.0, 1.0, 2.0, 3.0, 4.0],
"b": [-2.0, 1.0, 4.0, 7.0, 10.0, 13.0]
})
def model_provider():
model = Sequential([Dense(units=1, input_shape=(1, ))])
model.compile(optimizer='sgd', loss=custom_loss_function)
return model, custom_loss_function
model = KerasModel(
model_provider,
FeaturesAndLabels(["a"], ["b"]),
)
fit = df.model.fit(model)
temp = os.path.join(tempfile.gettempdir(), str(uuid.uuid4()))
try:
fit.model.save(temp)
copy = Model.load(temp)
pd.testing.assert_frame_equal(df.model.predict(fit.model),
df.model.predict(copy),
check_less_precise=True)
finally:
os.remove(temp)
def test_partial_fit_regression(self):
data = make_regression(100, 2, 1)
df = pd.DataFrame(data[0])
df["label"] = data[1]
with df.model() as m:
fit_partial = m.fit(
SkModel(
MLPRegressor(max_iter=1, random_state=42),
FeaturesAndLabels(features=[0, 1], labels=['label'])
),
FittingParameter(
naive_splitter(0.3),
batch_size=10,
fold_epochs=10
)
)
with df.model() as m:
fit = m.fit(
SkModel(
MLPRegressor(max_iter=10, random_state=42),
FeaturesAndLabels(features=[0, 1], labels=['label'])
),
FittingParameter(naive_splitter(0.3))
)
self.assertAlmostEqual(df.model.predict(fit.model).iloc[0,-1], df.model.predict(fit_partial.model).iloc[0,-1], 4)
def _gross_confusion(self):
cm = np.empty(self.confusion_indices.shape)
for i in np.ndindex(cm.shape):
cm[i] = self.df_gross_loss["loss"].loc[
self.confusion_indices[i]].clip(
upper=self.clip_profit_at).mean()
return pd.DataFrame(cm)
def test_multi_model(self):
"""given some toy classification data"""
df = pd.DataFrame({
"a": [
1,
0,
1,
0,
1,
0,
1,
0,
],
"b": [
0,
0,
1,
1,
0,
0,
1,
1,
],
"c": [
1,
0,
0,
1,
1,
0,
0,
1,
],
})
model = MultiModel(SkModel(
MLPClassifier(activation='logistic',
max_iter=1000,
hidden_layer_sizes=(3, ),
alpha=0.001,
solver='lbfgs',
random_state=42),
FeaturesAndLabels(features=["a", "b"],
labels=[lambda df, i: df["c"].rename(f"c_{i}")],
label_type=int),
summary_provider=ClassificationSummary),
2,
model_index_variable="i",
summary_provider=MultiModelSummary)
fit = df.model.fit(model,
NaiveSplitter(0.49),
epochs=1500,
verbose=True)
print(fit.training_summary._repr_html_()[:100])
pdf = df.model.predict(fit.model, tail=2)
print(pdf)
def _init(self) -> Tuple[np.ndarray, np.ndarray]:
