def check_print_model_weights(task='classification'):
# create some simple classification or regression data
if task == 'classification':
train_fs, _ = make_classification_data(train_test_ratio=0.8)
else:
train_fs, _, _ = make_regression_data(num_features=4,
train_test_ratio=0.8)
# now train the appropriate model
if task == 'classification':
learner = Learner('LogisticRegression')
learner.train(train_fs)
else:
learner = Learner('LinearRegression')
learner.train(train_fs, grid_objective='pearson')
# now save the model to disk
model_file = join(_my_dir, 'output',
'test_print_model_weights.model')
learner.save(model_file)
# now call print_model_weights main() and capture the output
print_model_weights_cmd = [model_file]
err = ''
try:
old_stderr = sys.stderr
old_stdout = sys.stdout
sys.stderr = mystderr = StringIO()
sys.stdout = mystdout = StringIO()
pmw.main(print_model_weights_cmd)
out = mystdout.getvalue()
err = mystderr.getvalue()
finally:
sys.stderr = old_stderr
sys.stdout = old_stdout
print(err)
# now parse the output of the print_model_weight command
# and get the intercept and the feature values
if task == 'classification':
lines_to_parse = [l for l in out.split('\n')[1:] if l]
intercept = safe_float(lines_to_parse[0].split('\t')[0])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[2], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_[0])
assert_allclose(learner.model.coef_[0], feature_values)
else:
lines_to_parse = [l for l in out.split('\n') if l]
intercept = safe_float(lines_to_parse[0].split('=')[1])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[1], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_)
assert_allclose(learner.model.coef_, feature_values)
def check_print_model_weights(task='classification'):
# create some simple classification or regression data
if task == 'classification' or task == 'classification_no_intercept':
train_fs, _ = make_classification_data(train_test_ratio=0.8)
elif task == 'multiclass_classification':
train_fs, _ = make_classification_data(train_test_ratio=0.8, num_labels=3)
else:
train_fs, _, _ = make_regression_data(num_features=4,
train_test_ratio=0.8)
# now train the appropriate model
if task == 'classification' or task == 'multiclass_classification':
learner = Learner('LogisticRegression')
learner.train(train_fs, grid_objective='f1_score_micro')
elif task == 'classification_no_intercept':
learner = Learner('LogisticRegression')
learner.train(train_fs, grid_objective='f1_score_micro', param_grid=[{'fit_intercept':[False]}])
elif task == 'regression':
learner = Learner('LinearRegression')
learner.train(train_fs, grid_objective='pearson')
else:
learner = Learner('LinearSVR')
learner.train(train_fs, grid_objective='pearson')
# now save the model to disk
model_file = join(_my_dir, 'output',
'test_print_model_weights.model')
learner.save(model_file)
# now call print_model_weights main() and capture the output
print_model_weights_cmd = [model_file]
err = ''
try:
old_stderr = sys.stderr
old_stdout = sys.stdout
sys.stderr = mystderr = StringIO()
sys.stdout = mystdout = StringIO()
pmw.main(print_model_weights_cmd)
out = mystdout.getvalue()
err = mystderr.getvalue()
finally:
sys.stderr = old_stderr
sys.stdout = old_stdout
print(err)
# now parse the output of the print_model_weight command
# and get the intercept and the feature values
if task == 'classification':
lines_to_parse = [l for l in out.split('\n')[1:] if l]
intercept = safe_float(lines_to_parse[0].split('\t')[0])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[2], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_[0])
assert_allclose(learner.model.coef_[0], feature_values)
elif task == 'multiclass_classification':
# for multiple classes we get an intercept for each class
# as well as a list of weights for each class
lines_to_parse = [l for l in out.split('\n')[1:] if l]
intercept = []
for intercept_string in lines_to_parse[0:3]:
intercept.append(safe_float(intercept_string.split('\t')[0]))
feature_values = [[], [], []]
for ltp in lines_to_parse[3:]:
fields = ltp.split('\t')
feature_values[int(fields[1])].append((fields[2], safe_float(fields[0])))
for index, weights in enumerate(feature_values):
feature_values[index] = [t[1] for t in sorted(weights)]
for index, weights in enumerate(learner.model.coef_):
assert_array_almost_equal(weights, feature_values[index])
assert_array_almost_equal(intercept, learner.model.intercept_)
