def main(file, interactive=False, debug=False):
if file is not None:
env = Environment()
with open(file, "r") as f:
program_str = f.read()
l = Lexer(program_str)
p = Parser(l)
program = p.parse_program()
if debug:
print("PARSED PROGRAM")
print("-" * 50)
print(program)
print("-" * 50)
if len(p.errors) != 0:
repl.print_parser_errors(p.errors)
exit(0)
evaluated = evaluator.eval(program, env)
if (not interactive and evaluated is not None
and evaluated != NULL) or evaluated.typ == mobject.ERROR_OBJ:
print(evaluated.inspect)
if interactive:
repl.start(env=env)
else:
repl.start()
def eval_test(input: str) -> MonkeyObject:
l = lexer.Lexer(input)
p = parser.Parser(l)
program = p.parse_program()
env = mobject.Environment()
return evaluator.eval(program, env)
def test_bang_operator(input_data, expected_val):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
output = eval(program)
assert output.value == expected_val
def test_eval_integer_expression(input_data, expected_val):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
output = eval(program)
assert output.value == expected_val
def main(input): tokens = lexer.get_tokens(input) parser_tree = parser.parse(tokens) if type(parser_tree) == str: return parser_tree else: return evaluator.eval(parser_tree)
def test_if_else_expression(input_data, expected_output):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
output = eval(program)
if hasattr(output, "value"):
assert output.value == expected_output
else:
assert str(output) == expected_output
def load(filename):
"""Load scheme source file `filename`
"""
# The parameter fildname is of the form '"path"'
filename = filename[1:-1]
with open(filename) as file:
input = file.read()
result = []
parseInput(input, 0, result)
for exp in result:
output = eval(exp, the_global_environment)
return output
def excute(self, env, name, value):
if isinstance(name, t.List): # Function definition
fname = name[0]
args = name[1:]
func = t.Function(args, value, env, fname)
env[fname] = func
return t.Null()
elif isinstance(name, t.Symbol): # Value definition
env[name] = ev.eval(value, env)
return t.Null()
else:
raise SyntaxError('define')
def __main__():
sys.stdout.write("-> ")
sys.stdout.flush()
for line in sys.stdin:
try:
ast = parser.parse(line)
result = evaluator.eval(ast, global_env)
print("# " + str(result))
sys.stdout.write("-> ")
sys.stdout.flush()
except Exception as e:
print(e)
sys.stdout.write("-> ")
sys.stdout.flush()
def repl(prompt='lispy> ', inport=p.InPort(sys.stdin), out=sys.stdout):
"""A prompt-read-eval-print loop.
"""
sys.stderr.write("Lispy version 2.0\n")
while True:
try:
if prompt:
sys.stderr.write(prompt)
x = p.parse(inport)
if x is p.eof_object:
return
val = e.eval(x)
if val is not None and out:
print >> out, to_string(val)
except Exception, ex:
print '{0}: {1}'.format(type(ex).__name__, ex)
break
def repl(prompt='lispy> ', inport=p.InPort(sys.stdin), out=sys.stdout):
"""A prompt-read-eval-print loop.