# this is reinforcement learning, we can only extract features (no labels)!
self._symbol = np.random.choice(self.symbols, 1).item()
self._df = self.cache.get_data_or_fetch(self._symbol)
self._features, self._features_index = self.cache.get_feature_frames_or_fetch(
self._df, self._symbol, self.features_and_labels)
self._is_feature_tuple = isinstance(self._features, tuple)
nr_of_samples = len(
self._features[0]) if self._is_feature_tuple else len(
self._features)
if self.mode in ['train', 'test']:
if self.mode == 'train':
self._last_index = int(nr_of_samples * 0.8)
# allow at least one step
self._state_idx = np.random.randint(1, self._last_index - 1,
1).item()
if self.mode == 'test':
self._last_index = nr_of_samples
# if min samples is infinity then we start from the first index of the test data
test_start_idx = int(nr_of_samples * 0.8)
test_end_idx = min(nr_of_samples - self.min_training_samples,
test_start_idx + 1)
self._state_idx = np.random.randint(test_start_idx,
test_end_idx, 1).item()
else:
self._last_index = nr_of_samples
self._labels = pd.DataFrame({})
self._sample_weights = pd.DataFrame({})
self._gross_loss = pd.DataFrame({})
self._state_idx = 0
if self.observation_space is None:
self.observation_space = gym.spaces.Tuple(
(SpaceUtils.unbounded_tuple_boxes(
*[f.shape[1:]
for f in self._features]) if self._is_feature_tuple else
SpaceUtils.unbounded_box(self._features.shape[1:]),
SpaceUtils.unbounded_box(
self.strategy.current_state().shape)))
self._start_idx = self._state_idx
self.done = self._state_idx >= self._last_index
return self._current_state()
def test_auto_encoder(self):
"""given the implementation can handle auto encoders"""
model = self.provide_auto_encoder_model(
FeaturesAndLabels(["a", "b"], ["a", "b"]))
if model is None:
return
"""and some toy classification data"""
df = pd.DataFrame({
"a": [
1,
0,
1,
0,
],
"b": [
0,
1,
0,
1,
],
})
"""when we fit the model"""
fit = df.model.fit(model, NaiveSplitter(0.49), verbose=0, epochs=500)
print(fit.training_summary.df)
"""then we can encoder"""
encoded_prediction = df.model.predict(fit.model.as_encoder())
print(encoded_prediction)
"""and we can decoder"""
decoder_features = encoded_prediction.columns.to_list()[0:1]
decoded_prediction = encoded_prediction.model.predict(
fit.model.as_decoder(decoder_features))
print(decoded_prediction)
np.testing.assert_array_almost_equal(
decoded_prediction["prediction"].values > 0.5, df[["a",
"b"]].values)
"""and we can encoder and decore after safe and load"""
temp = os.path.join(tempfile.gettempdir(), str(uuid.uuid4()))
try:
fit.model.save(temp)
copy = Model.load(temp)
pd.testing.assert_frame_equal(df.model.predict(
fit.model.as_encoder()),
df.model.predict(copy.as_encoder()),
check_less_precise=True)
pd.testing.assert_frame_equal(
encoded_prediction.model.predict(
fit.model.as_decoder(decoder_features)),
encoded_prediction.model.predict(
copy.as_decoder(decoder_features)),
check_less_precise=True)
finally:
os.remove(temp)
def test_make_training_data(self):
"""given"""
df = pd.DataFrame({
"featureA": [1, 2, 3, 4, 5],
"labelA": [1, 2, 3, 4, 5]
})
"""when"""
train_ix, test_ix = random_splitter(test_size=0.5)(df.index)
"""then"""
self.assertEqual(2, len(train_ix))
self.assertEqual(3, len(test_ix))
def test_multi_index_nested_values(self):
df = pd.DataFrame(
{
("A", "a"): [1, 2, 3, 4, 5],
("A", "b"): [3, 2, 1, 0, 0],
("A", "c"): [3, 2, 1, 0, 0],
("B", "a"): [1, 2, 3, 1, 2],
("B", "b"): [3, 2, 1, 0, 1],
("B", "c"): [3, 2, 1, 0, 1],
("C", "a"): [
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4))
],
("C", "b"): [
