def main():
"""
"""
# data = credit.dataset_31_credit_g()
data = wine.wine_quality_red_csv()
print(data.columns)
# column = data['volatile_acidity'].values.reshape(-1, 1)
# column = data[].values.reshape(-1, 1)
X, y = data['volatile_acidity'].values.reshape(-1, 1), data['class']
X_train, X_test, y_train, y_test = split(X,
y,
test_size=0.2,
random_state=0)
sets = split(X_test, y_test, test_size=.5, random_state=0)
X_first_half, X_second_half, y_first_half, y_second_half = sets
# print(X_first_half.shape, X_second_half.shape)
# X_train, X_test, y_train, y_test = split(X, y,
# test_size=0.2,
# random_state=0)
pipeline = WineQualityPipeline()
classifier = RandomForest()
model = pipeline.with_estimator(classifier).fit(X_train, y_train)
# prediction = model.predict(X_test)
# pipeline = CreditGPipeline()
shift_detector = SklearnDataShiftDetector(model, n_bins=30)
shift_detector.iteration(X_first_half)
new_second_half = deepcopy(X_second_half)
mask = np.logical_and(X_second_half > .4, X_second_half < 1.)
new_second_half[mask] *= 3.
plt.plot(range(X_first_half.shape[0]), X_first_half, 'go')
plt.plot(range(new_second_half.shape[0]), new_second_half, 'r^')
plt.show()
shift_detector.iteration(new_second_half)
print(shift_detector.data_is_shifted())
def main():
"""
"""
resource_path = get_resource_path()
folder = os.path.join(resource_path, 'data/amazon')
datafile_train = 'Electronics_5.json'
datafile_test = 'Books_5.json'
X_train, y_train = [], []
X_test, y_test = [], []
for line in open(os.path.join(folder, datafile_train)):
content = json.loads(line)
X_train.append(content["reviewText"])
y_train.append(float(content["overall"]))
for line in open(os.path.join(folder, datafile_test)):
content = json.loads(line)
X_test.append(content["reviewText"])
y_test.append(float(content["overall"]))
size = 100
# pipeline = FullTextPipeline(RandomForest())
pipeline = HashingPipeline(RandomForest())
# pipeline = TfIdfPipeline(RandomForest())
model = pipeline.fit(X_train[:size], y_train[:size])
shift_detector = SklearnDataShiftDetector(model, n_bins=1000)
shift_detector.iteration(X_train[:100])
shift_detector.iteration(X_test[:100])
print(shift_detector.data_is_shifted())
def test_typos_in_data_with_random_forest(self):
classifier = RandomForest()
model = self.pipeline.with_estimator(classifier).fit(self.X_train,
self.y_train)
error_generator = Typos()
num_cols = 3
# Will fail if the number of columns is less than 3
columns = np.random.choice(self.features, num_cols, replace=False)
corrupted_X_test = error_generator.run(self.X_test, columns=columns)
# prediction = model.predict(X_test)
# print(accuracy_score(y_test, prediction))
# suite = TestSuite()
pipeline_profile = SklearnPipelineProfiler().on(model)
tests, warnings = (self.automated_suite
.with_profiles(self.data_profile, pipeline_profile)
.on(corrupted_X_test))
for column, profile in zip(columns, self.data_profile.profiles):
if profile.scale != DataScale.NOMINAL:
continue
self.assertIn(Test(Severity.CRITICAL).is_in_range(profile), tests)
self.assertIn(Warning(ErrorType.NOT_IN_RANGE,
Severity.CRITICAL, Message().not_in_range %
(profile.column_name, str(profile.range))),
warnings)
def main():
"""
"""
# data = credit.dataset_31_credit_g()
data = wine.wine_quality_red_csv()
print(data.shape)
print(data.columns)
target = "class"
X, y = data[[col for col in data.columns if col != target]], data[target]
X_train, X_test, y_train, y_test = split(X,
y,
test_size=0.2,
random_state=0)
# pipeline = CreditGPipeline()
pipeline = WineQualityPipeline()
classifier = RandomForest(size=40)
model = pipeline.with_estimator(classifier).fit(X_train, y_train)
prediction = model.predict(X_test)
print(accuracy_score(y_test, prediction))
suite = TestSuite()
automated_suite = AutomatedTestSuite()
data_profile = DataFrameProfiler().on(X_train)
pipeline_profile = SklearnPipelineProfiler().on(model)