"""
sys.stderr.write("Lispy version 2.0\n")
while True:
try:
if prompt:
sys.stderr.write(prompt)
x = p.parse(inport)
if x is p.eof_object:
return
val = e.eval(x)
if val is not None and out:
print >> out, to_string(val)
except Exception, ex:
print '{0}: {1}'.format(type(ex).__name__, ex)
break
def repl(prompt="> "):
while True:
program = ''
try:
program = input(prompt)
except (KeyboardInterrupt, EOFError):
print()
return
if len(program) > 0:
val = None
try:
val = eval(parse(program))
except NameError as e:
print(e)
continue
if val is not None:
print(sexpr(val))
def start(env=None):
if env is None:
env = mobject.Environment()
while True:
print(PROMPT, end=" ")
line = input()
if not line:
return
l = lexer.Lexer(line)
p = parser.Parser(l)
program = p.parse_program()
if len(p.errors) != 0:
print_parser_errors(p.errors)
continue
evaluated = evaluator.eval(program, env)
if evaluated is not None:
print(evaluated.inspect)
def build_cnn(lang, odir):
'''Train, valid, test CNN
lang: The language name
odir: output directory of prediction results
'''
doc_idx = 2
max_len = 40 # sequence length
epochs = 10
encode_dir = './data/encode/' + lang + '/'
indices_dir = './data/indices/' + lang + '/'
wt_dir = './resources/weight/'
res_dir = './resources/classifier/cnn/'
clf_path = res_dir + lang + '.clf'
# don't reload classifier for debug usage
# load embedding weights
weights = np.load(wt_dir + lang + '.npy')
# build model architecture
text_input = Input(shape=(max_len, ), dtype='int32', name='input')
embeds = Embedding(weights.shape[0],
weights.shape[1],
weights=[weights],
input_length=max_len,
trainable=True,
name='embedding')(text_input)
# convolution
conv3 = Conv1D(kernel_size=3, filters=100, padding='same',
name='conv3')(embeds)
maxp3 = MaxPool1D()(conv3)
conv4 = Conv1D(kernel_size=4, filters=100, padding='same',
name='conv4')(embeds)
maxp4 = MaxPool1D()(conv4)
conv5 = Conv1D(kernel_size=5, filters=100, padding='same',
name='conv5')(embeds)
maxp5 = MaxPool1D()(conv5)
# merge
merge_convs = keras.layers.concatenate([maxp3, maxp4, maxp5], axis=-1)
# flatten
flat_l = Flatten()(merge_convs)
# dense, according to kim'14 paper,
# regularizer applies to the both kernel and bias
dense_l = Dense(
100,
activation='softplus',
name='dense',
kernel_regularizer=keras.regularizers.l1_l2(0, 0.03),
bias_regularizer=keras.regularizers.l1_l2(0, 0.03),
)(flat_l)
dp_l = Dropout(0.3, name='dropout')(dense_l)
# predict, binary prediction
predicts = Dense(1, activation='sigmoid', name='predict')(dp_l)
# model
model = Model(inputs=text_input, outputs=predicts)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
print(model.summary())
best_valid_f1 = 0.0
best_model = None
for e in range(epochs):
accuracy = 0.0
loss = 0.0
step = 1
print('--------------Epoch: {}--------------'.format(e))
# load training and batch dataset
train_iter = evaluator.data_iter(indices_dir + 'train.tsv',
batch_size=64)
# train model
for class_wt, x_train, y_train in train_iter:
if len(np.unique(y_train)) == 1:
continue
tmp = model.train_on_batch([x_train],
y_train,
class_weight=class_wt)
loss += tmp[0]
loss_avg = loss / step
accuracy += tmp[1]
accuracy_avg = accuracy / step
if step % 30 == 0:
print('Step: {}'.format(step))
print('\tLoss: {}. Accuracy: {}'.format(
loss_avg, accuracy_avg))
print('--------------------------------------')
step += 1
# valid model to find the best model
print('---------------Validation------------')
valid_iter = evaluator.data_iter(indices_dir + 'valid.tsv',
batch_size=64,
if_shuffle=False)
y_preds = []
y_valids = []
for _, x_valid, y_valid in valid_iter:
tmp_preds = model.predict([x_valid])
for item_tmp in tmp_preds:
y_preds.append(round(item_tmp[0]))
y_valids.extend(y_valid)
valid_f1 = f1_score(
y_true=y_valids,
y_pred=y_preds,
average='weighted',
)
print('Validating f1-macro score: ' + str(valid_f1))
if best_valid_f1 < valid_f1:
best_valid_f1 = valid_f1
best_model = model
pickle.dump(best_model, open(clf_path, 'wb'))
# test moddel
print('--------------Test--------------------')
y_preds = []
y_probs = []
test_iter = evaluator.data_iter(indices_dir + 'test.tsv',
batch_size=64,
if_shuffle=False)
for _, x_test, y_test in test_iter:
tmp_preds = best_model.predict([x_test])
for item_tmp in tmp_preds:
y_probs.append(item_tmp[0])
y_preds.append(int(round(item_tmp[0])))
with open(odir + lang + '.tsv', 'w') as wfile:
with open(indices_dir + 'test.tsv') as dfile:
wfile.write(dfile.readline().strip() +
'\tpred\tpred_prob\n')
for idx, line in enumerate(dfile):
wfile.write(line.strip() + '\t' + str(y_preds[idx]) +
'\t' + str(y_probs[idx]) + '\n')
# save the predicted results
evaluator.eval(odir + lang + '.tsv', odir + lang + '.score')
def build_bert(lang, odir, params=None):
'''Google Bert Classifier
lang: The language name
odir: output directory of prediction results
'''
if not params:
params = dict()
params['balance_ratio'] = 0.9
params['freeze'] = False
params['decay_rate'] = .001
params['lr'] = 2e-5
params['warm_steps'] = 100
params['train_steps'] = 1000
params['batch_size'] = 16
params['balance'] = True
split_dir = './data/split/' + lang + '/'
if torch.cuda.is_available():
device = str(get_freer_gpu())
torch.cuda.set_device(device)
else:
device = torch.device('cpu')
print(device)
n_gpu = torch.cuda.device_count()
print(torch.cuda.get_device_name())
print('Number of GPUs: ', n_gpu)
print('Loading Datasets and oversample training data...')
