labels = data[['diagnosis']].copy()
features = data.drop(columns='diagnosis')
feature_list = list(features)
train_features, test_features = np.split(features, [int(.9 * len(features))])
train_labels, test_labels = np.split(labels, [int(.9 * len(labels))])
print('Training Features Shape:', train_features.shape)
print('Training Labels Shape:', train_labels.shape)
print('Testing Features Shape:', test_features.shape)
print('Testing Labels Shape:', test_labels.shape)
# Define pca object
pca = PCA(n_components=2)
train_features = pca.fit_transform(train_features)
test_features = pca.fit_transform(test_features)
rfr = Ridge(type='classifier')
print('Train started............')
rfr.fit(train_features, train_labels)
print('Train completed..........')
# Use the forest's predict method on the test data
print('Prediction started............')
predictions = rfr.predict(test_features)
print('Prediction completed..........')
correct = 0
df = pd.DataFrame(data=predictions.flatten())
def build_model(model_type,
prediction_type,
configs,
feature_headers,
label_headers,
pca=None):
if model_type == 'Ridge':
model = Ridge(label_headers=label_headers,
alpha=configs['alpha'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'DecisionTree':
model = DecisionTree(label_headers=label_headers,
max_depth=configs['max_depth'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'AdaBoost':
model = AdaBoost(label_headers=label_headers,
n_estimators=configs['n_estimators'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'GradientBoost':
model = GradientBoost(label_headers=label_headers,
n_estimators=configs['n_estimators'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'RandomForest':
model = RandomForest(label_headers=label_headers,
n_estimators=configs['n_estimators'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'KernelSVM':
model = KernelSVM(kernel=configs['kernel'],
degree=configs['degree'],
cfg=args.cfg)
elif model_type == 'NeuralNetwork':
model = NeuralNetwork(feature_headers,
label_headers,
epochs=configs['epochs'],
batch_size=configs['batch_size'],
type=prediction_type,
cfg=args.cfg,
pca=pca)
elif model_type == 'ConvolutionalNeuralNetwork':
model = ConvolutionalNeuralNetwork(height=configs['height'],
width=configs['width'],
dimension=configs['dimension'],
classes=configs['classes'],
epochs=configs['epochs'],
batch_size=configs['batch_size'],
cfg=args.cfg)
elif model_type == 'LSTM':
model = LSTMModel(feature_headers,
label_headers,
epochs=configs['epochs'],
batch_size=configs['batch_size'],
type=prediction_type,
lookback=configs['lookback'],
num_of_cells=configs['num_of_cells'],
cfg=args.cfg,
pca=pca)
elif model_type == 'PCA':
model = PCA(n_components=configs['n_components'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'PLS':
model = PLS(n_components=configs['n_components'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'Lasso':
model = Lasso(label_headers=label_headers,
alpha=configs['alpha'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'AdaptiveLasso':
model = AdaptiveLasso(label_headers=label_headers,
alpha=configs['alpha'],
n_itr=configs['n_itr'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'GroupLasso':
model = GLasso(feature_headers=feature_headers,
label_headers=label_headers,
groups=configs['groups'],
type=prediction_type,
cfg=args.cfg)
elif model_type == 'ElasticNet':
model = ElasticNet(label_headers=label_headers,
l1_ratio=configs['l1_ratio'],
type=prediction_type,
cfg=args.cfg)
else:
print(model_type, ' is not implemented yet')
model = None
return model
labels = data[['diagnosis']].copy()
features = data.drop(columns='diagnosis')
feature_list = list(features)
train_features, test_features = np.split(features, [int(.9 * len(features))])
train_labels, test_labels = np.split(labels, [int(.9 * len(labels))])
print('Training Features Shape:', train_features.shape)
print('Training Labels Shape:', train_labels.shape)
print('Testing Features Shape:', test_features.shape)
print('Testing Labels Shape:', test_labels.shape)
# Define pca object
pca = PCA(n_components=2)
train_features = pca.fit_transform(train_features)
test_features = pca.fit_transform(test_features)
rfr = Ridge(type='classifier')
print('Train started............')
rfr.fit(train_features, train_labels)
print('Train completed..........')
# Use the forest's predict method on the test data
print('Prediction started............')
predictions = rfr.predict(test_features)
print('Prediction completed..........')
predict = Evaluation(evaluation=predictions, test_labels=test_labels)
r2s = predict.getAccuracy()
labels = data[label_headers].copy()
features = data[feature_headers].copy()
model = None
if '[' in model_type:
model_type = model_type.replace('[','')
model_type = model_type.replace(']','')
sub_models = model_type.split(',')
sub_models_list = []
index = 0
for sub_model_type in sub_models:
sub_model_type = sub_model_type.lstrip()
sub_model_type = sub_model_type.rstrip()
if index == 0:
tmp_features = PCA.fit(features)
else:
model = load_model(modelpath, model_type, type, feature_headers, label_headers)
index = 1
else:
model = load_model(modelpath, model_type, type, feature_headers, label_headers)
predictions = model.predict(features)
#print(predictions)
dict = {}
index = 0
for label_header in label_headers:
dict[label_header] = predictions
index += 1