├── README.md
└── Run_Code.py


/README.md:
--------------------------------------------------------------------------------
 1 | # GenderClassifier
 2 | Gender_classification_challenge
 3 | 
 4 | ## Dependencies 
 5 | 
 6 | * Scikit-learn
 7 | * numpy
 8 | * scipy
 9 | 
10 | ## Usage
11 | 
12 | ```
13 | python Run_Code.py
14 | ```
15 | 


--------------------------------------------------------------------------------
/Run_Code.py:
--------------------------------------------------------------------------------
 1 | from sklearn import tree
 2 | from sklearn.svm import SVC
 3 | from sklearn.linear_model import Perceptron
 4 | from sklearn.neighbors import KNeighborsClassifier
 5 | from sklearn.metrics import accuracy_score
 6 | import numpy as np
 7 | 
 8 | # Data and labels
 9 | X = [[181, 80, 44], [177, 70, 43], [160, 60, 38], [154, 54, 37], [166, 65, 40], [190, 90, 47], [175, 64, 39],
10 |      [177, 70, 40], [159, 55, 37], [171, 75, 42], [181, 85, 43]]
11 | 
12 | Y = ['male', 'male', 'female', 'female', 'male', 'male', 'female', 'female', 'female', 'male', 'male']
13 | 
14 | # Classifiers
15 | # using the default values for all the hyperparameters
16 | clf_tree = tree.DecisionTreeClassifier()
17 | clf_svm = SVC()
18 | clf_perceptron = Perceptron()
19 | clf_KNN = KNeighborsClassifier()
20 | 
21 | # Training the models
22 | clf_tree.fit(X, Y)
23 | clf_svm.fit(X, Y)
24 | clf_perceptron.fit(X, Y)
25 | clf_KNN.fit(X, Y)
26 | 
27 | # Testing using the same data
28 | pred_tree = clf_tree.predict(X)
29 | acc_tree = accuracy_score(Y, pred_tree) * 100
30 | print('Accuracy for DecisionTree: {}'.format(acc_tree))
31 | 
32 | pred_svm = clf_svm.predict(X)
33 | acc_svm = accuracy_score(Y, pred_svm) * 100
34 | print('Accuracy for SVM: {}'.format(acc_svm))
35 | 
36 | pred_per = clf_perceptron.predict(X)
37 | acc_per = accuracy_score(Y, pred_per) * 100
38 | print('Accuracy for perceptron: {}'.format(acc_per))
39 | 
40 | pred_KNN = clf_KNN.predict(X)
41 | acc_KNN = accuracy_score(Y, pred_KNN) * 100
42 | print('Accuracy for KNN: {}'.format(acc_KNN))
43 | 
44 | # The best classifier from svm, per, KNN
45 | index = np.argmax([acc_svm, acc_per, acc_KNN])
46 | classifiers = {0: 'SVM', 1: 'Perceptron', 2: 'KNN'}
47 | print('Best gender classifier is {}'.format(classifiers[index]))
48 | 


--------------------------------------------------------------------------------