train_df = pd.read_csv(split_dir + 'train.tsv', sep='\t', na_values='x')
# oversample the minority class
if params['balance']:
label_count = Counter(train_df.label)
for label_tmp in label_count:
sample_num = label_count.most_common(
1)[0][1] - label_count[label_tmp]
if sample_num == 0:
continue
train_df = pd.concat([
train_df, train_df[train_df.label == label_tmp].sample(
int(sample_num * params['balance_ratio']), replace=True)
])
train_df = train_df.reset_index() # to prevent index key error
valid_df = pd.read_csv(split_dir + 'valid.tsv',
sep='\t',
na_values='x')
test_df = pd.read_csv(split_dir + 'train.tsv', sep='\t', na_values='x')
data_df = [train_df, valid_df, test_df]
# We need to add special tokens at the beginning and end of each sentence for BERT to work properly
for doc_df in data_df:
doc_df.text = doc_df.text.apply(lambda x: '[CLS] ' + x + ' [SEP]')
if lang == 'English':
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased',
do_lower_case=True)
elif lang == 'Chinese':
tokenizer = BertTokenizer.from_pretrained('bert-base-chinese',
do_lower_case=True)
else:
tokenizer = BertTokenizer.from_pretrained(
'bert-base-multilingual-uncased', do_lower_case=True)
print('Padding Datasets...')
for doc_df in data_df:
doc_df.text = doc_df.text.apply(lambda x: tokenizer.tokenize(x))
# convert to indices and pad the sequences
max_len = 25
for doc_df in data_df:
doc_df.text = doc_df.text.apply(lambda x: pad_sequences(
[tokenizer.convert_tokens_to_ids(x)], maxlen=max_len, dtype="long")
[0])
# create attention masks
for doc_df in data_df:
attention_masks = []
for seq in doc_df.text:
seq_mask = [float(idx > 0) for idx in seq]
attention_masks.append(seq_mask)
doc_df['masks'] = attention_masks
# format train, valid, test
train_inputs = torch.tensor(data_df[0].text)
train_labels = torch.tensor(data_df[0].label)
train_masks = torch.tensor(data_df[0].masks)
valid_inputs = torch.tensor(data_df[1].text)
valid_labels = torch.tensor(data_df[1].label)
valid_masks = torch.tensor(data_df[1].masks)
test_inputs = torch.tensor(data_df[2].text)
test_labels = torch.tensor(data_df[2].label)
test_masks = torch.tensor(data_df[2].masks)
batch_size = params['batch_size']
train_data = TensorDataset(train_inputs, train_masks, train_labels)
train_sampler = RandomSampler(train_data)
train_dataloader = DataLoader(train_data,
sampler=train_sampler,
batch_size=batch_size)
valid_data = TensorDataset(valid_inputs, valid_masks, valid_labels)
valid_sampler = SequentialSampler(valid_data)
valid_dataloader = DataLoader(valid_data,
sampler=valid_sampler,
batch_size=batch_size)
test_data = TensorDataset(test_inputs, test_masks, test_labels)
test_sampler = SequentialSampler(test_data)
test_dataloader = DataLoader(test_data,
sampler=test_sampler,
batch_size=batch_size)
# load the pretrained model
print('Loading Pretrained Model...')