suite.add(Test().is_complete(
data_profile.for_column('volatile_acidity')).is_in_range(
data_profile.for_column('alcohol')))
warnings = suite.on(X_test)
print("*** TEST_SUITE, X_TEST")
if warnings and (len(warnings) != 0):
print("======= WARNINGS =======")
for warn in warnings:
print(warn)
error_generator = ExplicitMissingValues()
corrupted_X_test = error_generator.run(X_test, ['volatile_acidity'])
warnings = suite.on(corrupted_X_test)
print("*** TEST_SUITE, CORRUPTED_X_TEST")
if warnings and (len(warnings) != 0):
print("======= WARNINGS =======")
for warn in warnings:
print(warn)
tests, warnings = (automated_suite.with_profiles(
data_profile, pipeline_profile).run(corrupted_X_test))
print("*** AUTOMATED_TEST_SUITE, CORRUPTED_X_TEST")
if warnings and (len(warnings) != 0):
print("======= WARNINGS =======")
for warn in warnings:
print(warn)
def comparing_models(X_train, X_test, y_train, y_test):
AdaBoost(X_train, X_test, y_train, y_test)
Logistic_Regression(X_train, X_test, y_train, y_test)
NaiveBayes(X_train, X_test, y_train, y_test)
XGBoost(X_train, X_test, y_train, y_test)
RandomForest(X_train, X_test, y_train, y_test)
SVM(X_train, X_test, y_train, y_test)
NeuralNetwork(X_train, X_test, y_train, y_test)
def main():
"""
"""
from pipelines import CreditGPipeline
from models import RandomForest
dataframe = pd.read_csv('resources/data/dataset_31_credit-g.csv')
DataFrameProfiler().on(dataframe)
pipeline = CreditGPipeline()
SklearnPipelineProfiler().on(pipeline.with_estimator(RandomForest(40)))
def trainWithHotEncoding(hot_encoded_train_features, hot_encoded_train_labels,
hot_encoded_test_features, hot_encoded_test_labels,
results, algorithms, isTesting):
# TRAIIN RANDOM FOREST
class_weights = class_weight.compute_class_weight(
'balanced', np.unique(hot_encoded_train_labels.flatten()),
hot_encoded_train_labels.flatten())
param_grid = {
'max_features': [
# None,
# "sqrt",
"log2"
],
'n_estimators': [
# 1000,
2000,
# 3000
]
}
if (isTesting):
print("TESTING MODE RF: ONLY TRAINING 1 MODEL")
param_grid = {}
rf_hot_encoding = RandomForest(class_weights=class_weights,
param_grid=param_grid)
rf_hot_encoding.title = "RANDOM FOREST HOT ENCODING TRAIN"
rf_hot_encoding.train(hot_encoded_train_features, hot_encoded_train_labels)
model_name = 'RF-HOT.model'
print("SAVING MODEL: ", model_name)
try:
joblib.dump(rf_hot_encoding.model, model_name)
except Exception as e:
print("Cannot save {} because: \n\n".format(model_name), str(e))
algorithms["RANDOM FOREST HOT ENCODING"] = rf_hot_encoding
rf_hot_encoding.drawCurves(X=hot_encoded_train_features,
y=hot_encoded_train_labels)
rf_hot_encoding.title = "RANDOM FOREST HOT ENCODING TEST"
results["RANDOM FOREST HOT ENCODING"] = rf_hot_encoding.drawCurves(
X=hot_encoded_test_features, y=hot_encoded_test_labels)
return rf_hot_encoding, results, algorithms
def trainWithFrecuencies(tetra_freq_train_features, tetra_freq_train_labels,
tetra_freq_test_features, tetra_freq_test_labels,
results, algorithms, isTesting):
class_weights = class_weight.compute_class_weight(
'balanced', np.unique(tetra_freq_train_labels.flatten()),
tetra_freq_train_labels.flatten())
param_grid = {
'max_features': [
# None,
# "sqrt",
"log2"
],
'n_estimators': [
# 1000,
2000,
# 3000
]
}
if (isTesting):
print("TESTING MODE RF: ONLY TRAINING 1 MODEL")
param_grid = {}
rf = RandomForest(class_weights=class_weights, param_grid=param_grid)
rf.title = "RANDOM FOREST TETRA NUCLEOTIDE FREQUENCY TRAIN"
rf.train(tetra_freq_train_features, tetra_freq_train_labels)
model_name = 'RF-TETRA.model'
print("SAVING MODEL USING JOBLIB: ", model_name)
try:
joblib.dump(rf.model, model_name)
except Exception as e:
print("Cannot save {} because: \n\n".format(model_name), str(e))
algorithms["RANDOM FOREST"] = rf
rf.drawCurves(X=tetra_freq_train_features, y=tetra_freq_train_labels)
rf.title = "RANDOM FOREST TETRA NUCLEOTIDE FREQUENCY TEST"
