def main(argv):
input_filename_x = 'train_data.csv'
input_filename_y = 'train_labels.csv'
test_input_filename = 'test_data.csv'
svc_model_filename = 'svc_classif.pkl'
lr_model_filename = 'lr_classif.pkl'
rfc_model_filename = 'rfc_classif.pkl'
rfc_feat_imp_filename = 'rfc_feat_imp.png'
model_comp_result_chart_filename = 'method_comp_res.png'
io = lib.io.IO()
viz = lib.viz.Viz()
# Read data
X_o, y_o = io.read_data(input_filename_x, input_filename_y)
test_x = io.read_data(test_input_filename, None)
print "There are " + str(len(X_o)) + " samples in the train set."
print "There are " + str(len(test_x)) + " samples in the test set."
SVC_ll , SVC_a, RFC_ll, RFC_a, LR_ll, LR_a = [], [], [], [], [], []
comps = [10, 20, 50, 100, 150, 200, 264]
for s in comps:
print("Amount of components: %d"%s)
cl = lib.cl.CL(io, viz)
X = copy.deepcopy(X_o)
y = copy.deepcopy(y_o)
test_x = np.matrix(test_x)
test_ids = range(1, len(test_x)+1)
# Remove outliers
X, y = cl.lof(np.matrix(X), np.matrix(y))
# Shuffle
X, y = io.shuffle(X, y)
# PCA
X = cl.pca(np.matrix(X), components=s, filename=None).tolist()
# test_x = cl.pca(np.matrix(test_x), components=s, filename=None).tolist()
val_ids, val_x, val_y = io.pick_set(X, y, 726)
train_ids, train_x, train_y = io.pick_set(X, y, 3200)
# Train
cl.lr_cl_train(train_x, train_y, filename=lr_model_filename)
# Validate
ll, a = cl.lr_cl_val(val_x, val_y)
LR_ll.append(ll)
LR_a.append(a)
# Draw some results
viz.cross_results(comps, LR_ll, LR_a, 'pca_cross_val.png')
def main(argv):
input_filename_x = 'train_data.csv'
input_filename_y = 'train_labels.csv'
test_input_filename = 'test_data.csv'
lr_model_filename = 'lr2_classif.pkl'
model_comp_result_chart_filename = 'method_comp_res.png'
io = lib.io.IO()
viz = lib.viz.Viz()
cl = lib.cl.CL(io, viz)
# Read data
X, y = io.read_data(input_filename_x, input_filename_y)
test_x = io.read_data(test_input_filename, None)
X_ = copy.deepcopy(X)
y_ = copy.deepcopy(y)
print "There are " + str(len(X)) + " samples in the train set."
print "There are " + str(len(test_x)) + " samples in the test set."
test_x = np.matrix(test_x)
test_ids = range(1, len(test_x) + 1)
# Remove outliers
X, y = cl.lof(np.matrix(X), np.matrix(y))
# Shuffle
X, y = io.shuffle(X, y)
# PCA
#X = cl.pca(np.matrix(X), 'pca_explained_variance.png').tolist()
#test_x = cl.pca(np.matrix(test_x), None).tolist()
# Split data to train and validation set
val_ids, val_x, val_y = io.pick_set(X, y, 726)
train_ids, train_x, train_y = io.pick_set(X, y, 3200)
# Train
# cl.lr_cl_train(train_x, train_y, filename=lr_model_filename)
cl.lr_cl_load(lr_model_filename)
# Validate
cl.lr_cl_val(val_x, val_y)
# predict
pred_class, pred_proba = cl.lr_cl_pred(test_x)
# Output
io.write_classes('classes_lr2_result.csv', test_ids, pred_class)
io.write_probabilities('probabilities_lr2_result.csv', test_ids,
pred_proba)
def main(argv):
input_filename_x = 'train_data.csv'
input_filename_y = 'train_labels.csv'
test_input_filename = 'test_data.csv'
svc_model_filename = 'svc_classif.pkl'
# lr_model_filename = 'lr_classif.pkl'
lr_model_filename = 'classif.pkl'
rfc_model_filename = 'rfc_classif.pkl'
rfc_feat_imp_filename = 'rfc_feat_imp.png'
model_comp_result_chart_filename = 'method_comp_res.png'
io = lib.io.IO()
viz = lib.viz.Viz()
cl = lib.cl.CL(io, viz)
# Read data
X, y = io.read_data(input_filename_x, input_filename_y)
test_x = io.read_data(test_input_filename, None)
X_ = copy.deepcopy(X)
y_ = copy.deepcopy(y)
print "There are " + str(len(X)) + " samples in the train set."
