isitmaglab1

lab1.py

import numpy as np
from sklearn import model_selection

from sklearn import tree

imported_data = []

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

npdata = np.array(imported_data)

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

X_train, X_test, y_train, y_test = model_selection.train_test_split(X,y,train_size=0.9,shuffle=True)
print "TOTAL: ", len(X), "TRAIN: ", len(X_train)

clf = tree.DecisionTreeClassifier(max_depth=4).fit(X_train,y_train)

y_predicted = clf.predict(X_test)

guessed = 0

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

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