"make a random prediction)")
args = parser.parse_args()
#==============================================================================
# Generate classification data
#==============================================================================
SEED = 2018
# Load training data
LS = load_from_csv(args.ls)
# Load test data
TS = load_from_csv(args.ts)
with measure_time("Creating fingerprint"):
X_train = create_fingerprints(LS["SMILES"].values)
y_train = LS["ACTIVE"].values
TS = load_from_csv(args.ts)
X_test = create_fingerprints(TS["SMILES"].values)
#==============================================================================
# Define Base (level 0) and Stacking (level 1) estimators
#==============================================================================
base_clf = [
RandomForestClassifier(n_estimators=3100,
bootstrap=True,
max_depth=None,
class_weight='balanced_subsample'),
MLPClassifier(random_state=42,
alpha=1e-5,
help="Use a decision tree classifier (by default, "
"make a random prediction)")
args = parser.parse_args()
# Load training data
LS = load_from_csv(args.ls)
# Load test data
TS = load_from_csv(args.ts)
# -------------------------- Model --------------------------- #
# LEARNING
# Create fingerprint features and output
with measure_time("Creating fingerprint"):
X_LS = create_fingerprints(LS["SMILES"].values)
y_LS = LS["ACTIVE"].values
# Set the parameters by cross-validation
tuned_parameters = [{ # every hyper-parameter can be tested
}]
scores = ['roc_auc']
for score in scores:
# Chercher GridSearchCV dans documentation
clf = GridSearchCV(KNeighborsClassifier(n_neighbors=53, algorithm='auto',
weights='distance'),
tuned_parameters, cv=2, scoring='%s' % score, n_jobs=-1, verbose=10)
clf.fit(X_LS, y_LS)
minority = LS[LS.ACTIVE == 1]
# Upsample minority class
minority_upsampled = resample(
minority,
replace=True, # sample with replacement
n_samples=len(majority), # to match majority class
random_state=0) # reproducible results
# Combine majority class with upsampled minority class
LS_upsampled = pd.concat([majority, minority_upsampled])
# -------------------------- Model --------------------------- #
# LEARNING
# Create fingerprint features and output
with measure_time("Creating fingerprint"):
X_LS = create_fingerprints(LS_upsampled["SMILES"].values)
y_LS = LS_upsampled["ACTIVE"].values
# Set the parameters by cross-validation
tuned_parameters = [{ # every hyper-parameter can be tested
}]
scores = ['roc_auc']
for score in scores:
# Chercher GridSearchCV dans documentation
clf = GridSearchCV(RandomForestClassifier(
n_estimators=3100,
bootstrap=True,
max_depth=None,
class_weight='balanced_subsample',
