def predictSubchallenge2(estimator, opt, output, model_output=None, features_output=None):
# Load data
print "loading data"
d = load_datasets(
opt["subchallenge"],
opt["final"],
opt["filterQA"],
opt["use_mut"],
opt["use_CNV"],
opt["use_exp"],
opt["use_methyl"],
opt["use_drug_info"],
opt["use_cell_info"],
)
saveObserved(d)
if opt["use_drug_info"]:
# Get split datasets
# add cell_and_IDs here
data = [
(d["comb_train_input_None"], d["comb_train_output_None"], d["leaderboard_None"]),
(d["comb_train_input_One"], d["comb_train_output_One"], d["leaderboard_One"]),
(d["comb_train_input_Both"], d["comb_train_output_Both"], d["leaderboard_Both"]),
]
# in this case, data is a list that contains 3 sets of X, y, LB
else:
data = [(d["comb_train_input"], d["comb_train_output"], d["leaderboard"])]
if path.exists(output):
remove(output)
f = open(output, "a") # append mode
f.write("Estimator:\t" + estimator[0] + "\n\n")
f.write("Estimator parameters:\n" + str(estimator[1].get_params()) + "\n\n")
f.write("Options:\n")
for key in opt:
f.write(key + "\t" + str(opt[key]) + "\n")
f.write("\n")
iters_predictions = []
feature_lists = []
for i in xrange(len(data)):
if len(data) > 1:
f.write("Model " + str(i + 1) + "\n")
# Preprocess data
print "preprocessing data"
X_train, LB, feature_names = preprocess(
data[i][0],
data[i][2],
d,
opt["use_mut"],
opt["use_CNV"],
opt["use_exp"],
opt["exp_threshold"],
opt["use_methyl"],
opt["use_cell_info"],
opt["scale"],
)
y_train = data[i][1].values
# Feature selection
print "feature selection"
if opt["num_features"] > len(feature_names):
selected = featureSelection(X_train, y_train, opt["selection_method"], estimator[1], "all")
else:
selected = featureSelection(X_train, y_train, opt["selection_method"], estimator[1], opt["num_features"])
X_train = X_train[:, selected]
LB = LB[:, selected]
feature_lists.append([feature for (feature, mask) in zip(feature_names, selected) if mask])
# Predict leaderboard/test output:
print "predicting"
estimator[1].fit(X_train, y_train)
iters_predictions.append(estimator[1].predict(LB))
if features_output != None:
saveFeatures(feature_lists, features_output)
# Save predictions and confidence
if opt["use_drug_info"]:
predictions = pd.concat(
[
pd.Series(data=iters_predictions[0], name="PREDICTION", index=d["leaderboard_None"].index),
pd.Series(data=iters_predictions[1], index=d["leaderboard_One"].index),
pd.Series(data=iters_predictions[2], index=d["leaderboard_Both"].index),
],
axis=0,
)
else:
predictions = pd.Series(data=iters_predictions[0], name="PREDICTION", index=d["leaderboard"].index)
savePredictionsSubch2(predictions, d)
saveConfidenceSubch2(d)
# Save model
if model_output != None:
joblib.dump(estimator, model_output)
f.close()
def evaluateAndPredict(estimator, opt, output, evaluate=True, predict=False, model_output=None, features_output=None):
# Load data
print "loading data"
d = load_datasets(
opt["subchallenge"],
opt["final"],
opt["filterQA"],
opt["use_mut"],
opt["use_CNV"],
opt["use_exp"],
opt["use_methyl"],
opt["use_drug_info"],
opt["use_cell_info"],
)
saveObserved(d)
if opt["use_drug_info"]:
# Get split datasets
data = [
(d["comb_train_input_None"], d["comb_train_output_None"], d["leaderboard_None"]),
(d["comb_train_input_One"], d["comb_train_output_One"], d["leaderboard_One"]),
(d["comb_train_input_Both"], d["comb_train_output_Both"], d["leaderboard_Both"]),
]
# in this case, data is a list that contains 3 sets of X, y, LB
else:
data = [(d["comb_train_input"], d["comb_train_output"], d["leaderboard"])]
if path.exists(output):
remove(output)
f = open(output, "a") # append mode
f.write("Estimator:\t" + estimator[0] + "\n\n")
f.write("Options:\n")
for key in opt:
f.write(key + "\t" + str(opt[key]) + "\n")
f.write("\n")
iters_cv_pred = []
iters_predictions = []
iters_confidence = []
feature_lists = []
for i in xrange(len(data)):
if len(data) > 1:
f.write("Model " + str(i + 1) + "\n")
# Preprocess data
print "preprocessing data"
X_train, LB, feature_names = preprocess(
data[i][0],
data[i][2],
d,
opt["use_mut"],
opt["use_CNV"],
opt["use_exp"],
opt["exp_threshold"],
