def get_classifier(self, X, y, word_index):
print('===== MLP Keras =====')
# generate embedding matrix
self._embedding_matrix = self.get_embeddings(word_index)
def create_model(neurons=1):
input_dim = X.shape[1]
model = Sequential()
model.add(
layers.Embedding(input_dim=self._vocab_size,
output_dim=self._embedding_dim,
weights=[self._embedding_matrix],
input_length=self._maxlen,
trainable=True))
model.add(layers.LSTM(units=neurons))
#model.add(layers.Flatten())
#model.add(layers.Dense(neurons, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(loss="binary_crossentropy",
optimizer="adam",
metrics=["accuracy"])
#model.summary()
return model
print('===== Keras hyperparameter optimization =====')
model = KerasClassifier(build_fn=create_model, epochs=150, verbose=0)
params = {'neurons': [1, 10, 20, 30, 50]}
cfl = GridSearchCV(model, params, cv=2, scoring='accuracy')
cfl.fit(X, y)
for param, value in cfl.best_params_.items():
print("%s : %s" % (param, value))
model = KerasClassifier(build_fn=create_model, epochs=150, verbose=0)
model.set_params(**cfl.best_params_)
return model
def get_classifier(self, X, y):
print('===== MLP Keras =====')
def create_model(neurons=1):
input_dim = X.shape[1]
model = Sequential()
model.add(
layers.Dense(neurons, input_dim=input_dim, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(loss="binary_crossentropy",
optimizer="adam",
metrics=["accuracy"])
#model.summary()
return model
print('===== Keras hyperparameter optimization =====')
model = KerasClassifier(build_fn=create_model, epochs=150, verbose=0)
params = {'neurons': [1, 10, 20, 30, 50]}
cfl = GridSearchCV(model, params, cv=2, scoring='accuracy')
cfl.fit(X, y)
for param, value in cfl.best_params_.items():
print("%s : %s" % (param, value))
model = KerasClassifier(build_fn=create_model, epochs=150, verbose=0)
model.set_params(**cfl.best_params_)
return model
class model():
def __init__(self):
self.model = KerasClassifier(build_fn=self.create_nn, verbose=0)
self.params= {'optimizer':['rmsprop', 'adam'],
'init':['glorot_uniform', 'normal', 'uniform'],
'epochs':[50, 100, 150],
'batch_size':[5, 10, 20]}
def create_nn(self,optimizer='rmsprop', init='glorot_uniform'):
model = Sequential()
model.add(Dense(12, input_dim=8, kernel_initializer=init, activation='relu'))
model.add(Dense(8, kernel_initializer=init, activation='relu'))
model.add(Dense(1, kernel_initializer=init, activation='sigmoid'))
#compile model
model.compile(loss='binary_crossentropy',optimizer=optimizer,metrics=['accuracy'])
return model
def grid_search(self, train_dataset):
gs_clf = GridSearchCV(estimator=self.model, param_grid=self.params)
gs_clf = gs_clf.fit(train_dataset.x, train_dataset.y)
# summarize results
print("Best: %f using %s" % (gs_clf.best_score_, gs_clf.best_params_))
means = gs_clf.cv_results_['mean_test_score']
stds = gs_clf.cv_results_['std_test_score']
params = gs_clf.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))
self.save_model(gs_clf, 'keras_model.pkl')
self.model.set_params(**gs_clf.best_params_)
def cross_validation(self, train_dataset):
predicted = cross_val_predict(self.model, train_dataset.x, train_dataset.y, cv=10)
print(metrics.classification_report(train_dataset.y, predicted, target_names=train_dataset.target_names))
fpr,tpr,thresholds = metrics.roc_curve(train_dataset.y, predicted)
print("AUC is: " + str(metrics.auc(fpr,tpr)) + "\n")
def save_model(self, gs_clf, file_name):
joblib.dump(gs_clf.best_estimator_, file_name)
def load_model_params(self, file_name):
self.model.set_params(**joblib.load(file_name).best_params_)
def best_keras_clf_estimator(
y_type, best_nn_build_fn, nb_epoch, input_dim, labels, batch_size=None):
best_model_estim = None
best_model_estim = KerasClassifier(
build_fn=best_nn_build_fn, nb_epoch=nb_epoch,
input_dim=input_dim, verbose=0)
if y_type == 'multiclass':
if labels is None:
raise ValueError("%r is not a valid type for var 'labels'" % labels)
elif not isinstance(labels, list):
raise TypeError("Multiclass keras models need a list of string labels.")
else:
output_dim = len(labels)
best_model_estim.set_params(output_dim=output_dim)
if batch_size is not None and isinstance(batch_size, int):
best_model_estim.set_params(batch_size=batch_size)
return best_model_estim
class FinalModelATC(BaseEstimator, TransformerMixin):
def __init__(self,
model,
model_name=None,
ml_for_analytics=False,
type_of_estimator='classifier',
output_column=None,
name=None,
_scorer=None,
training_features=None,
column_descriptions=None,
feature_learning=False,
uncertainty_model=None,
uc_results=None,
training_prediction_intervals=False,
min_step_improvement=0.0001,
interval_predictors=None,
keep_cat_features=False,
is_hp_search=None,
X_test=None,
y_test=None):
self.model = model
self.model_name = model_name
self.ml_for_analytics = ml_for_analytics
self.type_of_estimator = type_of_estimator
self.name = name
self.training_features = training_features
self.column_descriptions = column_descriptions
self.feature_learning = feature_learning
self.uncertainty_model = uncertainty_model
self.uc_results = uc_results
self.training_prediction_intervals = training_prediction_intervals
self.min_step_improvement = min_step_improvement
self.interval_predictors = interval_predictors
self.is_hp_search = is_hp_search
self.keep_cat_features = keep_cat_features
self.X_test = X_test
self.y_test = y_test
if self.type_of_estimator == 'classifier':
self._scorer = _scorer
else:
self._scorer = _scorer
def get(self, prop_name, default=None):
try:
return getattr(self, prop_name)
except AttributeError:
return default
def fit(self, X, y):
global keras_imported, KerasRegressor, KerasClassifier, EarlyStopping, ModelCheckpoint, TerminateOnNaN, keras_load_model
self.model_name = get_name_from_model(self.model)
X_fit = X
if self.model_name[:12] == 'DeepLearning' or self.model_name in [
'BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit',
'ARDRegression', 'Perceptron', 'PassiveAggressiveClassifier',
'SGDClassifier', 'RidgeClassifier', 'LogisticRegression'
]:
if scipy.sparse.issparse(X_fit):
X_fit = X_fit.todense()
if self.model_name[:12] == 'DeepLearning':
if keras_imported == False:
# Suppress some level of logs
os.environ['TF_CPP_MIN_VLOG_LEVEL'] = '3'
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
from keras.callbacks import EarlyStopping, ModelCheckpoint, TerminateOnNaN
from keras.models import load_model as keras_load_model
from keras.wrappers.scikit_learn import KerasRegressor, KerasClassifier
keras_imported = True
# For Keras, we need to tell it how many input nodes to expect, which is our num_cols
num_cols = X_fit.shape[1]
model_params = self.model.get_params()
del model_params['build_fn']
try:
del model_params['feature_learning']
except:
pass
try:
del model_params['num_cols']
except:
pass
if self.type_of_estimator == 'regressor':
self.model = KerasRegressor(
build_fn=utils_models.make_deep_learning_model,
num_cols=num_cols,
feature_learning=self.feature_learning,
**model_params)
elif self.type_of_estimator == 'classifier':
self.model = KerasClassifier(
build_fn=utils_models.make_deep_learning_classifier,
num_cols=num_cols,
feature_learning=self.feature_learning,
**model_params)
if self.model_name[:12] == 'DeepLearning':
try:
if self.is_hp_search == True:
patience = 5
verbose = 0
else:
patience = 25
verbose = 2
X_fit, y, X_test, y_test = self.get_X_test(X_fit, y)
try:
X_test = X_test.toarray()
except AttributeError as e:
pass
if not self.is_hp_search:
print(
'\nWe will stop training early if we have not seen an improvement in validation accuracy in {} epochs'
.format(patience))
print(
'To measure validation accuracy, we will split off a random 10 percent of your training data set'
)
early_stopping = EarlyStopping(monitor='val_loss',
patience=patience,
verbose=verbose)
terminate_on_nan = TerminateOnNaN()
now_time = datetime.datetime.now()
time_string = str(now_time.year) + '_' + str(
now_time.month) + '_' + str(now_time.day) + '_' + str(
now_time.hour) + '_' + str(now_time.minute)
temp_file_name = 'tmp_dl_model_checkpoint_' + time_string + str(
random.random()) + '.h5'
model_checkpoint = ModelCheckpoint(temp_file_name,
monitor='val_loss',
save_best_only=True,
mode='min',
period=1)
callbacks = [early_stopping, terminate_on_nan]
if not self.is_hp_search:
callbacks.append(model_checkpoint)
self.model.fit(X_fit,
y,
callbacks=callbacks,
validation_data=(X_test, y_test),
verbose=verbose)
