def test_scaler_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = Scaler(with_mean=False)
X_scaled = scaler.fit(X).transform(X, copy=True)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(
X_scaled.mean(axis=0), [0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
X_scaled_back = scaler.inverse_transform(X_scaled)
assert X_scaled_back is not X
assert X_scaled_back is not X_scaled
assert_array_almost_equal(X_scaled_back, X)
X_scaled = scale(X, with_mean=False)
assert not np.any(np.isnan(X_scaled))
assert_array_almost_equal(
X_scaled.mean(axis=0), [0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert X_scaled is not X
X_scaled_back = scaler.inverse_transform(X_scaled)
assert X_scaled_back is not X
assert X_scaled_back is not X_scaled
assert_array_almost_equal(X_scaled_back, X)
def test_scaler_1d():
"""Test scaling of dataset along single axis"""
rng = np.random.RandomState(0)
X = rng.randn(5)
X_orig_copy = X.copy()
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
# check inverse transform
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_array_almost_equal(X_scaled_back, X_orig_copy)
# Test with 1D list
X = [0., 1., 2, 0.4, 1.]
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
X_scaled = scale(X)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
def test_regressors_train():
estimators = all_estimators()
regressors = [(name, E) for name, E in estimators
if issubclass(E, RegressorMixin)]
boston = load_boston()
X, y = boston.data, boston.target
X, y = shuffle(X, y, random_state=0)
# TODO: test with intercept
# TODO: test with multiple responses
X = Scaler().fit_transform(X)
y = Scaler().fit_transform(y)
for name, Reg in regressors:
if Reg in dont_test or Reg in meta_estimators:
continue
# catch deprecation warnings
with warnings.catch_warnings(record=True):
reg = Reg()
if hasattr(reg, 'alpha'):
reg.set_params(alpha=0.01)
# raises error on malformed input for fit
assert_raises(ValueError, reg.fit, X, y[:-1])
# fit
reg.fit(X, y)
reg.predict(X)
assert_greater(reg.score(X, y), 0.5)
def test_scaler_without_copy():
"""Check that Scaler.fit does not change input"""
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sp.csr_matrix(X)
X_copy = X.copy()
Scaler(copy=False).fit(X)
assert_array_equal(X, X_copy)
X_csr_copy = X_csr.copy()
Scaler(with_mean=False, copy=False).fit(X_csr)
assert_array_equal(X_csr.toarray(), X_csr_copy.toarray())
def test_scale_sparse_with_mean_raise_exception():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X_csr = sp.csr_matrix(X)
# check scaling and fit with direct calls on sparse data
assert_raises(ValueError, scale, X_csr, with_mean=True)
assert_raises(ValueError, Scaler(with_mean=True).fit, X_csr)
# check transform and inverse_transform after a fit on a dense array
scaler = Scaler(with_mean=True).fit(X)
assert_raises(ValueError, scaler.transform, X_csr)
X_transformed_csr = sp.csr_matrix(scaler.transform(X))
assert_raises(ValueError, scaler.inverse_transform, X_transformed_csr)
def utl_scaleImpute(X_data, p_imputeColumns, p_scaleColumns, p_scalers = None):
X_data = X_data.copy()
v_imputeColumns = [column for column in p_imputeColumns if column in X_data.columns]
v_scaleColumns = [column for column in p_scaleColumns if column in X_data.columns]
for column in v_imputeColumns:
v_values = X_data[column].astype(float).values.reshape(-1, 1)
if np.isnan(v_values).all():
X_data[column] = -999
else:
try:
X_data[column] = Imputer(strategy = 'mean', axis = 0).fit_transform(v_values)
except:
values = [np.unique(-999 if np.isnan(ll).all() else ll) for ll in v_values.reshape(1, -1)]
print(column, values)
raise
if p_scalers is None:
p_scalers = {}
for column in v_scaleColumns:
v_values = X_data[column].value_counts(dropna = True).index.tolist()
p_scalers[column] = Scaler().fit(np.array(v_values).reshape(-1, 1))
for column in v_scaleColumns:
