amm2-lab1

lab1.py

import numpy as np
from sklearn import model_selection as ms
from sklearn import tree

imported_data = []

for line in open("transfusion.data","r"):
    line = line.split(",")
    line = map(int,line)
    imported_data.append(line)
#print imported_data

npdata = np.array(imported_data)

X = npdata[:,:4]
y = npdata[:,4]

print "TOTAL DATA LENGTH: ", len(y)

X_train, X_test, y_train, y_test = ms.train_test_split(X, y, train_size=0.9)

print "TRAIN DATA SIZE: ", len(y_train)


clf = tree.DecisionTreeClassifier().fit(X_train,y_train)
y_predicted = clf.predict(X_test)

guessed = 0

for ind in range(0,len(y_test)):
    if y_predicted[ind] == y_test[ind]:
        guessed += 1

print "GUESSED RIGHT: ", guessed, " OUT OF: ", len(y_test)
print "ACCURACY: ", 1.0*guessed/len(y_test)