def classification_ann(instruction,
callback=False,
dataset=None,
text=[],
ca_threshold=None,
preprocess=True,
callback_mode='min',
drop=None,
random_state=49,
test_size=0.2,
epochs=50,
generate_plots=True,
maximizer="val_accuracy",
save_model=False,
save_path=os.getcwd(),
add_layer={}):
'''
Body of the classification function used that is called in the neural network query
if the data is categorical.
:param many parameters: used to preprocess, tune, plot generation, and parameterizing the neural network trained.
:return dictionary that holds all the information for the finished model.
'''
if dataset is None:
dataReader = DataReader(get_file())
else:
dataReader = DataReader(dataset)
logger("Reading in dataset")
data = dataReader.data_generator()
if drop is not None:
data.drop(drop, axis=1, inplace=True)
data, y, remove, full_pipeline = initial_preprocessor(
data,
instruction,
preprocess,
ca_threshold,
text,
test_size=test_size,
random_state=random_state)
logger("->", "Target column found: {}".format(remove))
# Needed to make a custom label encoder due to train test split changes
# Can still be inverse transformed, just a bit of extra work
y = pd.concat([y['train'], y['test']], axis=0)
num_classes = len(np.unique(y))
if num_classes < 2:
raise Exception("Number of classes must be greater than or equal to 2")
X_train = data['train']
X_test = data['test']
if num_classes >= 2:
# ANN needs target one hot encoded for classification
one_hotencoder = OneHotEncoder()
y = pd.DataFrame(one_hotencoder.fit_transform(
np.reshape(y.values, (-1, 1))).toarray(),
columns=one_hotencoder.get_feature_names())
y_train = y.iloc[:len(X_train)]
y_test = y.iloc[len(X_train):]
models = []
losses = []
accuracies = []
model_data = []
logger("Establishing callback function")
# early stopping callback
es = EarlyStopping(monitor=maximizer, mode='max', verbose=0, patience=5)
callback_value = None
if callback is not False:
callback_value = [es]
i = 0
model = get_keras_model_class(data, i, num_classes, add_layer)
logger("Training initial model")
history = model.fit(X_train,
y_train,
callbacks=callback_value,
epochs=epochs,
validation_data=(X_test, y_test),
verbose=0)
model_data.append(model)
models.append(history)
col_name = [[
"Initial number of layers ", "| Training Accuracy ", "| Test Accuracy "
]]
col_width = max(len(word) for row in col_name for word in row) + 2
for row in col_name:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
values = []
values.append(str(len(model.layers)))
values.append("| " + str(history.history['accuracy'][
len(history.history['val_accuracy']) - 1]))
values.append("| " + str(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1]))
datax = []
datax.append(values)
for row in datax:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
# print((" " * 2 * counter)+ tabulate(datax, headers=col_name, tablefmt='orgtbl'))
losses.append(history.history[maximizer][len(history.history[maximizer]) -
1])
accuracies.append(
history.history['val_accuracy'][len(history.history['val_accuracy']) -
1])
# keeps running model and fit functions until the validation loss stops
# decreasing
logger("Testing number of layers")
col_name = [[
"Current number of layers", "| Training Accuracy", "| Test Accuracy"
]]
col_width = max(len(word) for row in col_name for word in row) + 2
for row in col_name:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
datax = []
# while all(x < y for x, y in zip(accuracies, accuracies[1:])):
while (len(accuracies) <= 2 or
accuracies[len(accuracies) - 1] > accuracies[len(accuracies) - 2]):
model = get_keras_model_class(data, i, num_classes, add_layer)
history = model.fit(X_train,
y_train,
callbacks=callback_value,
epochs=epochs,
validation_data=(X_test, y_test),
verbose=0)
values = []
datax = []
values.append(str(len(model.layers)))
values.append("| " + str(history.history['accuracy'][
len(history.history['accuracy']) - 1]))
values.append("| " + str(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1]))
datax.append(values)
for row in datax:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
del values, datax
losses.append(
history.history[maximizer][len(history.history[maximizer]) - 1])
accuracies.append(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1])
models.append(history)
model_data.append(model)
i += 1
# print((" " * 2 * counter)+ tabulate(datax, headers=col_name, tablefmt='orgtbl'))
# del values, datax
final_model = model_data[accuracies.index(max(accuracies))]
final_hist = models[accuracies.index(max(accuracies))]
print("")
logger('->',
"Best number of layers found: " + str(len(final_model.layers)))
logger(
'->', "Training Accuracy: " + str(final_hist.history['accuracy'][
len(final_hist.history['val_accuracy']) - 1]))
logger(
'->', "Test Accuracy: " + str(final_hist.history['val_accuracy'][
len(final_hist.history['val_accuracy']) - 1]))
# genreates appropriate classification plots by feeding all information
plots = {}
if generate_plots:
plots = generate_classification_plots(models[len(models) - 1])
if save_model:
save(final_model, save_model, save_path)
print("")
logger("Stored model under 'classification_ANN' key")
clearLog()
K.clear_session()
# stores the values and plots into the object dictionary
return {
'id': generate_id(),
"model": final_model,
'num_classes': num_classes,
"plots": plots,
"target": remove,
"preprocessor": full_pipeline,
"interpreter": one_hotencoder,
'test_data': {
'X': X_test,
'y': y_test
},
'losses': {
'training_loss': final_hist.history['loss'],
'val_loss': final_hist.history['val_loss']
},
'accuracy': {
'training_accuracy': final_hist.history['accuracy'],
'validation_accuracy': final_hist.history['val_accuracy']
}
}
def classification_ann(instruction,
dataset=None,
text=None,
ca_threshold=None,
preprocess=True,
callback_mode='min',
drop=None,
random_state=49,
test_size=0.2,
epochs=50,
generate_plots=True,
maximizer="val_loss",
save_model=True,
save_path=os.getcwd()):
global currLog
logger("Reading in dataset...")