X_data[column] = p_scalers[column].transform(X_data[column].values.reshape(-1, 1) )
return X_data, p_scalers
def getPreparedData():
data = getData()
attributes = data.columns
# transformacia kategorickych parametrov na celociselne
data['school'] = data['school'].apply(school_to_numeric)
data['sex'] = data['sex'].apply(sex_to_numeric)
data['address'] = data['address'].apply(address_to_numeric)
data['famsize'] = data['famsize'].apply(famsize_to_numeric)
data['Pstatus'] = data['Pstatus'].apply(Pstatus_to_numeric)
data['Mjob'] = data['Mjob'].apply(job_to_numeric)
data['Fjob'] = data['Fjob'].apply(job_to_numeric)
data['reason'] = data['reason'].apply(reason_to_numeric)
data['guardian'] = data['guardian'].apply(guardian_to_numeric)
data['schoolsup'] = data['schoolsup'].apply(yesno_to_numeric)
data['famsup'] = data['famsup'].apply(yesno_to_numeric)
data['paid'] = data['paid'].apply(yesno_to_numeric)
data['activities'] = data['activities'].apply(yesno_to_numeric)
data['nursery'] = data['nursery'].apply(yesno_to_numeric)
data['higher'] = data['higher'].apply(yesno_to_numeric)
data['internet'] = data['internet'].apply(yesno_to_numeric)
data['romantic'] = data['romantic'].apply(yesno_to_numeric)
# transformacia vsetkych dat do intervalu [0,1]
scaler = Scaler(feature_range=(0, 1)).fit(data)
data = pd.DataFrame(scaler.transform(data), columns=attributes)
return np.array(data)
def test_fit_transform():
rng = np.random.RandomState(0)
X = rng.random_sample((5, 4))
for obj in ((Scaler(), Normalizer(), Binarizer())):
X_transformed = obj.fit(X).transform(X)
X_transformed2 = obj.fit_transform(X)
assert_array_equal(X_transformed, X_transformed2)
def cluster(playlist):
arq = 'Total ' + playlist + '.csv'
n_clusters = 0
Full_data = pd.read_csv(arq)
Full_data = Full_data.dropna(axis=1, how='all')
Full_data = Full_data.dropna(axis=0, how='any')
ID = Full_data['id']
Mode = Full_data['mode']
length = Full_data['duration_ms']
artist = Full_data['artist']
Full_data = Full_data.drop(
columns=['track', 'album_id', 'artist', 'id', 'mode'])
Fdata = Full_data.values
scaler = Scaler()
data_u = scaler.fit_transform(Fdata)
# pca_transf = PCA(0.8)
# PCA_data = pca_transf.fit_transform(data_u)
clusterer = AffinityPropagation(random_state=None, preference=-500)
# clusterer = HDBSCAN(min_cluster_size=20)
# clusterer = MeanShift()
labels = clusterer.fit_predict(data_u)
n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
labels.shape = (len(labels), 1)
Full_data['cluster'] = labels + 1
Full_data['id'] = ID
Full_data['mode'] = Mode
Full_data['artist'] = artist
Full_data['duration_ms'] = length
# Full_data.sort_values(by='cluster')
Full_data.to_csv('clustered.csv', index=False)
# sns.pairplot(Full_data, hue="cluster", palette='YlGnBu')
# plt.show()
return n_clusters
def cluster(playlist):
arq = 'Total ' + playlist + '.csv'
n_clusters = 0
Full_data = pd.read_csv(arq)
Full_data = Full_data.dropna(axis=1, how='all')
Full_data = Full_data.dropna(axis=0, how='any')
ID = Full_data['id']
Mode = Full_data['mode']
length = Full_data['duration_ms']
artist = Full_data['artist']
key = Full_data['key']
time_signature = Full_data['time_signature']
Full_data = Full_data.drop(columns=[
'track', 'album_id', 'artist', 'artist_id', 'id', 'mode',
'duration_ms', 'key', 'time_signature'
])
Fdata = Full_data.values
scaler = Scaler()
data_u = scaler.fit_transform(Fdata)
clusterer = AgglomerativeClustering(n_clusters=None, distance_threshold=35)
labels = clusterer.fit_predict(data_u)
score = silhouette_score(data_u, labels)
n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
labels.shape = (len(labels), 1)
Full_data['cluster'] = labels + 1
Full_data['id'] = ID
Full_data['mode'] = Mode
Full_data['artist'] = artist
Full_data['duration_ms'] = length
Full_data['key'] = key
Full_data['time_signature'] = time_signature
Full_data.to_csv('clustered.csv', index=False)
return n_clusters, score
def __init__(self, env):
