def classifierForTopNFeatures(n, sortedFeatures, XFile, yFile, mlAlg):
topFeatureIndeces = []
for i in range(n):
topFeatureIndeces.append(sortedFeatures[i][2])
print(topFeatureIndeces)
allX, allY, features = chooseFeatures(topFeatureIndeces, XFile, yFile)
scores = getModelScores(mlAlg, allX, allY, 10)
print('error for top 6 features', features, scores.mean())
def enterFeatureIndeces(XFeatures, yFeature, XFile, yFile, mlAlg):
allX, allY, features = chooseFeatures(XFeatures, XFile, yFile)
scores = getModelScores(mlAlg, allX, allY, 10)
#myModel = linear_model.LinearRegression()
#scores = cross_val_score(myModel,allX,allY,scoring='neg_mean_squared_error', cv=10)
print(scores.mean()) #take the mean score of all cross val runs
print(features)
def specifyDataset(
XFile, yFile, mlAlg, numFeatures
): #if featuresList is empty, by default start with all features specified in dataset
f = open("file.txt", "a")
f.write("newew")
f.write('newew')
loopLength, non, non1 = readAllFeatures(XFile,
yFile) # just to get length of x
emptyList = []
start = time.time()
num_cores = multiprocessing.cpu_count()
var = Parallel(n_jobs=num_cores)(
delayed(singVarClassifier)(i, XFile, yFile, mlAlg, numFeatures)
for i in range(len(loopLength[0])))
end = time.time()
print("time for parallel ", str(end - start))
print('var is')
print(var)
# emptyList.append(var)
# print(emptyList)
# emptyList = []
start = time.time()
for i in range(len(
loopLength[0])): #there are 19 total features in standard X file
if i != 1 and i != 2:
allX, allY, features = chooseFeatures([i], XFile, yFile)
scores = getModelScores(mlAlg, allX, allY, 10)
#print(scores.mean(),features[0],i)
#f = open("file.txt","a")
#f.write('here')
# f.write(str(scores.mean())+ ' ' + features[0]+ ' ' +str(i) + '\n')
#f.close
emptyList.append([scores.mean(), features[0], i])
end = time.time()
print("time for sequential", str(end - start))
print(emptyList)
sortedList = sorted(var, reverse=True)
#f.write(sortedList)
f.close
for i in range(len(sortedList)):
print(sortedList[i])
classifierForTopNFeatures(
6, sortedList, XFile, yFile,
mlAlg) #first arg is number of top ranked features to run
def specifyDataset(
XFile, yFile, mlAlg, numFeatures
): #if featuresList is empty, by default start with all features specified in dataset
X, y, features = readAllFeatures(XFile, yFile)
startingFeatures = range(
len(X[0])
) #create a list starting with all feature indeces in ascending order
scores = getModelScores(mlAlg, X, y, 10)
print('error for all features',
scores.mean()) #baseline score for using all features
optimalFeatures = recursiveElim(
startingFeatures, 6, XFile, yFile,
mlAlg) #second arg is what num of features to stop at
print(optimalFeatures)
allX, allY, features = chooseFeatures(optimalFeatures, XFile, yFile)
scores = getModelScores(mlAlg, allX, allY, 10)
print('scores for optimal features', scores.mean())
print(list(features))
def recursiveElim(startingFeatures, optimalSetSize, XFile, yFile, mlAlg):
if len(
startingFeatures
) == optimalSetSize: #certain ml algs like svm may have better scores with less features at times than with all features. Implement this later
return startingFeatures #end recursion
featureScores = []
print('starting features for current round', startingFeatures)
print('number of features left', len(startingFeatures))
for index in range(len(startingFeatures)):
tempFeatures = [startingFeatures[0:index]]
tempFeatures.append(startingFeatures[index + 1:])
tempFeatures = list(chain.from_iterable(
tempFeatures)) #remove nested list and present as all one list
# tempFeatures = np.delete(startingFeatures,[index],1)#all features in current round minus one (i.e. remove a column)
print(tempFeatures)
allX, allY, features = chooseFeatures(tempFeatures, XFile, yFile)
non, non2, nonFeatures = chooseFeatures(
[startingFeatures[index]], XFile,
yFile) #this is just a lazy way to get the feature name
scores = getModelScores(mlAlg, allX, allY, 10)
print('error for this set of features', scores.mean())
featureScores.append(
[scores.mean(), nonFeatures[0], startingFeatures[index]])
sortedList = sorted(featureScores,
reverse=False) #make boolean ifMinimizing
print('\n\n\neliminate feature', (sortedList[-1][1]), '\n\n')
sortedList = sortedList[:-1] #remove the worst performing feature
startingFeatures = [] #reset list for next recursion round
for el in sortedList:
startingFeatures.append(
el[2]
) #append the feature indeces for later call to chooseFeatures
startingFeatures = sorted(startingFeatures) #for consistency
#print(startingFeatures)
startingFeatures = recursiveElim(startingFeatures, optimalSetSize, XFile,
yFile, mlAlg)
return startingFeatures
def singVarClassifier(i, XFile, yFile, mlAlg, numFeatures):
allX, allY, features = chooseFeatures([i], XFile, yFile)
print(i)
scores = getModelScores(mlAlg, allX, allY, 30)
print(scores.mean(), features[0], i)
return [scores.mean(), features[0], i]