# TODO: give some kind of logging on how the model did here! best epoch, best accuracy, etc.
if self.is_hp_search is False:
self.model = keras_load_model(temp_file_name)
try:
os.remove(temp_file_name)
except OSError as e:
pass
except KeyboardInterrupt as e:
print(
'Stopping training at this point because we heard a KeyboardInterrupt'
)
print(
'If the deep learning model is functional at this point, we will output the model in its latest form'
)
print(
'Note that this feature is an unofficial beta-release feature that is known to fail on occasion'
)
if self.is_hp_search is False:
self.model = keras_load_model(temp_file_name)
try:
os.remove(temp_file_name)
except OSError as e:
pass
elif self.model_name[:4] == 'LGBM':
X_fit = X.toarray()
X_fit, y, X_test, y_test = self.get_X_test(X_fit, y)
try:
X_test = X_test.toarray()
except AttributeError as e:
pass
if self.type_of_estimator == 'regressor':
eval_metric = 'rmse'
elif self.type_of_estimator == 'classifier':
if len(set(y_test)) > 2:
eval_metric = 'multi_logloss'
else:
eval_metric = 'binary_logloss'
verbose = True
if self.is_hp_search == True:
verbose = False
if self.X_test is not None:
eval_name = 'X_test_the_user_passed_in'
else:
eval_name = 'random_holdout_set_from_training_data'
cat_feature_indices = self.get_categorical_feature_indices()
if cat_feature_indices is None:
self.model.fit(X_fit,
y,
eval_set=[(X_test, y_test)],
early_stopping_rounds=100,
eval_metric=eval_metric,
eval_names=[eval_name],
verbose=verbose)
else:
self.model.fit(X_fit,
y,
eval_set=[(X_test, y_test)],
early_stopping_rounds=100,
eval_metric=eval_metric,
eval_names=[eval_name],
categorical_feature=cat_feature_indices,
verbose=verbose)
elif self.model_name[:8] == 'CatBoost':
X_fit = X_fit.toarray()
if self.type_of_estimator == 'classifier' and len(
pd.Series(y).unique()) > 2:
# TODO: we might have to modify the format of the y values, converting them all to ints, then back again (sklearn has a useful inverse_transform on some preprocessing classes)
self.model.set_params(loss_function='MultiClass')
cat_feature_indices = self.get_categorical_feature_indices()
self.model.fit(X_fit, y, cat_features=cat_feature_indices)
elif self.model_name[:16] == 'GradientBoosting':
if not sklearn_version > '0.18.1':
X_fit = X_fit.toarray()
patience = 20
best_val_loss = -10000000000
num_worse_rounds = 0
best_model = deepcopy(self.model)
X_fit, y, X_test, y_test = self.get_X_test(X_fit, y)
# Add a variable number of trees each time, depending how far into the process we are
if os.environ.get('is_test_suite', False) == 'True':
num_iters = list(range(1, 50, 1)) + list(range(
50, 100, 2)) + list(range(100, 250, 3))
else:
num_iters = list(range(
1, 50, 1)) + list(range(50, 100, 2)) + list(
range(100, 250, 3)) + list(range(250, 500, 5)) + list(
range(500, 1000, 10)) + list(range(
1000, 2000, 20)) + list(range(
2000, 10000, 100))
# TODO: get n_estimators from the model itself, and reduce this list to only those values that come under the value from the model
try:
for num_iter in num_iters:
warm_start = True
if num_iter == 1:
warm_start = False
self.model.set_params(n_estimators=num_iter,
warm_start=warm_start)
self.model.fit(X_fit, y)
if self.training_prediction_intervals == True:
val_loss = self.model.score(X_test, y_test)
else:
try:
val_loss = self._scorer.score(self, X_test, y_test)
except Exception as e:
val_loss = self.model.score(X_test, y_test)
if val_loss - self.min_step_improvement > best_val_loss:
best_val_loss = val_loss
num_worse_rounds = 0
best_model = deepcopy(self.model)
else:
num_worse_rounds += 1
print(
'[' + str(num_iter) +
'] random_holdout_set_from_training_data\'s score is: '
+ str(round(val_loss, 3)))
if num_worse_rounds >= patience:
break
except KeyboardInterrupt:
print(
'Heard KeyboardInterrupt. Stopping training, and using the best checkpointed GradientBoosting model'
)
pass
self.model = best_model
print(
'The number of estimators that were the best for this training dataset: '
+ str(self.model.get_params()['n_estimators']))
print('The best score on the holdout set: ' + str(best_val_loss))
else:
self.model.fit(X_fit, y)
if self.X_test is not None:
del self.X_test
del self.y_test
return self
def remove_categorical_values(self, features):
clean_features = set([])
for feature in features:
if '=' not in feature:
clean_features.add(feature)
else:
clean_features.add(feature[:feature.index('=')])
return clean_features
def verify_features(self, X, raw_features_only=False):
if self.column_descriptions is None:
print(
'This feature is not enabled by default. Depending on the shape of the training data, it can add hundreds of KB to the saved file size.'
)
print(
'Please pass in `ml_predictor.train(data, verify_features=True)` when training a model, and we will enable this function, at the cost of a potentially larger file size.'
)
warnings.warn(
'Please pass verify_features=True when invoking .train() on the ml_predictor instance.'
)
return None
print(
'\n\nNow verifying consistency between training features and prediction features'
)
if isinstance(X, dict):
prediction_features = set(X.keys())
elif isinstance(X, pd.DataFrame):
prediction_features = set(X.columns)
# If the user passed in categorical features, we will effectively one-hot-encode them ourselves here
# Note that this assumes we're using the "=" as the separater in DictVectorizer/DataFrameVectorizer
date_col_names = []
categorical_col_names = []
for key, value in self.column_descriptions.items():
if value == 'categorical' and 'day_part' not in key:
try:
# This covers the case that the user passes in a value in column_descriptions that is not present in their prediction data
column_vals = X[key].unique()
for val in column_vals:
prediction_features.add(key + '=' + str(val))
categorical_col_names.append(key)
except:
print(
'\nFound a column in your column_descriptions that is not present in your prediction data:'
)
print(key)
elif 'day_part' in key:
# We have found a date column. Make sure this date column is in our prediction data
# It is outside the scope of this function to make sure that the same date parts are available in both our training and testing data
raw_date_col_name = key[:key.index('day_part') - 1]
date_col_names.append(raw_date_col_name)
elif value == 'output':
try:
prediction_features.remove(key)
except KeyError:
pass
# Now that we've added in all the one-hot-encoded categorical columns (name=val1, name=val2), remove the base name from our prediction data
prediction_features = prediction_features - set(categorical_col_names)
# Get only the unique raw_date_col_names
date_col_names = set(date_col_names)
training_features = set(self.training_features)
# Remove all of the transformed date column feature names from our training data
features_to_remove = []
for feature in training_features:
for raw_date_col_name in date_col_names:
if raw_date_col_name in feature:
features_to_remove.append(feature)
training_features = training_features - set(features_to_remove)
# Make sure the raw_date_col_name is in our training data after we have removed all the transformed feature names
training_features = training_features | date_col_names
# MVP means ignoring text features
print_nlp_warning = False
nlp_example = None
for feature in training_features:
if 'nlp_' in feature:
print_nlp_warning = True
nlp_example = feature
training_features.remove(feature)
if print_nlp_warning == True:
print('\n\nWe found an NLP column in the training data')
print(
'verify_features() currently does not support checking all of the values within an NLP column, so if the text of your NLP column has dramatically changed, you will have to check that yourself.'