self.env = env
# sampleing envrionment state in order to featurize it.
observation_examples = np.array([self.env.observation_space.sample() for x in range(10000)])
# Feature Preprocessing: Normalize to zero mean and unit variance
# We use a few samples from the observation space to do this
self.scaler = Scaler()
self.scaler.fit(observation_examples)
# Used to convert a state to a featurizes represenation.
# We use RBF kernels with different variances to cover different parts of the space
self.featurizer = FeatureUnion([
("rbf1", RBF(gamma=5.0, n_components=100)),
("rbf2", RBF(gamma=2.0, n_components=100)),
("rbf3", RBF(gamma=1.0, n_components=100)),
("rbf4", RBF(gamma=0.5, n_components=100))
])
self.featurizer.fit(self.scaler.transform(observation_examples))
# action model for SGD regressor
self.action_models = []
self.nA = self.env.action_space.n
for na in range(self.nA):
model = SGD(learning_rate="constant")
model.partial_fit([self.__featurize_state(self.env.reset())], [0])
self.action_models.append(model)
def test_pipeline_methods_preprocessing_svm():
"""Test the various methods of the pipeline (preprocessing + svm)."""
iris = load_iris()
X = iris.data
y = iris.target
n_samples = X.shape[0]
n_classes = len(np.unique(y))
scaler = Scaler()
pca = RandomizedPCA(n_components=2, whiten=True)
clf = SVC(probability=True)
for preprocessing in [scaler, pca]:
pipe = Pipeline([('scaler', scaler), ('svc', clf)])
pipe.fit(X, y)
# check shapes of various prediction functions
predict = pipe.predict(X)
assert_equal(predict.shape, (n_samples, ))
proba = pipe.predict_proba(X)
assert_equal(proba.shape, (n_samples, n_classes))
log_proba = pipe.predict_log_proba(X)
assert_equal(log_proba.shape, (n_samples, n_classes))
decision_function = pipe.decision_function(X)
assert_equal(decision_function.shape, (n_samples, n_classes))
pipe.score(X, y)
def test_regressors_int():
# test if regressors can cope with integer labels (by converting them to
# float)
estimators = all_estimators()
regressors = [(name, E) for name, E in estimators if issubclass(E,
RegressorMixin)]
boston = load_boston()
X, y = boston.data, boston.target
X, y = shuffle(X, y, random_state=0)
X = Scaler().fit_transform(X)
y = np.random.randint(2, size=X.shape[0])
for name, Reg in regressors:
if Reg in dont_test or Reg in meta_estimators:
continue
# catch deprecation warnings
with warnings.catch_warnings(record=True):
# separate estimators to control random seeds
reg1 = Reg()
reg2 = Reg()
if hasattr(reg1, 'alpha'):
reg1.set_params(alpha=0.01)
reg2.set_params(alpha=0.01)
if hasattr(reg1, 'random_state'):
reg1.set_params(random_state=0)
reg2.set_params(random_state=0)
# fit
reg1.fit(X, y)
pred1 = reg1.predict(X)
reg2.fit(X, y.astype(np.float))
pred2 = reg2.predict(X)
assert_array_almost_equal(pred1, pred2, 2)
def load_data(path, label_encoder):
data = {
"train_o": [],
"train_i": [],
"val_o": [],
"val_i": [],
"test_o": [],
"test_i": []
}
for data_type in ["train", "val", "test"]:
csv_files_path = list(
paths.list_files(os.path.join(path, data_type), ".csv"))
for csv_path in tqdm(csv_files_path):
df = pd.read_csv(csv_path)
df = df["close"]
input_data = df.values
input_data = Scaler().fit_transform(input_data.reshape(
-1, 1)).flatten()
output_data = os.path.normpath(csv_path)
output_data = output_data.split(os.path.sep)[-2]
data[f"{data_type}_o"].append(label_encoder[output_data])
data[f"{data_type}_i"].append(input_data)
for key in data:
