def getData(fileNameParam):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
trainData = testAndTrainData[0]
testData = testAndTrainData[1]
return trainData, testData
def experiemnt_random_forest(fileNameParam):
import exp_x_classifiers , IO_
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
#print testAndTrainData
print "This is 'experiemnt_random_forest' "
# settign up train data
trainData = testAndTrainData[0]
#print trainData
original_rows = trainData.shape[0]
original_cols = trainData.shape[1]
print "Size of training data : rows: {}, columns: {}".format( original_rows , original_cols )
# settign up test data
testData = testAndTrainData[1]
#print testData
for selCount in xrange(original_cols):
count_ = selCount + 1
if count_ <= original_cols:
slected_training_data = giveSelectedTrainingData(trainData, testData, count_ )
print "################# No. of features to work with={} ############".format(count_)
print "Size of selected training data : ", slected_training_data.shape
emperiemntSplitters=[float(x)/float(10) for x in xrange(10) if x > 0]
for elem in emperiemntSplitters:
#print "Training size: {} %".format(float(elem*100))
exp_x_classifiers.runRandomForest(slected_training_data, testData, elem)
def experiemnt_CART(fileNameParam):
import exp_x_classifiers, IO_
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
print "This is 'experiemnt_CART' "
# settign up train data
trainData = testAndTrainData[0]
original_rows = trainData.shape[0]
original_cols = trainData.shape[1]
print "Size of training data : rows: {}, columns: {}".format(
original_rows, original_cols)
# settign up test data
testData = testAndTrainData[1]
# for selCount in xrange(original_cols):
# count_ = selCount + 1
# if count_ < original_cols:
slected_training_data = giveSelectedTrainingData(trainData, testData,
original_cols)
print "################# No. of features to work with={} ############".format(
original_cols)
print "Size of selected training data : ", slected_training_data.shape
emperiemntSplitters = [float(x) / float(10) for x in xrange(10) if x > 0]
for elem in emperiemntSplitters:
#print "Training size: {} %".format(float(elem*100))
param_exp_classifier.runCART(slected_training_data, testData, elem)
def getData(fileNameParam): testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam) trainData = testAndTrainData[0] testData = testAndTrainData[1] return trainData, testData
def experiemnt_gaussian_naive_bayes(fileNameParam):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
print "This is 'experiemnt_gaussian_naive_bayes' "
# settign up train data
trainData = testAndTrainData[0]
original_rows = trainData.shape[0]
original_cols = trainData.shape[1]
print "Size of training data : rows: {}, columns: {}".format(
original_rows, original_cols)
# settign up test data
testData = testAndTrainData[1]
for selCount in xrange(original_cols):
count_ = selCount + 1
if count_ <= original_cols:
slected_training_data = giveSelectedTrainingData(
trainData, testData, count_)
print "################# No. of features to work with={} ############".format(
count_)
print "Size of selected training data : ", slected_training_data.shape
emperiemntSplitters = [
float(x) / float(10) for x in xrange(10) if x > 0
]
for elem in emperiemntSplitters:
#print "Training size: {} %".format(float(elem*100))
exp_x_classifiers.runGNB(slected_training_data, testData, elem)
def experiment_mobilesoft_knn(fileNameParam):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
trainData = testAndTrainData[0]
testData = testAndTrainData[1]
#print trainData
selected_training_data = getPCAedFeatures(trainData)
print "Size of selected training data : ", np.shape(selected_training_data)
print "=" * 50
exp_x_classifiers.runKNN(selected_training_data, testData, 0.90)
print "=" * 50
def mobilesoft_cart(fileNameParam, fileToWriteP):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
trainData = testAndTrainData[0]
testData = testAndTrainData[1]
selected_training_data = pca_mobilesoft.getPCAedFeatures(trainData)
print "Size of selected training data : ", np.shape(selected_training_data)
print "=" * 50
dict_of_results = param_exp_classifier.runCART(selected_training_data,
testData, 0.90)
reportStr = param_exp_analysis.analyzeThis(dict_of_results)
IO_.writeStrToFile(fileToWriteP, reportStr)