)
print(
'Here is one example of an NLP feature in the training data:')
print(nlp_example)
training_not_prediction = training_features - prediction_features
if raw_features_only == True:
training_not_prediction = self.remove_categorical_values(
training_not_prediction)
if len(training_not_prediction) > 0:
print(
'\n\nHere are the features this model was trained on that were not present in this prediction data:'
)
print(sorted(list(training_not_prediction)))
else:
print(
'All of the features this model was trained on are included in the prediction data'
)
prediction_not_training = prediction_features - training_features
if raw_features_only == True:
prediction_not_training = self.remove_categorical_values(
prediction_not_training)
if len(prediction_not_training) > 0:
# Separate out those values we were told to ignore by column_descriptions
ignored_features = []
for feature in prediction_not_training:
if self.column_descriptions.get(feature, 'False') == 'ignore':
ignored_features.append(feature)
prediction_not_training = prediction_not_training - set(
ignored_features)
print(
'\n\nHere are the features available in the prediction data that were not part of the training data:'
)
print(sorted(list(prediction_not_training)))
if len(ignored_features) > 0:
print(
'\n\nAdditionally, we found features in the prediction data that we were told to ignore in the training data'
)
print(sorted(list(ignored_features)))
else:
print(
'All of the features in the prediction data were in this model\'s training data'
)
print('\n\n')
return {
'training_not_prediction': training_not_prediction,
'prediction_not_training': prediction_not_training
}
def score(self, X, y, verbose=False):
# At the time of writing this, GradientBoosting does not support sparse matrices for predictions
if (self.model_name[:16] == 'GradientBoosting' or self.model_name in [
'BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit',
'ARDRegression'
]) and scipy.sparse.issparse(X):
X = X.todense()
if self._scorer is not None:
if self.type_of_estimator == 'regressor':
return self._scorer.score(self, X, y)
elif self.type_of_estimator == 'classifier':
return self._scorer.score(self, X, y)
else:
return self.model.score(X, y)
def predict_proba(self, X, verbose=False):
if (self.model_name[:16] == 'GradientBoosting' or self.model_name[:12]
== 'DeepLearning' or self.model_name in [
'BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit',
'ARDRegression'
]) and scipy.sparse.issparse(X):
X = X.todense()
elif (self.model_name[:8] == 'CatBoost'
or self.model_name[:4] == 'LGBM') and scipy.sparse.issparse(X):
X = X.toarray()
try:
if self.model_name[:4] == 'LGBM':
try:
best_iteration = self.model.best_iteration
except AttributeError:
best_iteration = self.model.best_iteration_
predictions = self.model.predict_proba(
X, num_iteration=best_iteration)
else:
predictions = self.model.predict_proba(X)
except AttributeError as e:
try:
predictions = self.model.predict(X)
except TypeError as e:
if scipy.sparse.issparse(X):
X = X.todense()
predictions = self.model.predict(X)
except TypeError as e:
if scipy.sparse.issparse(X):
X = X.todense()
predictions = self.model.predict_proba(X)
# If this model does not have predict_proba, and we have fallen back on predict, we want to make sure we give results back in the same format the user would expect for predict_proba, namely each prediction is a list of predicted probabilities for each class.
# Note that this DOES NOT WORK for multi-label problems, or problems that are not reduced to 0,1
# If this is not an iterable (ignoring strings, which might be iterable), then we will want to turn our predictions into tupled predictions
if not (hasattr(predictions[0], '__iter__')
and not isinstance(predictions[0], str)):
tupled_predictions = []
for prediction in predictions:
if prediction == 1:
tupled_predictions.append([0, 1])
else:
tupled_predictions.append([1, 0])
predictions = tupled_predictions
# This handles an annoying edge case with libraries like Keras that, for a binary classification problem, with return a single predicted probability in a list, rather than the probability of both classes in a list
if len(predictions[0]) == 1:
tupled_predictions = []
for prediction in predictions:
tupled_predictions.append([1 - prediction[0], prediction[0]])
predictions = tupled_predictions
if X.shape[0] == 1:
return predictions[0]
else:
return predictions
def predict(self, X, verbose=False):
if (self.model_name[:16] == 'GradientBoosting' or self.model_name[:12]
== 'DeepLearning' or self.model_name in [
'BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit',
'ARDRegression'
]) and scipy.sparse.issparse(X):
X_predict = X.todense()
elif self.model_name[:8] == 'CatBoost' and scipy.sparse.issparse(X):
X_predict = X.toarray()
else:
X_predict = X
if self.model_name[:4] == 'LGBM':
try:
best_iteration = self.model.best_iteration
except AttributeError:
best_iteration = self.model.best_iteration_
predictions = self.model.predict(X, num_iteration=best_iteration)
else:
predictions = self.model.predict(X_predict)
# Handle cases of getting a prediction for a single item.
# It makes a cleaner interface just to get just the single prediction back, rather than a list with the prediction hidden inside.
if isinstance(predictions, np.ndarray):
predictions = predictions.tolist()
if isinstance(predictions, float) or isinstance(
predictions, int) or isinstance(predictions, str):
return predictions
if isinstance(predictions[0], list) and len(predictions[0]) == 1:
predictions = [row[0] for row in predictions]
if len(predictions) == 1:
return predictions[0]
else:
return predictions
def predict_intervals(self, X, return_type=None):
if self.interval_predictors is None:
print(
'!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!'
)
print('This model was not trained to predict intervals')
print(
'Please follow the documentation to tell this model at training time to learn how to predict intervals'
)
print(
'!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!'
)
raise ValueError('This model was not trained to predict intervals')
base_prediction = self.predict(X)
result = {'prediction': base_prediction}
for tup in self.interval_predictors:
predictor_name = tup[0]
predictor = tup[1]
result[predictor_name] = predictor.predict(X)
if scipy.sparse.issparse(X):
len_input = X.shape[0]
else:
len_input = len(X)
if (len_input == 1 and return_type is None) or return_type == 'dict':
return result
elif (len_input > 1 and return_type is None
) or return_type == 'df' or return_type == 'dataframe':
return pd.DataFrame(result)
elif return_type == 'list':
if len_input == 1:
list_result = [base_prediction]
for tup in self.interval_predictors:
list_result.append(result[tup[0]])
else:
list_result = []
for idx in range(len_input):
row_result = [base_prediction[idx]]
for tup in self.interval_predictors:
row_result.append(result[tup[0]][idx])
list_result.append(row_result)
return list_result
else:
print(
'Please pass in a return_type value of one of the following: ["dict", "dataframe", "df", "list"]'
)
raise (ValueError(
'Please pass in a return_type value of one of the following: ["dict", "dataframe", "df", "list"]'
))
# transform is initially designed to be used with feature_learning
def transform(self, X):
predicted_features = self.predict(X)
predicted_features = list(predicted_features)
X = scipy.sparse.hstack([X, predicted_features], format='csr')
return X
# Allows the user to get the fully transformed data
def transform_only(self, X):
return X
def predict_uncertainty(self, X):
if self.uncertainty_model is None:
print(
'!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!'
)
print('This model was not trained to predict uncertainties')
print(
'Please follow the documentation to tell this model at training time to learn how to predict uncertainties'
)
print(
'!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!'