dataReader = DataReader(dataset)
data = dataReader.data_generator()
if drop is not None:
data.drop(drop, axis=1, inplace=True)
data, y, remove, full_pipeline = initial_preprocesser(
data, instruction, preprocess, ca_threshold, text)
logger("->", "Target Column Found: {}".format(remove))
# Needed to make a custom label encoder due to train test split changes
# Can still be inverse transformed, just a bit of extra work
y = pd.concat([y['train'], y['test']], axis=0)
num_classes = len(np.unique(y))
X_train = data['train']
X_test = data['test']
# ANN needs target one hot encoded for classification
one_hot_encoder = OneHotEncoder()
y = pd.DataFrame(one_hot_encoder.fit_transform(
np.reshape(y.values, (-1, 1))).toarray(),
columns=one_hot_encoder.get_feature_names())
y_train = y.iloc[:len(X_train)]
y_test = y.iloc[len(X_train):]
models = []
losses = []
accuracies = []
model_data = []
logger("Establishing callback function...")
# early stopping callback
es = EarlyStopping(monitor=maximizer, mode='min', verbose=0, patience=5)
i = 0
model = get_keras_model_class(data, i, num_classes)
logger("Training initial model...")
history = model.fit(X_train,
y_train,
epochs=epochs,
validation_data=(X_test, y_test),
callbacks=[es],
verbose=0)
model_data.append(model)
models.append(history)
col_name = [[
"Initial number of layers ", "| Training Loss ", "| Test Loss "
]]
col_width = max(len(word) for row in col_name for word in row) + 2
for row in col_name:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
values = []
values.append(str(len(model.layers)))
values.append(
"| " +
str(history.history['loss'][len(history.history['val_loss']) - 1]))
values.append(
"| " +
str(history.history['val_loss'][len(history.history['val_loss']) - 1]))
datax = []
datax.append(values)
for row in datax:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
#print((" " * 2 * counter)+ tabulate(datax, headers=col_name, tablefmt='orgtbl'))
losses.append(history.history[maximizer][len(history.history[maximizer]) -
1])
# keeps running model and fit functions until the validation loss stops
# decreasing
logger("Testing number of layers...")
col_name = [["Current number of layers", "| Training Loss", "| Test Loss"]]
col_width = max(len(word) for row in col_name for word in row) + 2
for row in col_name:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
datax = []
while (all(x > y for x, y in zip(losses, losses[1:]))):
model = get_keras_model_class(data, i, num_classes)
history = model.fit(X_train,
y_train,
epochs=epochs,
validation_data=(X_test, y_test),
callbacks=[es],
verbose=0)
values = []
datax = []
values.append(str(len(model.layers)))
values.append(
"| " +
str(history.history['loss'][len(history.history['val_loss']) - 1]))
values.append("| " + str(history.history['val_loss'][
len(history.history['val_loss']) - 1]))
datax.append(values)
for row in datax:
print((" " * 2 * counter) + "| " +
("".join(word.ljust(col_width) for word in row)) + " |")
losses.append(
history.history[maximizer][len(history.history[maximizer]) - 1])
accuracies.append(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1])
i += 1
#print((" " * 2 * counter)+ tabulate(datax, headers=col_name, tablefmt='orgtbl'))
#del values, datax
final_model = model_data[losses.index(min(losses))]
final_hist = models[losses.index(min(losses))]
print("")
logger('->',
"Best number of layers found: " + str(len(final_model.layers)))
logger(
'->', "Training Accuracy: " + str(final_hist.history['accuracy'][
len(final_hist.history['val_accuracy']) - 1]))
logger(
'->', "Test Accuracy: " + str(final_hist.history['val_accuracy'][
len(final_hist.history['val_accuracy']) - 1]))
# genreates appropriate classification plots by feeding all information
plots = generate_classification_plots(models[len(models) - 1], data, y,
model, X_test, y_test)
if save_model:
save(final_model, save_model)
print("")
logger("Stored model under 'classification_ANN' key")
# stores the values and plots into the object dictionary
return {
'id': generate_id(),
"model": final_model,
'num_classes': num_classes,
"plots": plots,
"target": remove,
"preprocesser": full_pipeline,
"interpreter": one_hot_encoder,
'losses': {
'training_loss': final_hist.history['loss'],
'val_loss': final_hist.history['val_loss']
},
'accuracy': {
'training_accuracy': final_hist.history['accuracy'],
'validation_accuracy': final_hist.history['val_accuracy']
}
}