data[key] = np.asarray(data[key])
return data
def test_classifiers_classes():
# test if classifiers can cope with non-consecutive classes
estimators = all_estimators()
classifiers = [(name, E) for name, E in estimators
if issubclass(E, ClassifierMixin)]
iris = load_iris()
X, y = iris.data, iris.target
X, y = shuffle(X, y, random_state=7)
X = Scaler().fit_transform(X)
y = 2 * y + 1
# TODO: make work with next line :)
#y = y.astype(np.str)
for name, Clf in classifiers:
if Clf in dont_test or Clf in meta_estimators:
continue
if Clf in [MultinomialNB, BernoulliNB]:
# TODO also test these!
continue
# catch deprecation warnings
with warnings.catch_warnings(record=True) as w:
clf = Clf()
# fit
clf.fit(X, y)
y_pred = clf.predict(X)
# training set performance
assert_array_equal(np.unique(y), np.unique(y_pred))
assert_greater(zero_one_score(y, y_pred), 0.78)
def dimension(fnames, fp='ECFP', alg='PCA', maximum=int(1e5), ref='GPCR'):
df = pd.DataFrame()
for i, fname in enumerate(fnames):
sub = pd.read_table(fname).dropna(subset=['Smiles'])
sub = sub[sub.VALID == True]
if maximum is not None and len(sub) > maximum:
sub = sub.sample(maximum)
if ref not in fname:
sub = sub[sub.DESIRE == True]
sub = sub.drop_duplicates(subset='Smiles')
sub['LABEL'] = i
df = df.append(sub)
if fp == 'similarity':
ref = df[(df.LABEL == 0) & (df.DESIRE == True)]
refs = Predictor.calc_ecfp(ref.Smiles)
fps = Predictor.calc_ecfp(df.Smiles)
from rdkit.Chem import DataStructs
fps = np.array(
[DataStructs.BulkTanimotoSimilarity(fp, refs) for fp in fps])
else:
fp_alg = Predictor.calc_ecfp if fp == 'ECFP' else Predictor.calc_physchem
fps = fp_alg(df.Smiles)
fps = Scaler().fit_transform(fps)
pca = PCA(n_components=2) if alg == 'PCA' else TSNE(n_components=2)
xy = pca.fit_transform(fps)
df['X'], df['Y'] = xy[:, 0], xy[:, 1]
if alg == 'PCA':
ratio = pca.explained_variance_ratio_[:2]
return df, ratio
else:
return df
def reorder(data):
F = bm.TSPCF
scaler = Scaler()
c_data = data.drop(
columns=['cluster', 'id', 'artist', 'duration_ms', 'time_signature'])
c_data = scaler.fit_transform(c_data)
dist = distance_matrix(c_data, c_data)
M = 2 * np.max(dist)
np.fill_diagonal(dist, M)
L = len(c_data)
limite = [L * [0], L * [(L - 1)]]
p = L * [1]
A, B, C, D = PSO.run(F, 1000, limite, 5, 10, dist, passo=p, permut=True)
edge_lengths = [dist[-1][0]]
for i in range(len(A) - 1):
d = dist[i][i + 1]
edge_lengths.append(d)
m_d = max(edge_lengths)
M = edge_lengths.index(m_d)
A = np.append(A[M:], A[:M])
B -= m_d
try:
L_range = list(range(len(A)))
N_order = [list(A).index(val) for val in L_range]
data['new_order'] = N_order
data = data.sort_values(by='new_order')
dataset = data.drop(columns=['new_order'])
try:
dataset = data.drop(columns=['Unnamed: 0'])
except:
pass
return dataset
except:
return data
def test_scaler_2d_arrays():
"""Test scaling of 2d array along first axis"""
rng = np.random.RandomState(0)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is not X)
# check inverse transform
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_scaled = scale(X, axis=1, with_std=False)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
X_scaled = scale(X, axis=1, with_std=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=1), 4 * [1.0])
# Check that the data hasn't been modified
assert_true(X_scaled is not X)
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is X)
X = rng.randn(4, 5)
X[:, 0] = 1.0 # first feature is a constant, non zero feature