)
raise ValueError(
'This model was not trained to predict uncertainties')
base_predictions = self.predict(X)
if isinstance(base_predictions, Iterable):
base_predictions_col = [[val] for val in base_predictions]
base_predictions_col = np.array(base_predictions_col)
else:
base_predictions_col = [base_predictions]
X_combined = scipy.sparse.hstack([X, base_predictions_col],
format='csr')
uncertainty_predictions = self.uncertainty_model.predict_proba(
X_combined)
results = {
'base_prediction': base_predictions,
'uncertainty_prediction': uncertainty_predictions
}
if isinstance(base_predictions, Iterable):
results['uncertainty_prediction'] = [
row[1] for row in results['uncertainty_prediction']
]
results = pd.DataFrame.from_dict(results, orient='columns')
if self.uc_results is not None:
calibration_results = {}
# grab the relevant properties from our uc_results, and make them each their own list in calibration_results
for key, value in self.uc_results[1].items():
calibration_results[key] = []
for proba in results['uncertainty_prediction']:
max_bucket_proba = 0
bucket_num = 1
while proba > max_bucket_proba:
calibration_result = self.uc_results[bucket_num]
max_bucket_proba = self.uc_results[bucket_num][
'max_proba']
bucket_num += 1
for key, value in calibration_result.items():
calibration_results[key].append(value)
# TODO: grab the uncertainty_calibration data for DataFrames
df_calibration_results = pd.DataFrame.from_dict(
calibration_results, orient='columns')
del df_calibration_results['max_proba']
results = pd.concat([results, df_calibration_results], axis=1)
else:
if self.uc_results is not None:
# TODO: grab the uncertainty_calibration data for dictionaries
for bucket_name, bucket_result in self.uc_results.items():
if proba > bucket_result['max_proba']:
break
results.update(bucket_result)
del results['max_proba']
return results
def score_uncertainty(self, X, y, verbose=False):
return self.uncertainty_model.score(X, y, verbose=False)
def get_categorical_feature_indices(self):
cat_feature_indices = None
if self.keep_cat_features == True:
cat_feature_names = [
k for k, v in self.column_descriptions.items()
if v == 'categorical'
]
cat_feature_indices = [
self.training_features.index(cat_name)
for cat_name in cat_feature_names
]
return cat_feature_indices
def get_X_test(self, X_fit, y):
if self.X_test is not None:
return X_fit, y, self.X_test, self.y_test
else:
X_fit, X_test, y, y_test = train_test_split(X_fit,
y,
test_size=0.15)
return X_fit, y, X_test, y_test
'\u03BB',
'parameters',
col_names_nn_Keras_classifier,
row_names_nn_Keras_classifier,
True,
savefig=True,
figname='Images/NN_clas_accuracy_2' + wine_type + '.png')
#refit best NN classifier
print(clf.best_params_)
nnKerasBest = KerasClassifier(build_fn=build_network,
n_outputs=y_onehot.shape[1],
output_activation='softmax',
loss="categorical_crossentropy",
verbose=0)
nnKerasBest.set_params(**clf.best_params_)
hist = nnKerasBest.fit(Xtrain,
ytrain_onehot,
validation_data=(Xtest, ytest_onehot))
pred_nnKerasBest_train = nnKerasBest.predict(Xtrain)
pred_nnKerasBest_test = nnKerasBest.predict(Xtest)
print('Neural network classifier accuracy train: %g' %
accuracy_score(ytrain, pred_nnKerasBest_train))
print('Neural network classifier accuracy test: %g' %
accuracy_score(ytest, pred_nnKerasBest_test))
#learning chart for best model (accuracy and loss) and confusion matrix
plot_several(np.tile(np.arange(clf.best_params_['epochs'])[:, None], [1, 2]),
np.concatenate((np.reshape(hist.history['accuracy'],
(clf.best_params_['epochs'], 1)),
np.reshape(hist.history['val_accuracy'],
class FinalModelATC(BaseEstimator, TransformerMixin):
def __init__(self, model, model_name=None, ml_for_analytics=False, type_of_estimator='classifier', output_column=None, name=None, _scorer=None, training_features=None, column_descriptions=None, feature_learning=False, uncertainty_model=None, uc_results = None):
self.model = model
self.model_name = model_name
self.ml_for_analytics = ml_for_analytics
self.type_of_estimator = type_of_estimator
self.name = name
self.training_features = training_features
self.column_descriptions = column_descriptions
self.feature_learning = feature_learning
self.uncertainty_model = uncertainty_model
self.uc_results = uc_results
if self.type_of_estimator == 'classifier':
self._scorer = _scorer
else:
self._scorer = _scorer
def get(self, prop_name, default=None):
try:
return getattr(self, prop_name)
except AttributeError:
return default
def fit(self, X, y):
self.model_name = get_name_from_model(self.model)
X_fit = X
if self.model_name[:12] == 'DeepLearning' or self.model_name in ['BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit', 'ARDRegression', 'Perceptron', 'PassiveAggressiveClassifier', 'SGDClassifier', 'RidgeClassifier', 'LogisticRegression']:
if scipy.sparse.issparse(X_fit):
X_fit = X_fit.todense()
if self.model_name[:12] == 'DeepLearning':
# For Keras, we need to tell it how many input nodes to expect, which is our num_cols
num_cols = X_fit.shape[1]
model_params = self.model.get_params()
del model_params['build_fn']
if self.type_of_estimator == 'regressor':
self.model = KerasRegressor(build_fn=utils_models.make_deep_learning_model, num_cols=num_cols, feature_learning=self.feature_learning, **model_params)
elif self.type_of_estimator == 'classifier':
self.model = KerasClassifier(build_fn=utils_models.make_deep_learning_classifier, num_cols=num_cols, feature_learning=self.feature_learning, **model_params)
try:
if self.model_name[:12] == 'DeepLearning':
print('\nWe will stop training early if we have not seen an improvement in training accuracy in 25 epochs')
from keras.callbacks import EarlyStopping
early_stopping = EarlyStopping(monitor='loss', patience=25, verbose=1)
self.model.fit(X_fit, y, callbacks=[early_stopping])
elif self.model_name[:16] == 'GradientBoosting':
if scipy.sparse.issparse(X_fit):
X_fit = X_fit.todense()
patience = 20
best_val_loss = -10000000000
num_worse_rounds = 0
best_model = deepcopy(self.model)
X_fit, X_test, y, y_test = train_test_split(X_fit, y, test_size=0.15)
# Add a variable number of trees each time, depending how far into the process we are
num_iters = list(range(1, 50, 1)) + list(range(50, 100, 2)) + list(range(100, 250, 3)) + list(range(250, 500, 5)) + list(range(500, 1000, 10)) + list(range(1000, 2000, 20)) + list(range(2000, 10000, 100))
try:
for num_iter in num_iters:
warm_start = True
if num_iter == 1:
warm_start = False
self.model.set_params(n_estimators=num_iter, warm_start=warm_start)
self.model.fit(X_fit, y)
try:
val_loss = self._scorer.score(self, X_test, y_test)
except Exception as e:
val_loss = self.model.score(X_test, y_test)
if val_loss > best_val_loss:
best_val_loss = val_loss
num_worse_rounds = 0
best_model = deepcopy(self.model)
else:
num_worse_rounds += 1
if num_worse_rounds >= patience:
break
except KeyboardInterrupt:
print('Heard KeyboardInterrupt. Stopping training, and using the best checkpointed GradientBoosting model')
pass
self.model = best_model
print('The number of estimators that were the best for this training dataset: ' + str(self.model.get_params()['n_estimators']))
print('The best score on a random 15 percent holdout set of the training data: ' + str(best_val_loss))
else:
self.model.fit(X_fit, y)
except TypeError as e:
if scipy.sparse.issparse(X_fit):
X_fit = X_fit.todense()
self.model.fit(X_fit, y)
except KeyboardInterrupt as e:
print('Stopping training at this point because we heard a KeyboardInterrupt')
print('If the model is functional at this point, we will output the model in its latest form')
print('Note that not all models can be interrupted and still used, and that this feature generally is an unofficial beta-release feature that is known to fail on occasion')
pass
return self
def remove_categorical_values(self, features):
clean_features = set([])
for feature in features:
if '=' not in feature:
clean_features.add(feature)
else:
clean_features.add(feature[:feature.index('=')])
return clean_features
def verify_features(self, X, raw_features_only=False):
if self.column_descriptions is None:
print('This feature is not enabled by default. Depending on the shape of the training data, it can add hundreds of KB to the saved file size.')