opt["use_methyl"],
opt["use_cell_info"],
opt["scale"],
)
y_train = data[i][1].values
# Feature selection (if using SelectKBest)
if opt["selection_method"] == "kbest":
print "feature selection"
if opt["num_features"] > len(feature_names):
selected = featureSelection(X_train, y_train, opt["selection_method"], estimator[1], "all")
else:
selected = featureSelection(
X_train, y_train, opt["selection_method"], estimator[1], opt["num_features"]
)
X_train = X_train[:, selected]
LB = LB[:, selected]
# Optimize parameters (only does the actual optimization if parameters dict is not empty) and write best parameters to file
opt_est = optParameters(estimator[1], X_train, y_train, estimator[2], data[i][0])
f.write("Best parameters:\n" + str(opt_est[1]) + "\n\n")
# Feature selection (if not using SelectKBest)
if opt["selection_method"] != "kbest":
selected = featureSelection(X_train, y_train, opt["selection_method"], opt_est[0], opt["num_features"])
X_train = X_train[:, selected]
LB = LB[:, selected]
feature_lists.append([feature for (feature, mask) in zip(feature_names, selected) if mask])
if evaluate:
print "evaluating model"
# Model evaluation
predictions, confidence = evalModel(opt_est[0], X_train, y_train, 5, opt["cv_iterations"])
iters_cv_pred.append(predictions)
iters_confidence.append(confidence)
if predict:
print "predicting"
# Predict leaderboard/test output:
opt_est[0].fit(X_train, y_train)
iters_predictions.append(opt_est[0].predict(LB))
if features_output != None:
saveFeatures(feature_lists, features_output)
# Join dataset subsets and calculate scores/save to file
if evaluate:
print "calculating scores"
if opt["use_drug_info"]:
cv_predictions = pd.Series(
data=iters_cv_pred[0], name="PREDICTION", index=d["comb_train_input_None"].index
).append(pd.Series(data=iters_cv_pred[1], name="PREDICTION", index=d["comb_train_input_One"].index))
cv_predictions = cv_predictions.append(
pd.Series(data=iters_cv_pred[2], name="PREDICTION", index=d["comb_train_input_Both"].index)
)
confidence = pd.concat(
[
pd.Series(data=iters_confidence[0], name="CONFIDENCE", index=d["comb_train_input_None"].index),
pd.Series(data=iters_confidence[1], name="CONFIDENCE", index=d["comb_train_input_One"].index),
pd.Series(data=iters_confidence[2], name="CONFIDENCE", index=d["comb_train_input_Both"].index),
],
axis=0,
)
else:
if estimator[0] == "PLS":
iters_cv_pred[0] = [float(iters_cv_pred[0][i]) for i in xrange(len(iters_cv_pred[0]))]
iters_confidence[0] = [float(iters_confidence[0][i]) for i in xrange(len(iters_confidence[0]))]
cv_predictions = pd.Series(data=iters_cv_pred[0], name="PREDICTION", index=d["comb_train_input"].index)
confidence = pd.Series(data=iters_confidence[0], name="CONFIDENCE", index=d["comb_train_input"].index)
savePredictions(cv_predictions, d, CV=True)
saveConfidence(confidence, d)
# Calculate scores and write to file
r2 = r2_score(d["comb_train_output"].values, cv_predictions.values)
challenge_performance = drugCombiScore(d["comb_train_output"].values, cv_predictions.values, d)
challenge_global = globalScore(d["comb_train_output"].values, cv_predictions.values, d)
print challenge_performance
print challenge_global
f.write("Model Evaluation\n")
f.write("R2:\t" + str(r2) + "\n")
f.write("Performance score:\t" + str(challenge_performance[0]) + "\n")
f.write("Standard error:\t" + str(challenge_performance[1]) + "\n")
f.write("Global score:\t" + str(challenge_global[0]) + "\n")
f.write("Primary metric:\t" + str(challenge_global[1]) + "\n")
f.write("Tie-breaking metric:\t" + str(challenge_global[2]) + "\n")
if predict:
if opt["use_drug_info"]:
predictions = pd.concat(
[
pd.Series(data=iters_predictions[0], name="PREDICTION", index=d["leaderboard_None"].index),
pd.Series(data=iters_predictions[1], index=d["leaderboard_One"].index),
pd.Series(data=iters_predictions[2], index=d["leaderboard_Both"].index),
],
axis=0,
)
else:
predictions = pd.Series(data=iters_predictions[0], name="PREDICTION", index=d["leaderboard"].index)
savePredictions(predictions, d, CV=False)
# Save model
if model_output != None:
joblib.dump(estimator, model_output)
f.close()