scaler = Scaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is not X)
def Classifier():
scaler = Scaler()
es = callbacks.EarlyStopping(
monitor="val_loss",
min_delta=0,
patience=500,
verbose=0,
mode="auto",
baseline=None,
restore_best_weights=True,
)
mc = tf.keras.callbacks.ModelCheckpoint(
'best_model.h5',
monitor="val_accuracy",
verbose=0,
save_best_only=True,
save_weights_only=False,
mode="auto",
save_freq="epoch",
)
in_data = 'clustered.csv'
data = pd.read_csv(in_data)
data = data.dropna()
id = data['id']
data = data.drop(columns=['id'])
step = 1
train_label = data['cluster']
train_data = data.drop(columns=['cluster', 'artist'])
train_data = train_data.fillna(0)
train_label = train_label.fillna(0)
train_data = scaler.fit_transform(train_data)
n_layers = 2
model = Sequential()
model.add(Dense(64, input_dim=len(train_data[0]), activation='relu'))
for _ in range(n_layers):
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense((1 + np.max(train_label.values)), activation='softmax'))
model.compile(loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(train_data,
train_label,
epochs=1000,
batch_size=50,
verbose=2,
callbacks=[es, mc],
validation_split=0.2,
shuffle=True)
model.load_weights('best_model.h5')
probs = model.predict(train_data)
predictions = np.argmax(probs, axis=-1)
P = pd.DataFrame(probs)
dp = pd.DataFrame(predictions, columns=['predicted_cluster'])
dp['predicted_prob'] = np.max(probs, axis=-1)
P.to_csv('Song_Probs.csv', index=False)
dp.to_csv('Song_preds.csv', index=False)
def __init__(self, set_name='AWA1', batch_size=256, **kwargs):
super().__init__(set_name, batch_size, **kwargs)
self.content = [
'feat', 'label', 'label_emb', 's_cls', 'u_cls', 'cls_emb',
's_cls_emb', 'u_cls_emb'
]
self.parts = ['training', 'seen', 'unseen']
self.scaler = Scaler()
self._init_scaler()
def test_regressors_train():
estimators = all_estimators()
regressors = [(name, E) for name, E in estimators
if issubclass(E, RegressorMixin)]
boston = load_boston()
X, y = boston.data, boston.target
X, y = shuffle(X, y, random_state=0)
# TODO: test with intercept
# TODO: test with multiple responses
X = Scaler().fit_transform(X)
y = Scaler().fit_transform(y)
succeeded = True
for name, Reg in regressors:
if Reg in dont_test or Reg in meta_estimators:
continue
# catch deprecation warnings
with warnings.catch_warnings(record=True):
reg = Reg()
if hasattr(reg, 'alpha'):
reg.set_params(alpha=0.01)
# raises error on malformed input for fit
assert_raises(ValueError, reg.fit, X, y[:-1])
# fit
try:
if Reg in (_PLS, PLSCanonical, PLSRegression, CCA):
y_ = np.vstack([y, 2 * y + np.random.randint(2, size=len(y))])
y_ = y_.T
else:
y_ = y
reg.fit(X, y_)
reg.predict(X)
if Reg not in (PLSCanonical, CCA): # TODO: find out why
assert_greater(reg.score(X, y_), 0.5)
except Exception as e:
print(reg)
print e
print
succeeded = False
assert_true(succeeded)
def test_classifiers_train():
# test if classifiers do something sensible on training set
# also test all shapes / shape errors
estimators = all_estimators()
classifiers = [(name, E) for name, E in estimators
if issubclass(E, ClassifierMixin)]
iris = load_iris()
X, y = iris.data, iris.target
X, y = shuffle(X, y, random_state=7)
n_samples, n_features = X.shape
n_labels = len(np.unique(y))
X = Scaler().fit_transform(X)
for name, Clf in classifiers:
if Clf in dont_test or Clf in meta_estimators:
continue
if Clf in [MultinomialNB, BernoulliNB]:
# TODO also test these!
continue
# catch deprecation warnings
with warnings.catch_warnings(record=True) as w:
clf = Clf()
# fit
clf.fit(X, y)
y_pred = clf.predict(X)
assert_equal(y_pred.shape, (n_samples, ))
# training set performance
assert_greater(zero_one_score(y, y_pred), 0.78)
# raises error on malformed input for predict
assert_raises(ValueError, clf.predict, X.T)
if hasattr(clf, "decision_function"):
try:
# decision_function agrees with predict:
decision = clf.decision_function(X)
assert_equal(decision.shape, (n_samples, n_labels))
if not isinstance(clf, BaseLibSVM):
# 1on1 of LibSVM works differently
assert_array_equal(np.argmax(decision, axis=1), y_pred)
# raises error on malformed input for decision_function
assert_raises(ValueError, clf.decision_function, X.T)
except NotImplementedError:
pass
if hasattr(clf, "predict_proba"):
try:
# predict_proba agrees with predict:
y_prob = clf.predict_proba(X)
assert_equal(y_prob.shape, (n_samples, n_labels))
assert_array_equal(np.argmax(y_prob, axis=1), y_pred)
# raises error on malformed input for predict_proba
assert_raises(ValueError, clf.predict_proba, X.T)
except NotImplementedError:
pass
def single_task(feat, alg='RF', reg=False, is_extra=True):
df = pd.read_table('data/LIGAND_RAW.tsv').dropna(subset=pair[1:2])
df = df[df[pair[0]] == feat]
df = df[pair].set_index(pair[1])
year = df[pair[-1:]].groupby(pair[1]).min().dropna()
test = year[year[pair[-1]] > 2015].index
numery = df[pair[2]].groupby(pair[1]).mean().dropna()
comments = df[(df.Comment.str.contains('Not Active') == True)]
inhibits = df[(df.Standard_Type == 'Inhibition')
& df.Standard_Relation.isin(['<', '<='])]
relations = df[df.Standard_Type.isin(['EC50', 'IC50', 'Kd', 'Ki'])
& df.Standard_Relation.isin(['>', '>='])]
binary = pd.concat([comments, inhibits, relations], axis=0)
binary = binary[~binary.index.isin(numery.index)]
binary[pair[2]] = 3.99
binary = binary[pair[2]].groupby(binary.index).first()
df = numery.append(binary) if is_extra else numery
if not reg:
df = (df > th).astype(float)
df = df.sample(len(df))
print(feat, len(numery[numery >= th]), len(numery[numery < th]),
len(binary))
test_ix = set(df.index).intersection(test)
test = df.loc[test_ix].dropna()
data = df.drop(test.index)
test_x = utils.Predictor.calc_fp(
[Chem.MolFromSimles(mol) for mol in test.index])
data_x = utils.Predictor.calc_fp(
[Chem.MolFromSimles(mol) for mol in data.index])
out = 'output/single/%s_%s_%s' % (alg, 'REG' if reg else 'CLS', feat)
if alg != 'RF':
scaler = Scaler()
scaler.fit(data_x)
test_x = scaler.transform(test_x)
data_x = scaler.transform(data_x)
else:
X = np.concatenate([data_x, test_x], axis=0)
y = np.concatenate([data.values, test.values], axis=0)
Train_RF(X, y[:, 0], out=out + '.pkg', reg=reg)
data, test = data.to_frame(name='Label'), test.to_frame(name='Label')
data['Score'], test['Score'] = cross_validation(data_x,
data.values,
test_x,