print('Please pass in `ml_predictor.train(data, verify_features=True)` when training a model, and we will enable this function, at the cost of a potentially larger file size.')
warnings.warn('Please pass verify_features=True when invoking .train() on the ml_predictor instance.')
return None
print('\n\nNow verifying consistency between training features and prediction features')
if isinstance(X, dict):
prediction_features = set(X.keys())
elif isinstance(X, pd.DataFrame):
prediction_features = set(X.columns)
# If the user passed in categorical features, we will effectively one-hot-encode them ourselves here
# Note that this assumes we're using the "=" as the separater in DictVectorizer/DataFrameVectorizer
date_col_names = []
categorical_col_names = []
for key, value in self.column_descriptions.items():
if value == 'categorical' and 'day_part' not in key:
try:
# This covers the case that the user passes in a value in column_descriptions that is not present in their prediction data
column_vals = X[key].unique()
for val in column_vals:
prediction_features.add(key + '=' + str(val))
categorical_col_names.append(key)
except:
print('\nFound a column in your column_descriptions that is not present in your prediction data:')
print(key)
elif 'day_part' in key:
# We have found a date column. Make sure this date column is in our prediction data
# It is outside the scope of this function to make sure that the same date parts are available in both our training and testing data
raw_date_col_name = key[:key.index('day_part') - 1]
date_col_names.append(raw_date_col_name)
elif value == 'output':
try:
prediction_features.remove(key)
except KeyError:
pass
# Now that we've added in all the one-hot-encoded categorical columns (name=val1, name=val2), remove the base name from our prediction data
prediction_features = prediction_features - set(categorical_col_names)
# Get only the unique raw_date_col_names
date_col_names = set(date_col_names)
training_features = set(self.training_features)
# Remove all of the transformed date column feature names from our training data
features_to_remove = []
for feature in training_features:
for raw_date_col_name in date_col_names:
if raw_date_col_name in feature:
features_to_remove.append(feature)
training_features = training_features - set(features_to_remove)
# Make sure the raw_date_col_name is in our training data after we have removed all the transformed feature names
training_features = training_features | date_col_names
# MVP means ignoring text features
print_nlp_warning = False
nlp_example = None
for feature in training_features:
if 'nlp_' in feature:
print_nlp_warning = True
nlp_example = feature
training_features.remove(feature)
if print_nlp_warning == True:
print('\n\nWe found an NLP column in the training data')
print('verify_features() currently does not support checking all of the values within an NLP column, so if the text of your NLP column has dramatically changed, you will have to check that yourself.')
print('Here is one example of an NLP feature in the training data:')
print(nlp_example)
training_not_prediction = training_features - prediction_features
if raw_features_only == True:
training_not_prediction = self.remove_categorical_values(training_not_prediction)
if len(training_not_prediction) > 0:
print('\n\nHere are the features this model was trained on that were not present in this prediction data:')
print(sorted(list(training_not_prediction)))
else:
print('All of the features this model was trained on are included in the prediction data')
prediction_not_training = prediction_features - training_features
if raw_features_only == True:
prediction_not_training = self.remove_categorical_values(prediction_not_training)
if len(prediction_not_training) > 0:
# Separate out those values we were told to ignore by column_descriptions
ignored_features = []
for feature in prediction_not_training:
if self.column_descriptions.get(feature, 'False') == 'ignore':
ignored_features.append(feature)
prediction_not_training = prediction_not_training - set(ignored_features)
print('\n\nHere are the features available in the prediction data that were not part of the training data:')
print(sorted(list(prediction_not_training)))
if len(ignored_features) > 0:
print('\n\nAdditionally, we found features in the prediction data that we were told to ignore in the training data')
print(sorted(list(ignored_features)))
else:
print('All of the features in the prediction data were in this model\'s training data')
print('\n\n')
return {
'training_not_prediction': training_not_prediction
, 'prediction_not_training': prediction_not_training
}
def score(self, X, y, verbose=False):
# At the time of writing this, GradientBoosting does not support sparse matrices for predictions
if (self.model_name[:16] == 'GradientBoosting' or self.model_name in ['BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit', 'ARDRegression']) and scipy.sparse.issparse(X):
X = X.todense()
if self._scorer is not None:
if self.type_of_estimator == 'regressor':
return self._scorer.score(self, X, y)
elif self.type_of_estimator == 'classifier':
return self._scorer.score(self, X, y)
else:
return self.model.score(X, y)
def predict_proba(self, X, verbose=False):
if (self.model_name[:16] == 'GradientBoosting' or self.model_name[:12] == 'DeepLearning' or self.model_name in ['BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit', 'ARDRegression']) and scipy.sparse.issparse(X):
X = X.todense()
try:
predictions = self.model.predict_proba(X)
except AttributeError as e:
try:
predictions = self.model.predict(X)
except TypeError as e:
if scipy.sparse.issparse(X):
X = X.todense()
predictions = self.model.predict(X)
except TypeError as e:
if scipy.sparse.issparse(X):
X = X.todense()
predictions = self.model.predict_proba(X)
# If this model does not have predict_proba, and we have fallen back on predict, we want to make sure we give results back in the same format the user would expect for predict_proba, namely each prediction is a list of predicted probabilities for each class.
# Note that this DOES NOT WORK for multi-label problems, or problems that are not reduced to 0,1
# If this is not an iterable (ignoring strings, which might be iterable), then we will want to turn our predictions into tupled predictions
if not (hasattr(predictions[0], '__iter__') and not isinstance(predictions[0], str)):
tupled_predictions = []
for prediction in predictions:
if prediction == 1:
tupled_predictions.append([0,1])
else:
tupled_predictions.append([1,0])
predictions = tupled_predictions
# This handles an annoying edge case with libraries like Keras that, for a binary classification problem, with return a single predicted probability in a list, rather than the probability of both classes in a list
if len(predictions[0]) == 1:
tupled_predictions = []
for prediction in predictions:
tupled_predictions.append([1 - prediction[0], prediction[0]])
predictions = tupled_predictions
if X.shape[0] == 1:
return predictions[0]
else:
return predictions
def predict(self, X, verbose=False):
if (self.model_name[:16] == 'GradientBoosting' or self.model_name[:12] == 'DeepLearning' or self.model_name in ['BayesianRidge', 'LassoLars', 'OrthogonalMatchingPursuit', 'ARDRegression']) and scipy.sparse.issparse(X):
X_predict = X.todense()
else:
X_predict = X
prediction = self.model.predict(X_predict)
# Handle cases of getting a prediction for a single item.
# It makes a cleaner interface just to get just the single prediction back, rather than a list with the prediction hidden inside.
if isinstance(prediction, np.ndarray):
prediction = prediction.tolist()
if isinstance(prediction, float) or isinstance(prediction, int) or isinstance(prediction, str):
return prediction
if len(prediction) == 1:
return prediction[0]
else:
return prediction
# transform is initially designed to be used with feature_learning
def transform(self, X):
predicted_features = self.predict(X)
predicted_features = list(predicted_features)
X = scipy.sparse.hstack([X, predicted_features], format='csr')
return X
def predict_uncertainty(self, X):
if self.uncertainty_model is None:
print('!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!')
print('This model was not trained to predict uncertainties')
print('Please follow the documentation to tell this model at training time to learn how to predict uncertainties')
print('!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!')
