def knnlearner_test(filenames):
for filename in filenames:
train_time =[]
query_time =[]
rmse_series=[]
rmse_series_insample=[]
covariance_series=[]
for i in xrange(1,51):
knnlearner=KNNLearner(k=i)
get_set = knnlearner.getflatcsv(filename)
get_set_60pr,get_set_40pr = numpy.split(get_set,[600])
(X,Y) = numpy.split(get_set,[2],axis=1)
(XTrain,XTest) = numpy.split(X,[600])
(Ytrain,YTest) = numpy.split(Y,[600])
knnlearner.build_hash(get_set_60pr)
with Timer() as t:
knnlearner.addEvidence(XTrain,Ytrain)
train_time.append(t.interval)
query_X = numpy.array(XTest)
with Timer() as t:
(XY_return,Y_return) = knnlearner.query(XTest)
query_time.append(t.interval)
Y_Test = np.squeeze(np.asarray(YTest))
Y_Return = numpy.array(Y_return)
rmse_series.append(get_rmse(Y_Test,Y_Return))
(XY_return_insample,Y_return_insample) = knnlearner.query(XTrain)
Y_Train = np.squeeze(np.asarray(Ytrain))
Y_return_insample = numpy.array(Y_return_insample)
rmse_series_insample.append(get_rmse(Y_Train,Y_return_insample))
covariance_series.append(get_correlation(Y_Test,Y_Return))
min_rmse = min(float(i) for i in rmse_series)
k_index = rmse_series.index(min_rmse)
print "best k = ",k_index+1," for ",filename
knnlearner_scatter = KNNLearner(k=k_index+1)
get_set = knnlearner_scatter.getflatcsv(filename)
get_set_60pr,get_set_40pr = numpy.split(get_set,[600])
(X,Y) = numpy.split(get_set,[2],axis=1)
(XTrain,XTest) = numpy.split(X,[600])
(Ytrain,YTest) = numpy.split(Y,[600])
knnlearner_scatter.build_hash(get_set_60pr)
knnlearner_scatter.addEvidence(XTrain,Ytrain)
(XY_return,Y_return) = knnlearner_scatter.query(XTest)
Y_Test = np.squeeze(np.asarray(YTest))
Y_Return = numpy.array(Y_return)
scatter(Y_Return,Y_Test,"scatterplot("+filename+")(for bestk).pdf")
get_graph(numpy.arange(1,51),train_time,"K","Train time in seconds","KNN_Train_time("+filename+").pdf",4)
get_graph(numpy.arange(1,51),query_time,"K","Query time in seconds","KNN_Query_time("+filename+").pdf",4)
get_graph(numpy.arange(1,51),rmse_series,"K","RMSE Error","RMSEvsk("+filename+").pdf")
get_graph(numpy.arange(1,51),covariance_series,"K","Covariance Coefficeint","Covariance Coeff vs K("+filename+").pdf")
get_graph_two_plots(numpy.arange(1,51),rmse_series_insample,rmse_series,"K","RMSE","insample_error_vs_outsample_error("+filename+").pdf")
def knnlearner_test(filenames):
for filename in filenames:
rmse_series=[]
covariance_series=[]
for i in xrange(1,101):
knnlearner=KNNLearner(k=i)
get_set = knnlearner.getflatcsv(filename)
get_set_60pr,get_set_40pr = numpy.split(get_set,[600])
(X,Y) = numpy.split(get_set,[2],axis=1)
(XTrain,XTest) = numpy.split(X,[600])
(Ytrain,YTest) = numpy.split(Y,[600])
knnlearner.build_hash(get_set_60pr)
knnlearner.addEvidence(XTrain,Ytrain)
query_X = numpy.array(XTest)
(XY_return,Y_return) = knnlearner.query(XTest)
Y_Test = np.squeeze(np.asarray(YTest))
Y_Return = numpy.array(Y_return)
rmse_series.append(get_rmse(Y_Test,Y_Return))
covariance_series.append(get_correlation(Y_Test,Y_Return))
return (rmse_series,covariance_series)