results["RANDOM FOREST"] = rf.drawCurves(X=tetra_freq_test_features,
y=tetra_freq_test_labels)
return rf, results, algorithms
def main(grid): # Get Clean Data X, Y = read_clean_data() # Linear Regression try: LinearRegression(X, Y, grid) except Exception as e: print(e) # Binarize Y Y_binary = BinaryY(Y) # Logistic Regression try: LogisticRegression(X, Y_binary, grid) except Exception as e: print(e) # Decision Tree try: DecisionTree(X, Y_binary, grid) except Exception as e: print(e) # Support Vector Machine try: SVM(X, Y_binary, grid) except Exception as e: print(e) # Random Forest try: RandomForest(X, Y_binary, grid) except Exception as e: print(e) # Bagging Classifier try: Bagging(X, Y_binary, grid) except Exception as e: print(e) # Neural Network try: NeuralNet(X, Y_binary, grid) except Exception as e: print(e)
def test_missing_values_in_data_with_random_forest(self):
classifier = RandomForest()
model = self.pipeline.with_estimator(classifier).fit(self.X_train,
self.y_train)
error_generator = ExplicitMissingValues()
num_cols = 3
# Will fail if the number of columns is less than 3
columns = np.random.choice(self.features, num_cols, replace=False)
corrupted_X_test = error_generator.run(self.X_test, columns=columns)
# prediction = model.predict(X_test)
# print(accuracy_score(y_test, prediction))
# suite = TestSuite()
pipeline_profile = SklearnPipelineProfiler().on(model)
tests, warnings = (self.automated_suite
.with_profiles(self.data_profile, pipeline_profile)
.on(corrupted_X_test))
for column, profile in zip(columns, self.data_profile.profiles):
self.assertIn(Test(Severity.CRITICAL).is_complete(profile), tests)
self.assertIn(Warning(ErrorType.MISSING_VALUE,
Severity.CRITICAL,
Message().not_complete % column),
warnings)
def __init__(self):
self.resource_folder = get_resource_path()
# for dataset_name in sorted(os.listdir(folder)):
# if dataset_name.endswith('.csv'):
# print(dataset_name[:-4])
self.pipelines = {
'credit-g': (
'credit-g/dataset_31_credit-g.csv', 'class',
CreditGPipeline()),
'wine-quality': (
'wine-quality/wine-quality-red.csv', 'class',
WineQualityPipeline()),
'wq-missing': (
'wine-quality/wine-quality-red.csv', 'class',
WineQualityMissingPipeline()),
'abalone': (
'abalone/abalone.csv', 'Rings',
AbalonePipeline()),
'adult': (
'adult/adult.csv', 'class',
AdultPipeline()),
'adult-missing': (
'adult/adult.csv', 'class',
AdultMissingPipeline()),
'heart': (
'heart/heart.csv', 'class',
HeartPipeline())}
self.classifiers = {
'dtc': DecisionTree(),
'rfc40': RandomForest(size=40),
'ertc40': ExtremelyRandomizedTrees(size=40),
'xgb': XGB(),
'svm': SVM(),
'lsvm': LinearSVM(),
'knn': KNN(n_neighbors=7),
'logreg': LogRegression(),
'gaus': GausNB(),
'brfc40': BaggingRandomForest(size=40),
'mlpc': MLPC(input_size=[16, 32, 16, 8])
}
self.error_gens = {
'numeric anomalies': (
Anomalies(), lambda x: x.dtype in [DataType.INTEGER,
DataType.FLOAT]),
'typos': (
Typos(), lambda x: x.dtype == DataType.STRING),
'explicit misvals': (
ExplicitMissingValues(), lambda x: True),
'implicit misvals': (
ImplicitMissingValues(), lambda x: True),
'swap fields': (
SwapFields(), lambda x: True)}
self.params = [0.01, 0.05, 0.1, 0.2, 0.3, 0.5, 0.8]
self.tests = {'num disc': lambda x: (x.scale == DataScale.NOMINAL
and x.dtype in [DataType.INTEGER,
DataType.FLOAT]),
'num cont': lambda x: (x.scale == DataScale.NOMINAL
and x.dtype in [DataType.INTEGER,
DataType.FLOAT]),
'string': lambda x: x.dtype == DataType.STRING}
self.results = Table(rows=sorted(self.pipelines.keys()),
columns=sorted(self.classifiers.keys()),
subrows=self.tests.keys(),
subcolumns=self.error_gens.keys())
forecast_pr = model_pr.predict(start=model_pr.test.index[0],
end=model_pr.test.index[-1])
eval_pr = EvaluateModel(model_pr.test, forecast_pr)
print('RMSE for Prophet model: ', eval_pr.rmse())
eval_pr.plot(label='Prophet')