raise ValueError('This model was not trained to predict uncertainties')
base_predictions = self.predict(X)
if isinstance(base_predictions, Iterable):
base_predictions_col = [[val] for val in base_predictions]
base_predictions_col = np.array(base_predictions_col)
else:
base_predictions_col = [base_predictions]
X_combined = scipy.sparse.hstack([X, base_predictions_col], format='csr')
uncertainty_predictions = self.uncertainty_model.predict_proba(X_combined)
results = {
'base_prediction': base_predictions
, 'uncertainty_prediction': uncertainty_predictions
}
if isinstance(base_predictions, Iterable):
results['uncertainty_prediction'] = [row[1] for row in results['uncertainty_prediction']]
results = pd.DataFrame.from_dict(results, orient='columns')
if self.uc_results is not None:
calibration_results = {}
# grab the relevant properties from our uc_results, and make them each their own list in calibration_results
for key, value in self.uc_results[1].items():
calibration_results[key] = []
for proba in results['uncertainty_prediction']:
max_bucket_proba = 0
bucket_num = 1
while proba > max_bucket_proba:
calibration_result = self.uc_results[bucket_num]
max_bucket_proba = self.uc_results[bucket_num]['max_proba']
bucket_num += 1
for key, value in calibration_result.items():
calibration_results[key].append(value)
# TODO: grab the uncertainty_calibration data for DataFrames
df_calibration_results = pd.DataFrame.from_dict(calibration_results, orient='columns')
del df_calibration_results['max_proba']
results = pd.concat([results, df_calibration_results], axis=1)
else:
if self.uc_results is not None:
# TODO: grab the uncertainty_calibration data for dictionaries
for bucket_name, bucket_result in self.uc_results.items():
if proba > bucket_result['max_proba']:
break
results.update(bucket_result)
del results['max_proba']
return results
def score_uncertainty(self, X, y, verbose=False):
return self.uncertainty_model.score(X, y, verbose=False)
class BaseKerasSklearnModel(base_model.BaseModel):
'''
base keras model based on keras's model(without sklearn)
'''
## def __init__(self, data_file, delimiter, lst_x_keys, lst_y_keys, log_filename=DEFAULT_LOG_FILENAME, model_path=DEFAULT_MODEL_PATH, create_model_func=create_model_demo):
## '''
## init
## '''
## import framework.tools.log as log
## loger = log.init_log(log_filename)
## self.load_data(data_file, delimiter, lst_x_keys, lst_y_keys)
## self.model_path = model_path
## self.create_model_func=create_model_func
def __init__(self, **kargs):
'''
init
'''
import framework.tools.log as log
self.kargs = kargs
log_filename = self.kargs["basic_params"]["log_filename"]
model_path = self.kargs["basic_params"]["model_path"]
self.load_data_func = self.kargs["load_data"]["method"]
self.create_model_func = self.kargs["create_model"]["method"]
loger = log.init_log(log_filename)
(self.dataset, self.X, self.Y, self.X_evaluation,
self.Y_evaluation) = self.load_data_func(
**self.kargs["load_data"]["params"])
self.model_path = model_path
self.dic_params = {}
def load_data(self, data_file, delimiter, lst_x_keys, lst_y_keys):
'''
load data
'''
# Load the dataset
self.dataset = numpy.loadtxt(data_file, delimiter=",")
self.X = self.dataset[:, lst_x_keys]
self.Y = self.dataset[:, lst_y_keys]
def init_callbacks(self):
'''
init all callbacks
'''
os.system("mkdir -p %s" % (self.model_path))
checkpoint_callback = ModelCheckpoint(self.model_path + '/weights.{epoch:02d}-{acc:.2f}.hdf5', \
monitor='acc', save_best_only=False)
history_callback = LossHistory()
callbacks_list = [checkpoint_callback, history_callback]
self.dic_params["callbacks"] = callbacks_list
def init_model(self):
'''
init model
'''
train_params = {"nb_epoch": 10, "batch_size": 10}
self.dic_params.update(train_params)
self.model = KerasClassifier(build_fn=self.create_model_func,
**self.kargs["create_model"]["params"])
# self.model = KerasClassifier(build_fn=self.create_model_func)
self.model.set_params(**self.dic_params)
def train_model(self):
'''
train model
'''
X = self.X
Y = self.Y
X_evaluation = self.X_evaluation
Y_evaluation = self.Y_evaluation
seed = 7
numpy.random.seed(seed) # Load the dataset
history = self.model.fit(X, Y)
scores = self.model.score(X, Y)
#history_callback = self.dic_params["callbacks"][1]
# print dir(history_callback)
# logging.info(str(history_callback.losses))
logging.info("final : %.2f%%" % (scores * 100))
logging.info(str(history.history))
def process(self):
'''
process
'''
self.init_callbacks()
self.init_model()
self.train_model()
classifier.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch)
print('Testing score function')
score = classifier.score(X_train, Y_train)
print('Score: ', score)
print('Testing predict function')
preds = classifier.predict(X_test)
print('Preds.shape: ', preds.shape)
print('Testing predict proba function')
proba = classifier.predict_proba(X_test)
print('Proba.shape: ', proba.shape)
print('Testing get params')
print(classifier.get_params())
print('Testing set params')
classifier.set_params(optimizer='sgd', loss='mse')
print(classifier.get_params())
print('Testing attributes')
print('Classes')
print(classifier.classes_)
print('Config')
print(classifier.config_)
print('Weights')
print(classifier.weights_)
print('Test script complete.')
def _fit_and_score_keras2(method,
X,
y,
scorer,
train,
test,
verbose,
parameters,
fit_params,
type="Classification",
return_train_score=False,
return_parameters=False,
return_n_test_samples=False,
return_times=False,
error_score='raise'):
"""Fit estimator and compute scores for a given dataset split for KerasClassifier and KerasRegressor.
Parameters
----------
estimator : estimator object implementing 'fit'
The object to use to fit the data.
X : array-like of shape at least 2D
The data to fit.
y : array-like, optional, default: None
The target variable to try to predict in the case of
supervised learning.
scorer : A single callable or dict mapping scorer name to the callable
If it is a single callable, the return value for ``train_scores`` and
``test_scores`` is a single float.
For a dict, it should be one mapping the scorer name to the scorer
callable object / function.
The callable object / fn should have signature
``scorer(estimator, X, y)``.
train : array-like, shape (n_train_samples,)
Indices of training samples.
test : array-like, shape (n_test_samples,)
Indices of test samples.
verbose : integer
The verbosity level.
error_score : 'raise' (default) or numeric
Value to assign to the score if an error occurs in estimator fitting.
If set to 'raise', the error is raised. If a numeric value is given,
FitFailedWarning is raised. This parameter does not affect the refit
step, which will always raise the error.
parameters : dict or None
Parameters to be set on the estimator.
fit_params : dict or None
Parameters that will be passed to ``estimator.fit``.
return_train_score : boolean, optional, default: False
Compute and return score on training set.
return_parameters : boolean, optional, default: False
Return parameters that has been used for the estimator.
return_n_test_samples : boolean, optional, default: False
Whether to return the ``n_test_samples``
return_times : boolean, optional, default: False
Whether to return the fit/score times.
session : Keras backend with a tensorflow session attached
The keras backend session for applying K.clear_session()
after the classifier or regressor has been train and scored
given the split. This is mainly required to avoid posible
Out Of Memory errors with tensorflow not deallocating the
GPU memory after each iteration of the Cross Validation.
Returns
-------
train_scores : dict of scorer name -> float, optional
Score on training set (for all the scorers),
returned only if `return_train_score` is `True`.
test_scores : dict of scorer name -> float, optional
Score on testing set (for all the scorers).
n_test_samples : int
Number of test samples.
fit_time : float
Time spent for fitting in seconds.
score_time : float
Time spent for scoring in seconds.
parameters : dict or None, optional
The parameters that have been evaluated.
"""
from keras import backend as K
import tensorflow as tf
tf.logging.set_verbosity(
tf.logging.ERROR) # This is useful to avoid the info log of tensorflow
# The next 4 lines are for avoiding tensorflow to allocate all the GPU memory
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
K.set_session(sess)
if verbose > 1:
if parameters is None:
msg = ''
else:
msg = '%s' % (', '.join('%s=%s' % (k, v)
for k, v in parameters.items()))
print("[CV] %s %s" % (msg, (64 - len(msg)) * '.'))