if lang == 'English':
model = BertForSequenceClassification.from_pretrained(
'bert-base-uncased', num_labels=2)
elif lang == 'Chinese':
model = BertForSequenceClassification.from_pretrained(
'bert-base-chinese', num_labels=2)
else: # for Spanish, Italian, Portuguese and Polish
model = BertForSequenceClassification.from_pretrained(
'bert-base-multilingual-uncased', num_labels=2)
model.to(device)
# organize parameters
param_optimizer = list(model.named_parameters())
if params['freeze']:
no_decay = ['bias', 'bert'] # , 'bert' freeze all bert parameters
else:
no_decay = ['bias']
optimizer_grouped_parameters = [{
'params':
[p for n, p in param_optimizer if not any(nd in n for nd in no_decay)],
'weight_decay_rate':
params['decay_rate']
}, {
'params':
[p for n, p in param_optimizer if any(nd in n for nd in no_decay)],
'weight_decay_rate':
0.0
}]
optimizer = AdamW(optimizer_grouped_parameters, lr=params['lr'])
scheduler = get_linear_schedule_with_warmup(
optimizer,
num_warmup_steps=params['warm_steps'],
num_training_steps=params['train_steps'])
# Number of training epochs (authors recommend between 2 and 4)
epochs = 10
# Training
print('Training the model...')
for _ in trange(epochs, desc='Epoch'):
model.train()
# Tracking variables
tr_loss = 0
nb_tr_examples, nb_tr_steps = 0, 0
# train batch
for step, batch in enumerate(train_dataloader):
# Add batch to GPU
batch = tuple(t.to(device) for t in batch)
# Unpack the inputs from our dataloader
b_input_ids, b_input_mask, b_labels = batch
# Clear out the gradients (by default they accumulate)
optimizer.zero_grad()
# Forward pass
outputs = model(b_input_ids,
token_type_ids=None,
attention_mask=b_input_mask,
labels=b_labels)
# backward pass
# outputs[0].backward()
outputs.backward()
# Update parameters and take a step using the computed gradient
optimizer.step()
# Update tracking variables
tr_loss += outputs[0].item()
nb_tr_examples += b_input_ids.size(0)
nb_tr_steps += 1
print("Train loss: {}".format(tr_loss / nb_tr_steps))
'''Validation'''
best_valid_f1 = 0.0
# Put model in evaluation mode to evaluate loss on the validation set
model.eval()
# tracking variables
eval_loss, eval_accuracy = 0, 0
nb_eval_steps, nb_eval_examples = 0, 0
# batch eval
y_preds = []
for batch in valid_dataloader:
# Add batch to GPU
batch = tuple(t.to(device) for t in batch)
# Unpack the inputs from our dataloader
b_input_ids, b_input_mask, b_labels = batch
# Telling the model not to compute or store gradients, saving memory and speeding up validation
with torch.no_grad():
# Forward pass, calculate logit predictions
outputs = model(b_input_ids,
token_type_ids=None,
attention_mask=b_input_mask)
# Move logits and labels to CPU
logits = outputs[0].detach().cpu().numpy()
# record the prediction
pred_flat = np.argmax(logits, axis=1).flatten()
y_preds.extend(pred_flat)
label_ids = b_labels.to('cpu').numpy()
tmp_eval_accuracy = flat_accuracy(logits, label_ids)
eval_accuracy += tmp_eval_accuracy
nb_eval_steps += 1
print("Validation Accuracy: {}".format(eval_accuracy / nb_eval_steps))
# evaluate the validation f1 score
f1_m_valid, f1_w_valid = flat_f1(y_preds, valid_df.label)
if f1_m_valid > best_valid_f1:
print('Test....')