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4))
],
("C", "c"): [
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4))
],
("D", "a"): [
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4)),
np.ones((2, 4))
],
},
index=[1, 2, 3, 4, 5],
)
df.columns = pd.MultiIndex.from_tuples(df.columns.tolist())
"""when"""
print(df)
rnnShape = df[["A"]].ml.values
rnnShape2 = df[["A", "B"]].ml.values
rnnShapeExt = df["C"].ml.values
labelShape = df["D"].ml.values
"""then"""
print(rnnShape.shape, rnnShape2.shape, rnnShapeExt.shape,
labelShape.shape)
self.assertEqual((5, 1, 3), rnnShape.shape)
self.assertEqual((5, 2, 3), rnnShape2.shape)
self.assertEqual((5, 3, 2, 4), rnnShapeExt.shape)
self.assertEqual((5, 1, 2, 4), labelShape.shape)
def test_naive_splitter(self):
"""given"""
df = pd.DataFrame({
"featureA": [1, 2, 3, 4, 5],
"labelA": [1, 2, 3, 4, 5]
})
"""when"""
train_ix, test_ix = naive_splitter(0.3)(df.index)
"""then"""
print(train_ix, test_ix)
self.assertListEqual([0, 1, 2], train_ix.tolist())
self.assertListEqual([3, 4], test_ix.tolist())
def test_youngest_portion(self):
"""given"""
df = pd.DataFrame({
"featureA": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
"labelA": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
})
"""when"""
train_ix, test_ix = random_splitter(test_size=0.6,
youngest_size=0.25)(df.index)
"then"
self.assertEqual(6, len(test_ix))
np.testing.assert_array_equal(test_ix[-2:], np.array([8, 9]))
def test_no_training_data(self):
"""given"""
df = pd.DataFrame({
"featureA": [1, 2, 3, 4, 5],
"labelA": [1, 2, 3, 4, 5]
})
"""when"""
train_ix, test_ix = random_splitter(0)(df.index)
train_ix2, test_ix2 = dummy_splitter(df.index)
"""then"""
np.testing.assert_array_almost_equal(train_ix.values, df.index.values)
np.testing.assert_array_almost_equal(train_ix.values, train_ix2.values)
self.assertEqual(0, len(test_ix))
def test_stratified_random_splitter(self):
"""given"""
df = pd.DataFrame({
"featureA": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
"labelA": [1, 1, 1, 1, 1, 1, 2, 2, 3, 3]
})
"""when"""
train_ix, test_ix = stratified_random_splitter(test_size=0.5)(
df.index, y=df[["labelA"]])
"""then each class is represented similarly often in each train and test set"""
self.assertIn(2, df.loc[train_ix, "labelA"].to_list())
self.assertIn(3, df.loc[train_ix, "labelA"].to_list())
self.assertIn(2, df.loc[test_ix, "labelA"].to_list())
self.assertIn(3, df.loc[test_ix, "labelA"].to_list())
def test_naive_splitter_multi_index_row(self):
"""given"""
df = pd.DataFrame({"featureA": range(10), "labelA": range(10)})
df.index = pd.MultiIndex.from_product([["A", "B"], range(5)])
"""when"""
train_ix, test_ix = naive_splitter(
0.3, partition_row_multi_index=True)(df.index)
"""then"""
print(train_ix.tolist(), test_ix.tolist())
self.assertListEqual([('A', 0), ('A', 1), ('A', 2), ('B', 0), ('B', 1),
('B', 2)], train_ix.tolist())
self.assertListEqual([('A', 3), ('A', 4), ('B', 3), ('B', 4)],
test_ix.tolist())
def test_random_splitter_multi_index_row(self):
"""given"""
df = pd.DataFrame({"featureA": range(10), "labelA": range(10)})
df.index = pd.MultiIndex.from_product([["A", "B"], range(5)])
"""when"""
train_ix, test_ix = random_splitter(test_size=0.6,
youngest_size=0.25,
partition_row_multi_index=True)(
df.index)
print(train_ix.tolist(), test_ix.tolist())
"""then"""
self.assertEqual(8, len(test_ix))
self.assertIn(('A', 4), test_ix)
self.assertIn(('B', 4), test_ix)
def test_add_multi_index(self):
df = pd.DataFrame({}, index=[1, 2, 3, 4])
df1 = add_multi_index(df, "A", axis=0)
df2 = add_multi_index(df1, "B", axis=0, level=1)
df3 = add_multi_index(df1, "B", axis=0, level=2)