# Adjust length of sample weights
fit_params = fit_params if fit_params is not None else {}
fit_params = dict([(k, _index_param_value(X, v, train))
for k, v in fit_params.items()])
test_scores = {}
train_scores = {}
estimator = None
if type == "Classification":
from keras.wrappers.scikit_learn import KerasClassifier
estimator = KerasClassifier(build_fn=method, verbose=0)
else:
from keras.wrappers.scikit_learn import KerasRegressor
estimator = KerasRegressor(build_fn=method, verbose=0)
if parameters is not None:
estimator.set_params(**parameters)
start_time = time.time()
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
is_multimetric = not callable(scorer)
n_scorers = len(scorer.keys()) if is_multimetric else 1
try:
if y_train is None:
estimator.fit(X_train, **fit_params)
else:
estimator.fit(X_train, y_train, **fit_params)
except Exception as e:
# Note fit time as time until error
fit_time = time.time() - start_time
score_time = 0.0
if error_score == 'raise':
raise
elif isinstance(error_score, numbers.Number):
if is_multimetric:
test_scores = dict(
zip(scorer.keys(), [
error_score,
] * n_scorers))
if return_train_score:
train_scores = dict(
zip(scorer.keys(), [
error_score,
] * n_scorers))
else:
test_scores = error_score
if return_train_score:
train_scores = error_score
warnings.warn(
"Classifier fit failed. The score on this train-test"
" partition for these parameters will be set to %f. "
"Details: \n%r" % (error_score, e), FitFailedWarning)
else:
raise ValueError("error_score must be the string 'raise' or a"
" numeric value. (Hint: if using 'raise', please"
" make sure that it has been spelled correctly.)")
else:
fit_time = time.time() - start_time
# _score will return dict if is_multimetric is True
test_scores = _score(estimator, X_test, y_test, scorer, is_multimetric)
score_time = time.time() - start_time - fit_time
if return_train_score:
train_scores = _score(estimator, X_train, y_train, scorer,
is_multimetric)
if verbose > 2:
if is_multimetric:
for scorer_name, score in test_scores.items():
msg += ", %s=%s" % (scorer_name, score)
else:
msg += ", score=%s" % test_scores
if verbose > 1:
total_time = score_time + fit_time
end_msg = "%s, total=%s" % (msg, logger.short_format_time(total_time))
print("[CV] %s %s" % ((64 - len(end_msg)) * '.', end_msg))
ret = [train_scores, test_scores] if return_train_score else [test_scores]
if return_n_test_samples:
ret.append(_num_samples(X_test))
if return_times:
ret.extend([fit_time, score_time])
if return_parameters:
ret.append(parameters)
# The estimator is erased
del estimator
# We assign the keras backend
# Clean the session
K.clear_session()
# The garbage collector is called in order to ensure that the estimator is erased from memory
for i in range(15):
gc.collect()
return ret
classifier.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch)
print('Testing score function')
score = classifier.score(X_train, Y_train)
print('Score: ', score)
print('Testing predict function')
preds = classifier.predict(X_test)
print('Preds.shape: ', preds.shape)
print('Testing predict proba function')
proba = classifier.predict_proba(X_test)
print('Proba.shape: ', proba.shape)
print('Testing get params')
print(classifier.get_params())
print('Testing set params')
classifier.set_params(optimizer='sgd', loss='mse')
print(classifier.get_params())
print('Testing attributes')
print('Classes')
print(classifier.classes_)
print('Config')
print(classifier.config_)
print('Weights')
print(classifier.weights_)
print('Test script complete.')
def neural_network_learning(x_train, y_train, x_test, y_test,
listoftraintestsplits,
config_learning: ConfigurationLearning,
num_classes: int):
# A. Preprocessing
for i in range(len(listoftraintestsplits)):
sc = preprocessing.StandardScaler().fit(
listoftraintestsplits[i][0].todense())
listoftraintestsplits[i][0] = sc.transform(
listoftraintestsplits[i][0].todense())
listoftraintestsplits[i][1] = sc.transform(
listoftraintestsplits[i][1].todense())
listoftraintestsplits[i][2] = to_categorical(
listoftraintestsplits[i][2], num_classes=num_classes)
listoftraintestsplits[i][3] = to_categorical(
listoftraintestsplits[i][3], num_classes=num_classes)
listoftraintestsplits[i][0], listoftraintestsplits[i][2] = shuffle(
listoftraintestsplits[i][0],
listoftraintestsplits[i][2],
random_state=31 * 9)
listoftraintestsplits[i][1], listoftraintestsplits[i][3] = shuffle(
listoftraintestsplits[i][1],
listoftraintestsplits[i][3],
random_state=31 * 9)
sc = preprocessing.StandardScaler().fit(x_train.todense())
x_train = sc.transform(x_train.todense())
x_test = sc.transform(x_test.todense())
y_train_c = to_categorical(y_train, num_classes=num_classes)
y_test_c = to_categorical(y_test, num_classes=num_classes)
x_train, y_train_c = shuffle(x_train, y_train_c, random_state=31 * 5)
x_test, y_test_c, y_test = shuffle(x_test,
y_test_c,
y_test,
random_state=31 * 7)
# B. Grid search to get best params
# activation = ['relu', 'tanh', 'sigmoid']
if config_learning.hyperparameters is None:
neurons_eq = [(25, 25), (25, 25, 25), (50, 50), (50, 50, 50),
(100, 100), (100, 100, 100), (175, 175), (175, 175, 175),
(200, 200), (200, 200, 200), (300, 300)]
param_grid = {
"optimizer_eq":
['RMSprop'], # ['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam'],
"epochs": [100, 200, 300, 400, 500],
"neurons_eq": neurons_eq, #50
"dropout_eq": [0, 0.01, 0.1, 0.25, 0.5],
}
else:
param_grid = config_learning.hyperparameters
kerasclf = KerasClassifier(build_fn=_my_keras_model,
batch_size=20,
verbose=0)
best_params, best_params_acc = customized_grid_search_dnn(
param_grid=param_grid,
clf=kerasclf,
listoftraintestsplits=listoftraintestsplits)
# C. Learn on best params
clf_best = KerasClassifier(build_fn=_my_keras_model,
batch_size=30,
input_dim_eq=x_train.shape[1],
output_dim_eq=y_train_c.shape[1],
verbose=0)
clf_best.set_params(**best_params)
clf_best.fit(x_train, y_train_c)
acc = np.mean(np.argmax(y_test_c, axis=1) == clf_best.predict(x_test))
print("DNN-Acc:", acc)
return acc, clf_best, sc
class BaseKerasSklearnModel(base_model.BaseModel):
'''
base keras model based on keras's model(without sklearn)
'''
## def __init__(self, data_file, delimiter, lst_x_keys, lst_y_keys, log_filename=DEFAULT_LOG_FILENAME, model_path=DEFAULT_MODEL_PATH, create_model_func=create_model_demo):
## '''
## init
## '''
## import framework.tools.log as log
## loger = log.init_log(log_filename)
## self.load_data(data_file, delimiter, lst_x_keys, lst_y_keys)
## self.model_path = model_path
## self.create_model_func=create_model_func
def __init__(self, **kargs):
'''
init
'''
import framework.tools.log as log
self.kargs = kargs
log_filename = self.kargs["basic_params"]["log_filename"]
model_path = self.kargs["basic_params"]["model_path"]
self.load_data_func = self.kargs["load_data"]["method"]
self.create_model_func = self.kargs["create_model"]["method"]
loger = log.init_log(log_filename)