best_valid_f1 = f1_m_valid
y_preds = []
y_probs = []
# test if valid gets better results
for batch in test_dataloader:
batch = tuple(t.to(device) for t in batch)
b_input_ids, b_input_mask, b_labels = batch
with torch.no_grad():
outputs = model(b_input_ids,
token_type_ids=None,
attention_mask=b_input_mask)
probs = F.softmax(outputs[0], dim=1)
probs = probs.detach().cpu().numpy()
pred_flat = np.argmax(probs, axis=1).flatten()
y_preds.extend(pred_flat)
y_probs.extend([item[1] for item in probs])
# save the predicted results
with open(odir + lang + '.tsv', 'w') as wfile:
with open(split_dir + 'test.tsv') as dfile:
wfile.write(dfile.readline().strip() +
'\tpred\tpred_prob\n')
for idx, line in enumerate(dfile):
wfile.write(line.strip() + '\t' + str(y_preds[idx]) +
'\t' + str(y_probs[idx]) + '\n')
# save the predicted results
evaluator.eval(odir + lang + '.tsv', odir + lang + '.score')
def excute(self, env, first, *args):
last = t.Null()
for item in itertools.chain([first], args):
last = ev.eval(item, env)
return last
def excute(self, env, state, true, false):
if ev.eval(state, env):
return ev.eval(true, env)
else:
return ev.eval(false, env)
def build_rnn(lang, odir):
'''Train, valid, test RNN
lang: The language name
odir: output directory of prediction results
'''
doc_idx = 2
rnn_size = 200
max_len = 40 # sequence length
epochs = 10
encode_dir = './data/encode/' + lang + '/'
indices_dir = './data/indices/' + lang + '/'
wt_dir = './resources/weight/'
res_dir = './resources/classifier/rnn/'
clf_path = res_dir + lang + '.clf'
# don't reload classifier for debug usage
# load embedding weights
weights = np.load(wt_dir + lang + '.npy')
# build model architecture
text_input = Input(shape=(max_len, ), dtype='int32', name='input')
embeds = Embedding(weights.shape[0],
weights.shape[1],
weights=[weights],
input_length=max_len,
trainable=True,
name='embedding')(text_input)
bigru = Bidirectional(GRU(rnn_size,
kernel_initializer="glorot_uniform"))(embeds)
dp = Dropout(rate=.2)(bigru)
predicts = Dense(1, activation='sigmoid',
name='predict')(dp) # binary prediction
model = Model(inputs=text_input, outputs=predicts)
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
print(model.summary())
best_valid_f1 = 0.0
best_model = None
for e in range(epochs):
accuracy = 0.0
loss = 0.0
step = 1
print('--------------Epoch: {}--------------'.format(e))
# load training and batch dataset
train_iter = evaluator.data_iter(indices_dir + 'train.tsv',
batch_size=64)
# train model
for class_wt, x_train, y_train in train_iter:
if len(np.unique(y_train)) == 1:
continue
tmp = model.train_on_batch([x_train],
y_train,
class_weight=class_wt)
loss += tmp[0]
loss_avg = loss / step
accuracy += tmp[1]
accuracy_avg = accuracy / step
if step % 30 == 0:
print('Step: {}'.format(step))
print('\tLoss: {}. Accuracy: {}'.format(
loss_avg, accuracy_avg))
print('--------------------------------------')
step += 1
# valid model to find the best model
print('---------------Validation------------')
valid_iter = evaluator.data_iter(indices_dir + 'valid.tsv',
batch_size=64,
if_shuffle=False)
y_preds = []
y_valids = []
for _, x_valid, y_valid in valid_iter:
tmp_preds = model.predict([x_valid])
for item_tmp in tmp_preds:
y_preds.append(round(item_tmp[0]))
y_valids.extend(y_valid)
valid_f1 = f1_score(
y_true=y_valids,
y_pred=y_preds,
average='weighted',
)
print('Validating f1-macro score: ' + str(valid_f1))
if best_valid_f1 < valid_f1:
best_valid_f1 = valid_f1
best_model = model
pickle.dump(best_model, open(clf_path, 'wb'))
# test moddel
print('--------------Test--------------------')
y_preds = []
y_probs = []
test_iter = evaluator.data_iter(indices_dir + 'test.tsv',
batch_size=64,
if_shuffle=False)
for _, x_test, y_test in test_iter:
tmp_preds = model.predict([x_test])
for item_tmp in tmp_preds:
y_probs.append(item_tmp[0])
y_preds.append(int(round(item_tmp[0])))
with open(odir + lang + '.tsv', 'w') as wfile:
with open(indices_dir + 'test.tsv') as dfile:
wfile.write(dfile.readline().strip() +
'\tpred\tpred_prob\n')
for idx, line in enumerate(dfile):
wfile.write(line.strip() + '\t' + str(y_preds[idx]) +
'\t' + str(y_probs[idx]) + '\n')
# save the predicted results
evaluator.eval(odir + lang + '.tsv', odir + lang + '.score')
filename = filename[1:-1]
with open(filename) as file:
input = file.read()
result = []
parseInput(input, 0, result)
for exp in result:
output = eval(exp, the_global_environment)
return output
primitive_procedure_names.append('load')
primitive_procedure_objects.append(['primitive', load])
the_global_environment = Environment(primitive_procedure_names, primitive_procedure_objects)
load('"./init.scm"')
if __name__ == "__main__":
if len(sys.argv) == 1:
while True:
input = input("Input: ")
result = []
parseInput(input, 0, result)
for exp in result:
print(formatOutput(eval(exp, the_global_environment)))
else:
with open(sys.argv[1]) as file:
input = file.read()
result = []
parseInput(input, 0, result)
for exp in result:
print(formatOutput(eval(exp, the_global_environment)))
def build_lr(lang, odir):
'''Train, valid, test lr
lang: The language name
odir: output directory of prediction results
'''
doc_idx = 2
encode_dir = './data/encode/'+lang+'/'
split_dir = './data/split/'+lang+'/'
res_dir = './resources/classifier/lr/'
vec_path = res_dir + lang + '.vect'
clf_path = res_dir + lang + '.clf'
# don't load classifier for debug usage
print('Building vectorizer...')
