def main():
# Read training set
print
print 'Reading training set...'
train = utils.ReadFile('train.csv', 1)
print 'Finished reading...\n'
# Preliminary Statistics
print 'Preliminary Statistics:'
print np.shape(train)[0] - 1, 'people.', np.shape(
train)[1] - 2, 'features.'
print(train[1:, 1] == '1').sum(), 'survivors.', (
train[1:, 1] == '0').sum(), 'deceased.\n'
#Testing
id = 10
mask = train[1:, id] == ''
#print list(set(tmp))
#print train[1:,id]
#print mask.sum()
# Map string features to floats
print 'Mapping Features to Floats.\n'
dictN = {} # modified in call (useful for name feature)
dictC = {} # modified in call (useful for cabin feature)
dat, dictN, dictC = utils.mapToF(train[1:, :], 0, dictN, dictC)
# Class labels
lab = np.array([int(h) for h in train[1:, 1]])
# Generate better model for missing Age feature
means = np.zeros(len(dictN), dtype=np.float64)
dat, means = utils.AgeModel(dat, dictN, means, 1)
# Preliminary Plots
print 'Generating preliminary scatter plots of data.\n'
utils.PrelimPlots(dat, lab)
dat = utils.MeanNorm(dat)
# ML algorithms
print "Choosing best parameters for Gradient Boosting algorithm:"
optim = TestGradBoost(dat, lab)
# Plotting Learning Curve
print "Plotting the learning curve\n"
plotLearningCurve(dat, lab, optim)
# Read in test set
print "Reading in Test Set\n"
test = utils.ReadFile('test.csv', 0)
# Map to floats
testF, dictN, dictC = utils.mapToF(test[1:, :], 1, dictN, dictC)
# Make better prediction for missing Age Features
testF, means = utils.AgeModel(testF, dictN, means, 0)
testF = utils.MeanNorm(testF)
# Make prediction
print "Making Prediction\n"
clf = GradientBoostingClassifier(learning_rate=optim[0],
subsample=optim[1])
clf = clf.fit(dat, lab)
pred = clf.predict(testF)
# Now output prediction
print "Outputting Prediction\n"
utils.OutputFile(pred, train[0, :2], test[1, 0], 2)
print "Done"
def main():
# Read training set
print
print 'Reading training set...'
train = utils.ReadFile('train.csv', 1)
print 'Finished reading...\n'
# Preliminary Statistics
print 'Preliminary Statistics:'
print np.shape(train)[0] - 1, 'people.', np.shape(
train)[1] - 2, 'features.'
print(train[1:, 1] == '1').sum(), 'survivors.', (
train[1:, 1] == '0').sum(), 'deceased.\n'
#Testing
id = 10
mask = train[1:, id] == ''
#print list(set(tmp))
#print train[1:,id]
#print mask.sum()
# Map string features to floats
print 'Mapping Features to Floats.\n'
dictN = {} # modified in call (useful for name feature)
dictC = {} # modified in call (useful for cabin feature)
dat, dictN, dictC = utils.mapToF(train[1:, :], 0, dictN, dictC)
# Class labels
lab = np.array([int(h) for h in train[1:, 1]])
# Generate better model for missing Age feature
#means = np.zeros(len(dictN), dtype = np.float64)
#dat, means = utils.AgeModel(dat, dictN, means, 1)
mask = dat[:, 2] != -1.0
dat2 = np.zeros((mask.sum(), 9), dtype=np.float64)
tar2 = np.zeros(mask.sum(), dtype=np.float64)
dat, dat2, tar2 = utils.AgeModel2(dat, dat2, tar2, 1)
# Preliminary Plots
print 'Generating preliminary scatter plots of data.\n'
utils.PrelimPlots(dat, lab)
utils.AgePlots(dat)
# Mean Normalization
dat = utils.MeanNorm(dat)
# ML algorithms
print "Choosing best parameters for Random Forest algorithm:"
optimRF = TestRandForest(dat, lab)
print "Choosing best parameters for Gradient Boosting algorithm:"
optimGB = TestGradBoost(dat, lab)
print "Choosing best parameters for SVM algorithm:"