def speedup_random_forest(fileNameParam, fileToWriteP): testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam) trainData = testAndTrainData[0] testData = testAndTrainData[1] #print trainData selected_training_data = pca_mobilesoft.getPCAedFeatures(trainData) print "Size of selected training data : ", np.shape(selected_training_data) print "="*50 dict_of_results = runRandomForest(selected_training_data, testData) reportStr = param_exp_analysis.analyzeThis(dict_of_results) IO_.writeStrToFile(fileToWriteP, reportStr)
def mobilesoft_cart(fileNameParam, fileToWriteP): indexVector = [0, 5, 10, 12, 13, 18, 19, 20] testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam) trainData = testAndTrainData[0] testData = testAndTrainData[1] selected_training_data = createMobileSoftFeatures(trainData, indexVector) print "Size of selected training data : ", np.shape(selected_training_data) print "="*50 print "Glimpse at selected features (10th entry): \n", selected_training_data.iloc[9, :] print "="*50 print "Glimpse at labels (10th entry): \n", testData.iloc[9] print "="*50 dict_of_results = param_exp_classifier.runCART(selected_training_data, testData, 0.90) reportStr = param_exp_analysis.analyzeThis(dict_of_results) IO_.writeStrToFile(fileToWriteP, reportStr)
def experiment_mobilesoft_knn(fileNameParam, indexVector):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
trainData = testAndTrainData[0]
testData = testAndTrainData[1]
#print trainData
selected_training_data = createMobileSoftFeatures(trainData, indexVector)
print "Size of selected training data : ", np.shape(selected_training_data)
print "=" * 50
print "Glimpse at selected features (10th entry): \n", selected_training_data.iloc[
9, :]
print "=" * 50
print "Glimpse at labels (10th entry): \n", testData.iloc[9]
print "=" * 50
exp_x_classifiers.runKNN(selected_training_data, testData, 0.90)
print "=" * 50
def experiemnt_random_forest(fileNameParam, fileToWriteP):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
print "This is 'experiemnt_random_forest' "
# settign up train data
trainData = testAndTrainData[0]
original_rows = trainData.shape[0]
original_cols = trainData.shape[1]
print "Size of training data : rows: {}, columns: {}".format( original_rows , original_cols )
# settign up test data
testData = testAndTrainData[1]
dict_of_results = param_exp_classifier.runRandomForest(trainData, testData)
reportStr = param_exp_analysis.analyzeThis(dict_of_results)
IO_.writeStrToFile(fileToWriteP, reportStr)
def experiemnt_random_forest(fileNameParam, fileToWriteP):
testAndTrainData = IO_.giveTestAndTrainingData(fileNameParam)
print "This is 'experiemnt_random_forest' "
# settign up train data
trainData = testAndTrainData[0]
original_rows = trainData.shape[0]
original_cols = trainData.shape[1]
print "Size of training data : rows: {}, columns: {}".format(
original_rows, original_cols)
# settign up test data
testData = testAndTrainData[1]
dict_of_results = param_exp_classifier.runRandomForest(trainData, testData)
reportStr = param_exp_analysis.analyzeThis(dict_of_results)
IO_.writeStrToFile(fileToWriteP, reportStr)
def runSVM(fileNamaParam, trainizingSizeParam): # what percent will you use ? testSplitSize = 1.0 - trainizingSizeParam testAndTrainData = IO_.giveTestAndTrainingData(fileNamaParam) trainData = testAndTrainData[0] testData = testAndTrainData[1] ### classification ## get the test and training sets featureSpace_train, featureSpace_test, vScore_train, vScore_test = cross_validation.train_test_split(trainData, testData, test_size=testSplitSize, random_state=0) ## fire up the model theSVMModel = svm.SVC(kernel='rbf', C=1).fit(featureSpace_train, vScore_train) thePredictedScores = theSVMModel.predict(featureSpace_test) #print "The original vector: " #print vScore_test #print "The predicted score vector: " #print thePredictedScores evalClassifier(vScore_test, thePredictedScores)
def runCART(fileNamaParam, trainizingSizeParam):
# what percent will you use ?
testSplitSize = 1.0 - trainizingSizeParam
testAndTrainData = IO_.giveTestAndTrainingData(fileNamaParam)
trainData = testAndTrainData[0]
testData = testAndTrainData[1]
### classification
## get the test and training sets
featureSpace_train, featureSpace_test, vScore_train, vScore_test = cross_validation.train_test_split(
trainData, testData, test_size=testSplitSize, random_state=0)
## fire up the model
theQDAModel = DecisionTreeClassifier()
theQDAModel.fit(featureSpace_train, vScore_train)
thePredictedScores = theQDAModel.predict(featureSpace_test)
#print "The original vector: "
#print vScore_test
#print "The predicted score vector: "
#print thePredictedScores
evalClassifier(vScore_test, thePredictedScores)