if os.path.exists(vec_path):
vect = pickle.load(open(vec_path, 'rb'))
else:
corpus = []
with open(encode_dir + 'corpus.tsv') as dfile:
dfile.readline() # skip column names
for line in dfile:
line = line.strip().split('\t')
corpus.append(line[doc_idx])
vect = TfidfVectorizer(
ngram_range=(1, 3), max_features=15000)
vect.fit(corpus)
pickle.dump(vect, open(vec_path, 'wb'))
print('Building classifier...')
# load training data
data = {'x':[], 'y':[]}
with open(split_dir+'train.tsv') as dfile:
dfile.readline()
for line in dfile:
line = line.strip().split('\t')
data['x'].append(line[doc_idx])
data['y'].append(int(line[-1]))
# calculate the weight of labels
weights = dict(zip(
np.unique(data['y']), compute_class_weight(
'balanced', np.unique(data['y']),
data['y']
)
))
# shuffle the data before training
data['x'], data['y'] = shuffle(data['x'], data['y'])
# build classifier
clf = LogisticRegression(
class_weight=weights, solver='liblinear')
clf.fit(vect.transform(data['x']), data['y'])
# save the classifier
pickle.dump(clf, open(clf_path, 'wb'))
# test the classifier
data = []
with open(split_dir+'test.tsv') as dfile:
dfile.readline()
for line in dfile:
line = line.strip().split('\t')
data.append(line[doc_idx])
data = vect.transform(data)
y_preds = clf.predict(data)
y_probs = clf.predict_proba(data)
# save the test results
with open(odir+lang+'.tsv', 'w') as wfile:
with open(split_dir+'test.tsv') as dfile:
wfile.write(
dfile.readline().strip()+'\tpred\tpred_prob\n'
)
for idx, line in enumerate(dfile):
# 1 is the hate speech label
wfile.write(line.strip()+'\t'+str(y_preds[idx])+'\t'+str(y_probs[idx][1])+'\n')
# save the predicted results
evaluator.eval(
odir+lang+'.tsv',
odir+lang+'.score'
)
import preprocess_clueweb as p
import single_model_handler as mh
import evaluator as e
import params
import sys
if __name__ == "__main__":
preprocess = p.preprocess()
X, y, queries = preprocess.retrieve_data_from_file(params.data_set_file,
params.normalized)
sys.stdout.flush()
number_of_queries = len(set(queries))
evaluator = e.eval()
evaluator.create_index_to_doc_name_dict()
evaluator.remove_score_file_from_last_run()
sys.stdout.flush()
train, validation = preprocess.create_test_train_split_cluweb(queries)
sys.stdout.flush()
X_i, y_i = preprocess.create_data_set(X[train], y[train], queries[train])
sys.stdout.flush()
C_array = [0.1, 0.01, 0.001]
single_model_handler = mh.single_model_handler(C_array)
single_model_handler.fit_model_on_train_set_and_choose_best_for_competition(
X, y, X_i, y_i, validation, queries, evaluator, preprocess)
print("learning is finished")
def __call__(self, *args, **kwargs):
import evaluator
new_env = Environment(self.env)
for s, v in zip(self.args, args):
new_env[s] = v
return evaluator.eval(self.body, new_env)