optimSVM = TestSVM(dat, lab)
# Plotting Learning Curve
#print "Plotting the learning curve\n"
#plotLearningCurve(dat, lab, optim)
# Read in test set
print "Reading in Test Set\n"
test = utils.ReadFile('test.csv', 0)
# Map to floats
testF, dictN, dictC = utils.mapToF(test[1:, :], 1, dictN, dictC)
# Make better prediction for missing Age Features
#testF, means = utils.AgeModel(testF, dictN, means, 0)
testF, dat2, tar2 = utils.AgeModel2(testF, dat2, tar2, 0)
# Mean Normalization
testF = utils.MeanNorm(testF)
# Make prediction array
predA = np.zeros((len(testF), 3), dtype=np.float64)
# Make prediction
print "Making Prediction for RF:"
clf = RandomForestClassifier(n_estimators=optimRF[0],
max_features=optimRF[1],
min_samples_split=1)
clf = clf.fit(dat, lab)
predA[:, 0] = clf.predict(testF)
print "Making Prediction for GB:"
clf = GradientBoostingClassifier(learning_rate=optimGB[0],
subsample=optimGB[1])
clf = clf.fit(dat, lab)
predA[:, 1] = clf.predict(testF)
# Make prediction
print "Making Prediction for SVM:\n"
clf = svm.SVC(C=optimSVM)
clf = clf.fit(dat, lab)
predA[:, 2] = clf.predict(testF)
# choose the prediction with the most votes
#print predA
pred = stats.mode(predA, axis=1)[0]
#print pred
# Now output prediction
print "Outputting Prediction\n"
utils.OutputFile(pred, train[0, :2], test[1, 0], 3)
print "Done"
def main():
# Read training set
print
print 'Reading training set...'
train = utils.ReadFile('train.csv', 1)
print 'Finished reading...\n'
# Preliminary Statistics
print 'Preliminary Statistics:'
print np.shape(train)[0] - 1, 'people.', np.shape(train)[1] - 2, 'features.'
print (train[1:,1] == '1').sum(), 'survivors.', (train[1:,1] == '0').sum(), 'deceased.\n'
#Testing
id = 10
mask = train[1:,id] == ''
#print list(set(tmp))
#print train[1:,id]
#print mask.sum()
# Map string features to floats
print 'Mapping Features to Floats.\n'
dictN = {} # modified in call (useful for name feature)
dictC = {} # modified in call (useful for cabin feature)
dat, dictN, dictC = utils.mapToF(train[1:,:], 0, dictN, dictC)
# Class labels
lab = np.array([int(h) for h in train[1:,1]])
# Generate better model for missing Age feature
means = np.zeros(len(dictN), dtype = np.float64)
dat, means = utils.AgeModel(dat, dictN, means, 1)
# Preliminary Plots
print 'Generating preliminary scatter plots of data.\n'
utils.PrelimPlots(dat, lab)
dat = utils.MeanNorm(dat)
# ML algorithms
print "Choosing best parameters for SVM algorithm:"
optim = TestSVM(dat, lab)
# Plotting Learning Curve
print "Plotting the learning curve\n"
plotLearningCurve(dat, lab, optim)
# Read in test set
print "Reading in Test Set\n"
test = utils.ReadFile('test.csv',0)
# Map to floats
testF, dictN, dictC = utils.mapToF(test[1:,:], 1, dictN, dictC)
# Make better prediction for missing Age Features
testF, means = utils.AgeModel(testF, dictN, means, 0)
testF = utils.MeanNorm(testF)
# Make prediction
print "Making Prediction\n"
clf = svm.SVC(C = optim)
clf = clf.fit(dat, lab)
pred = clf.predict(testF)
# Now output prediction
print "Outputting Prediction\n"
utils.OutputFile(pred, train[0,:2], test[1,0], 1)
print "Done"
def main():
# Read training set
print
print 'Reading training set...'
train = utils.ReadFile('train.csv', 1)
print 'Finished reading...\n'
# Preliminary Statistics
print 'Preliminary Statistics:'
print np.shape(train)[0] - 1, 'people.', np.shape(train)[1] - 2, 'features.'