elif task == 'classification_no_intercept':
lines_to_parse = [l for l in out.split('\n')[0:] if l]
intercept = safe_float(lines_to_parse[0].split('=')[1])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[2], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_)
assert_allclose(learner.model.coef_[0], feature_values)
elif task == 'regression':
lines_to_parse = [l for l in out.split('\n') if l]
intercept = safe_float(lines_to_parse[0].split('=')[1])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[1], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_)
assert_allclose(learner.model.coef_, feature_values)
else:
lines_to_parse = [l for l in out.split('\n') if l]
intercept_list = ast.literal_eval(lines_to_parse[0].split('=')[1].strip())
intercept = []
for intercept_string in intercept_list:
intercept.append(safe_float(intercept_string))
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[1], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_array_almost_equal(intercept, learner.model.intercept_)
assert_allclose(learner.model.coef_, feature_values)
def check_print_model_weights(task='classification'):
# create some simple classification or regression data
if task == 'classification':
train_fs, _ = make_classification_data(train_test_ratio=0.8)
elif task == 'multiclass_classification':
train_fs, _ = make_classification_data(train_test_ratio=0.8, num_labels=3)
else:
train_fs, _, _ = make_regression_data(num_features=4,
train_test_ratio=0.8)
# now train the appropriate model
if task == 'classification' or task == 'multiclass_classification':
learner = Learner('LogisticRegression')
learner.train(train_fs, grid_objective='f1_score_micro')
elif task == 'regression':
learner = Learner('LinearRegression')
learner.train(train_fs, grid_objective='pearson')
else:
learner = Learner('LinearSVR')
learner.train(train_fs, grid_objective='pearson')
# now save the model to disk
model_file = join(_my_dir, 'output',
'test_print_model_weights.model')
learner.save(model_file)
# now call print_model_weights main() and capture the output
print_model_weights_cmd = [model_file]
err = ''
try:
old_stderr = sys.stderr
old_stdout = sys.stdout
sys.stderr = mystderr = StringIO()
sys.stdout = mystdout = StringIO()
pmw.main(print_model_weights_cmd)
out = mystdout.getvalue()
err = mystderr.getvalue()
finally:
sys.stderr = old_stderr
sys.stdout = old_stdout
print(err)
# now parse the output of the print_model_weight command
# and get the intercept and the feature values
if task == 'classification':
lines_to_parse = [l for l in out.split('\n')[1:] if l]
intercept = safe_float(lines_to_parse[0].split('\t')[0])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[2], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_[0])
assert_allclose(learner.model.coef_[0], feature_values)
elif task == 'multiclass_classification':
# for multiple classes we get an intercept for each class
# as well as a list of weights for each class
lines_to_parse = [l for l in out.split('\n')[1:] if l]
intercept = []
for intercept_string in lines_to_parse[0:3]:
intercept.append(safe_float(intercept_string.split('\t')[0]))
feature_values = [[], [], []]
for ltp in lines_to_parse[3:]:
fields = ltp.split('\t')
feature_values[int(fields[1])].append((fields[2], safe_float(fields[0])))
for index, weights in enumerate(feature_values):
feature_values[index] = [t[1] for t in sorted(weights)]
for index, weights in enumerate(learner.model.coef_):
assert_array_almost_equal(weights, feature_values[index])
assert_array_almost_equal(intercept, learner.model.intercept_)
elif task == 'regression':
lines_to_parse = [l for l in out.split('\n') if l]
intercept = safe_float(lines_to_parse[0].split('=')[1])
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[1], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_almost_equal(intercept, learner.model.intercept_)
assert_allclose(learner.model.coef_, feature_values)
else:
lines_to_parse = [l for l in out.split('\n') if l]
intercept_list = ast.literal_eval(lines_to_parse[0].split('=')[1].strip())
intercept = []
for intercept_string in intercept_list:
intercept.append(safe_float(intercept_string))
feature_values = []
for ltp in lines_to_parse[1:]:
fields = ltp.split('\t')
feature_values.append((fields[1], safe_float(fields[0])))
feature_values = [t[1] for t in sorted(feature_values)]
assert_array_almost_equal(intercept, learner.model.intercept_)
assert_allclose(learner.model.coef_, feature_values)