test.values,
alg,
out,
reg=reg)
data.to_csv(out + '.cv.tsv', sep='\t')
test.to_csv(out + '.ind.tsv', sep='\t')
def __init__(self):
"""
Model initialization
"""
self.model = Pipeline(
steps=[('imputer', Imputer(strategy='median')),
('feature_union',
FeatureUnion(
n_jobs=1,
transformer_list=[
('band_1_pipe',
Pipeline(steps=[
('band_1', FunctionTransformer(self.band1)),
('band_1_standard_scale', Scaler()),
])),
('band_2_pipe',
Pipeline(steps=[
('band_2', FunctionTransformer(self.band2)),
('band_2_standard_scale', Scaler()),
])), ('inc_angle',
FunctionTransformer(self.angle))
])), ('xgboost', XGBClassifier(n_estimators=100))])
def test_scaler_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sp.csr_matrix(X)
scaler = Scaler(with_mean=False).fit(X)
X_scaled = scaler.transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
scaler_csr = Scaler(with_mean=False).fit(X_csr)
X_csr_scaled = scaler_csr.transform(X_csr, copy=True)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
assert_equal(scaler.mean_, scaler_csr.mean_)
assert_array_almost_equal(scaler.std_, scaler_csr.std_)
assert_array_almost_equal(X_scaled.mean(axis=0),
[0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis0(X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
# Check that X has not been modified (copy)
assert_true(X_scaled is not X)
assert_true(X_csr_scaled is not X_csr)
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_csr_scaled_back = scaler_csr.inverse_transform(X_csr_scaled)
assert_true(X_csr_scaled_back is not X_csr)
assert_true(X_csr_scaled_back is not X_csr_scaled)
assert_array_almost_equal(X_scaled_back, X)
def test_regressors_int():
estimators = all_estimators()
clustering = [(name, E) for name, E in estimators if issubclass(E,
ClusterMixin)]
boston = load_boston()
X, y = boston.data, boston.target
X, y = shuffle(X, y, random_state=0)
# TODO: test with intercept
# TODO: test with multiple responses
X_m = Scaler().fit_transform(X_m)
X = Scaler().fit_transform(X)
succeeded = True
for name, Reg in regressors:
if Reg in dont_test or Reg in meta_estimators:
continue
# catch deprecation warnings
with warnings.catch_warnings(record=True):
# separate estimators to control random seeds
reg1 = Reg()
reg2 = Reg()
if hasattr(reg1, 'random_state'):
reg1.set_params(random_state=0)
reg2.set_params(random_state=0)
def sparser(dataset):
d = dataset.drop(columns=['id', 'artist', 'cluster', 'probs'])
scaler = Scaler()
scaled_d = scaler.fit_transform(d)
# scaled_d = scaled_d[-20:]
dist = np.triu(spy.distance_matrix(scaled_d, scaled_d))
scaled_dist = scaler.fit_transform(dist)
arg = np.max(scaled_dist)
indexes = np.argwhere(dist > (.25 * arg))
I = indexes.T
keep = list(set(I[0]))
sparse_d = dataset.iloc[keep, :]
sparse_d = sparse_d.sort_values('probs', ascending=False)
return sparse_d
def test_pipeline_methods_scaler_svm():
"""Test the various methods of the pipeline (scaler + svm)."""