print (train[1:,1] == '1').sum(), 'survivors.', (train[1:,1] == '0').sum(), 'deceased.\n'
#Testing
id = 10
mask = train[1:,id] == ''
#print list(set(tmp))
#print train[1:,id]
#print mask.sum()
# Map string features to floats
print 'Mapping Features to Floats.\n'
dictN = {} # modified in call (useful for name feature)
dictC = {} # modified in call (useful for cabin feature)
dat, dictN, dictC = utils.mapToF(train[1:,:], 0, dictN, dictC)
# Class labels
lab = np.array([int(h) for h in train[1:,1]])
# Generate better model for missing Age feature
#means = np.zeros(len(dictN), dtype = np.float64)
#dat, means = utils.AgeModel(dat, dictN, means, 1)
mask = dat[:,2] != -1.0
dat2 = np.zeros((mask.sum(),9), dtype = np.float64)
tar2 = np.zeros(mask.sum(), dtype = np.float64)
dat, dat2, tar2 = utils.AgeModel2(dat, dat2, tar2, 1)
# testing
#mask = dat[:,2] == -1.0
#print mask.sum()
# Preliminary Plots
print 'Generating preliminary scatter plots of data.\n'
utils.PrelimPlots(dat, lab)
utils.AgePlots(dat)
#dat = utils.MeanNorm(dat)
# ML algorithms
print "Choosing best parameters for Random Forest algorithm:"
optim = TestRandForest(dat, lab)
# Plotting Learning Curve
print
print "Plotting the learning curve\n"
plotLearningCurve(dat, lab, optim)
# Where is algorithm failing?
print "Where is algorithm failing:\n"
whereFailing(dat, lab, optim)
# Read in test set
print "Reading in Test Set\n"
test = utils.ReadFile('test.csv', 0)
# Map to floats
testF, dictN, dictC = utils.mapToF(test[1:,:], 1, dictN, dictC)
# Make better prediction for missing Age Features
#testF, means = utils.AgeModel(testF, dictN, means, 0)
testF, dat2, tar2 = utils.AgeModel2(testF, dat2, tar2, 0)
# Generate scatter plot for test set
utils.plotData(testF, 0)
#testF = utils.MeanNorm(testF)
# Make prediction
print "Making Prediction\n"
clf = RandomForestClassifier(n_estimators = optim[0],
max_features = optim[1],
min_samples_split = 1)
clf = clf.fit(dat, lab)
pred = clf.predict(testF)
# Now output prediction
print "Outputting Prediction\n"
utils.OutputFile(pred, train[0,:2], test[1,0], 0)
print "Done"
def main():
# Read training set
print
print 'Reading training set...'
train = utils.ReadFile('train.csv', 1)
print 'Finished reading...\n'
# Preliminary Statistics
print 'Preliminary Statistics:'
print np.shape(train)[0] - 1, 'people.', np.shape(
train)[1] - 2, 'features.'
print(train[1:, 1] == '1').sum(), 'survivors.', (
train[1:, 1] == '0').sum(), 'deceased.\n'
#Testing
id = 10
mask = train[1:, id] == ''
#print list(set(tmp))
#print train[1:,id]
#print mask.sum()
# Map string features to floats
print 'Mapping Features to Floats.\n'
dictN = {} # modified in call (useful for name feature)
dictC = {} # modified in call (useful for cabin feature)
dat, dictN, dictC = utils.mapToF(train[1:, :], 0, dictN, dictC)
# Class labels
lab = np.array([int(h) for h in train[1:, 1]])
# Generate better model for missing Age feature
#means = np.zeros(len(dictN), dtype = np.float64)
#dat, means = utils.AgeModel(dat, dictN, means, 1)
mask = dat[:, 2] != -1.0
dat2 = np.zeros((mask.sum(), 9), dtype=np.float64)
tar2 = np.zeros(mask.sum(), dtype=np.float64)
dat, dat2, tar2 = utils.AgeModel2(dat, dat2, tar2, 1)
# testing
#mask = dat[:,2] == -1.0
#print mask.sum()
# Preliminary Plots
print 'Generating preliminary scatter plots of data.\n'
utils.PrelimPlots(dat, lab)
utils.AgePlots(dat)
#dat = utils.MeanNorm(dat)
# ML algorithms
print "Choosing best parameters for Random Forest algorithm:"
optim = TestRandForest(dat, lab)
# Plotting Learning Curve
print
print "Plotting the learning curve\n"
plotLearningCurve(dat, lab, optim)
