The file “multicommodity.csv” contains information about 500 customers who have purchased one or more of the 20 products that a company sells. The company has information about the gender of these 500 customers through a survey that they conducted. The company wants to learn a model such that it is able to predict the gender of a customer based on the portfolio of products purchased.

Importing libraries

from sklearn import tree
from sklearn import metrics
import numpy as np
import csv

Reading data file as list object

import csv
def readFileThroughCSV(filename):
    csvfile = open(filename)
    readerobject = csv.reader(csvfile, delimiter=',')
    lst = list(readerobject)
    csvfile.close()

    # removing first row from list
    lst = lst[1:]
    arr = np.array(lst)
    data = arr.astype(float)

    # extract first column which is classification
    c = data[:,0]

    # extract remaining data
    d = data[:,1:]
    return(c,d)

import pandas as pd
def readFileThroughPandas(filename):
    c = pd.read_csv(filename, usecols = [0])
    d = pd.read_csv(filename, usecols = np.arange(1,21))
    cnum = c.values
    dnum = d.values
    
    #You may also use the following
    #num = c.to_numpy()
    #dnum = d.to_numpy()
    
    cnum = cnum[:,0]
    return(cnum,dnum)

(c,d) = readFileThroughPandas("multicommodity.csv")
#(c,d) = readFileThroughCSV("multicommodity.csv")
print(c.shape)
print(d.shape)

(500,)
(500, 20)

Fitting a decision tree

# Note that only 80% of the dataset is being used for training
clf = tree.DecisionTreeClassifier()
clf.fit(X=d[0:300,:],y=c[0:300])

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')

Printing performance metrics

# returns accuracy
print("Training accuracy",clf.score(X=d[:300,:],y=c[:300]))
print("Testing accuracy",clf.score(X=d[300:,:],y=c[300:]))

indices = range(300,500)
c_predicted = clf.predict(d[indices,:])

Training accuracy 1.0
Testing accuracy 0.68

Always look at the confusion matrix

m = metrics.confusion_matrix(c[indices],c_predicted)
print(m)

[[91 25]
 [39 45]]