def runWithoutWndchrm(self):
print "Loading the classifier"
classifier = data_io.load_model()
imageCollections = data_io.get_valid_df()
featureGetter = FeatureGetter()
print "Getting the features"
fileName = data_io.get_savez_name_test()
if not self.load: #Last features calculated from candidates
(namesObservations, coordinates,
valid) = Utils.calculateFeatures(fileName, featureGetter,
imageCollections)
else:
(namesObservations, coordinates,
valid) = Utils.loadFeatures(fileName)
print "Making predictions"
#valid = normalize(valid, axis=0) #askdfhashdf
predictions = classifier.predict(valid)
predictions = predictions.reshape(len(predictions), 1)
print "Writing predictions to file"
data_io.write_submission(namesObservations, coordinates, predictions)
data_io.write_submission_nice(namesObservations, coordinates,
predictions)
print "Calculating final results"
return Predictor.finalResults(namesObservations, predictions,
coordinates)
def main():
print("Reading in the training data")
data = data_io.get_train_df()
print("Extracting features")
feature_extractor = Vectorizer(MAX_FEATURES)
category_vectorizer = DictVectorizer()
#category_title = pd.get_dummies(train['Title'])
#print (category_vectorizer.shape, X.shape)
X = form_input(data, feature_extractor, category_vectorizer)
#location = pd.get_dummies(train['LocationNormalized'])
#X = hstack((X, location))
#contract_time = pd.get_dummies(train['ContractTime'])
#X = hstack((X, contract_time))
#print(X)
y = data["SalaryNormalized"]
print("Training model")
linreg.train(X, y)
print("Making predictions")
predictions = linreg.predict(X)
mae_train = metrics.MAE(predictions, data["SalaryNormalized"])
print('MAE train=%s', mae_train)
print("Validating...")
data = data_io.get_valid_df()
X = form_input(data, feature_extractor, category_vectorizer, train=False)
predictions = linreg.predict(X)
data_io.write_submission(predictions)
'''
def main():
print("Loading the model")
model = data_io.load_model()
print("Making predictions")
valid = data_io.get_valid_df()
predictions = model * np.ones(len(valid))
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Loading the model")
model = data_io.load_model()
print("Making predictions")
valid = data_io.get_valid_df()
predictions = model * np.ones(len(valid))
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
valid = data_io.get_valid_df()
predictions = classifier.predict(valid)
predictions = predictions.reshape(len(predictions), 1)
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
valid = data_io.get_valid_df()
predictions = classifier.predict(valid)
predictions = predictions.reshape(len(predictions), 1)
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
valid = data_io.get_valid_df()
predictions = classifier.predict(valid)
predictions = np.rint(predictions) # Round predictions to nearest integer.
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
valid = data_io.get_valid_df()
predictions = classifier.predict(valid)
predictions = np.rint(predictions) # Round predictions to nearest integer.
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
valid = data_io.get_valid_df()
P={}
for key in valid:
print("Loading the classifier for %s" %key)
classifier = data_io.load_model(key)
print("Making predictions")
P[key] = classifier.predict(valid[key])
P[key] = P[key].reshape(len(P[key]), 1)
print("Writing predictions to file")
data_io.write_submission(P)
def run(self):
print "Preparing the environment"
self.prepareEnvironment()
print "Loading the classifier"
classifier = data_io.load_model()
imageCollections = data_io.get_valid_df()
featureGetter = FeatureGetter()
wndchrmWorker = WndchrmWorkerPredict()
print "Getting the features"
if not self.loadWndchrm: #Last wndchrm set of features
fileName = data_io.get_savez_name_test()
if not self.load: #Last features calculated from candidates
(namesObservations, coordinates,
_) = Utils.calculateFeatures(fileName, featureGetter,
imageCollections)
else:
(namesObservations, coordinates,
_) = Utils.loadFeatures(fileName)
print "Saving images"
imageSaver = ImageSaver(coordinates, namesObservations,
imageCollections, featureGetter.patchSize)
imageSaver.saveImages()
print "Executing wndchrm algorithm"
valid = wndchrmWorker.executeWndchrm(namesObservations)
else:
(valid, namesObservations) = wndchrmWorker.loadWndchrmFeatures()
print "Making predictions"
predictions = classifier.predict(valid)
predictions = predictions.reshape(len(predictions), 1)
print "Writing predictions to file"
data_io.write_submission(namesObservations, coordinates, predictions)
data_io.write_submission_nice(namesObservations, coordinates,
predictions)
print "Calculating final results"
return Predictor.finalResults(namesObservations, predictions,
coordinates)