# Where is algorithm failing?
print "Where is algorithm failing:\n"
whereFailing(dat, lab, optim)
# Read in test set
print "Reading in Test Set\n"
test = utils.ReadFile('test.csv', 0)
# Map to floats
testF, dictN, dictC = utils.mapToF(test[1:, :], 1, dictN, dictC)
# Make better prediction for missing Age Features
#testF, means = utils.AgeModel(testF, dictN, means, 0)
testF, dat2, tar2 = utils.AgeModel2(testF, dat2, tar2, 0)
# Generate scatter plot for test set
utils.plotData(testF, 0)
#testF = utils.MeanNorm(testF)
# Make prediction
print "Making Prediction\n"
clf = RandomForestClassifier(n_estimators=optim[0],
max_features=optim[1],
min_samples_split=1)
clf = clf.fit(dat, lab)
pred = clf.predict(testF)
# Now output prediction
print "Outputting Prediction\n"
utils.OutputFile(pred, train[0, :2], test[1, 0], 0)
print "Done"
def main():
# Read training set
print
print "Reading training set..."
train = utils.ReadFile("train.csv", 1)
print "Finished reading...\n"
# Preliminary Statistics
print "Preliminary Statistics:"
print np.shape(train)[0] - 1, "people.", np.shape(train)[1] - 2, "features."
print (train[1:, 1] == "1").sum(), "survivors.", (train[1:, 1] == "0").sum(), "deceased.\n"
# Testing
id = 10
mask = train[1:, id] == ""
# print list(set(tmp))
# print train[1:,id]
# print mask.sum()
# Map string features to floats
print "Mapping Features to Floats.\n"
dictN = {} # modified in call (useful for name feature)
dictC = {} # modified in call (useful for cabin feature)
dat, dictN, dictC = utils.mapToF(train[1:, :], 0, dictN, dictC)
# Class labels
lab = np.array([int(h) for h in train[1:, 1]])
# Generate better model for missing Age feature
# means = np.zeros(len(dictN), dtype = np.float64)
# dat, means = utils.AgeModel(dat, dictN, means, 1)
mask = dat[:, 2] != -1.0
dat2 = np.zeros((mask.sum(), 9), dtype=np.float64)
tar2 = np.zeros(mask.sum(), dtype=np.float64)
dat, dat2, tar2 = utils.AgeModel2(dat, dat2, tar2, 1)
# Preliminary Plots
print "Generating preliminary scatter plots of data.\n"
utils.PrelimPlots(dat, lab)
utils.AgePlots(dat)
# Mean Normalization
dat = utils.MeanNorm(dat)
# ML algorithms
print "Choosing best parameters for Random Forest algorithm:"
optimRF = TestRandForest(dat, lab)
print "Choosing best parameters for Gradient Boosting algorithm:"
optimGB = TestGradBoost(dat, lab)
print "Choosing best parameters for SVM algorithm:"
optimSVM = TestSVM(dat, lab)
# Plotting Learning Curve
# print "Plotting the learning curve\n"
# plotLearningCurve(dat, lab, optim)
# Read in test set
print "Reading in Test Set\n"
test = utils.ReadFile("test.csv", 0)
# Map to floats
testF, dictN, dictC = utils.mapToF(test[1:, :], 1, dictN, dictC)
# Make better prediction for missing Age Features
# testF, means = utils.AgeModel(testF, dictN, means, 0)
testF, dat2, tar2 = utils.AgeModel2(testF, dat2, tar2, 0)
# Mean Normalization
testF = utils.MeanNorm(testF)
# Make prediction array
predA = np.zeros((len(testF), 3), dtype=np.float64)
# Make prediction
print "Making Prediction for RF:"
clf = RandomForestClassifier(n_estimators=optimRF[0], max_features=optimRF[1], min_samples_split=1)
clf = clf.fit(dat, lab)
predA[:, 0] = clf.predict(testF)
print "Making Prediction for GB:"
clf = GradientBoostingClassifier(learning_rate=optimGB[0], subsample=optimGB[1])
clf = clf.fit(dat, lab)
predA[:, 1] = clf.predict(testF)
# Make prediction
print "Making Prediction for SVM:\n"
clf = svm.SVC(C=optimSVM)
clf = clf.fit(dat, lab)
predA[:, 2] = clf.predict(testF)
# choose the prediction with the most votes
# print predA
pred = stats.mode(predA, axis=1)[0]
# print pred
# Now output prediction
print "Outputting Prediction\n"
utils.OutputFile(pred, train[0, :2], test[1, 0], 3)
print "Done"