import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn import tree from sklearn.model_selection import train_test_split, cross_val_score from sklearn import metrics

data = pd.read_csv('car.csv', header= None)

data.columns = ['price','maintenance','n_doors','capacity','size_lug','safety','class'] data.sample(3)

#data.maintenance.unique() #data.n_doors.unique() #data.capacity.unique() data['class'].unique()

#Crear Modelo de Arbol de Desicion / para evaluar si compramos un vehiculo data.price.replace(('vhigh','high','med','low') , (4,3,2,1) , inplace=True) data.maintenance.replace(('vhigh','high','med','low') , (4,3,2,1) , inplace=True) data.n_doors.replace(('2','3','4','5more') , (1,2,3,4) , inplace=True) data.capacity.replace(('2','4','more') , (1,2,3) , inplace=True) data.size_lug.replace(('small','med','big') , (1,2,3) , inplace=True) data.safety.replace(('low','med','high') , (1,2,3) , inplace=True) data['class'].replace(('unacc','acc','good','vgood') , (1,2,3,4) , inplace=True)

data.head()

# 80% APRENDIZAJE # 20 PRUEBAS dataset = data.values #type(dataset) --> numpy.ndarray X = dataset[: , 0:6] #All rows , Cols 0 - 6 Y = np.asarray(dataset[:, 6] , dtype='S6') #All rows , 6 (only this col) #type(Y) Y

x_train, x_test, y_train, y_test = train_test_split(X,Y, test_size=0.2, random_state=0)

tr = tree.DecisionTreeClassifier(max_depth=10)

tr.fit(x_train,y_train)

y_pred = tr.predict(x_test)

y_pred

score= tr.score(x_test,y_test) print("Precision: %0.4f" % (score))