iris = load_iris()
X = iris.data
y = iris.target
# Test with Scaler + SVC
clf = SVC(probability=True)
scaler = Scaler()
pipe = Pipeline([('scaler', scaler), ('svc', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def processData(filename, split, trainingSet, testSet):
DATASET_PATH = './'
data_path = os.path.join(DATASET_PATH, filename)
dataset = pd.read_csv(data_path, header=None)
dataset.columns = [
"Pregnancies", "Glucose", "BloodPressure", "SkinThickness", "Insulin",
"BMI", "DiabetesPedigreeFunction", "Age", "Outcome"
]
median_bmi = dataset['BMI'].median()
dataset['BMI'] = dataset['BMI'].replace(to_replace=0, value=median_bmi)
median_bloodp = dataset['BloodPressure'].median()
dataset['BloodPressure'] = dataset['BloodPressure'].replace(
to_replace=0, value=median_bloodp)
median_plglcconc = dataset['Glucose'].median()
dataset['Glucose'] = dataset['Glucose'].replace(to_replace=0,
value=median_plglcconc)
median_skinthick = dataset['SkinThickness'].median()
dataset['SkinThickness'] = dataset['SkinThickness'].replace(
to_replace=0, value=median_skinthick)
median_twohourserins = dataset['Insulin'].median()
dataset['Insulin'] = dataset['Insulin'].replace(to_replace=0,
value=median_twohourserins)
# print(dataset.head())
# print(dataset['BMI'][0])
scaler = Scaler()
scaler.fit(dataset)
scaled_dataset = scaler.transform(dataset)
# print(dataset['BMI'][0])
df = pd.DataFrame(data=scaled_dataset)
# print(df.head())
# datasetlst = pd.
# datasetlst = list(dataset)
datasetlst = df.values.tolist()
# map(datasetlst,dataset.values)
# datasetlst = list(dataset.values)
# print(datasetlst[0][5])
print(len(datasetlst))
for x in range(0, len(datasetlst) - 1):
for y in range(9):
datasetlst[x][y] = float(datasetlst[x][y])
if random.random() < split:
trainingSet.append(datasetlst[x])
else:
testSet.append(datasetlst[x])
def SVM_fit(X_in, y_in, X_out, gamma, C):
M = len(X_in[0]) #Number of features
seed(time())
#To prevent data snooping, breakes the input set into train. cross validation and test sets, with sizes proportional to 8-1-1
#First puts aside 10% of the data for the tests
test_indices, train_indices = split_indices(len(X_in),
int(round(0.1 * len(X_in))))
shuffle(X_in, y_in)
X_test = [X_in[i] for i in test_indices]
y_test = [y_in[i] for i in test_indices]
X_in = [X_in[i] for i in train_indices]
y_in = [y_in[i] for i in train_indices]
#scale data first
scaler = Scaler(copy=False) #in place modification
#Normalize the data and stores as inner parameters the mean and standard deviation
#To avoid data snooping, normalization is computed on training set only, and then reported on data
scaler.fit(X_test, y_test)
X_in = scaler.transform(X_in)
X_test = scaler.transform(X_test)
X_out = scaler.transform(
X_out) #uses the same transformation (same mean_ and std_) fit before
std_test = X_test.std(axis=0)
f_indices = [j for j in range(M) if std_test[j] > 1e-7]
#Removes feature with null variance
X_in = [[X_in[i][j] for j in f_indices] for i in range(len(X_in))]
X_test = [[X_test[i][j] for j in f_indices] for i in range(len(X_test))]
X_out = [[X_out[i][j] for j in f_indices] for i in range(len(X_out))]
M = len(f_indices)
#Then, on the remaining data, performs a ten-fold cross validation over the number of features considered
svc = svm.SVC(kernel='rbf',
C=C,
gamma=gamma,
verbose=False,
cache_size=4092,
tol=1e-5)
svc.fit(X_in, y_in)
y_out = svc.predict(X_out)
return y_out