# ======================================================================================================================
# Random Forest
# ======================================================================================================================
FE = FeatureEngineering(DL)
FE.generate_lags(features_to_lag=['Customers'], lags=[1, 12])
FE.split_features_target(type='train')
model_rf = RandomForest(FE)
model_rf.fit(trend='additive', seasonality=12)
X_test, y_test = FE.split_features_target(type='test')
X_test = X_test[model_rf.selected_features]
forecast_rf = model_rf.predict(X_test)
forecast_rf.set_index(keys=model_rf.test.index, inplace=True)
eval_rf = EvaluateModel(model_rf.test[model_rf.target], forecast_rf)
print('RMSE for Random Forest model: ', eval_rf.rmse())
eval_rf.plot(label='Random Forest')
# ======================================================================================================================
# Extra-tree regressor
# ======================================================================================================================
FE = FeatureEngineering(DL)
'[+] Loading last saved BaseLine class. Delete it if you want to train a new model!'
)
curr_dir = os.path.dirname(os.path.abspath(__file__))
BaseLine_path = os.path.abspath(curr_dir + f"/utils/model/BaseLine.bcls")
BaseLine_file = open(BaseLine_path, 'rb')
model = pickle.load(BaseLine_file)
else:
logging.info('[+] Training on selected model...')
if model == "sgd_classifier":
model = _SGDClassifier(training_dataloader=training_dataloader)
elif model == "naive_bayesian":
model = NaiveBayesian(training_dataloader=training_dataloader)
elif model == "support_vector_machine":
model = SupportVectorMachine(training_dataloader=training_dataloader)
elif model == "random_forest":
model = RandomForest(training_dataloader=training_dataloader)
elif model == "logistic_regression":
model = _LogisticRegression(training_dataloader=training_dataloader)
else:
print("[?] Invalid Model!")
sys.exit(1)
model.train()
# ------------ testing and statistical process based on pre-trained model
# --------------------------------------------------------------------------
statistics = model.stat()
print("\t- Accuracy : ", statistics["accuracy"])
print("\t- Precision : ", statistics["precision"])
print("\t- Recall : ", statistics["recall"])
print("\t- f1-score : ", statistics["f1_score"])
print("\t- ROC AUC score : ", statistics["roc_auc_score"])
test = {
'outlook': 'sunny',
'temp': 'hot',
'humidity': 'normal',
'windy': False
}
return df, target, test
if __name__ == '__main__':
X_tr, Y_tr, X_ts, Y_ts = load_data()
# decision tree
model = DecisionTree(n_attrs=4)
model.fit(X_tr, Y_tr)
y_pred = model.predict(X_ts)
assert accuracy(y_pred, Y_ts) == 0.7837837837837838
# random forest
model = RandomForest()
model.fit(X_tr, Y_tr)
y_pred = model.predict(X_ts)
assert accuracy(y_pred, Y_ts) == 1
# decision tree categorical
df, attr_targe, record_test = load_data_categorical()
tree = DecicionTreeCategorical()
tree.fit(df, attr_targe)
assert tree.predict_one(record_test) == {'yes': 1.0}
y = model.predict(X)
preds_to_lab(y, param['hop_size'], param['fs'], category, save_path,
song_name)
if __name__ == '__main__':
parser = get_train_rf_parser()
args = parser.parse_args(sys.argv[1:])
log.info('Arguments:\n' + pformat(args.__dict__))
# prepare train dataset
params, y_size, y_ind = get_params_by_category(args.category)
conv_root = args.conv_root
if args.use_librosa:
conv_root = conv_root + '/librosa/'
else:
conv_root = conv_root + '/mauch/'
conv_list = args.conv_list
if not conv_list:
conv_list = gen_train_data(args.songs_list,
args.audio_root,
args.gt_root,
params,
conv_root,
args.subsong_len,
args.song_len,
use_librosa=args.use_librosa)
model = RandomForest(criterion=args.criterion,
max_features=args.max_features,
n_estimators=args.n_estimators)
model = train_rf(model, conv_list)
