def randFor(rData, lData):
randClass = RandomForestClassifier(n_estimators = 100)
respTrain, respTest, labTrain, labTest = train_test_split(rData, lData, random_state=1)
vect = TfidfVectorizer(min_df=1, max_df=1.0, stop_words='english')
respTrainVec = vect.fit_transform(respTrain)
# To be commented for Pickle Building of Vectorizer
respTestVec = vect.transform(respTest)
randClass.fit(respTrainVec, labTrain)
# To be commented for Pickle Building of Rand Class Model
labPredClass = randClass.predict(respTestVec)
#display(HTML(eli5.show_weights(randClass, top=5)))
#print type(eli5.explain_prediction(randClass, respTest[0], vec=vect, target_names=targetList))
#tDF = eli5.explain_prediction_df(randClass)
#tDF1 = eli5.show_weights(randClass, vec=vect, target_names=targetList)
#print type(eli5.show_prediction(randClass, respTest[0], vec=vect, target_names=targetList))
# Explain the Weights of this Estimator ----------------------------------
#print eli5.explain_weights(randClass)
print eli5.format_as_dataframes(eli5.show_weights(randClass))
print respTest[0]
#prediction = eli5.explain_prediction (randClass, respTest[0], vec=vect, target_names=targetList, top=5)
#weigths = eli5.explain_prediction (randClass, respTest[0], vec=vect, target_names=targetList, top=5)
#print ( eli5.format_as_dataframes( weigths ) )
# Modify to return specfic class types
return (metrics.accuracy_score(labTest, labPredClass))
def test_feature_importances(with_std, with_value):
expl = Explanation(estimator='some estimator',
feature_importances=FeatureImportances(
importances=[
FeatureWeight('a',
1,
std=0.1 if with_std else None,
value=1 if with_value else None),
FeatureWeight('b',
2,
std=0.2 if with_std else None,
value=3 if with_value else None),
],
remaining=10,
))
df_dict = format_as_dataframes(expl)
assert isinstance(df_dict, dict)
assert list(df_dict) == ['feature_importances']
df = df_dict['feature_importances']
expected_df = pd.DataFrame({'weight': [1, 2]}, index=['a', 'b'])
if with_std:
expected_df['std'] = [0.1, 0.2]
if with_value:
expected_df['value'] = [1, 3]
print(df, expected_df, sep='\n')
assert expected_df.equals(df)
single_df = format_as_dataframe(expl)
assert expected_df.equals(single_df)
def test_transition_features():
expl = Explanation(
estimator='some estimator',
targets=[
TargetExplanation('class1',
feature_weights=FeatureWeights(
pos=[FeatureWeight('pos', 13, value=1)],
neg=[],
)),
TargetExplanation('class2',
feature_weights=FeatureWeights(
pos=[FeatureWeight('pos', 13, value=1)],
neg=[],
)),
],
transition_features=TransitionFeatureWeights(
class_names=['class2', 'class1'], # reverse on purpose
coef=np.array([[1.5, 2.5], [3.5, 4.5]]),
))
df_dict = format_as_dataframes(expl)
assert isinstance(df_dict, dict)
assert set(df_dict) == {'targets', 'transition_features'}
assert df_dict['targets'].equals(format_as_dataframe(expl.targets))
df = df_dict['transition_features']
print(df)
print(format_as_text(expl))
assert str(df) == ('to class2 class1\n'
'from \n'
'class2 1.5 2.5\n'
'class1 3.5 4.5')
with pytest.warns(UserWarning):
single_df = format_as_dataframe(expl)
assert single_df.equals(df)
def transition_features(self):
data_frame = eli5.format_as_dataframes(
eli5.explain_weights_sklearn_crfsuite(self.crf))
return list(
zip(data_frame['transition_features']['from'],
data_frame['transition_features']['coef'],
data_frame['transition_features']['to']))
def test_sklearn_crfsuite(xseq, yseq):
crf = CRF(c1=0.0, c2=0.1, max_iterations=50)
crf.fit([xseq], [yseq])
expl = explain_weights(crf)
text, html = format_as_all(expl, crf)
assert "y='sunny' top features" in text
assert "y='rainy' top features" in text
assert "Transition features" in text
assert "sunny -0.130 0.696" in text
assert u'+0.124 солнце:не светит' in text
html_nospaces = html.replace(' ', '').replace("\n", '')