# print(df3)
self.assertListEqual(df1.index.to_list(), [("A", 1), ("A", 2),
("A", 3), ("A", 4)])
self.assertListEqual(df2.index.to_list(),
[("A", "B", 1), ("A", "B", 2), ("A", "B", 3),
("A", "B", 4)])
self.assertListEqual(df3.index.to_list(),
[(1, "A", "B"), (2, "A", "B"), (3, "A", "B"),
(4, "A", "B")])
def test__item_normal_index(self):
df = pd.DataFrame({}, columns=[a_x, b_y, c_y])
# pandas_ml_common_test ordinary access
for col in df.columns.tolist():
self.assertEqual(col, df._[col].name)
# pandas_ml_common_test ordinary access multi
cols = []
for col in df.columns.tolist():
cols.append(col)
self.assertEqual(cols, df._[cols].columns.tolist())
# pandas_ml_common_test regex
self.assertListEqual([a_x], df._["a_."].columns.tolist())
self.assertListEqual([b_y, c_y], df._["..y"].columns.tolist())
def test_stratified_random_splitter_multi_index_row(self):
"""given"""
df = pd.DataFrame({
"featureA": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] * 2,
"labelA": [1, 1, 1, 1, 1, 1, 2, 2, 3, 3] * 2
})
df.index = pd.MultiIndex.from_product([["A", "B"], range(10)])
"""when"""
train_ix, test_ix = stratified_random_splitter(
test_size=0.5, partition_row_multi_index=True)(df.index,
y=df[["labelA"]])
print(train_ix.tolist(), test_ix.tolist())
"""then each class is represented similarly often in each train and test set"""
self.assertIn(2, df.loc[train_ix, "labelA"].to_list())
self.assertIn(3, df.loc[train_ix, "labelA"].to_list())
self.assertIn(2, df.loc[test_ix, "labelA"].to_list())
self.assertIn(3, df.loc[test_ix, "labelA"].to_list())
def test_lag_smoothing_nan(self):
"""given"""
df = pd.DataFrame({"featureA": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})
# 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] # original
# 1, 2, 3, 4, 5, 6, 7, 8, 9] # lag 1
# 1, 2, 3, 4, 5, 6, 7] # lag 1 + shift 2
# ^ # this is where the df starts
"""when lag smoothing is enabled using shift (which is introducing nan into the data frame)"""
rnn = lag_columns(df[["featureA"]],
feature_lags=[0, 1],
lag_smoothing={
1: lambda df: df["featureA"].shift(2)
}).dropna()
"""then"""
self.assertAlmostEqual(rnn[0, "featureA"].iloc[0], 4)
self.assertAlmostEqual(rnn[1, "featureA"].iloc[0], 1.0)
self.assertAlmostEqual(rnn[0, "featureA"].iloc[-1], 10)
self.assertAlmostEqual(rnn[1, "featureA"].iloc[-1], 7.0)
def __init__(self,
df: Typing.PatchedDataFrame,
clip_profit_at=0,
classes=None,
**kwargs):
super().__init__(df)
self.clip_profit_at = clip_profit_at
self.targets = df[TARGET_COLUMN_NAME]
# calculate confusion indices
truth, prediction = self._fix_label_prediction_representation()
distinct_values = len({*truth.reshape(
(-1, ))}) if classes is None else classes
cm = empty_lists((distinct_values, distinct_values))
for i, (t, p) in enumerate(zip(truth, prediction)):
cm[int(t), int(p)].append(self.df.index[i])
self.confusion_indices = cm
# we can calculate the gross loss from the predicted band and the true price,
# therefore we need to pass the true price as gross loss such that we calculate the real loss
self.df_gross_loss = pd.DataFrame(
{
"bucket":
df[[TARGET_COLUMN_NAME]].apply(get_buckets, axis=1, raw=True),
"pidx":
df.apply(
lambda r: int(r[PREDICTION_COLUMN_NAME]._.values.argmax()),
axis=1,
raw=False),
"price":
df[GROSS_LOSS_COLUMN_NAME].values[:, 0]
},
index=df.index)
# find target for predicted value
mid = self.targets.shape[1] / 2.0
self.df_gross_loss["loss"] = self.df_gross_loss.apply(
lambda r: (r["price"] - r["bucket"][r["pidx"]][0])
if r["pidx"] <= mid else (r["bucket"][r["pidx"]][1] - r["price"]),
axis=1,
raw=False).fillna(0)