if config.dataset_path != 'imdb' and config.dataset_path != 'imdb_small':
train = pd.read_csv(config.dataset_path + '/6_train.csv')
test = pd.read_csv(config.dataset_path + '/6_test.csv')
val = pd.read_csv(config.dataset_path + '/6_val.csv')
X_train, meta_train, Y_train, label_encoder_train = splitFeatures(train)
X_test, meta_test, Y_test, label_encoder_test = splitFeatures(test)
X_val, meta_val, Y_val, label_encoder_val = splitFeatures(val)
n_classes = max(len(label_encoder_val.classes_),
len(label_encoder_test.classes_),
len(label_encoder_train.classes_))
elif config.dataset_path == 'imdb_small':
dl = DataLoader()
X_train, X_val, X_test, Y_train, Y_val, Y_test, _, _, _ = dl.load_data(
data_path='../imdb_small/budgetandactors2.txt')
Y_val = [1 if y == 1 else 0 for y in Y_val]
Y_test = [1 if y == 1 else 0 for y in Y_test]
n_classes = 2
else:
dl = DataLoader()
X_train, X_val, X_test, Y_train, Y_val, Y_test, _, _, _ = dl.load_data(
data_path='./data/imdb/budgetandactors.txt')
Y_val = [1 if y == 1 else 0 for y in Y_val]
Y_test = [1 if y == 1 else 0 for y in Y_test]
n_classes = 2
# print("X_val", X_val)
# print("X_train", X_train)
# print("Y_val", Y_val)
def main():
warnings.filterwarnings("ignore")
dataset='imdb'
from data.loader import DataLoader
dl = DataLoader()
train_primitive_matrix, val_primitive_matrix, test_primitive_matrix, \
train_ground, val_ground, test_ground, _, _, _ = dl.load_data(dataset=dataset)
hg = HeuristicGenerator(train_primitive_matrix, val_primitive_matrix, val_ground, train_ground, b=0.5)
hg.run_synthesizer(max_cardinality=1, idx=None, keep=3, model='dt')
syn = Synthesizer(val_primitive_matrix, val_ground, b=0.5)
heuristics, feature_inputs = syn.generate_heuristics('nn', 1)
print("Total Heuristics Generated: ", np.shape(heuristics)[1])
optimal_betas = syn.find_optimal_beta(heuristics[0], val_primitive_matrix, feature_inputs[0], val_ground)
top_idx = hg.prune_heuristics(heuristics, feature_inputs, keep=3)
print('Features chosen heuristics are based on: ', top_idx)
verifier = Verifier(hg.L_train, hg.L_val, val_ground, has_snorkel=False)
verifier.train_gen_model()
verifier.assign_marginals()
feedback_idx = verifier.find_vague_points(gamma=0.1, b=0.5)
print('Percentage of Low Confidence Points: ', np.shape(feedback_idx)[0] / float(np.shape(val_ground)[0]))
validation_accuracy = []
training_accuracy = []
validation_coverage = []
training_coverage = []
training_marginals = []
idx = None
hg = HeuristicGenerator(train_primitive_matrix, val_primitive_matrix,
val_ground, train_ground,
b=0.5)
plt.figure(figsize=(12, 6));
for i in range(3, 26):
if (i - 2) % 5 == 0:
print
"Running iteration: ", str(i - 2)
# Repeat synthesize-prune-verify at each iterations
if i == 3:
hg.run_synthesizer(max_cardinality=1, idx=idx, keep=3, model='dt')
else:
hg.run_synthesizer(max_cardinality=1, idx=idx, keep=1, model='dt')
hg.run_verifier()
# Save evaluation metrics
va, ta, vc, tc = hg.evaluate()
validation_accuracy.append(va)
training_accuracy.append(ta)
training_marginals.append(hg.vf.train_marginals)
validation_coverage.append(vc)
training_coverage.append(tc)
# Plot Training Set Label Distribution
if i <= 8:
plt.subplot(2, 3, i - 2)
plt.hist(training_marginals[-1], bins=10, range=(0.0, 1.0));
plt.title('Iteration ' + str(i - 2));
plt.xlim([0.0, 1.0])
plt.ylim([0, 825])
# Find low confidence datapoints in the labeled set
hg.find_feedback()
idx = hg.feedback_idx
# Stop the iterative process when no low confidence labels
if idx == []:
break
plt.tight_layout()
plt.hist(training_marginals[-1], bins=10, range=(0.0, 1.0));
plt.title('Final Distribution');
print("Program Synthesis Train Accuracy: ", training_accuracy[-1])
print("Program Synthesis Train Coverage: ", training_coverage[-1])
print("Program Synthesis Validation Accuracy: ", validation_accuracy[-1])
import warnings
warnings.filterwarnings("ignore")
import numpy as np
from sklearn import *
from lstm.imdb_lstm import *
import matplotlib.pyplot as plt
dataset = 'imdb'
from data.loader import DataLoader
dl = DataLoader()
_, _, _, train_ground, val_ground, test_ground, train_text, val_text, test_text = dl.load_data(
dataset=dataset)
train_reef = np.load('./data/imdb_reef.npy')
f1_all = []
pr_all = []
re_all = []
val_acc_all = []
bs_arr = [64, 128, 256]
n_epochs_arr = [5, 10, 25]
for bs in bs_arr:
for n in n_epochs_arr:
y_pred = lstm_simple(train_text,
train_reef,
val_text,
val_ground,
import numpy as np
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore")
dataset = 'imdb'
from data.loader import DataLoader
dl = DataLoader()
#train_primitive_matrix, val_primitive_matrix, test_primitive_matrix, \
#train_ground, val_ground, test_ground, class_count = dl.load_data_sheet()
train_primitive_matrix, val_primitive_matrix, test_primitive_matrix, \
train_ground, val_ground, test_ground, _, _, _ = dl.load_data(dataset=dataset)
class_count = 2
#train_primitive_matrix, val_primitive_matrix, test_primitive_matrix, \
#rain_ground, val_ground, test_ground, class_count = dl.load_data_synt(4)
b = 1 / class_count
from program_synthesis.heuristic_generator import HeuristicGenerator
'''hg = HeuristicGenerator(train_primitive_matrix, val_primitive_matrix, val_ground, train_ground, b=b, class_count = class_count)
hg.run_synthesizer(max_cardinality=1, idx=None, keep=3, model='lr')
from program_synthesis.synthesizer import Synthesizer
syn = Synthesizer(val_primitive_matrix, val_ground, b=b)
heuristics, feature_inputs = syn.generate_heuristics('lr', 1)