(self.dataset, self.X, self.Y, self.X_evaluation, self.Y_evaluation) = self.load_data_func(**self.kargs["load_data"]["params"])
self.model_path = model_path
self.dic_params = {}
def load_data(self, data_file, delimiter, lst_x_keys, lst_y_keys):
'''
load data
'''
# Load the dataset
self.dataset = numpy.loadtxt(data_file, delimiter=",")
self.X = self.dataset[:, lst_x_keys]
self.Y = self.dataset[:, lst_y_keys]
def init_callbacks(self):
'''
init all callbacks
'''
os.system("mkdir -p %s" % (self.model_path))
checkpoint_callback = ModelCheckpoint(self.model_path + '/weights.{epoch:02d}-{acc:.2f}.hdf5', \
monitor='acc', save_best_only=False)
history_callback = LossHistory()
callbacks_list = [checkpoint_callback, history_callback]
self.dic_params["callbacks"] = callbacks_list
def init_model(self):
'''
init model
'''
train_params = {"nb_epoch": 10, "batch_size": 10}
self.dic_params.update(train_params)
self.model = KerasClassifier(build_fn=self.create_model_func, **self.kargs["create_model"]["params"])
# self.model = KerasClassifier(build_fn=self.create_model_func)
self.model.set_params(**self.dic_params)
def train_model(self):
'''
train model
'''
X = self.X
Y = self.Y
X_evaluation = self.X_evaluation
Y_evaluation = self.Y_evaluation
seed = 7
numpy.random.seed(seed) # Load the dataset
history = self.model.fit(X, Y)
scores = self.model.score(X, Y)
#history_callback = self.dic_params["callbacks"][1]
# print dir(history_callback)
# logging.info(str(history_callback.losses))
logging.info("final : %.2f%%" % (scores * 100))
logging.info(str(history.history))
def process(self):
'''
process
'''
self.init_callbacks()
self.init_model()
self.train_model()
batch_size = [20, 25, 30]
epochs = [20, 25, 30]
learn_rate = [0.005, 0.01, 0.015]
momentum = [0.85, 0.9, 0.95]
grid = dict(epochs=epochs,
batch_size=batch_size,
learn_rate=learn_rate,
momentum=momentum)
t1 = time.time()
scores = []
model_tt = KerasClassifier(build_fn=create_model, verbose=0)
for g in ParameterGrid(grid):
model_tt.set_params(**g)
model_tt.fit(X_train, Y_train)
scores.append(dict(params=g, score=model_tt.score(X_test, Y_test)))
print('model#', len(scores), scores[-1])
t2 = time.time()
print("Training time:", t2 - t1, 'sec')
df = pandas.DataFrame([{**row['params'], **row} for row in scores])
df = df.drop('params', axis=1)
df.sort_values('score')
model_tt.model.save('my_model.h5')
model = keras.models.load_model('my_model.h5')
def r_neural_network_learning(x_train, y_train, x_test, y_test,
listoftraintestsplits,
config_learning: ConfigurationLearningRNN,
num_classes: int):
# A. Preprocessing
for i in range(len(listoftraintestsplits)):
if config_learning.scale:
sc = preprocessing.StandardScaler().fit(
listoftraintestsplits[i][0].todense())
listoftraintestsplits[i][0] = sc.transform(
listoftraintestsplits[i][0].todense())
listoftraintestsplits[i][1] = sc.transform(
listoftraintestsplits[i][1].todense())
else:
listoftraintestsplits[i][0] = np.array(
listoftraintestsplits[i][0].todense())
listoftraintestsplits[i][1] = np.array(
listoftraintestsplits[i][1].todense())
listoftraintestsplits[i].append(
to_categorical(listoftraintestsplits[i][2],
num_classes=num_classes))
listoftraintestsplits[i].append(
to_categorical(listoftraintestsplits[i][3],
num_classes=num_classes))
# listoftraintestsplits[i][0], listoftraintestsplits[i][2] = shuffle(listoftraintestsplits[i][0],
# listoftraintestsplits[i][2],
# random_state=31 * 9)
# listoftraintestsplits[i][1], listoftraintestsplits[i][3] = shuffle(listoftraintestsplits[i][1],
# listoftraintestsplits[i][3],
# random_state=31 * 9)
trainsplitshape = (listoftraintestsplits[i][0].shape[0], 1,
listoftraintestsplits[i][0].shape[1])
testsplitshape = (listoftraintestsplits[i][1].shape[0], 1,
listoftraintestsplits[i][1].shape[1])
listoftraintestsplits[i][0] = listoftraintestsplits[i][0].reshape(
trainsplitshape)
listoftraintestsplits[i][1] = listoftraintestsplits[i][1].reshape(
testsplitshape)
assert len(listoftraintestsplits[0]) == 6
if config_learning.scale:
sc = preprocessing.StandardScaler().fit(x_train.todense())
x_train = sc.transform(x_train.todense())
x_test = sc.transform(x_test.todense())
else:
sc = None
x_train = np.array(x_train.todense())
x_test = np.array(x_test.todense())
y_train_c = to_categorical(y_train, num_classes=num_classes)
y_test_c = to_categorical(y_test, num_classes=num_classes)
feature_dim = x_train.shape[1]
x_train = x_train.reshape(x_train.shape[0], 1, x_train.shape[1])
x_test = x_test.reshape(x_test.shape[0], 1, x_test.shape[1])
# x_train, y_train_c = shuffle(x_train, y_train_c, random_state=31 * 5)
# x_test, y_test_c, y_test = shuffle(x_test, y_test_c, y_test, random_state=31 * 7)
# "optimizer": ['RMSprop'], # ['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam'],
if config_learning.hyperparameters is None:
param_grid = {
"RNN_epochs": [100, 200, 300, 350, 450, 500], #350], #50],
"RNN_nounits": [32, 128, 196, 256, 288], #, feature_dim],
"RNN_dropout": [0.6],
"RNN_lstmlayersno": [3],
"RNN_denselayersno": [3],
"RNN_l2reg": [0.00001],
"RNN_denseneurons": [round(0.45 * feature_dim)]
}
else:
param_grid = config_learning.hyperparameters
param_grid['RNN_denseneurons'] = [
round(x * feature_dim) for x in param_grid['RNN_denseneurons']
]
if config_learning.cv_optimize_rlf_params:
param_grid_rf = {
"RF_n_estimators": [250],
"RF_max_features": [0.3, 0.6, 'auto'],
"RF_max_depth": [10, 25, 50, 75, None],
"RF_min_samples_leaf": [6, 12, 1],
}
param_grid.update(param_grid_rf)
kerasclf = KerasClassifier(build_fn=my_model,
batch_size=128,
input_dim_eq=feature_dim,
output_dim_eq=num_classes,
optimizer="Adam",
verbose=0)
best_params_, best_params_acc = customized_grid_search_rnn(
param_grid=param_grid,
clf=kerasclf,
listoftraintestsplits=listoftraintestsplits,
cv_use_rnn_output=config_learning.cv_use_rnn_output,
noofparallelthreads=config_learning.noofparallelthreads)
best_params_rnn, best_params_rf = split_params_into_rnn_rf(
params=best_params_)
early_stop = keras.callbacks.EarlyStopping(monitor="loss",
patience=20,
verbose=1,
min_delta=0.0)
# param['callbacks'] = [early_stop]
# param['validation_data'] = (x_test.reshape(x_test.shape[0], feature_dim, 1), y_test_c)
# C. Learn on best params
clf_best = KerasClassifier(build_fn=my_model,
batch_size=128,
input_dim_eq=feature_dim,
output_dim_eq=num_classes,
optimizer=keras.optimizers.Adam(lr=10e-4),
callbacks=[early_stop],
verbose=1)
clf_best.set_params(**best_params_rnn)
rnnhist = clf_best.fit(x_train, y_train_c)
rnnacc: float = np.mean(
np.argmax(y_test_c, axis=1) == clf_best.predict(x_test))
# D. Learn RF
rlf_deep, rfaccuracy = compute_rlf_on_rnn(
clf_best=clf_best,
x_train=x_train,
x_test=x_test,
y_train=y_train,
y_test=y_test,
params=best_params_rf,
noofparallelthreads=config_learning.noofparallelthreads)
print("DNN-Acc: {}% // RF-Acc: {}%".format(round(rnnacc * 100, 2),
round(rfaccuracy * 100, 2)))
return rnnacc, clf_best, sc, rlf_deep, rfaccuracy, rnnhist