print "There are " + str(len(test_x)) + " samples in the test set."
test_x = np.matrix(test_x)
test_ids = range(1, len(test_x) + 1)
# PCA etc.
X = cl.pca(np.matrix(X), 'pca_explained_variance.png').tolist()
# test_x = cl.pca(test_x, None).tolist()
val_ids, val_x, val_y = io.pick_set(X, y, 1063)
_, no_pca_val_x, no_pca_val_y = io.pick_set(X_, y_, 1063)
#train_ids, train_x, train_y = io.pick_set(X, y, 4000)
#_, no_pca_train_x, no_pca_train_y = io.pick_set(X_, y_, 4000)
# Train
# cl.svc_cl_train(train_x, train_y, filename=svc_model_filename)
# cl.lr_cl_train(train_x, train_y, filename=lr_model_filename)
#cl.rfc_cl_train(no_pca_train_x, no_pca_train_y,
# filename=rfc_model_filename,
# feat_imp_plot_filename=rfc_feat_imp_filename)
cl.svc_cl_load(svc_model_filename)
cl.lr_cl_load(lr_model_filename)
cl.rfc_cl_load(rfc_model_filename)
# validate
results = {}
results['SVC'] = cl.svc_cl_val(val_x, val_y)
results['Linear Regression'] = cl.lr_cl_val(no_pca_val_x, no_pca_val_y)
results['Random Forest Classifier'] = cl.rfc_cl_val(
no_pca_val_x, no_pca_val_y)
# Draw some results
viz.model_comp_results(results, model_comp_result_chart_filename)
# predict
# pred_class, pred_proba = cl.svc_cl_pred(test_x)
pred_class, pred_proba = cl.rfc_cl_pred(test_x)
# pred_class, pred_proba = cl.lr_cl_pred(test_x)
# Output
io.write_classes('classes_sub_result.csv', test_ids, pred_class)
io.write_probabilities('probabilities_sub_result.csv', test_ids,
pred_proba)
def main(argv):
input_filename_x = 'train_data.csv'
input_filename_y = 'train_labels.csv'
test_input_filename = 'test_data.csv'
svc_model_filename = 'svc_classif.pkl'
lr_model_filename = 'lr_classif.pkl'
rfc_model_filename = 'rfc_classif.pkl'
rfc_feat_imp_filename = 'rfc_feat_imp.png'
model_comp_result_chart_filename = 'method_comp_res.png'
io = lib.io.IO()
viz = lib.viz.Viz()
# Read data
X_o, y_o = io.read_data(input_filename_x, input_filename_y)
test_x = io.read_data(test_input_filename, None)
print "There are " + str(len(X_o)) + " samples in the train set."
print "There are " + str(len(test_x)) + " samples in the test set."
SVC_ll, SVC_a, RFC_ll, RFC_a, LR_ll, LR_a = [], [], [], [], [], []
for s in range(50):
print("Iteration %d" % s)
cl = lib.cl.CL(io, viz)
X = copy.deepcopy(X_o)
y = copy.deepcopy(y_o)
X_ = copy.deepcopy(X_o)
y_ = copy.deepcopy(y_o)
test_x = np.matrix(test_x)
test_ids = range(1, len(test_x) + 1)
# Remove outliers
X, y = cl.lof(np.matrix(X), np.matrix(y))
X_, y_ = cl.lof(np.matrix(X_), np.matrix(y_))
# Shuffle
X, y = io.shuffle(X, y)
X_, y_ = io.shuffle(X_, y_)
# PCA
X = cl.pca(np.matrix(X), 'pca_explained_variance.png').tolist()
test_x = cl.pca(np.matrix(test_x), None).tolist()
val_ids, val_x, val_y = io.pick_set(X, y, 726)
_, no_pca_val_x, no_pca_val_y = io.pick_set(X_, y_, 726)
train_ids, train_x, train_y = io.pick_set(X, y, 3200)
_, no_pca_train_x, no_pca_train_y = io.pick_set(X_, y_, 3200)
# Train
cl.svc_cl_train(train_x, train_y, filename=svc_model_filename)
cl.lr_cl_train(train_x, train_y, filename=lr_model_filename)
cl.rfc_cl_train(no_pca_train_x,
no_pca_train_y,
filename=rfc_model_filename,
feat_imp_plot_filename=rfc_feat_imp_filename)
# validate
ll, a = cl.svc_cl_val(val_x, val_y)
SVC_ll.append(ll)
SVC_a.append(a)
ll, a = cl.lr_cl_val(val_x, val_y)
LR_ll.append(ll)
LR_a.append(a)
ll, a = cl.rfc_cl_val(no_pca_val_x, no_pca_val_y)
RFC_ll.append(ll)
RFC_a.append(a)
# Draw some results
results = {