assert u'солнце:не светит' in html
assert '<th>rainy</th><th>sunny</th>' in html_nospaces
try:
from eli5 import format_as_dataframe, format_as_dataframes
except ImportError:
pass
else:
from .test_formatters_as_dataframe import check_targets_dataframe
df_dict = format_as_dataframes(expl)
check_targets_dataframe(df_dict['targets'], expl)
df_transition = df_dict['transition_features']
transition = expl.transition_features
print(df_transition)
assert list(transition.class_names) == ['rainy', 'sunny']
assert np.isclose(df_transition['rainy']['rainy'], transition.coef[0,
0])
assert np.isclose(df_transition['sunny']['rainy'], transition.coef[0,
1])
assert np.isclose(df_transition['rainy']['sunny'], transition.coef[1,
0])
def weight_targets(self):
data_frame = eli5.format_as_dataframes(
eli5.explain_weights_sklearn_crfsuite(self.crf, top=2**10000))
return list(
zip(data_frame['targets']['target'],
data_frame['targets']['feature'],
data_frame['targets']['weight']))
def test_targets(with_std, with_value):
expl = Explanation(
estimator='some estimator',
targets=[
TargetExplanation(
'y',
feature_weights=FeatureWeights(
pos=[
FeatureWeight('a',
13,
std=0.13 if with_std else None,
value=2 if with_value else None),
FeatureWeight('b',
5,
std=0.5 if with_std else None,
value=1 if with_value else None)
],
neg=[
FeatureWeight('neg1',
-10,
std=0.2 if with_std else None,
value=5 if with_value else None),
FeatureWeight('neg2',
-1,
std=0.3 if with_std else None,
value=4 if with_value else None)
],
)),
TargetExplanation('y2',
feature_weights=FeatureWeights(
pos=[FeatureWeight('f', 1)],
neg=[],
)),
],
)
df_dict = format_as_dataframes(expl)
assert isinstance(df_dict, dict)
assert list(df_dict) == ['targets']
df = df_dict['targets']
expected_df = pd.DataFrame(
{
'target': ['y', 'y', 'y', 'y', 'y2'],
'feature': ['a', 'b', 'neg2', 'neg1', 'f'],
'weight': [13, 5, -1, -10, 1]
},
columns=['target', 'feature', 'weight'])
if with_std:
expected_df['std'] = [0.13, 0.5, 0.3, 0.2, None]
if with_value:
expected_df['value'] = [2, 1, 4, 5, None]
print(df, expected_df, sep='\n')
assert expected_df.equals(df)
single_df = format_as_dataframe(expl)
assert expected_df.equals(single_df)
def test_transition_features():
expl = Explanation(
estimator='some estimator',
targets=[
TargetExplanation('class1',
feature_weights=FeatureWeights(
pos=[FeatureWeight('pos', 13, value=1)],
neg=[],
)),
TargetExplanation('class2',
feature_weights=FeatureWeights(
pos=[FeatureWeight('pos', 13, value=1)],
neg=[],
)),
],
transition_features=TransitionFeatureWeights(
class_names=['class2', 'class1'], # reverse on purpose
coef=np.array([[1.5, 2.5], [3.5, 4.5]]),
))
df_dict = format_as_dataframes(expl)
assert isinstance(df_dict, dict)
assert set(df_dict) == {'targets', 'transition_features'}
assert df_dict['targets'].equals(format_as_dataframe(expl.targets))
df = df_dict['transition_features']
print(df)
print(format_as_text(expl))
expected = pd.DataFrame([
{
'from': 'class2',
'to': 'class2',
'coef': 1.5
},
{
'from': 'class2',
'to': 'class1',
'coef': 2.5
},
{
'from': 'class1',
'to': 'class2',
'coef': 3.5
},
{
'from': 'class1',
'to': 'class1',
'coef': 4.5
},
],
columns=['from', 'to', 'coef'])
assert df.equals(expected)
with pytest.warns(UserWarning):
single_df = format_as_dataframe(expl)
assert single_df.equals(df)
def transition_features_to_csv(self):
data_frame = eli5.format_as_dataframes(
eli5.explain_weights_sklearn_crfsuite(self.crf))
data_frame['transition_features'].to_csv(os.path.abspath(
'server/nlp/data/data_transition_features.csv'))
return 'ok'
def state_features_to_csv(self):
data_frame = eli5.format_as_dataframes(
eli5.explain_weights_sklearn_crfsuite(self.crf, top=2**10000))
data_frame['targets'].to_csv(os.path.abspath(
'server/nlp/data/data_state_features.csv'))
return 'ok'