'SVC': (sum(SVC_ll) / len(SVC_ll), sum(SVC_a) / len(SVC_a)),
'Logistic Regression':
(sum(LR_ll) / len(LR_ll), sum(LR_a) / len(LR_a)),
'Random Forest Classifier':
(sum(RFC_ll) / len(RFC_ll), sum(RFC_a) / len(RFC_a))
}
viz.model_comp_results(results, model_comp_result_chart_filename)
# predict
pred_class, pred_proba = cl.lr_cl_pred(test_x)
# Output
io.write_classes('classes_sub_result.csv', test_ids, pred_class)
io.write_probabilities('probabilities_sub_result.csv', test_ids,
pred_proba)
test_ids = range(1, len(test_x) + 1)
# load from file
if options.load_path is not None:
model = load_model(options.load_path + '/' + model_filename,
options.load_path + '/' + weights_filename)
# train
else:
# Remove outliers
X, y = cl.lfo(np.matrix(X), np.matrix(y))
# Shuffle
X, y = io.shuffle(X, y)
# Pick val and train set
val_ids, val_x, val_y = io.pick_set(X, y, 526)
train_ids, train_x, train_y = io.pick_set(X, y, 3400)
# train
model, history = train_model(train_x, train_y, val_x, val_y)
# Save model
full_model_filename = options.model_path + '/' + model_filename
full_weights_filename = options.model_path + '/' + weights_filename
with open(full_model_filename, 'w') as f:
f.write(model.to_yaml())
model.save_weights(full_weights_filename)
# Print metrics
viz.plot_nn_perf(history, options.output_path + '/nn_perf.png')
def main(argv):
input_filename_x = 'train_data.csv'
input_filename_y = 'train_labels.csv'
test_input_filename = 'test_data.csv'
svc_model_filename = 'svc_classif.pkl'
lr_model_filename = 'lr_classif.pkl'
rfc_model_filename = 'rfc_classif.pkl'
rfc_feat_imp_filename = 'rfc_feat_imp.png'
model_comp_result_chart_filename = 'method_comp_res.png'
nn_model_filename = 'nn1.pkl'
io = lib.io.IO()
viz = lib.viz.Viz()
nn = lib.nn.NN(io, viz)
cl = lib.cl.CL(io, viz)
# Read data
print "Reading train data..."
X, y = io.read_data(input_filename_x, input_filename_y)
y = io.shift_v(y, shift=-1)
print "Reading test data..."
test_x = io.read_data(test_input_filename, None)
print "There are " + str(len(X)) + " samples in the train set."
print "There are " + str(len(test_x)) + " samples in the test set."
test_x = np.matrix(test_x)
test_ids = range(1, len(test_x) + 1)
# PCA etc.
X = cl.pca(np.matrix(X), 'pca_explained_variance.png').tolist()
test_x = cl.pca(test_x, None).tolist()
# Split data to train and validation set
# mini_batches
#ids, batches_x, batches_y = io.split_data(X, y, 100, 100)
val_ids, val_x, val_y = io.pick_set(X, y, 563)
train_ids, train_x, train_y = io.pick_set(X, y, 3800)
nn.initialize(train_x.shape[1], nn1=18, nn2=9,
alpha=0.01) #, filename=nn_model_filename)
# Train
pred, proba, acc = nn.predict(train_x, train_y)
print("Train set classification accuray before training: %.4f" % acc)
nn.train(train_x, train_y, val_x, val_y, training_steps=100000)
nn.save_nn(nn_model_filename)
# validate
pred, proba, acc = nn.predict(train_x, train_y)
print("Train set classification accuray after training: %.4f" % acc)
pred, proba, acc = nn.predict(val_x, val_y)
print("Validation set classification accuray after training: %.4f" % acc)
# Draw some results
# viz.model_comp_results(results, model_comp_result_chart_filename)
# predict
pred_class, pred_proba, _ = nn.predict(test_x)
pred_class = io.shift_v(pred_class, shift=1)
# Output
io.write_classes('nn_classes_sub_result.csv', test_ids, pred_class)
io.write_probabilities('nn_probabilities_sub_result.csv', test_ids,
pred_proba)